{"version":"configuration-source-6","generatedAt":"2026-10-23T17:41:31.580Z","snapshotId":"sha256-3848b85526102e7a985d53044e8baa86203d9d16f2affbb4a93bcb265f95b8fb","effortDatasetId":"sha256-49305f3d640f7387a764d95d62f10bbce44aeff4a4012ddba973eddf1e57a707+sha256-443256461e035ccdee585c01fdbd68b4b26545d45e2bd6b2bd93e1e913a2d41a+sha256-32c6374f8a0cdb9cd64f17244f1a697dd35d31cff071002599f3e1226d1e027d+sha256-9b7bfe52f0cba33df0362a330cb12551ea2f5853bf843931b08dad98e5d8d15c+sha256-c4f243913106bee769c57849d3cb4662fee3097206d30d3c8d4d37d687f8e556+sha256-c6f9cb8b67b4289e79e621b65d529e5f57eee55d89d86915f397859092051dad+sha256-78cb5ce46bffe96a698a9a7117551eafb90b2c3d05066722f4a703be2680aa55+sha256-e34a2de55476481fa69ea734e4027620fbc14df27f896c3bcec6c07275b0da42","inputHash":"sha256-c08e5361e3db590bb99b151f88c634090cd4280fcb8a50acc5c815e2dd562bb1","scope":"Diagnostic reuse of the available public dataset, not an untouched final test set. All methods use identical predictable independent targets. Missing comparisons are not imputed. Coverage includes zero-prediction folds. Loss averages only predictable folds. Source ablations refit the graph; weight shares are not causal score contributions or confidence intervals.","rules":{"version":"configuration-source-6","smoothing":0.1,"capabilitySmoothing":0.2,"maximumLabWeightShare":0.25,"minimumIndependentSources":1,"minimumIndependentFamilies":2,"referencePanel":["gpt-5.6-sol--effort-high","claude-opus-4-8--effort-high","gemini-3.1-pro--effort-high"],"minimumFamilies":3,"minimumOpponents":3,"capabilityReferencePanel":["gpt-5.6-sol--effort-high","claude-opus-4-7--effort-max","gemini-3.5-flash--effort-high"]},"convergence":{"converged":true,"iterations":6},"summary":{"family":{"totalFolds":50,"predictableFolds":49,"meanCoverageAllFolds":0.9661872935028134,"weightedCoverage":0.9803526213874615,"methods":{"source-balanced":{"meanLogLossPredictableFolds":0.41968536198693884},"equal-family":{"meanLogLossPredictableFolds":0.4197457808006005},"equal-model-exposure":{"meanLogLossPredictableFolds":0.42373852924650607},"configuration-exposure":{"meanLogLossPredictableFolds":0.4241779396171011},"equal-model-pair":{"meanLogLossPredictableFolds":0.4417247914961486}}},"source":{"totalFolds":11,"predictableFolds":11,"meanCoverageAllFolds":0.7823527866857511,"weightedCoverage":0.563126605601833,"methods":{"source-balanced":{"meanLogLossPredictableFolds":0.45568179722978175},"equal-family":{"meanLogLossPredictableFolds":0.46315314334153307},"equal-model-exposure":{"meanLogLossPredictableFolds":0.46813424877936427},"configuration-exposure":{"meanLogLossPredictableFolds":0.4614445166075848},"equal-model-pair":{"meanLogLossPredictableFolds":0.47742409266329316}}}},"folds":[{"kind":"family","key":"analyst-agent","totalWeight":22.02325581395318,"predictableWeight":22.02325581395318,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3616557006617179,"accuracy":0.8387011615628335,"converged":true},"equal-family":{"logLoss":0.3666245082354625,"accuracy":0.8323653643083456,"converged":true},"equal-model-exposure":{"logLoss":0.3789408119000708,"accuracy":0.8297254487856426,"converged":true},"configuration-exposure":{"logLoss":0.3714219274413441,"accuracy":0.8313093980992644,"converged":true},"equal-model-pair":{"logLoss":0.3824187034817698,"accuracy":0.8360612460401301,"converged":true}}},{"kind":"family","key":"briefcase","totalWeight":60.95370370370957,"predictableWeight":60.95370370370957,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3212892002572661,"accuracy":0.8551445642817226,"converged":true},"equal-family":{"logLoss":0.3201677948346917,"accuracy":0.8544052863435989,"converged":true},"equal-model-exposure":{"logLoss":0.32258195891883135,"accuracy":0.8594181983897783,"converged":true},"configuration-exposure":{"logLoss":0.32537348276535094,"accuracy":0.8578662210744712,"converged":true},"equal-model-pair":{"logLoss":0.3359340275718494,"accuracy":0.8563876651982235,"converged":true}}},{"kind":"family","key":"aime","totalWeight":87.74428104575469,"predictableWeight":87.74428104575469,"coverage":1,"methods":{"source-balanced":{"logLoss":0.36913082093162897,"accuracy":0.8364042806109495,"converged":true},"equal-family":{"logLoss":0.37591463704167954,"accuracy":0.8317179137815441,"converged":true},"equal-model-exposure":{"logLoss":0.3866090480198857,"accuracy":0.8303054239073377,"converged":true},"configuration-exposure":{"logLoss":0.38657938633191413,"accuracy":0.8305041118736025,"converged":true},"equal-model-pair":{"logLoss":0.39828214804109685,"accuracy":0.8258376086680081,"converged":true}}},{"kind":"family","key":"apex-agents","totalWeight":14.500000000000119,"predictableWeight":14.500000000000119,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3448619671040911,"accuracy":0.8694581280788161,"converged":true},"equal-family":{"logLoss":0.3346825699347506,"accuracy":0.8916256157635454,"converged":true},"equal-model-exposure":{"logLoss":0.35688497049025203,"accuracy":0.8768472906403925,"converged":true},"configuration-exposure":{"logLoss":0.357006602691613,"accuracy":0.8817733990147768,"converged":true},"equal-model-pair":{"logLoss":0.3762253517969783,"accuracy":0.8793103448275846,"converged":true}}},{"kind":"family","key":"aa-lcr","totalWeight":124.66052089054648,"predictableWeight":124.66052089054648,"coverage":1,"methods":{"source-balanced":{"logLoss":0.2877211926744042,"accuracy":0.8797525863887273,"converged":true},"equal-family":{"logLoss":0.2977826976601319,"accuracy":0.8731302000190465,"converged":true},"equal-model-exposure":{"logLoss":0.2922385001030149,"accuracy":0.8797261355899808,"converged":true},"configuration-exposure":{"logLoss":0.2934134674291293,"accuracy":0.8799967593867886,"converged":true},"equal-model-pair":{"logLoss":0.2940907358889018,"accuracy":0.8809802776879819,"converged":true}}},{"kind":"family","key":"automationbench","totalWeight":60.92660550459014,"predictableWeight":60.92660550459014,"coverage":1,"methods":{"source-balanced":{"logLoss":0.2815683113352501,"accuracy":0.8783240475832026,"converged":true},"equal-family":{"logLoss":0.2870906287238875,"accuracy":0.8755333032173984,"converged":true},"equal-model-exposure":{"logLoss":0.28830282713056715,"accuracy":0.8807559102544856,"converged":true},"configuration-exposure":{"logLoss":0.28928130168885935,"accuracy":0.8804371831551533,"converged":true},"equal-model-pair":{"logLoss":0.29779567472879465,"accuracy":0.8820007027054204,"converged":true}}},{"kind":"family","key":"critpt","totalWeight":121.39351851845305,"predictableWeight":120.74074074067673,"coverage":0.9946226307158476,"methods":{"source-balanced":{"logLoss":0.35975315510833206,"accuracy":0.8396964468303256,"converged":true},"equal-family":{"logLoss":0.37446735201024606,"accuracy":0.8329672588616921,"converged":true},"equal-model-exposure":{"logLoss":0.36617193602903153,"accuracy":0.8385221753579353,"converged":true},"configuration-exposure":{"logLoss":0.3633989360387319,"accuracy":0.8399325792434138,"converged":true},"equal-model-pair":{"logLoss":0.3649846394733137,"accuracy":0.8410212167689747,"converged":true}}},{"kind":"family","key":"enterprise-ops","totalWeight":22.023255813953007,"predictableWeight":22.023255813953007,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4212159689211884,"accuracy":0.8020063357972657,"converged":true},"equal-family":{"logLoss":0.40012021438144146,"accuracy":0.8178458289334843,"converged":true},"equal-model-exposure":{"logLoss":0.41805247546866653,"accuracy":0.8115100316789968,"converged":true},"configuration-exposure":{"logLoss":0.4233699890718358,"accuracy":0.8062302006335906,"converged":true},"equal-model-pair":{"logLoss":0.43196325225060517,"accuracy":0.7977824709609407,"converged":true}}},{"kind":"family","key":"gdp-pdf","totalWeight":59.39252336449692,"predictableWeight":59.39252336449692,"coverage":1,"methods":{"source-balanced":{"logLoss":0.2740567801855499,"accuracy":0.8820226855493961,"converged":true},"equal-family":{"logLoss":0.2754464044651544,"accuracy":0.8808654602674624,"converged":true},"equal-model-exposure":{"logLoss":0.2804050860847753,"accuracy":0.8861159192236701,"converged":true},"configuration-exposure":{"logLoss":0.27972028324037096,"accuracy":0.8883254655126861,"converged":true},"equal-model-pair":{"logLoss":0.28961193676788843,"accuracy":0.8873144505638283,"converged":true}}},{"kind":"family","key":"gdpval","totalWeight":78.05035971223839,"predictableWeight":78.05035971223839,"coverage":1,"methods":{"source-balanced":{"logLoss":0.2695056993932212,"accuracy":0.8879420530309482,"converged":true},"equal-family":{"logLoss":0.26979106554464083,"accuracy":0.886986511813637,"converged":true},"equal-model-exposure":{"logLoss":0.27212731123282985,"accuracy":0.892192828832102,"converged":true},"configuration-exposure":{"logLoss":0.27398177153575176,"accuracy":0.8915691154330165,"converged":true},"equal-model-pair":{"logLoss":0.2827674871796209,"accuracy":0.8901757458444205,"converged":true}}},{"kind":"family","key":"gmmlu","totalWeight":33.904761904763355,"predictableWeight":33.904761904763355,"coverage":1,"methods":{"source-balanced":{"logLoss":0.32425150109829165,"accuracy":0.8725811485642953,"converged":true},"equal-family":{"logLoss":0.3409716230200131,"accuracy":0.8633739076154813,"converged":true},"equal-model-exposure":{"logLoss":0.3305671572084672,"accuracy":0.8789794007490648,"converged":true},"configuration-exposure":{"logLoss":0.3320462835768663,"accuracy":0.8824126092384533,"converged":true},"equal-model-pair":{"logLoss":0.3269767981048457,"accuracy":0.8879525593008754,"converged":true}}},{"kind":"family","key":"gpqa","totalWeight":135.13065251573192,"predictableWeight":134.14716194969452,"coverage":0.992721928387618,"methods":{"source-balanced":{"logLoss":0.26031102429313946,"accuracy":0.9106021155425681,"converged":true},"equal-family":{"logLoss":0.26849626062243115,"accuracy":0.9041489917760097,"converged":true},"equal-model-exposure":{"logLoss":0.2727477296599306,"accuracy":0.9076502332256817,"converged":true},"configuration-exposure":{"logLoss":0.274838928814342,"accuracy":0.9076632434377019,"converged":true},"equal-model-pair":{"logLoss":0.28045550130591246,"accuracy":0.9052433733042315,"converged":true}}},{"kind":"family","key":"harvey","totalWeight":22.37368421052675,"predictableWeight":22.37368421052675,"coverage":1,"methods":{"source-balanced":{"logLoss":0.595560152822867,"accuracy":0.6947997529992908,"converged":true},"equal-family":{"logLoss":0.5490397941592503,"accuracy":0.7240575746883052,"converged":true},"equal-model-exposure":{"logLoss":0.5486281075637826,"accuracy":0.7097374147259432,"converged":true},"configuration-exposure":{"logLoss":0.5466526835150606,"accuracy":0.713354210773932,"converged":true},"equal-model-pair":{"logLoss":0.5511430456452059,"accuracy":0.7054296047988673,"converged":true}}},{"kind":"family","key":"hle","totalWeight":136.83675595242306,"predictableWeight":134.76532738099462,"coverage":0.9848620456030932,"methods":{"source-balanced":{"logLoss":0.2562703267313396,"accuracy":0.9019545108727473,"converged":true},"equal-family":{"logLoss":0.2658347409755604,"accuracy":0.8961308955272914,"converged":true},"equal-model-exposure":{"logLoss":0.2667936290363213,"accuracy":0.9002841138090675,"converged":true},"configuration-exposure":{"logLoss":0.26628006642364327,"accuracy":0.9021085484800068,"converged":true},"equal-model-pair":{"logLoss":0.27184358859571744,"accuracy":0.900403920836934,"converged":true}}},{"kind":"family","key":"ifbench","totalWeight":103.08988764044788,"predictableWeight":103.08988764044788,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3956030429121241,"accuracy":0.8222316076293956,"converged":true},"equal-family":{"logLoss":0.41927036387820393,"accuracy":0.8103705722070528,"converged":true},"equal-model-exposure":{"logLoss":0.40540337611617966,"accuracy":0.818244323342384,"converged":true},"configuration-exposure":{"logLoss":0.4044447775618116,"accuracy":0.8191235240689961,"converged":true},"equal-model-pair":{"logLoss":0.40020792733168425,"accuracy":0.8233297002724473,"converged":true}}},{"kind":"family","key":"itbench","totalWeight":20.524999999999793,"predictableWeight":20.524999999999793,"coverage":1,"methods":{"source-balanced":{"logLoss":0.45216701114064245,"accuracy":0.8002436053593285,"converged":true},"equal-family":{"logLoss":0.4454420526073714,"accuracy":0.7886723507917287,"converged":true},"equal-model-exposure":{"logLoss":0.43743077593075547,"accuracy":0.7941534713763813,"converged":true},"configuration-exposure":{"logLoss":0.4406254429403291,"accuracy":0.7935444579780866,"converged":true},"equal-model-pair":{"logLoss":0.4410611679285018,"accuracy":0.8008526187576231,"converged":true}}},{"kind":"family","key":"livecodebench","totalWeight":62.455357142851426,"predictableWeight":62.455357142851426,"coverage":1,"methods":{"source-balanced":{"logLoss":0.34364608014673204,"accuracy":0.8710686204431827,"converged":true},"equal-family":{"logLoss":0.34568188291615254,"accuracy":0.8636466523707493,"converged":true},"equal-model-exposure":{"logLoss":0.3537194373330064,"accuracy":0.8642304026685815,"converged":true},"configuration-exposure":{"logLoss":0.3548439686074772,"accuracy":0.8667846080533801,"converged":true},"equal-model-pair":{"logLoss":0.36265264061699676,"accuracy":0.8669799857040835,"converged":true}}},{"kind":"family","key":"math500","totalWeight":31.799999999999073,"predictableWeight":31.799999999999073,"coverage":1,"methods":{"source-balanced":{"logLoss":0.35499541136388896,"accuracy":0.8658280922431916,"converged":true},"equal-family":{"logLoss":0.3570710836595351,"accuracy":0.8643867924528353,"converged":true},"equal-model-exposure":{"logLoss":0.3779955774904499,"accuracy":0.8541666666666721,"converged":true},"configuration-exposure":{"logLoss":0.38092373917624534,"accuracy":0.852594339622647,"converged":true},"equal-model-pair":{"logLoss":0.39603273740938266,"accuracy":0.8410639412997963,"converged":true}}},{"kind":"family","key":"mmlu-pro","totalWeight":79.16666666666933,"predictableWeight":79.16666666666933,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3505431711811621,"accuracy":0.8596439400708904,"converged":true},"equal-family":{"logLoss":0.3440401849735829,"accuracy":0.8724086021505367,"converged":true},"equal-model-exposure":{"logLoss":0.35634735383635735,"accuracy":0.8651902421588777,"converged":true},"configuration-exposure":{"logLoss":0.3590415211867677,"accuracy":0.8645729008429393,"converged":true},"equal-model-pair":{"logLoss":0.36778453849134385,"accuracy":0.8599210079528193,"converged":true}}},{"kind":"family","key":"mmmu-pro","totalWeight":77.48387096773318,"predictableWeight":77.48387096773318,"coverage":1,"methods":{"source-balanced":{"logLoss":0.24802170256460088,"accuracy":0.9078190049958592,"converged":true},"equal-family":{"logLoss":0.26148987653582295,"accuracy":0.8976157021926476,"converged":true},"equal-model-exposure":{"logLoss":0.2618127956212211,"accuracy":0.9017476755481777,"converged":true},"configuration-exposure":{"logLoss":0.2623529214106914,"accuracy":0.902620212323085,"converged":true},"equal-model-pair":{"logLoss":0.26528223087705466,"accuracy":0.9041085553705452,"converged":true}}},{"kind":"family","key":"omniscience","totalWeight":129.41121495321383,"predictableWeight":129.41121495321383,"coverage":1,"methods":{"source-balanced":{"logLoss":0.37122960122549115,"accuracy":0.8294961604198505,"converged":true},"equal-family":{"logLoss":0.36638769806742383,"accuracy":0.8331756577839005,"converged":true},"equal-model-exposure":{"logLoss":0.36409413479281005,"accuracy":0.8331413543246649,"converged":true},"configuration-exposure":{"logLoss":0.3647156130999213,"accuracy":0.8322801569533925,"converged":true},"equal-model-pair":{"logLoss":0.36976839286843205,"accuracy":0.8296761031270516,"converged":true}}},{"kind":"family","key":"tau-bench","totalWeight":108.76104410333312,"predictableWeight":108.76104410333312,"coverage":1,"methods":{"source-balanced":{"logLoss":0.41673974414603543,"accuracy":0.8114721878648774,"converged":true},"equal-family":{"logLoss":0.426430369582434,"accuracy":0.8066951760909973,"converged":true},"equal-model-exposure":{"logLoss":0.416085050012158,"accuracy":0.8124343857346054,"converged":true},"configuration-exposure":{"logLoss":0.4160377304996645,"accuracy":0.8122076525340358,"converged":true},"equal-model-pair":{"logLoss":0.41608329351279294,"accuracy":0.8118376438259662,"converged":true}}},{"kind":"family","key":"terminal-bench-science","totalWeight":15.370370370370141,"predictableWeight":15.370370370370141,"coverage":1,"methods":{"source-balanced":{"logLoss":0.35417410064272004,"accuracy":0.8561847389558263,"converged":true},"equal-family":{"logLoss":0.40187487531086724,"accuracy":0.8299196787148629,"converged":true},"equal-model-exposure":{"logLoss":0.4133662231885187,"accuracy":0.835060240963859,"converged":true},"configuration-exposure":{"logLoss":0.40104975304793283,"accuracy":0.8449397590361478,"converged":true},"equal-model-pair":{"logLoss":0.41668650281330255,"accuracy":0.8414457831325337,"converged":true}}},{"kind":"family","key":"terminal-bench","totalWeight":118.7908873763054,"predictableWeight":117.21449848741649,"coverage":0.9867297153535419,"methods":{"source-balanced":{"logLoss":0.3299554864254954,"accuracy":0.8601676293498323,"converged":true},"equal-family":{"logLoss":0.33561361151224256,"accuracy":0.8546962933927229,"converged":true},"equal-model-exposure":{"logLoss":0.33311387789983565,"accuracy":0.8670216107490348,"converged":true},"configuration-exposure":{"logLoss":0.333119823890881,"accuracy":0.868667051147631,"converged":true},"equal-model-pair":{"logLoss":0.3370847345194317,"accuracy":0.869405320301302,"converged":true}}},{"kind":"family","key":"arc-agi","totalWeight":77.36734693876002,"predictableWeight":49.72278911564111,"coverage":0.6426844280313644,"methods":{"source-balanced":{"logLoss":0.38149417485576714,"accuracy":0.8469388104114701,"converged":true},"equal-family":{"logLoss":0.39010854941553824,"accuracy":0.8405325443787041,"converged":true},"equal-model-exposure":{"logLoss":0.40153294960378244,"accuracy":0.8428891473133421,"converged":true},"configuration-exposure":{"logLoss":0.3980268974861673,"accuracy":0.8449618633922833,"converged":true},"equal-model-pair":{"logLoss":0.4175652982132747,"accuracy":0.8371344529192525,"converged":true}}},{"kind":"family","key":"deepswe","totalWeight":20.71999999999947,"predictableWeight":20.71999999999947,"coverage":1,"methods":{"source-balanced":{"logLoss":0.41324790459402544,"accuracy":0.8125482625482632,"converged":true},"equal-family":{"logLoss":0.436735933206985,"accuracy":0.7868082368082362,"converged":true},"equal-model-exposure":{"logLoss":0.45055844490226793,"accuracy":0.8073680823680826,"converged":true},"configuration-exposure":{"logLoss":0.44991591246098245,"accuracy":0.813674388674389,"converged":true},"equal-model-pair":{"logLoss":0.4760425432816416,"accuracy":0.8229729729729738,"converged":true}}},{"kind":"family","key":"swe-bench-pro","totalWeight":1.5,"predictableWeight":0,"coverage":0,"methods":{"source-balanced":{"logLoss":null,"accuracy":null,"converged":true},"equal-family":{"logLoss":null,"accuracy":null,"converged":true},"equal-model-exposure":{"logLoss":null,"accuracy":null,"converged":true},"configuration-exposure":{"logLoss":null,"accuracy":null,"converged":true},"equal-model-pair":{"logLoss":null,"accuracy":null,"converged":true}}},{"kind":"family","key":"arc-agi-3","totalWeight":19.553571428571445,"predictableWeight":19.553571428571445,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3534081738648397,"accuracy":0.8742998477930121,"converged":true},"equal-family":{"logLoss":0.3778731407422575,"accuracy":0.856194824961963,"converged":true},"equal-model-exposure":{"logLoss":0.42277709548272496,"accuracy":0.8432191780822077,"converged":true},"configuration-exposure":{"logLoss":0.42224460513968176,"accuracy":0.8486605783866217,"converged":true},"equal-model-pair":{"logLoss":0.481682596958776,"accuracy":0.8292922374429383,"converged":true}}},{"kind":"family","key":"frontiercode","totalWeight":54.72499999999976,"predictableWeight":51.845000000000645,"coverage":0.947373229785306,"methods":{"source-balanced":{"logLoss":0.3595321756259658,"accuracy":0.837026678525415,"converged":true},"equal-family":{"logLoss":0.36651977338066044,"accuracy":0.8383911445441382,"converged":true},"equal-model-exposure":{"logLoss":0.3672267140818253,"accuracy":0.8560506209749498,"converged":true},"configuration-exposure":{"logLoss":0.3610712837391244,"accuracy":0.8618942503116824,"converged":true},"equal-model-pair":{"logLoss":0.3845191770812643,"accuracy":0.867870039969602,"converged":true}}},{"kind":"family","key":"enigma-eval","totalWeight":2.5,"predictableWeight":2.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4864563707748221,"accuracy":0.7,"converged":true},"equal-family":{"logLoss":0.5735387230305383,"accuracy":0.8,"converged":true},"equal-model-exposure":{"logLoss":0.5356679947944728,"accuracy":0.7,"converged":true},"configuration-exposure":{"logLoss":0.4953739343185878,"accuracy":0.7,"converged":true},"equal-model-pair":{"logLoss":0.5339814703698529,"accuracy":0.7,"converged":true}}},{"kind":"family","key":"swe-atlas-qna","totalWeight":3,"predictableWeight":3,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5852475958518096,"accuracy":0.6666666666666666,"converged":true},"equal-family":{"logLoss":0.5846933875422785,"accuracy":0.8333333333333334,"converged":true},"equal-model-exposure":{"logLoss":0.6485608216758173,"accuracy":0.8333333333333334,"converged":true},"configuration-exposure":{"logLoss":0.6684099025563134,"accuracy":0.8333333333333334,"converged":true},"equal-model-pair":{"logLoss":0.8122865553988091,"accuracy":0.6666666666666666,"converged":true}}},{"kind":"family","key":"swe-atlas-refactoring","totalWeight":2.5,"predictableWeight":2.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.29256552592188545,"accuracy":1,"converged":true},"equal-family":{"logLoss":0.18424660170998558,"accuracy":1,"converged":true},"equal-model-exposure":{"logLoss":0.2564066138748079,"accuracy":1,"converged":true},"configuration-exposure":{"logLoss":0.3006845182202195,"accuracy":1,"converged":true},"equal-model-pair":{"logLoss":0.4575361195380734,"accuracy":1,"converged":true}}},{"kind":"family","key":"swe-atlas-test-writing","totalWeight":3,"predictableWeight":3,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4070979363514227,"accuracy":0.9166666666666666,"converged":true},"equal-family":{"logLoss":0.36689884279678725,"accuracy":0.75,"converged":true},"equal-model-exposure":{"logLoss":0.3429132902144483,"accuracy":0.75,"converged":true},"configuration-exposure":{"logLoss":0.373418202699709,"accuracy":0.75,"converged":true},"equal-model-pair":{"logLoss":0.47793490872480104,"accuracy":0.5833333333333334,"converged":true}}},{"kind":"family","key":"livebench-math","totalWeight":17.09090909090952,"predictableWeight":17.09090909090952,"coverage":1,"methods":{"source-balanced":{"logLoss":0.538385340362103,"accuracy":0.7247340425531911,"converged":true},"equal-family":{"logLoss":0.5353053493158012,"accuracy":0.7300531914893613,"converged":true},"equal-model-exposure":{"logLoss":0.534692098452918,"accuracy":0.72761524822695,"converged":true},"configuration-exposure":{"logLoss":0.5334362937258312,"accuracy":0.7242907801418436,"converged":true},"equal-model-pair":{"logLoss":0.5445155577497782,"accuracy":0.721187943262411,"converged":true}}},{"kind":"family","key":"livebench-coding","totalWeight":17.090909090909463,"predictableWeight":17.090909090909463,"coverage":1,"methods":{"source-balanced":{"logLoss":0.620623785834717,"accuracy":0.6797429078014171,"converged":true},"equal-family":{"logLoss":0.6025783330550125,"accuracy":0.6611258865248212,"converged":true},"equal-model-exposure":{"logLoss":0.5770629079374494,"accuracy":0.6837322695035447,"converged":true},"configuration-exposure":{"logLoss":0.575318703038658,"accuracy":0.6801861702127645,"converged":true},"equal-model-pair":{"logLoss":0.5710271036820469,"accuracy":0.6886081560283676,"converged":true}}},{"kind":"family","key":"livebench-language","totalWeight":17.090909090909452,"predictableWeight":17.090909090909452,"coverage":1,"methods":{"source-balanced":{"logLoss":0.606780510429564,"accuracy":0.672576832151298,"converged":true},"equal-family":{"logLoss":0.6038488532262103,"accuracy":0.6793735224586267,"converged":true},"equal-model-exposure":{"logLoss":0.6000095116000373,"accuracy":0.6702127659574447,"converged":true},"configuration-exposure":{"logLoss":0.5946155679846513,"accuracy":0.6713947990543715,"converged":true},"equal-model-pair":{"logLoss":0.5986979931415298,"accuracy":0.6731678486997615,"converged":true}}},{"kind":"family","key":"livebench-data","totalWeight":17.090909090909452,"predictableWeight":17.090909090909452,"coverage":1,"methods":{"source-balanced":{"logLoss":0.7867276657202478,"accuracy":0.6075650118203276,"converged":true},"equal-family":{"logLoss":0.752766049924028,"accuracy":0.5856973995271834,"converged":true},"equal-model-exposure":{"logLoss":0.7439951512648438,"accuracy":0.5856973995271834,"converged":true},"configuration-exposure":{"logLoss":0.7397602704007674,"accuracy":0.5927895981087437,"converged":true},"equal-model-pair":{"logLoss":0.7330165630827927,"accuracy":0.595153664302597,"converged":true}}},{"kind":"family","key":"multi-swe-bench","totalWeight":17.090909090909452,"predictableWeight":17.090909090909452,"coverage":1,"methods":{"source-balanced":{"logLoss":0.6067140973553077,"accuracy":0.6954787234042533,"converged":true},"equal-family":{"logLoss":0.5816984917765815,"accuracy":0.6951832151300217,"converged":true},"equal-model-exposure":{"logLoss":0.5778191864315176,"accuracy":0.7013888888888871,"converged":true},"configuration-exposure":{"logLoss":0.5847733772787698,"accuracy":0.6975472813238752,"converged":true},"equal-model-pair":{"logLoss":0.579270897483973,"accuracy":0.7058215130023623,"converged":true}}},{"kind":"family","key":"livebench-reasoning","totalWeight":17.09090909090952,"predictableWeight":17.09090909090952,"coverage":1,"methods":{"source-balanced":{"logLoss":0.590956205694631,"accuracy":0.6998005319148929,"converged":true},"equal-family":{"logLoss":0.5692939063929177,"accuracy":0.6971409574468077,"converged":true},"equal-model-exposure":{"logLoss":0.5623343621014015,"accuracy":0.7026817375886517,"converged":true},"configuration-exposure":{"logLoss":0.5638440280147383,"accuracy":0.7024601063829781,"converged":true},"equal-model-pair":{"logLoss":0.5644302729723626,"accuracy":0.7031249999999993,"converged":true}}},{"kind":"family","key":"livebench-instructions","totalWeight":17.09090909090952,"predictableWeight":17.09090909090952,"coverage":1,"methods":{"source-balanced":{"logLoss":0.6888260301848096,"accuracy":0.6369680851063818,"converged":true},"equal-family":{"logLoss":0.6598104800686924,"accuracy":0.6546985815602825,"converged":true},"equal-model-exposure":{"logLoss":0.6878278089221707,"accuracy":0.6161347517730483,"converged":true},"configuration-exposure":{"logLoss":0.6872622101010616,"accuracy":0.6179078014184385,"converged":true},"equal-model-pair":{"logLoss":0.7038041034934596,"accuracy":0.6112588652482257,"converged":true}}},{"kind":"family","key":"swe-rebench","totalWeight":7.759920634920638,"predictableWeight":7.759920634920638,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4634706219700085,"accuracy":0.7925083098951675,"converged":true},"equal-family":{"logLoss":0.47102387569328025,"accuracy":0.7925083098951676,"converged":true},"equal-model-exposure":{"logLoss":0.48955607781429034,"accuracy":0.7521094349271286,"converged":true},"configuration-exposure":{"logLoss":0.48502835304269076,"accuracy":0.768217847097929,"converged":true},"equal-model-pair":{"logLoss":0.5072875618543558,"accuracy":0.7628483763743288,"converged":true}}},{"kind":"family","key":"frontiermath","totalWeight":19.884920634921563,"predictableWeight":19.884920634921563,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3849327998478974,"accuracy":0.8221615570744322,"converged":true},"equal-family":{"logLoss":0.38656207959336786,"accuracy":0.825282815306322,"converged":true},"equal-model-exposure":{"logLoss":0.38642846958689986,"accuracy":0.8357020804230653,"converged":true},"configuration-exposure":{"logLoss":0.38469652390129666,"accuracy":0.8388576381959651,"converged":true},"equal-model-pair":{"logLoss":0.3939455473658173,"accuracy":0.8345265416084574,"converged":true}}},{"kind":"family","key":"epoch-game-puzzles","totalWeight":26.97619047619077,"predictableWeight":20.511904761905097,"coverage":0.7603706972639053,"methods":{"source-balanced":{"logLoss":0.5108809999582945,"accuracy":0.7703375894757155,"converged":true},"equal-family":{"logLoss":0.5067261727105983,"accuracy":0.7765283420390744,"converged":true},"equal-model-exposure":{"logLoss":0.5301587150959866,"accuracy":0.7697572064229008,"converged":true},"configuration-exposure":{"logLoss":0.5251631397386712,"accuracy":0.7729493132133826,"converged":true},"equal-model-pair":{"logLoss":0.5446397160375608,"accuracy":0.7722721996517651,"converged":true}}},{"kind":"family","key":"simpleqa","totalWeight":18.035714285714324,"predictableWeight":18.035714285714324,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5379098481663661,"accuracy":0.7217821782178229,"converged":true},"equal-family":{"logLoss":0.5813044558768666,"accuracy":0.7214521452145228,"converged":true},"equal-model-exposure":{"logLoss":0.5867556048770632,"accuracy":0.6917491749174942,"converged":true},"configuration-exposure":{"logLoss":0.5763542481015064,"accuracy":0.7062706270627079,"converged":true},"equal-model-pair":{"logLoss":0.6056875216190583,"accuracy":0.6937293729372963,"converged":true}}},{"kind":"family","key":"vals-finance-agent","totalWeight":19.999999999999936,"predictableWeight":19.999999999999936,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5255040004746774,"accuracy":0.735897435897436,"converged":true},"equal-family":{"logLoss":0.49792272621337463,"accuracy":0.732051282051282,"converged":true},"equal-model-exposure":{"logLoss":0.49941847567716086,"accuracy":0.7307692307692307,"converged":true},"configuration-exposure":{"logLoss":0.503044401842454,"accuracy":0.7333333333333334,"converged":true},"equal-model-pair":{"logLoss":0.5069009542537471,"accuracy":0.7256410256410256,"converged":true}}},{"kind":"family","key":"vals-code-migration","totalWeight":21.500000000000338,"predictableWeight":21.500000000000338,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4387500000548285,"accuracy":0.7851605758582384,"converged":true},"equal-family":{"logLoss":0.4535959990563487,"accuracy":0.7751937984496,"converged":true},"equal-model-exposure":{"logLoss":0.43732274341551697,"accuracy":0.8017718715393024,"converged":true},"configuration-exposure":{"logLoss":0.4342154886930928,"accuracy":0.808416389811728,"converged":true},"equal-model-pair":{"logLoss":0.43073666788837134,"accuracy":0.8106312292358699,"converged":true}}},{"kind":"family","key":"vals-legal-research","totalWeight":20.999999999999545,"predictableWeight":20.999999999999545,"coverage":1,"methods":{"source-balanced":{"logLoss":0.43831699062403906,"accuracy":0.7950058072009318,"converged":true},"equal-family":{"logLoss":0.4319626931318788,"accuracy":0.784552845528458,"converged":true},"equal-model-exposure":{"logLoss":0.42409462758093747,"accuracy":0.8054587688734055,"converged":true},"configuration-exposure":{"logLoss":0.42691132903144613,"accuracy":0.8077816492450663,"converged":true},"equal-model-pair":{"logLoss":0.4353020592764662,"accuracy":0.8101045296167272,"converged":true}}},{"kind":"family","key":"vals-excel-modeling","totalWeight":20.499999999999904,"predictableWeight":20.499999999999904,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3901543933100004,"accuracy":0.8134146341463512,"converged":true},"equal-family":{"logLoss":0.4076921178788873,"accuracy":0.8109756097561074,"converged":true},"equal-model-exposure":{"logLoss":0.39455312278311133,"accuracy":0.8304878048780576,"converged":true},"configuration-exposure":{"logLoss":0.39266376499588274,"accuracy":0.8353658536585452,"converged":true},"equal-model-pair":{"logLoss":0.3991546789208465,"accuracy":0.8414634146341546,"converged":true}}},{"kind":"family","key":"vibe-code","totalWeight":20.999999999999545,"predictableWeight":20.999999999999545,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3742482780887551,"accuracy":0.8339140534262508,"converged":true},"equal-family":{"logLoss":0.39101492599040505,"accuracy":0.8304297328687597,"converged":true},"equal-model-exposure":{"logLoss":0.38649772005236216,"accuracy":0.8466898954703854,"converged":true},"configuration-exposure":{"logLoss":0.3852675110615988,"accuracy":0.8490127758420463,"converged":true},"equal-model-pair":{"logLoss":0.39671325155155934,"accuracy":0.8478513356562158,"converged":true}}},{"kind":"family","key":"vals-tax-agent","totalWeight":19.999999999999936,"predictableWeight":19.999999999999936,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4381241581760448,"accuracy":0.7846153846153846,"converged":true},"equal-family":{"logLoss":0.42408950684716606,"accuracy":0.7871794871794872,"converged":true},"equal-model-exposure":{"logLoss":0.4185972737872666,"accuracy":0.8038461538461539,"converged":true},"configuration-exposure":{"logLoss":0.42269817167751617,"accuracy":0.8051282051282052,"converged":true},"equal-model-pair":{"logLoss":0.4306986061696424,"accuracy":0.8102564102564104,"converged":true}}},{"kind":"source","key":"Artificial Analysis","totalWeight":127.05104118022318,"predictableWeight":13.679735806737474,"coverage":0.10767118222457249,"methods":{"source-balanced":{"logLoss":0.4111215562274695,"accuracy":0.8114987697217397,"converged":true},"equal-family":{"logLoss":0.4460480590870215,"accuracy":0.7978053675154687,"converged":true},"equal-model-exposure":{"logLoss":0.4315575703140712,"accuracy":0.802885923203697,"converged":true},"configuration-exposure":{"logLoss":0.4245390777743373,"accuracy":0.8052097576794041,"converged":true},"equal-model-pair":{"logLoss":0.43012219235141846,"accuracy":0.8030700751515677,"converged":true}}},{"kind":"source","key":"ARC Prize","totalWeight":75.67066326529583,"predictableWeight":46.76676232992582,"coverage":0.6180302948576645,"methods":{"source-balanced":{"logLoss":0.3797916295027192,"accuracy":0.8477534406545045,"converged":true},"equal-family":{"logLoss":0.3968542515670788,"accuracy":0.8382905470841587,"converged":true},"equal-model-exposure":{"logLoss":0.407829534974148,"accuracy":0.8429500590593154,"converged":true},"configuration-exposure":{"logLoss":0.4052312040841407,"accuracy":0.843264163032276,"converged":true},"equal-model-pair":{"logLoss":0.4268022320804099,"accuracy":0.8371970925154797,"converged":true}}},{"kind":"source","key":"Datacurve","totalWeight":20.71999999999947,"predictableWeight":20.71999999999947,"coverage":1,"methods":{"source-balanced":{"logLoss":0.41341236331377973,"accuracy":0.8126447876447883,"converged":true},"equal-family":{"logLoss":0.43687669160797177,"accuracy":0.7868082368082362,"converged":true},"equal-model-exposure":{"logLoss":0.45057636155058367,"accuracy":0.807754182754183,"converged":true},"configuration-exposure":{"logLoss":0.4496887261939727,"accuracy":0.813674388674389,"converged":true},"equal-model-pair":{"logLoss":0.4759827956973106,"accuracy":0.8229729729729738,"converged":true}}},{"kind":"source","key":"LiveCodeBench","totalWeight":1,"predictableWeight":1,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4239900318504463,"accuracy":0.6666666666666666,"converged":true},"equal-family":{"logLoss":0.40719102484571046,"accuracy":0.6666666666666666,"converged":true},"equal-model-exposure":{"logLoss":0.4069684503116423,"accuracy":1,"converged":true},"configuration-exposure":{"logLoss":0.4196482383650062,"accuracy":0.6666666666666666,"converged":true},"equal-model-pair":{"logLoss":0.40224205814584135,"accuracy":1,"converged":true}}},{"kind":"source","key":"Scale","totalWeight":7.690476190476191,"predictableWeight":4.8690476190476195,"coverage":0.6331269349845202,"methods":{"source-balanced":{"logLoss":0.5605063366723586,"accuracy":0.6833740831295843,"converged":true},"equal-family":{"logLoss":0.45692076234242224,"accuracy":0.7072127139364301,"converged":true},"equal-model-exposure":{"logLoss":0.5101157253872669,"accuracy":0.7072127139364301,"converged":true},"configuration-exposure":{"logLoss":0.5016013992894306,"accuracy":0.7072127139364301,"converged":true},"equal-model-pair":{"logLoss":0.5569397242696881,"accuracy":0.7072127139364301,"converged":true}}},{"kind":"source","key":"Terminal-Bench","totalWeight":13.916666666666652,"predictableWeight":11.152777777777766,"coverage":0.8013972055888223,"methods":{"source-balanced":{"logLoss":0.4120879546346668,"accuracy":0.8455790784557912,"converged":true},"equal-family":{"logLoss":0.4904329865995383,"accuracy":0.6861768368617689,"converged":true},"equal-model-exposure":{"logLoss":0.47135336530752225,"accuracy":0.8293897882938984,"converged":true},"configuration-exposure":{"logLoss":0.44318709687837887,"accuracy":0.8704856787048572,"converged":true},"equal-model-pair":{"logLoss":0.4519616731528396,"accuracy":0.8804483188044835,"converged":true}}},{"kind":"source","key":"Cognition","totalWeight":54.72499999999976,"predictableWeight":51.845000000000645,"coverage":0.947373229785306,"methods":{"source-balanced":{"logLoss":0.3595321756259658,"accuracy":0.837026678525415,"converged":true},"equal-family":{"logLoss":0.36651977338066044,"accuracy":0.8383911445441382,"converged":true},"equal-model-exposure":{"logLoss":0.3672267140818253,"accuracy":0.8560506209749498,"converged":true},"configuration-exposure":{"logLoss":0.3610712837391244,"accuracy":0.8618942503116824,"converged":true},"equal-model-pair":{"logLoss":0.3845191770812643,"accuracy":0.867870039969602,"converged":true}}},{"kind":"source","key":"LiveBench","totalWeight":17.090909090909467,"predictableWeight":16.090909090909413,"coverage":0.9414893617021258,"methods":{"source-balanced":{"logLoss":0.6604868696347843,"accuracy":0.6714588377724056,"converged":true},"equal-family":{"logLoss":0.6584070938864026,"accuracy":0.6700015693659861,"converged":true},"equal-model-exposure":{"logLoss":0.6464367179595454,"accuracy":0.6666834813021336,"converged":true},"configuration-exposure":{"logLoss":0.6426910670398603,"accuracy":0.6694074522464434,"converged":true},"equal-model-pair":{"logLoss":0.6413945650784135,"accuracy":0.6681407497085546,"converged":true}}},{"kind":"source","key":"SWE-rebench","totalWeight":7.759920634920638,"predictableWeight":7.759920634920638,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4634706219700085,"accuracy":0.7925083098951675,"converged":true},"equal-family":{"logLoss":0.47102387569328025,"accuracy":0.7925083098951676,"converged":true},"equal-model-exposure":{"logLoss":0.48955607781429034,"accuracy":0.7521094349271286,"converged":true},"configuration-exposure":{"logLoss":0.48502835304269076,"accuracy":0.768217847097929,"converged":true},"equal-model-pair":{"logLoss":0.5072875618543558,"accuracy":0.7628483763743288,"converged":true}}},{"kind":"source","key":"Epoch AI","totalWeight":35.79620580454643,"predictableWeight":21.675171247666242,"coverage":0.6055158852872978,"methods":{"source-balanced":{"logLoss":0.43814734595790755,"accuracy":0.8008161308601105,"converged":true},"equal-family":{"logLoss":0.45407917976484763,"accuracy":0.7998797928270578,"converged":true},"equal-model-exposure":{"logLoss":0.4658903126732436,"accuracy":0.7986116952808985,"converged":true},"configuration-exposure":{"logLoss":0.45719571960730415,"accuracy":0.8049799199943816,"converged":true},"equal-model-pair":{"logLoss":0.47273627560988557,"accuracy":0.8088618567996146,"converged":true}}},{"kind":"source","key":"Vals AI","totalWeight":20.52400203668445,"predictableWeight":19.524002036684433,"coverage":0.9512765591129535,"methods":{"source-balanced":{"logLoss":0.4899528841374923,"accuracy":0.7650588076737879,"converged":true},"equal-family":{"logLoss":0.5103308779819306,"accuracy":0.7466666907594299,"converged":true},"equal-model-exposure":{"logLoss":0.5019659061988679,"accuracy":0.7477098585774384,"converged":true},"configuration-exposure":{"logLoss":0.48600751666918607,"accuracy":0.7636111466527615,"converged":true},"equal-model-pair":{"logLoss":0.5016767639747979,"accuracy":0.7561885383703689,"converged":true}}}],"sourceSensitivity":[{"source":"Artificial Analysis","disconnectedSupportedConfigurations":241,"largestScoreChanges":[{"id":"gpt-5.3-codex--effort-xhigh","baseline":0.18274994289090749,"withoutSource":0.01903234644690052,"change":-0.16371759644400696},{"id":"gemini-3.8-flash--effort-low","baseline":0.6038706084766922,"withoutSource":0.7135082560194704,"change":0.10963764754277827},{"id":"grok-4.7--effort-low","baseline":0.23260427337761289,"withoutSource":0.12871817702354219,"change":-0.1038860963540707},{"id":"claude-sonnet-5-5--effort-low","baseline":0.20124048734416985,"withoutSource":0.11903749491197002,"change":-0.08220299243219983},{"id":"claude-sonnet-5-5--effort-medium","baseline":0.32678284268329194,"withoutSource":0.2664593642589874,"change":-0.06032347842430452},{"id":"kimi-k3--effort-low","baseline":0.1276040501244639,"withoutSource":0.0723684410753036,"change":-0.055235609049160306},{"id":"deepseek-v4-pro-0424--effort-high","baseline":0.0961153034618835,"withoutSource":0.04114238479154921,"change":-0.05497291867033429},{"id":"claude-opus-5--effort-medium","baseline":0.8319049535030567,"withoutSource":0.8838015800325653,"change":0.05189662652950855},{"id":"gpt-5.4--effort-xhigh","baseline":0.37982263109015846,"withoutSource":0.4281558364215731,"change":0.048333205331414664},{"id":"qwen3.5-397b-a17b--effort-non-reasoning","baseline":0.0943903647858945,"withoutSource":0.1416792884903578,"change":0.04728892370446329}]},{"source":"ARC Prize","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"grok-4.7--effort-low","baseline":0.23260427337761289,"withoutSource":0.4875453927793007,"change":0.25494111940168784},{"id":"gemini-4-argon--effort-low","baseline":0.7328455654459817,"withoutSource":0.9736424693011694,"change":0.2407969038551877},{"id":"gemini-3.8-flash--effort-low","baseline":0.6038706084766922,"withoutSource":0.40094620398739855,"change":-0.2029244044892936},{"id":"deepseek-v4.1-flash--effort-high","baseline":0.7015963097002348,"withoutSource":0.9043078900652581,"change":0.20271158036502335},{"id":"claude-haiku-5-5--effort-medium","baseline":0.2547016862349431,"withoutSource":0.4220367024804,"change":0.16733501624545688},{"id":"kimi-k3--effort-high","baseline":0.3654281932425015,"withoutSource":0.5220639518406477,"change":0.1566357585981462},{"id":"gemini-3.6-flash--effort-minimal","baseline":0.07301812201611717,"withoutSource":0.223459795503171,"change":0.15044167348705384},{"id":"claude-haiku-5-5--effort-high","baseline":0.34056604028184706,"withoutSource":0.48077135014533606,"change":0.140205309863489},{"id":"gemini-3.5-flash--effort-low","baseline":0.3523442460739797,"withoutSource":0.48871825315269235,"change":0.13637400707871267},{"id":"claude-haiku-5-5--effort-low","baseline":0.11269543114836837,"withoutSource":0.23593753025894423,"change":0.12324209911057586}]},{"source":"Datacurve","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"glm-5.3-flash--effort-max","baseline":0.37240665773221826,"withoutSource":0.25010819197376616,"change":-0.1222984657584521},{"id":"glm-5.3--effort-max","baseline":0.5818778215067574,"withoutSource":0.46653692930199275,"change":-0.11534089220476462},{"id":"gemini-3.8-flash--effort-medium","baseline":0.7113553355969322,"withoutSource":0.6011507106727315,"change":-0.11020462492420069},{"id":"gpt-5.6-luna--effort-max","baseline":0.39711432955620496,"withoutSource":0.3102031780965917,"change":-0.08691115145961326},{"id":"grok-4.6--effort-medium","baseline":0.6251983967534925,"withoutSource":0.5425832961844482,"change":-0.08261510056904431},{"id":"gpt-5.6-sol--effort-medium","baseline":0.45344336908165067,"withoutSource":0.3718304513225972,"change":-0.0816129177590535},{"id":"gpt-5.6-terra--effort-max","baseline":0.5669778610965056,"withoutSource":0.48736032375352556,"change":-0.07961753734298005},{"id":"kimi-k3--effort-max","baseline":0.6647155773036123,"withoutSource":0.5851642363638727,"change":-0.07955134093973959},{"id":"gpt-5.6-terra--effort-xhigh","baseline":0.4609407036999364,"withoutSource":0.3830489750164287,"change":-0.07789172868350769},{"id":"gemini-3.8-flash--effort-high","baseline":0.7184744919870086,"withoutSource":0.6423532494648447,"change":-0.0761212425221639}]},{"source":"LiveCodeBench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"o4-mini--effort-high","baseline":0.1141101535499744,"withoutSource":0.06599657718797196,"change":-0.04811357636200245},{"id":"claude-sonnet-4-5-20250929--effort-thinking-32k","baseline":0.11102746648740552,"withoutSource":0.11329172857346988,"change":0.002264262086064353},{"id":"gemini-3-flash-preview--effort-reasoning","baseline":0.26763321264031936,"withoutSource":0.2661172426968501,"change":-0.001515969943469253},{"id":"gemini-3.5-flash--effort-medium","baseline":0.27610491597542064,"withoutSource":0.27466852108763956,"change":-0.0014363948877810784},{"id":"qwen3.8-flash-next--effort-reasoning","baseline":0.4032547970350735,"withoutSource":0.4018245716718177,"change":-0.0014302253632558215},{"id":"claude-opus-4-5-20251101--effort-reasoning","baseline":0.17772498909943243,"withoutSource":0.17636931359352823,"change":-0.001355675505904208},{"id":"qwen3.8-27b--effort-medium","baseline":0.13124370428032436,"withoutSource":0.13259742260401697,"change":0.0013537183236926043},{"id":"qwen3.8-27b--effort-low","baseline":0.13232120280947038,"withoutSource":0.13367427546790234,"change":0.0013530726584319586},{"id":"gpt-5.2--effort-high","baseline":0.28599634195703844,"withoutSource":0.28731417633797884,"change":0.001317834380940408},{"id":"gpt-5.4--effort-low","baseline":0.1848501773371577,"withoutSource":0.1861309258812707,"change":0.0012807485441130029}]},{"source":"Scale","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-fable-5--effort-xhigh","baseline":0.7409165255600528,"withoutSource":0.8759396799027722,"change":0.1350231543427194},{"id":"claude-opus-5--effort-xhigh","baseline":0.7852468407834232,"withoutSource":0.7205351945695769,"change":-0.06471164621384629},{"id":"claude-opus-4-8--effort-xhigh","baseline":0.4861014858027099,"withoutSource":0.5495566140986349,"change":0.06345512829592498},{"id":"claude-sonnet-5-5--effort-xhigh","baseline":0.7625670719788503,"withoutSource":0.8156799706105691,"change":0.05311289863171875},{"id":"claude-fable-5-1--effort-xhigh","baseline":0.8383805128572343,"withoutSource":0.7858352972111401,"change":-0.05254521564609416},{"id":"gemini-3.1-pro--effort-high","baseline":0.3476286549515228,"withoutSource":0.3122958144814148,"change":-0.035332840470107985},{"id":"gemini-3.5-flash--effort-high","baseline":0.37998464129275683,"withoutSource":0.41047312941966924,"change":0.030488488126912405},{"id":"claude-opus-4-6--effort-max","baseline":0.40815199969711724,"withoutSource":0.37918351894645036,"change":-0.02896848075066688},{"id":"claude-fable-5--effort-high","baseline":0.7974003321637468,"withoutSource":0.7692738086285469,"change":-0.028126523535199954},{"id":"claude-opus-4-6--effort-non-reasoning","baseline":0.09618606768230231,"withoutSource":0.12329717544602271,"change":0.027111107763720402}]},{"source":"Terminal-Bench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-sonnet-5-5--effort-max","baseline":0.7752346952613443,"withoutSource":0.6891190412967211,"change":-0.08611565396462317},{"id":"grok-4.7--effort-xhigh","baseline":0.6181766255704918,"withoutSource":0.5458403233184254,"change":-0.07233630225206644},{"id":"gemini-3.7-flash--effort-high","baseline":0.5884455537670358,"withoutSource":0.6511907247109766,"change":0.06274517094394083},{"id":"gemini-3.8-flash--effort-high","baseline":0.7184744919870086,"withoutSource":0.6605903769409334,"change":-0.05788411504607527},{"id":"claude-opus-5-5--effort-max","baseline":0.9192642183499763,"withoutSource":0.8691643639186765,"change":-0.05009985443129983},{"id":"claude-sonnet-5--effort-max","baseline":0.34355582708243687,"withoutSource":0.3897509704629374,"change":0.046195143380500514},{"id":"grok-4.6--effort-high","baseline":0.6133733610287327,"withoutSource":0.656541264576239,"change":0.043167903547506215},{"id":"claude-opus-4-8--effort-max","baseline":0.5292818767033628,"withoutSource":0.5701322028677991,"change":0.04085032616443629},{"id":"grok-4.5--effort-high","baseline":0.3309640230079927,"withoutSource":0.3604943407075614,"change":0.02953031769956871},{"id":"gpt-6.1-sol--effort-max","baseline":0.8231507026285795,"withoutSource":0.7951913475623321,"change":-0.02795935506624736}]},{"source":"Cognition","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"deepseek-v4.1-flash--effort-high","baseline":0.7015963097002348,"withoutSource":0.4422786049500829,"change":-0.25931770475015187},{"id":"gemini-4-argon--effort-low","baseline":0.7328455654459817,"withoutSource":0.572388095402122,"change":-0.16045747004385968},{"id":"claude-opus-5--effort-medium","baseline":0.8319049535030567,"withoutSource":0.6871572602134925,"change":-0.14474769328956416},{"id":"claude-sonnet-5-5--effort-low","baseline":0.20124048734416985,"withoutSource":0.33810710245270137,"change":0.13686661510853151},{"id":"deepseek-v4-flash--effort-high","baseline":0.21941248809962402,"withoutSource":0.3535647312124876,"change":0.13415224311286358},{"id":"claude-sonnet-5-5--effort-xhigh","baseline":0.7625670719788503,"withoutSource":0.6308637022582735,"change":-0.13170336972057684},{"id":"gpt-6-sol--effort-high","baseline":0.5988679090143599,"withoutSource":0.4791657941266519,"change":-0.11970211488770804},{"id":"claude-haiku-5-5--effort-high","baseline":0.34056604028184706,"withoutSource":0.2222918293533972,"change":-0.11827421092844986},{"id":"claude-sonnet-5-5--effort-medium","baseline":0.32678284268329194,"withoutSource":0.4436124250692175,"change":0.11682958238592556},{"id":"claude-haiku-5-5--effort-medium","baseline":0.2547016862349431,"withoutSource":0.13838757225312764,"change":-0.11631411398181546}]},{"source":"LiveBench","disconnectedSupportedConfigurations":1,"largestScoreChanges":[{"id":"claude-sonnet-4-6--effort-medium","baseline":0.1432365900388354,"withoutSource":0.07970517160579492,"change":-0.06353141843304048},{"id":"claude-sonnet-5-5--effort-xhigh","baseline":0.7625670719788503,"withoutSource":0.8242662700313458,"change":0.06169919805249546},{"id":"claude-haiku-5-5--effort-xhigh","baseline":0.45399371763893637,"withoutSource":0.5108885285820329,"change":0.05689481094309656},{"id":"claude-sonnet-5-5--effort-max","baseline":0.7752346952613443,"withoutSource":0.8213331810507706,"change":0.046098485789426324},{"id":"claude-haiku-5-5--effort-max","baseline":0.4388976713672646,"withoutSource":0.48448700081823737,"change":0.04558932945097277},{"id":"muse-wonder--effort-max","baseline":0.7321209992509411,"withoutSource":0.7773898128848565,"change":0.04526881363391544},{"id":"gemini-3.8-flash--effort-high","baseline":0.7184744919870086,"withoutSource":0.7605128563165894,"change":0.042038364329580746},{"id":"claude-opus-4-7--effort-xhigh","baseline":0.38697033423396476,"withoutSource":0.3451039735418773,"change":-0.04186636069208749},{"id":"gpt-6-sol--effort-max","baseline":0.6623840158950337,"withoutSource":0.702410015270786,"change":0.04002599937575224},{"id":"grok-4.7--effort-xhigh","baseline":0.6181766255704918,"withoutSource":0.6547873333123831,"change":0.036610707741891346}]},{"source":"SWE-rebench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"deepseek-v4-pro-0424--effort-high","baseline":0.0961153034618835,"withoutSource":0.2247324509153393,"change":0.12861714745345582},{"id":"gpt-5.3-codex--effort-xhigh","baseline":0.18274994289090749,"withoutSource":0.30220053274518116,"change":0.11945058985427368},{"id":"gpt-5.2--effort-medium","baseline":0.22531502441808815,"withoutSource":0.1549388998978923,"change":-0.07037612452019584},{"id":"claude-opus-4-7--effort-high","baseline":0.3269609272242716,"withoutSource":0.27297905322338567,"change":-0.05398187400088594},{"id":"gpt-5.6-sol--effort-medium","baseline":0.45344336908165067,"withoutSource":0.5036938254396929,"change":0.050250456358042206},{"id":"claude-fable-5--effort-high","baseline":0.7974003321637468,"withoutSource":0.844131025189255,"change":0.04673069302550814},{"id":"gpt-5.5--effort-medium","baseline":0.441367680834683,"withoutSource":0.3956914111716734,"change":-0.04567626966300958},{"id":"claude-opus-4-8--effort-xhigh","baseline":0.4861014858027099,"withoutSource":0.4409476868861655,"change":-0.04515379891654442},{"id":"claude-opus-5--effort-high","baseline":0.790553136546194,"withoutSource":0.7551963913629524,"change":-0.03535674518324161},{"id":"claude-sonnet-5--effort-high","baseline":0.25778760194914085,"withoutSource":0.28103316443732324,"change":0.02324556248818238}]},{"source":"Epoch AI","disconnectedSupportedConfigurations":13,"largestScoreChanges":[{"id":"claude-opus-4-6--effort-low","baseline":0.04986829901736858,"withoutSource":0.19447749061057115,"change":0.14460919159320257},{"id":"claude-fable-5--effort-low","baseline":0.5864641046398065,"withoutSource":0.6898036761762975,"change":0.10333957153649098},{"id":"claude-opus-4-6--effort-max","baseline":0.40815199969711724,"withoutSource":0.4799252147706597,"change":0.07177321507354245},{"id":"gemini-3-flash-preview--effort-high","baseline":0.23304171955123917,"withoutSource":0.16867603307670423,"change":-0.06436568647453494},{"id":"claude-opus-5--effort-low","baseline":0.4435690955310805,"withoutSource":0.5077733366820592,"change":0.06420424115097867},{"id":"glm-5.3-flash--effort-max","baseline":0.37240665773221826,"withoutSource":0.43596031798151985,"change":0.06355366024930159},{"id":"glm-5.3--effort-max","baseline":0.5818778215067574,"withoutSource":0.6395800358889923,"change":0.057702214382234884},{"id":"claude-sonnet-4-6--effort-max","baseline":0.18970871566299438,"withoutSource":0.24620306540216838,"change":0.056494349739174},{"id":"claude-sonnet-5--effort-max","baseline":0.34355582708243687,"withoutSource":0.3935643097998999,"change":0.050008482717463054},{"id":"kimi-k3--effort-low","baseline":0.1276040501244639,"withoutSource":0.17652034811628314,"change":0.048916297991819235}]},{"source":"Vals AI","disconnectedSupportedConfigurations":1,"largestScoreChanges":[{"id":"deepseek-v4-flash--effort-high","baseline":0.21941248809962402,"withoutSource":0.15829361831673314,"change":-0.06111886978289088},{"id":"claude-sonnet-5--effort-max","baseline":0.34355582708243687,"withoutSource":0.28492831429310245,"change":-0.058627512789334424},{"id":"gemini-3-flash-preview--effort-high","baseline":0.23304171955123917,"withoutSource":0.287345731117755,"change":0.05430401156651585},{"id":"claude-opus-4-7--effort-max","baseline":0.33492456408559734,"withoutSource":0.285493845322182,"change":-0.049430718763415316},{"id":"gpt-6-sol--effort-max","baseline":0.6623840158950337,"withoutSource":0.7041427693885659,"change":0.0417587534935322},{"id":"claude-sonnet-4-6--effort-max","baseline":0.18970871566299438,"withoutSource":0.14890760935614875,"change":-0.040801106306845636},{"id":"gpt-6.1-sol--effort-max","baseline":0.8231507026285795,"withoutSource":0.8607617820659713,"change":0.03761107943739184},{"id":"muse-wonder-full--effort-max","baseline":0.8500987270785633,"withoutSource":0.8164434959703145,"change":-0.03365523110824875},{"id":"muse-spark-1.1--effort-xhigh","baseline":0.40190957266266264,"withoutSource":0.3697356882002966,"change":-0.03217388446236602},{"id":"claude-opus-4-8--effort-max","baseline":0.5292818767033628,"withoutSource":0.4987330154647151,"change":-0.030548861238647695}]},{"source":"Provider reports · Anthropic","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-fable-5-1--effort-max","baseline":0.8990820461798595,"withoutSource":0.8378562191658316,"change":-0.0612258270140279},{"id":"claude-fable-5--effort-max","baseline":0.7395803680955662,"withoutSource":0.7897124299420465,"change":0.050132061846480336},{"id":"claude-opus-5--effort-max","baseline":0.7308935047612021,"withoutSource":0.7511742281972754,"change":0.020280723436073345},{"id":"claude-opus-5-5--effort-max","baseline":0.9192642183499763,"withoutSource":0.9163638108839122,"change":-0.0029004074660641255},{"id":"claude-sonnet-5-5--effort-max","baseline":0.7752346952613443,"withoutSource":0.7724024690497275,"change":-0.0028322262116167174},{"id":"claude-opus-5--effort-xhigh","baseline":0.7852468407834232,"withoutSource":0.7826472657541309,"change":-0.0025995750292923114},{"id":"muse-wonder-full--effort-max","baseline":0.8500987270785633,"withoutSource":0.8488356275694963,"change":-0.0012630995090670005},{"id":"claude-fable-5--effort-medium","baseline":0.7531156528332978,"withoutSource":0.7520273135176163,"change":-0.0010883393156815302},{"id":"glm-5.3--effort-max","baseline":0.5818778215067574,"withoutSource":0.5808173696711593,"change":-0.0010604518355981085},{"id":"claude-opus-4-8--effort-max","baseline":0.5292818767033628,"withoutSource":0.5303261867622872,"change":0.0010443100589243581}]},{"source":"Provider reports · Moonshot AI","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"kimi-k3--effort-max","baseline":0.6647155773036123,"withoutSource":0.5708026707644934,"change":-0.09391290653911888},{"id":"gpt-5.5--effort-xhigh","baseline":0.5686822678550768,"withoutSource":0.6451336187860727,"change":0.07645135093099586},{"id":"kimi-k2.6--effort-reasoning","baseline":0.23141342309568821,"withoutSource":0.2048501524909646,"change":-0.026563270604723604},{"id":"claude-opus-4-8--effort-max","baseline":0.5292818767033628,"withoutSource":0.5110663944800966,"change":-0.01821548222326619},{"id":"glm-5.2--effort-max","baseline":0.24611727687589333,"withoutSource":0.2606656481654873,"change":0.014548371289593992},{"id":"gpt-5.4--effort-xhigh","baseline":0.37982263109015846,"withoutSource":0.39043942469574594,"change":0.010616793605587482},{"id":"glm-5.3-flash--effort-reasoning","baseline":0.4063006062730237,"withoutSource":0.39984213524412554,"change":-0.006458471028898183},{"id":"step-5-preview--effort-reasoning","baseline":0.44330647820745145,"withoutSource":0.43688372887882315,"change":-0.006422749328628297},{"id":"gemini-3.1-pro--effort-high","baseline":0.3476286549515228,"withoutSource":0.35384545037511567,"change":0.00621679542359288},{"id":"qwen3.8-2.4t-a95b--effort-reasoning","baseline":0.42429541929465603,"withoutSource":0.4180904819636641,"change":-0.006204937330991922}]},{"source":"Provider reports · Meta","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"muse-spark-1.3--effort-xhigh","baseline":0.7427064995842336,"withoutSource":0.6560720123973566,"change":-0.08663448718687705},{"id":"muse-spark-1.2--effort-xhigh","baseline":0.4564649514260552,"withoutSource":0.5150217072610046,"change":0.0585567558349494},{"id":"muse-wonder--effort-max","baseline":0.7321209992509411,"withoutSource":0.7276805196102676,"change":-0.004440479640673511},{"id":"muse-wonder-full--effort-max","baseline":0.8500987270785633,"withoutSource":0.8473136715416435,"change":-0.002785055536919767},{"id":"qwen-3.8-max-0902--effort-xhigh","baseline":0.5256484128461368,"withoutSource":0.527776609414868,"change":0.0021281965687312},{"id":"claude-opus-4-5-20251101--effort-thinking-64k","baseline":0.3289358744880357,"withoutSource":0.32699560442906356,"change":-0.0019402700589721267},{"id":"claude-sonnet-5-5--effort-max","baseline":0.7752346952613443,"withoutSource":0.7733022900850223,"change":-0.001932405176321983},{"id":"claude-sonnet-5-5--effort-xhigh","baseline":0.7625670719788503,"withoutSource":0.7609961474893364,"change":-0.001570924489513903},{"id":"gpt-6-sol--effort-max","baseline":0.6623840158950337,"withoutSource":0.6608545224329779,"change":-0.0015294934620557754},{"id":"gpt-6.1-sol--effort-max","baseline":0.8231507026285795,"withoutSource":0.8216311885296497,"change":-0.0015195140989298084}]},{"source":"Provider reports · Mistral","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"gpt-6-astra--effort-xhigh","baseline":0.959334185153284,"withoutSource":0.959334185153284,"change":0},{"id":"claude-opus-5-5--effort-high","baseline":0.9227331396853704,"withoutSource":0.9227331396853704,"change":0},{"id":"claude-opus-5-5--effort-max","baseline":0.9192642183499763,"withoutSource":0.9192642183499763,"change":0},{"id":"gpt-6-astra--effort-high","baseline":0.9184835607694163,"withoutSource":0.9184835607694163,"change":0},{"id":"gpt-6-astra--effort-max","baseline":0.906830004646622,"withoutSource":0.906830004646622,"change":0},{"id":"gpt-6-astra--effort-medium","baseline":0.9041123205727614,"withoutSource":0.9041123205727614,"change":0},{"id":"gemini-4-argon--effort-medium","baseline":0.9018697849083788,"withoutSource":0.9018697849083788,"change":0},{"id":"claude-fable-5-1--effort-max","baseline":0.8990820461798595,"withoutSource":0.8990820461798595,"change":0},{"id":"claude-opus-5-5--effort-medium","baseline":0.8968900120893727,"withoutSource":0.8968900120893727,"change":0},{"id":"gemini-4-argon--effort-high","baseline":0.8940216642928943,"withoutSource":0.8940216642928943,"change":0}]},{"source":"Provider reports · OpenAI","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"gpt-6-sol--effort-max","baseline":0.6623840158950337,"withoutSource":0.7253895022195777,"change":0.06300548632454395},{"id":"gpt-6-astra--effort-low","baseline":0.7927593849681646,"withoutSource":0.731867934548367,"change":-0.0608914504197976},{"id":"gpt-6-sol--effort-xhigh","baseline":0.6411878464125557,"withoutSource":0.695585281248197,"change":0.0543974348356413},{"id":"gpt-6-sol--effort-high","baseline":0.5988679090143599,"withoutSource":0.6491276084189369,"change":0.050259699404576974},{"id":"gpt-6.1-sol--effort-high","baseline":0.8591089426089601,"withoutSource":0.8092162668132823,"change":-0.0498926757956778},{"id":"gpt-6-astra--effort-max","baseline":0.906830004646622,"withoutSource":0.8587654345741923,"change":-0.0480645700724297},{"id":"gpt-6.1-sol--effort-low","baseline":0.6276461507445094,"withoutSource":0.6732473493784782,"change":0.04560119863396883},{"id":"gpt-6-sol--effort-medium","baseline":0.48158702169889733,"withoutSource":0.5156608877007268,"change":0.03407386600182949},{"id":"gpt-6-astra--effort-xhigh","baseline":0.959334185153284,"withoutSource":0.9314623729746289,"change":-0.027871812178655087},{"id":"gpt-6-astra--effort-medium","baseline":0.9041123205727614,"withoutSource":0.8775467303031664,"change":-0.02656559026959493}]},{"source":"All provider reports","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"kimi-k3--effort-max","baseline":0.6647155773036123,"withoutSource":0.5712382789832925,"change":-0.09347729832031981},{"id":"muse-spark-1.3--effort-xhigh","baseline":0.7427064995842336,"withoutSource":0.6520598117519161,"change":-0.09064668783231755},{"id":"gpt-5.5--effort-xhigh","baseline":0.5686822678550768,"withoutSource":0.64085513858274,"change":0.07217287072766321},{"id":"claude-fable-5-1--effort-max","baseline":0.8990820461798595,"withoutSource":0.833438104395467,"change":-0.06564394178439259},{"id":"gpt-6-astra--effort-low","baseline":0.7927593849681646,"withoutSource":0.7302291383251743,"change":-0.06253024664299023},{"id":"gpt-6-sol--effort-max","baseline":0.6623840158950337,"withoutSource":0.7205974835699523,"change":0.05821346767491864},{"id":"muse-spark-1.2--effort-xhigh","baseline":0.4564649514260552,"withoutSource":0.5104080296082782,"change":0.05394307818222305},{"id":"gpt-6.1-sol--effort-high","baseline":0.8591089426089601,"withoutSource":0.8071373763601871,"change":-0.05197156624877297},{"id":"gpt-6-sol--effort-xhigh","baseline":0.6411878464125557,"withoutSource":0.6924980018362347,"change":0.051310155423679005},{"id":"gpt-6-astra--effort-max","baseline":0.906830004646622,"withoutSource":0.8555612032014773,"change":-0.051268801445144674}]}],"configurationStability":{"gpt-6-astra--effort-xhigh":{"score":0.959334185153284,"rank":1,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9691959435242389,"rank":1,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9605007678570551,"rank":3,"remainingConfigurations":444},{"removed":"Datacurve","score":0.9541408562555184,"rank":1,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9593327657714958,"rank":1,"remainingConfigurations":444},{"removed":"Scale","score":0.9605252186931422,"rank":1,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.9590558311165506,"rank":1,"remainingConfigurations":444},{"removed":"Cognition","score":0.9464120106591136,"rank":1,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9636249832570337,"rank":1,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9586972415692786,"rank":1,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.958693598515909,"rank":1,"remainingConfigurations":431},{"removed":"Vals AI","score":0.9585855656305254,"rank":1,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.9592587530298271,"rank":1,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.9598213090801341,"rank":1,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9591447699453584,"rank":1,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.959334185153284,"rank":1,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.9314623729746289,"rank":1,"remainingConfigurations":444},{"removed":"All provider reports","score":0.933123847679091,"rank":1,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9593131340477302,"rank":1,"remainingConfigurations":444},{"removed":"briefcase","score":0.9598972976935173,"rank":1,"remainingConfigurations":444},{"removed":"aime","score":0.9592533827153983,"rank":1,"remainingConfigurations":444},{"removed":"apex-agents","score":0.959400456835184,"rank":1,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9604555884957632,"rank":1,"remainingConfigurations":444},{"removed":"automationbench","score":0.9588364064424124,"rank":1,"remainingConfigurations":444},{"removed":"critpt","score":0.9592516403105322,"rank":1,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9593555616773202,"rank":1,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.958894436533797,"rank":1,"remainingConfigurations":444},{"removed":"gdpval","score":0.9607925810266195,"rank":1,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9592973204528356,"rank":1,"remainingConfigurations":444},{"removed":"gpqa","score":0.9584861589694523,"rank":1,"remainingConfigurations":444},{"removed":"harvey","score":0.9592194594635854,"rank":1,"remainingConfigurations":444},{"removed":"hle","score":0.9597020872590131,"rank":1,"remainingConfigurations":444},{"removed":"ifbench","score":0.958653073832957,"rank":1,"remainingConfigurations":444},{"removed":"itbench","score":0.959320907328959,"rank":1,"remainingConfigurations":444},{"removed":"livecodebench","score":0.9592690909597495,"rank":1,"remainingConfigurations":444},{"removed":"math500","score":0.9593020321495859,"rank":1,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9598082019582176,"rank":1,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9600581577364476,"rank":1,"remainingConfigurations":444},{"removed":"omniscience","score":0.9595141313502142,"rank":1,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9594787748672431,"rank":1,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.9592164918760132,"rank":1,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.9587578923582581,"rank":1,"remainingConfigurations":444},{"removed":"arc-agi","score":0.968237373431004,"rank":1,"remainingConfigurations":444},{"removed":"deepswe","score":0.9539613945623121,"rank":1,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9591833394303554,"rank":1,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.9564493397793976,"rank":1,"remainingConfigurations":444},{"removed":"frontiercode","score":0.9464120106591136,"rank":1,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.9596157155029026,"rank":1,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9590209836259443,"rank":1,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9593460068606303,"rank":1,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9587471746158117,"rank":1,"remainingConfigurations":444},{"removed":"livebench-math","score":0.959344382612075,"rank":1,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9594503572195995,"rank":1,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9591618072365137,"rank":1,"remainingConfigurations":444},{"removed":"livebench-data","score":0.958944083888936,"rank":1,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9593051101052051,"rank":1,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.9590224411643521,"rank":1,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9601342562151055,"rank":1,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9586972415692786,"rank":1,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9588572262505085,"rank":1,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9587330519170264,"rank":1,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9600801610122295,"rank":1,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9594580591686506,"rank":1,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.9591616895878885,"rank":1,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9593191084602218,"rank":1,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.959196191771022,"rank":1,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9591013836429801,"rank":1,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.959330720427534,"rank":1,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-opus-5-5--effort-high":{"score":0.9227331396853704,"rank":2,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9417317209223205,"rank":2,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9377168051151598,"rank":4,"remainingConfigurations":444},{"removed":"Datacurve","score":0.919771138948631,"rank":2,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9225953617896824,"rank":2,"remainingConfigurations":444},{"removed":"Scale","score":0.9278730569574187,"rank":2,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.9234800522226995,"rank":2,"remainingConfigurations":444},{"removed":"Cognition","score":0.8601952508488622,"rank":11,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9282672546171863,"rank":4,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9217509768969153,"rank":2,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9266103244988897,"rank":2,"remainingConfigurations":431},{"removed":"Vals AI","score":0.9191628763043402,"rank":3,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.921978976834492,"rank":2,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.921773904970869,"rank":2,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9224802088714993,"rank":2,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.9227331396853704,"rank":2,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.9223774458174961,"rank":2,"remainingConfigurations":444},{"removed":"All provider reports","score":0.9204185935545053,"rank":2,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9225491176276205,"rank":2,"remainingConfigurations":444},{"removed":"briefcase","score":0.9215064065286769,"rank":2,"remainingConfigurations":444},{"removed":"aime","score":0.9217160550181455,"rank":2,"remainingConfigurations":444},{"removed":"apex-agents","score":0.9228668163866479,"rank":2,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9245434897058553,"rank":2,"remainingConfigurations":444},{"removed":"automationbench","score":0.9243264082289956,"rank":2,"remainingConfigurations":444},{"removed":"critpt","score":0.9246005801955169,"rank":2,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9226365010916754,"rank":2,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9239282846632678,"rank":3,"remainingConfigurations":444},{"removed":"gdpval","score":0.9230554654729826,"rank":2,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9224804112266601,"rank":2,"remainingConfigurations":444},{"removed":"gpqa","score":0.9233694287485505,"rank":2,"remainingConfigurations":444},{"removed":"harvey","score":0.9229571283599124,"rank":3,"remainingConfigurations":444},{"removed":"hle","score":0.9251592851062194,"rank":2,"remainingConfigurations":444},{"removed":"ifbench","score":0.9207172191342679,"rank":2,"remainingConfigurations":444},{"removed":"itbench","score":0.922868899642394,"rank":3,"remainingConfigurations":444},{"removed":"livecodebench","score":0.9221411042024211,"rank":2,"remainingConfigurations":444},{"removed":"math500","score":0.9225045338913477,"rank":2,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9229929882097853,"rank":2,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9255995976560261,"rank":2,"remainingConfigurations":444},{"removed":"omniscience","score":0.9239747760872513,"rank":2,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9211967913904813,"rank":2,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.9227624457328089,"rank":2,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.9226407307956098,"rank":2,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9344274778920093,"rank":5,"remainingConfigurations":444},{"removed":"deepswe","score":0.9198994047078134,"rank":3,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9227418443001069,"rank":2,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.9230665197588247,"rank":2,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8601952508488622,"rank":11,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.9226450919575954,"rank":2,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9225747407267794,"rank":2,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9221190810350753,"rank":2,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.921477371618339,"rank":2,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9223283504629042,"rank":2,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9216557979797914,"rank":2,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9233624069466363,"rank":2,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9233527998559788,"rank":2,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.922211249755823,"rank":2,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.9223802111347288,"rank":2,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.923873478422828,"rank":2,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9217509768969153,"rank":2,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9228544932039401,"rank":2,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9214713348717279,"rank":2,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9243386143436831,"rank":2,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9228736237302385,"rank":2,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.9226200929931053,"rank":2,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9224379189910502,"rank":2,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.9225192184057466,"rank":2,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9223850535522704,"rank":2,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.9224390607282308,"rank":2,"remainingConfigurations":444}],"sharedOrderConflicts":2},"claude-opus-5-5--effort-max":{"score":0.9192642183499763,"rank":3,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9411247428529536,"rank":3,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9282250775555698,"rank":6,"remainingConfigurations":444},{"removed":"Datacurve","score":0.9111351844352341,"rank":3,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9192308375751091,"rank":3,"remainingConfigurations":444},{"removed":"Scale","score":0.9196731731246496,"rank":4,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8691643639186765,"rank":11,"remainingConfigurations":444},{"removed":"Cognition","score":0.9274986135845723,"rank":2,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9293274319993174,"rank":2,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9178481677389296,"rank":3,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9245771936043424,"rank":3,"remainingConfigurations":431},{"removed":"Vals AI","score":0.916153008482362,"rank":5,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.9163638108839122,"rank":4,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.9179387330794927,"rank":4,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9189306016306674,"rank":3,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.9192642183499763,"rank":3,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.9188141565714313,"rank":4,"remainingConfigurations":444},{"removed":"All provider reports","score":0.9142256467113091,"rank":4,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9182405592079387,"rank":4,"remainingConfigurations":444},{"removed":"briefcase","score":0.9170162625235947,"rank":4,"remainingConfigurations":444},{"removed":"aime","score":0.9187548147910328,"rank":3,"remainingConfigurations":444},{"removed":"apex-agents","score":0.9191954729168713,"rank":3,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9185700676626555,"rank":4,"remainingConfigurations":444},{"removed":"automationbench","score":0.918190784573533,"rank":3,"remainingConfigurations":444},{"removed":"critpt","score":0.9196715941722782,"rank":3,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9191670961332434,"rank":3,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9201279498117286,"rank":4,"remainingConfigurations":444},{"removed":"gdpval","score":0.9178989899777913,"rank":4,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9191190549789418,"rank":3,"remainingConfigurations":444},{"removed":"gpqa","score":0.920158808802228,"rank":3,"remainingConfigurations":444},{"removed":"harvey","score":0.9259727398746107,"rank":2,"remainingConfigurations":444},{"removed":"hle","score":0.9195511002603886,"rank":3,"remainingConfigurations":444},{"removed":"ifbench","score":0.9177243190616754,"rank":3,"remainingConfigurations":444},{"removed":"itbench","score":0.9281116719852701,"rank":2,"remainingConfigurations":444},{"removed":"livecodebench","score":0.9190450240362074,"rank":3,"remainingConfigurations":444},{"removed":"math500","score":0.919169142510198,"rank":3,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9198839246249837,"rank":3,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9209625807407488,"rank":3,"remainingConfigurations":444},{"removed":"omniscience","score":0.9198877370802391,"rank":3,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9177914363299671,"rank":4,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.9175414021588048,"rank":3,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8671666766287899,"rank":11,"remainingConfigurations":444},{"removed":"arc-agi","score":0.923821836586879,"rank":8,"remainingConfigurations":444},{"removed":"deepswe","score":0.9113742314507847,"rank":5,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9192698557656928,"rank":3,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.9165655026858343,"rank":3,"remainingConfigurations":444},{"removed":"frontiercode","score":0.9274986135845723,"rank":2,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.9195799997600704,"rank":3,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9182750482796501,"rank":3,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9197059145624831,"rank":3,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9172973564582545,"rank":4,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9184571614528717,"rank":3,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9176111106252799,"rank":4,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9199084907211835,"rank":3,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9208480334270419,"rank":3,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9183903782403253,"rank":3,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.918733336006398,"rank":3,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9209526192413863,"rank":3,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9178481677389296,"rank":3,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9186290852629707,"rank":3,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.917988632088567,"rank":3,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9209858959784719,"rank":3,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9195452144325825,"rank":3,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.9189521742808274,"rank":3,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9186256798810494,"rank":3,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.9186714782992608,"rank":3,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9184962782396435,"rank":3,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.9186347201326192,"rank":3,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-6-astra--effort-high":{"score":0.9184835607694163,"rank":4,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.936258788188551,"rank":4,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9217250276339333,"rank":8,"remainingConfigurations":444},{"removed":"Datacurve","score":0.9098299522210836,"rank":4,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9184838407989421,"rank":4,"remainingConfigurations":444},{"removed":"Scale","score":0.9213906288322455,"rank":3,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.9183904624183731,"rank":3,"remainingConfigurations":444},{"removed":"Cognition","score":0.8949448057959297,"rank":4,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9219978616414077,"rank":5,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9174467329545187,"rank":4,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9182751151883132,"rank":4,"remainingConfigurations":431},{"removed":"Vals AI","score":0.9171254441313258,"rank":4,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.918398608388101,"rank":3,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.9179929840906024,"rank":3,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9182864504554674,"rank":4,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.9184835607694163,"rank":4,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.9210785955293298,"rank":3,"remainingConfigurations":444},{"removed":"All provider reports","score":0.9204015829681303,"rank":3,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9184514721196316,"rank":3,"remainingConfigurations":444},{"removed":"briefcase","score":0.9198187634805626,"rank":3,"remainingConfigurations":444},{"removed":"aime","score":0.9181584278777541,"rank":4,"remainingConfigurations":444},{"removed":"apex-agents","score":0.91862629911853,"rank":4,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9197263478462071,"rank":3,"remainingConfigurations":444},{"removed":"automationbench","score":0.909340910054874,"rank":4,"remainingConfigurations":444},{"removed":"critpt","score":0.9191390503694309,"rank":4,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9184590527153603,"rank":4,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9298439590804232,"rank":2,"remainingConfigurations":444},{"removed":"gdpval","score":0.9208123403351477,"rank":3,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9183809511852293,"rank":4,"remainingConfigurations":444},{"removed":"gpqa","score":0.9172003493567922,"rank":4,"remainingConfigurations":444},{"removed":"harvey","score":0.918172376254749,"rank":4,"remainingConfigurations":444},{"removed":"hle","score":0.9195171830992539,"rank":4,"remainingConfigurations":444},{"removed":"ifbench","score":0.9171570721719134,"rank":4,"remainingConfigurations":444},{"removed":"itbench","score":0.9183938838152942,"rank":4,"remainingConfigurations":444},{"removed":"livecodebench","score":0.9182984179458318,"rank":4,"remainingConfigurations":444},{"removed":"math500","score":0.9183943299033693,"rank":4,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9194073533615326,"rank":4,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9201815683686084,"rank":4,"remainingConfigurations":444},{"removed":"omniscience","score":0.9188709717930724,"rank":4,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9184791833914853,"rank":3,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.9100863373797871,"rank":4,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.9177839674623348,"rank":3,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9380357151194536,"rank":4,"remainingConfigurations":444},{"removed":"deepswe","score":0.9236689785826089,"rank":2,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9184851608238356,"rank":4,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.912050211892089,"rank":4,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8949448057959297,"rank":4,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.9190572763813947,"rank":4,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9174321824210909,"rank":4,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9184324704180941,"rank":4,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9175485622952883,"rank":3,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9184479514378232,"rank":4,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9181623797019904,"rank":3,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9188246509034995,"rank":4,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9184435393368418,"rank":4,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9179470613436737,"rank":4,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.918177052329539,"rank":4,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.919389510758787,"rank":4,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9174467329545187,"rank":4,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9179248084265635,"rank":4,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9173398122314017,"rank":4,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9203085546418822,"rank":4,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9187320963095414,"rank":4,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.9181395411650356,"rank":4,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9185114860937066,"rank":4,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.9182160543540941,"rank":4,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9180131024104571,"rank":4,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.9185020914495169,"rank":4,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-6-astra--effort-max":{"score":0.906830004646622,"rank":5,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9080275801438229,"rank":8,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9042536285215018,"rank":11,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8905221748977391,"rank":7,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.906816978839004,"rank":5,"remainingConfigurations":444},{"removed":"Scale","score":0.9095643614980501,"rank":5,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8962140214334836,"rank":8,"remainingConfigurations":444},{"removed":"Cognition","score":0.8887753627248726,"rank":5,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9292221993198374,"rank":3,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9049422931488943,"rank":5,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9019896902327966,"rank":6,"remainingConfigurations":431},{"removed":"Vals AI","score":0.9317905352116758,"rank":2,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.905977969282147,"rank":5,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.905996533720223,"rank":5,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9060728468794897,"rank":5,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.906830004646622,"rank":5,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8587654345741923,"rank":11,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8555612032014773,"rank":10,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9070776394347152,"rank":5,"remainingConfigurations":444},{"removed":"briefcase","score":0.9066019781453201,"rank":5,"remainingConfigurations":444},{"removed":"aime","score":0.9075937778877652,"rank":5,"remainingConfigurations":444},{"removed":"apex-agents","score":0.9069421150613066,"rank":5,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9078271707844223,"rank":5,"remainingConfigurations":444},{"removed":"automationbench","score":0.9043250413374846,"rank":5,"remainingConfigurations":444},{"removed":"critpt","score":0.907091012786157,"rank":5,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9070721475208346,"rank":5,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9141687208232544,"rank":5,"remainingConfigurations":444},{"removed":"gdpval","score":0.9074314265299469,"rank":5,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9068361310268799,"rank":5,"remainingConfigurations":444},{"removed":"gpqa","score":0.9062623216323779,"rank":5,"remainingConfigurations":444},{"removed":"harvey","score":0.9100124635458043,"rank":5,"remainingConfigurations":444},{"removed":"hle","score":0.9077671571968261,"rank":5,"remainingConfigurations":444},{"removed":"ifbench","score":0.9057209032867792,"rank":5,"remainingConfigurations":444},{"removed":"itbench","score":0.907341640929265,"rank":5,"remainingConfigurations":444},{"removed":"livecodebench","score":0.9068224604883762,"rank":5,"remainingConfigurations":444},{"removed":"math500","score":0.9068381228068404,"rank":5,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9073417041531112,"rank":5,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9085072565215325,"rank":5,"remainingConfigurations":444},{"removed":"omniscience","score":0.9081258259219176,"rank":5,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9062448949534896,"rank":5,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.903485925259219,"rank":5,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8919695938757606,"rank":8,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9187535131551652,"rank":9,"remainingConfigurations":444},{"removed":"deepswe","score":0.8882691141218322,"rank":7,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9068290826956327,"rank":5,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.9034803039999525,"rank":5,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8887753627248726,"rank":5,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.907254735762632,"rank":5,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9057863247332344,"rank":5,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9066756239404637,"rank":5,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9057006523609209,"rank":5,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9060382846550229,"rank":5,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9081162091258538,"rank":5,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9062548334419911,"rank":5,"remainingConfigurations":444},{"removed":"livebench-data","score":0.904623736734736,"rank":5,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9087184239269789,"rank":5,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.9060550882842878,"rank":5,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9081145861652119,"rank":5,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9049422931488943,"rank":5,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9053111752115752,"rank":5,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9053588969549254,"rank":5,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9086180638693083,"rank":5,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9119229632219494,"rank":5,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.9015808925004173,"rank":7,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9108597179583663,"rank":5,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.9040824051248944,"rank":5,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9020528106796907,"rank":6,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.9106543989406674,"rank":5,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gpt-6-astra--effort-medium":{"score":0.9041123205727614,"rank":6,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9220323385588157,"rank":6,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9106118950337732,"rank":9,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8908788970175788,"rank":6,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9041145438757522,"rank":6,"remainingConfigurations":444},{"removed":"Scale","score":0.9077450994822961,"rank":6,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.9024532349588239,"rank":4,"remainingConfigurations":444},{"removed":"Cognition","score":0.8868987011348687,"rank":6,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9074365091082038,"rank":7,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9030365184110329,"rank":6,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9030184120402717,"rank":5,"remainingConfigurations":431},{"removed":"Vals AI","score":0.9018982057104772,"rank":6,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.9040393131929866,"rank":6,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.9035388702302348,"rank":6,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9038974521017674,"rank":6,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.9041123205727614,"rank":6,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8775467303031664,"rank":9,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8766291784278267,"rank":8,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9040807845132927,"rank":6,"remainingConfigurations":444},{"removed":"briefcase","score":0.9061707983890873,"rank":6,"remainingConfigurations":444},{"removed":"aime","score":0.9038241000412474,"rank":6,"remainingConfigurations":444},{"removed":"apex-agents","score":0.9042991396085434,"rank":6,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9052924232841265,"rank":6,"remainingConfigurations":444},{"removed":"automationbench","score":0.8983341342310496,"rank":9,"remainingConfigurations":444},{"removed":"critpt","score":0.9047047781939442,"rank":6,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9041013944650573,"rank":6,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8983137327540445,"rank":9,"remainingConfigurations":444},{"removed":"gdpval","score":0.9064337152710144,"rank":6,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9040356824771069,"rank":6,"remainingConfigurations":444},{"removed":"gpqa","score":0.9026864625378432,"rank":6,"remainingConfigurations":444},{"removed":"harvey","score":0.9037123002250231,"rank":7,"remainingConfigurations":444},{"removed":"hle","score":0.9051842307204786,"rank":6,"remainingConfigurations":444},{"removed":"ifbench","score":0.9026893398791379,"rank":6,"remainingConfigurations":444},{"removed":"itbench","score":0.9039995100904225,"rank":6,"remainingConfigurations":444},{"removed":"livecodebench","score":0.903959579579421,"rank":6,"remainingConfigurations":444},{"removed":"math500","score":0.9040370784996542,"rank":6,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9052654078043815,"rank":6,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9060535436395453,"rank":6,"remainingConfigurations":444},{"removed":"omniscience","score":0.9042647529939408,"rank":6,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9044353203117775,"rank":6,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8994213549905199,"rank":7,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.901841615675632,"rank":4,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9266955735046709,"rank":7,"remainingConfigurations":444},{"removed":"deepswe","score":0.9122447441325282,"rank":4,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.904114161940332,"rank":6,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.897891854631641,"rank":6,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8868987011348687,"rank":6,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.9046714200752959,"rank":6,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9030675907392757,"rank":6,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9040584090637079,"rank":6,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9030719492894644,"rank":6,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9040824940765156,"rank":6,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9037292233698332,"rank":6,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9045202873071373,"rank":6,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9040625204834383,"rank":6,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9034706386848831,"rank":6,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.9037597984551743,"rank":6,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9051661489424419,"rank":6,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9030365184110329,"rank":6,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9027599391922677,"rank":6,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9029016569019056,"rank":6,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9063769072551165,"rank":6,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9043806209458295,"rank":6,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.903725784947421,"rank":5,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9041364425206259,"rank":6,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.9038085462259927,"rank":6,"remainingConfigurations":444},{"removed":"vibe-code","score":0.903578493755323,"rank":5,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.9041301417603931,"rank":6,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-4-argon--effort-medium":{"score":0.9018697849083788,"rank":7,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9050411228866878,"rank":9,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9736424693011694,"rank":1,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8862482431709487,"rank":8,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.9019590775257483,"rank":7,"remainingConfigurations":444},{"removed":"Scale","score":0.9049039472453103,"rank":7,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.899302806233594,"rank":6,"remainingConfigurations":444},{"removed":"Cognition","score":0.8637458362218454,"rank":9,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9064988752831026,"rank":8,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.9001264650859445,"rank":7,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9016304314595566,"rank":8,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8999520445055333,"rank":7,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.9016058145688731,"rank":7,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.9007745961310816,"rank":7,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.9016826624734734,"rank":7,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.9018697849083788,"rank":7,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8995469861428677,"rank":5,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8980065867394762,"rank":5,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.9018621895537118,"rank":7,"remainingConfigurations":444},{"removed":"briefcase","score":0.9019904388000723,"rank":7,"remainingConfigurations":444},{"removed":"aime","score":0.9016271142021167,"rank":7,"remainingConfigurations":444},{"removed":"apex-agents","score":0.902109635434804,"rank":7,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.9019539293302765,"rank":7,"remainingConfigurations":444},{"removed":"automationbench","score":0.9011758237544906,"rank":6,"remainingConfigurations":444},{"removed":"critpt","score":0.9033565121486036,"rank":7,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.9018689203109496,"rank":7,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9024382718845644,"rank":6,"remainingConfigurations":444},{"removed":"gdpval","score":0.9023823019417797,"rank":7,"remainingConfigurations":444},{"removed":"gmmlu","score":0.9018439904297191,"rank":7,"remainingConfigurations":444},{"removed":"gpqa","score":0.9005645697844221,"rank":8,"remainingConfigurations":444},{"removed":"harvey","score":0.9015764571096242,"rank":8,"remainingConfigurations":444},{"removed":"hle","score":0.9033423423616852,"rank":7,"remainingConfigurations":444},{"removed":"ifbench","score":0.9004136065094478,"rank":7,"remainingConfigurations":444},{"removed":"itbench","score":0.9018384899121484,"rank":7,"remainingConfigurations":444},{"removed":"livecodebench","score":0.901902053521999,"rank":7,"remainingConfigurations":444},{"removed":"math500","score":0.9018478369006971,"rank":7,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.9030455496247738,"rank":7,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.903907739671225,"rank":7,"remainingConfigurations":444},{"removed":"omniscience","score":0.9022853076060672,"rank":7,"remainingConfigurations":444},{"removed":"tau-bench","score":0.9009605352408131,"rank":7,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.9017511499753571,"rank":6,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8993801961752537,"rank":6,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9412479645188938,"rank":2,"remainingConfigurations":444},{"removed":"deepswe","score":0.8866245059858393,"rank":8,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.9018668415747433,"rank":7,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8624969202819822,"rank":12,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8637458362218454,"rank":9,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.90212807672664,"rank":7,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.9009538671346166,"rank":7,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.9016922042286312,"rank":7,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.9006856624124713,"rank":7,"remainingConfigurations":444},{"removed":"livebench-math","score":0.9017936489758412,"rank":7,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.9017942615614875,"rank":7,"remainingConfigurations":444},{"removed":"livebench-language","score":0.9020954605636936,"rank":7,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9021947894869435,"rank":8,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.9011649052742863,"rank":7,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.9015275366154655,"rank":7,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9025421630887246,"rank":8,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.9001264650859445,"rank":7,"remainingConfigurations":444},{"removed":"frontiermath","score":0.9006290999601422,"rank":7,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.9004710993302387,"rank":7,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9036774622164779,"rank":7,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9019066683799236,"rank":7,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.901665850467427,"rank":6,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.9019050288320386,"rank":7,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.90162906004992,"rank":7,"remainingConfigurations":444},{"removed":"vibe-code","score":0.9014344037454283,"rank":7,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.901804563863429,"rank":7,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-fable-5-1--effort-max":{"score":0.8990820461798595,"rank":8,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.899163152045286,"rank":10,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9037128887362758,"rank":12,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8853294744991801,"rank":9,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8990672800442324,"rank":8,"remainingConfigurations":444},{"removed":"Scale","score":0.9010668863563008,"rank":9,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.9004810914328756,"rank":5,"remainingConfigurations":444},{"removed":"Cognition","score":0.9036213946166725,"rank":3,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9157187758305199,"rank":6,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8970695764367879,"rank":8,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8991505598034064,"rank":9,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8904908330577465,"rank":9,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8378562191658316,"rank":15,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8976331770205689,"rank":8,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8983860295992425,"rank":8,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8990820461798595,"rank":8,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8981358443625828,"rank":6,"remainingConfigurations":444},{"removed":"All provider reports","score":0.833438104395467,"rank":13,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8981229598449785,"rank":8,"remainingConfigurations":444},{"removed":"briefcase","score":0.8978203414104322,"rank":8,"remainingConfigurations":444},{"removed":"aime","score":0.8986033470485738,"rank":8,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8991970087514568,"rank":8,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.899064981198246,"rank":8,"remainingConfigurations":444},{"removed":"automationbench","score":0.8993091581930686,"rank":7,"remainingConfigurations":444},{"removed":"critpt","score":0.8998221137813288,"rank":9,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8991054486169231,"rank":8,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.9003855594517026,"rank":7,"remainingConfigurations":444},{"removed":"gdpval","score":0.8985531183318266,"rank":9,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8990616557700672,"rank":8,"remainingConfigurations":444},{"removed":"gpqa","score":0.9007347621440197,"rank":7,"remainingConfigurations":444},{"removed":"harvey","score":0.9066318481573822,"rank":6,"remainingConfigurations":444},{"removed":"hle","score":0.8999281131055669,"rank":8,"remainingConfigurations":444},{"removed":"ifbench","score":0.898062377028451,"rank":8,"remainingConfigurations":444},{"removed":"itbench","score":0.8999888291023957,"rank":8,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8990475163003446,"rank":8,"remainingConfigurations":444},{"removed":"math500","score":0.8990769024793511,"rank":8,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8986686345260612,"rank":8,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.901445691809453,"rank":8,"remainingConfigurations":444},{"removed":"omniscience","score":0.9004358800268082,"rank":8,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8981228021363433,"rank":8,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.898495176611104,"rank":8,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.9001064621316396,"rank":5,"remainingConfigurations":444},{"removed":"arc-agi","score":0.897854340818078,"rank":11,"remainingConfigurations":444},{"removed":"deepswe","score":0.8855013988956401,"rank":9,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8990876975806414,"rank":8,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8965818152031741,"rank":7,"remainingConfigurations":444},{"removed":"frontiercode","score":0.9036213946166725,"rank":3,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8996979156737003,"rank":8,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.897877488168421,"rank":8,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.899319037584925,"rank":8,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8972606482714155,"rank":8,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8967141936423643,"rank":8,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8959357232012991,"rank":8,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8993666830938308,"rank":8,"remainingConfigurations":444},{"removed":"livebench-data","score":0.9036694134055154,"rank":7,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8958729245467579,"rank":9,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8989804735967745,"rank":8,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.9029906343335763,"rank":7,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8970695764367879,"rank":8,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8974710427817075,"rank":8,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.897266193012254,"rank":8,"remainingConfigurations":444},{"removed":"simpleqa","score":0.9015937640919396,"rank":8,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.9001850148518452,"rank":8,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8999731795702489,"rank":8,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.89654160499393,"rank":8,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8964766805548957,"rank":9,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8978178005621672,"rank":8,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8966942309664626,"rank":8,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5-5--effort-medium":{"score":0.8968900120893727,"rank":9,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9202020212441996,"rank":7,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9308893889231767,"rank":5,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8916392462997896,"rank":5,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8967589201722564,"rank":9,"remainingConfigurations":444},{"removed":"Scale","score":0.902430620032785,"rank":8,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8969844417784119,"rank":7,"remainingConfigurations":444},{"removed":"Cognition","score":0.7885160202365175,"rank":22,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9032673221606778,"rank":9,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8957433020716352,"rank":9,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.9016506669287531,"rank":7,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8912097531735245,"rank":8,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8960968642627961,"rank":8,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8956202884663664,"rank":9,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.896574093819368,"rank":9,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8968900120893727,"rank":9,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8965906185060936,"rank":7,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8942236656880772,"rank":6,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8966085099917759,"rank":9,"remainingConfigurations":444},{"removed":"briefcase","score":0.895464218861624,"rank":9,"remainingConfigurations":444},{"removed":"aime","score":0.8956518884922969,"rank":9,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8970804324158205,"rank":9,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8971102630581177,"rank":10,"remainingConfigurations":444},{"removed":"automationbench","score":0.898423472143147,"rank":8,"remainingConfigurations":444},{"removed":"critpt","score":0.9001367744436922,"rank":8,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8967598241397644,"rank":9,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8989295988405869,"rank":8,"remainingConfigurations":444},{"removed":"gdpval","score":0.9000592273200066,"rank":8,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8966242167555311,"rank":9,"remainingConfigurations":444},{"removed":"gpqa","score":0.8977450321808164,"rank":9,"remainingConfigurations":444},{"removed":"harvey","score":0.8970925025132174,"rank":9,"remainingConfigurations":444},{"removed":"hle","score":0.8998548475851486,"rank":9,"remainingConfigurations":444},{"removed":"ifbench","score":0.8945351713716015,"rank":9,"remainingConfigurations":444},{"removed":"itbench","score":0.8970067271273089,"rank":9,"remainingConfigurations":444},{"removed":"livecodebench","score":0.89627627605116,"rank":9,"remainingConfigurations":444},{"removed":"math500","score":0.8966449608203707,"rank":9,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8973798435249267,"rank":9,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.9001270225517605,"rank":9,"remainingConfigurations":444},{"removed":"omniscience","score":0.8979714563409779,"rank":9,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8950004604101668,"rank":9,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.896183530806752,"rank":9,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8953286142082125,"rank":7,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9276504832374326,"rank":6,"remainingConfigurations":444},{"removed":"deepswe","score":0.8917781795556509,"rank":6,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8969015461390177,"rank":9,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8908220833719946,"rank":8,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7885160202365175,"rank":22,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8967036582193133,"rank":9,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.896128013630527,"rank":9,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8961499563839034,"rank":9,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8953129592387222,"rank":9,"remainingConfigurations":444},{"removed":"livebench-math","score":0.896392275651665,"rank":9,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8955113320077749,"rank":9,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8977257860855126,"rank":9,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8976508552022281,"rank":9,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8961901684833958,"rank":8,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8964269891996522,"rank":9,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8983643004801346,"rank":9,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8957433020716352,"rank":9,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8967489102054644,"rank":9,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8954747179795519,"rank":9,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8987458615595801,"rank":9,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8970493530796242,"rank":9,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.896740797924366,"rank":9,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8965168309753967,"rank":9,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8966293003872444,"rank":8,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8964463038283285,"rank":9,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8965230575364477,"rank":9,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gemini-4-argon--effort-high":{"score":0.8940216642928943,"rank":10,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.9254766548039183,"rank":5,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9239455826611639,"rank":7,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8787575236968787,"rank":10,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8940421041509531,"rank":10,"remainingConfigurations":444},{"removed":"Scale","score":0.8967757113432303,"rank":10,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8929709902866422,"rank":9,"remainingConfigurations":444},{"removed":"Cognition","score":0.8666462281828556,"rank":8,"remainingConfigurations":444},{"removed":"LiveBench","score":0.9020225877445256,"rank":10,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8922044092391838,"rank":10,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.895506842625096,"rank":10,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8723368488165869,"rank":10,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8932965751069789,"rank":9,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8924926129963536,"rank":10,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.892966578087195,"rank":10,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8940216642928943,"rank":10,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8921464162893669,"rank":8,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8888260579100126,"rank":7,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8954180838498119,"rank":10,"remainingConfigurations":444},{"removed":"briefcase","score":0.895459625385597,"rank":10,"remainingConfigurations":444},{"removed":"aime","score":0.893961994872131,"rank":10,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8941725692898093,"rank":10,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8976828276326886,"rank":9,"remainingConfigurations":444},{"removed":"automationbench","score":0.8903917120710384,"rank":10,"remainingConfigurations":444},{"removed":"critpt","score":0.8948218972593597,"rank":10,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8939943633520658,"rank":10,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8969358438586831,"rank":10,"remainingConfigurations":444},{"removed":"gdpval","score":0.8944619373873525,"rank":10,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8939776320957135,"rank":10,"remainingConfigurations":444},{"removed":"gpqa","score":0.8925381491202323,"rank":10,"remainingConfigurations":444},{"removed":"harvey","score":0.8964640211646805,"rank":10,"remainingConfigurations":444},{"removed":"hle","score":0.894106314803166,"rank":10,"remainingConfigurations":444},{"removed":"ifbench","score":0.8923263744777549,"rank":10,"remainingConfigurations":444},{"removed":"itbench","score":0.8941539057283578,"rank":10,"remainingConfigurations":444},{"removed":"livecodebench","score":0.893988153488022,"rank":10,"remainingConfigurations":444},{"removed":"math500","score":0.8940032951112783,"rank":10,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8955710141518693,"rank":10,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8961959333758652,"rank":10,"remainingConfigurations":444},{"removed":"omniscience","score":0.8972637259102897,"rank":10,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8926080902470788,"rank":10,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8912153364765594,"rank":10,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8918140845030357,"rank":9,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9128382299059066,"rank":10,"remainingConfigurations":444},{"removed":"deepswe","score":0.8789928297313939,"rank":10,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8940301665687026,"rank":10,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8846497046249127,"rank":9,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8666462281828556,"rank":8,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8944441454047944,"rank":10,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8929947545864826,"rank":10,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8938516078039825,"rank":10,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8923936021106215,"rank":10,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8936767458786132,"rank":10,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8938226610218619,"rank":10,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8946399439890659,"rank":10,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8947729475710348,"rank":10,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8929548580116332,"rank":10,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8936593976024998,"rank":10,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8947103565170252,"rank":10,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8922044092391838,"rank":10,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8929167732525674,"rank":10,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8924546440259448,"rank":10,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8956221578021858,"rank":10,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8921531582690099,"rank":10,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8933272671714092,"rank":10,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8937365997084039,"rank":10,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8939150221992399,"rank":10,"remainingConfigurations":444},{"removed":"vibe-code","score":0.893003846682214,"rank":10,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8925609415414576,"rank":10,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-opus-5-5--effort-xhigh":{"score":0.8737406978750922,"rank":11,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8806588908394021,"rank":12,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8823827784658285,"rank":13,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8671014393697479,"rank":11,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8736184699898298,"rank":11,"remainingConfigurations":444},{"removed":"Scale","score":0.8769325701925751,"rank":11,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8729762976182959,"rank":10,"remainingConfigurations":444},{"removed":"Cognition","score":0.8693641218659772,"rank":7,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8794555090614805,"rank":11,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8719728287816028,"rank":11,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8791859426588343,"rank":11,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8706054483712556,"rank":11,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8729530419564514,"rank":10,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8721989850332763,"rank":11,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8733762244974218,"rank":11,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8737406978750922,"rank":11,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.873522648035744,"rank":10,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8708441377156203,"rank":9,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8738747596157245,"rank":11,"remainingConfigurations":444},{"removed":"briefcase","score":0.8718047878079133,"rank":11,"remainingConfigurations":444},{"removed":"aime","score":0.8723087318112669,"rank":11,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8740374444765716,"rank":11,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8750019911541722,"rank":11,"remainingConfigurations":444},{"removed":"automationbench","score":0.8748700124971761,"rank":11,"remainingConfigurations":444},{"removed":"critpt","score":0.876908455540903,"rank":11,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.873739645771066,"rank":11,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8763947188549488,"rank":11,"remainingConfigurations":444},{"removed":"gdpval","score":0.8738230570639484,"rank":11,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8734679603973715,"rank":11,"remainingConfigurations":444},{"removed":"gpqa","score":0.8752787239956349,"rank":11,"remainingConfigurations":444},{"removed":"harvey","score":0.8742302683887665,"rank":11,"remainingConfigurations":444},{"removed":"hle","score":0.8747782560278307,"rank":11,"remainingConfigurations":444},{"removed":"ifbench","score":0.871150826584191,"rank":11,"remainingConfigurations":444},{"removed":"itbench","score":0.8740392821353158,"rank":11,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8731136410457242,"rank":11,"remainingConfigurations":444},{"removed":"math500","score":0.8734839440835764,"rank":11,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8744433794288868,"rank":11,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8778183752019357,"rank":11,"remainingConfigurations":444},{"removed":"omniscience","score":0.8759912590266737,"rank":11,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8721022122546107,"rank":11,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8716538603319158,"rank":11,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8725604814227829,"rank":10,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8745239897413297,"rank":13,"remainingConfigurations":444},{"removed":"deepswe","score":0.8672466521518167,"rank":11,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8737545663525452,"rank":11,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.876379830001485,"rank":10,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8693641218659772,"rank":7,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8725960111231009,"rank":11,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8733117586141574,"rank":11,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8729151748880097,"rank":11,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8719184374470664,"rank":11,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8731747340792921,"rank":11,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8721159106253475,"rank":11,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8747575981865615,"rank":11,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8746051502858888,"rank":11,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8728783408197689,"rank":11,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8731824187234866,"rank":11,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8754986546030287,"rank":11,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8719728287816028,"rank":11,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8740508563983846,"rank":11,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8722229074809317,"rank":11,"remainingConfigurations":444},{"removed":"simpleqa","score":0.874867122369588,"rank":11,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8739075707464464,"rank":11,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8735596167228529,"rank":11,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8733045999449282,"rank":11,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8734443513257709,"rank":11,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8732176788162463,"rank":11,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.87331662364641,"rank":11,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gpt-6.1-sol--effort-high":{"score":0.8591089426089601,"rank":12,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8763686640746893,"rank":13,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.864741267191501,"rank":15,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8431252538331423,"rank":12,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8591216245013064,"rank":12,"remainingConfigurations":444},{"removed":"Scale","score":0.8641552209948459,"rank":13,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8586177988694245,"rank":12,"remainingConfigurations":444},{"removed":"Cognition","score":0.8334580610445467,"rank":15,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8648280839515822,"rank":14,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.857679755224051,"rank":12,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8594392103719736,"rank":12,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8568615564502465,"rank":13,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.858893745361928,"rank":11,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8581095029581204,"rank":12,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8587705941888008,"rank":12,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8591089426089601,"rank":12,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8092162668132823,"rank":18,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8071373763601871,"rank":17,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8591652734271604,"rank":12,"remainingConfigurations":444},{"removed":"briefcase","score":0.8617562507407467,"rank":12,"remainingConfigurations":444},{"removed":"aime","score":0.8585531199649514,"rank":12,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8594512248769727,"rank":12,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8603707638694319,"rank":12,"remainingConfigurations":444},{"removed":"automationbench","score":0.8657636878697259,"rank":12,"remainingConfigurations":444},{"removed":"critpt","score":0.8605120461427199,"rank":12,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8591552275954829,"rank":12,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8446027644475108,"rank":13,"remainingConfigurations":444},{"removed":"gdpval","score":0.8626694865486292,"rank":12,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8589793015544173,"rank":12,"remainingConfigurations":444},{"removed":"gpqa","score":0.8570285202060907,"rank":12,"remainingConfigurations":444},{"removed":"harvey","score":0.8585972746348308,"rank":12,"remainingConfigurations":444},{"removed":"hle","score":0.8614099137805242,"rank":12,"remainingConfigurations":444},{"removed":"ifbench","score":0.85710243208959,"rank":12,"remainingConfigurations":444},{"removed":"itbench","score":0.8590378223862173,"rank":12,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8588187347568312,"rank":12,"remainingConfigurations":444},{"removed":"math500","score":0.858961966252279,"rank":12,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8608276988277724,"rank":12,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8625191665555775,"rank":12,"remainingConfigurations":444},{"removed":"omniscience","score":0.8598457384987066,"rank":13,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8582123755268499,"rank":12,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8666302989145712,"rank":12,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8578622739973785,"rank":12,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8798544203262394,"rank":12,"remainingConfigurations":444},{"removed":"deepswe","score":0.8304850485105701,"rank":15,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8591146691469095,"rank":12,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8628351247420688,"rank":11,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8334580610445467,"rank":15,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8601509783693649,"rank":12,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8573272954957923,"rank":13,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8589493366867268,"rank":12,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.857835540582371,"rank":12,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8590532138051573,"rank":12,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8585492443855477,"rank":12,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8597496906522779,"rank":12,"remainingConfigurations":444},{"removed":"livebench-data","score":0.859019650893337,"rank":12,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.858147998369691,"rank":12,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8586473973401251,"rank":12,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8605901634732058,"rank":12,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.857679755224051,"rank":12,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8586212077242475,"rank":12,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8572666536773793,"rank":12,"remainingConfigurations":444},{"removed":"simpleqa","score":0.862100814666119,"rank":12,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8594475359032333,"rank":12,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8585550923908117,"rank":12,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8591369079468882,"rank":12,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8586838746790483,"rank":12,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8583384753110246,"rank":12,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8591124756981264,"rank":12,"remainingConfigurations":444}],"sharedOrderConflicts":2},"muse-wonder-full--effort-max":{"score":0.8500987270785633,"rank":13,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8706353882193563,"rank":14,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8717356486677194,"rank":14,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8345572114709032,"rank":13,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8499125357142882,"rank":13,"remainingConfigurations":444},{"removed":"Scale","score":0.8542341198910286,"rank":14,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8511890085029936,"rank":13,"remainingConfigurations":444},{"removed":"Cognition","score":0.8472472418107732,"rank":13,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8663741956954238,"rank":13,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8480144181696705,"rank":13,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8521130411994188,"rank":13,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8164434959703145,"rank":18,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8488356275694963,"rank":12,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8475156939350619,"rank":13,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8473136715416435,"rank":13,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8500987270785633,"rank":13,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8488110822886689,"rank":12,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8421773354210638,"rank":11,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8511270148999784,"rank":13,"remainingConfigurations":444},{"removed":"briefcase","score":0.8450149207129575,"rank":13,"remainingConfigurations":444},{"removed":"aime","score":0.8501387252167144,"rank":13,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8502250494624893,"rank":13,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8549266337232851,"rank":13,"remainingConfigurations":444},{"removed":"automationbench","score":0.8451421275006165,"rank":13,"remainingConfigurations":444},{"removed":"critpt","score":0.8516753644243994,"rank":13,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8503606317042335,"rank":13,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8471532210731637,"rank":12,"remainingConfigurations":444},{"removed":"gdpval","score":0.8471041355385842,"rank":13,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8499971547220831,"rank":13,"remainingConfigurations":444},{"removed":"gpqa","score":0.8486560750688055,"rank":13,"remainingConfigurations":444},{"removed":"harvey","score":0.8324065406604543,"rank":15,"remainingConfigurations":444},{"removed":"hle","score":0.8555040142263964,"rank":13,"remainingConfigurations":444},{"removed":"ifbench","score":0.847591429947264,"rank":13,"remainingConfigurations":444},{"removed":"itbench","score":0.8513217648728788,"rank":13,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8498300295798699,"rank":13,"remainingConfigurations":444},{"removed":"math500","score":0.8500698352737156,"rank":13,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.851907512727796,"rank":13,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.854251917555149,"rank":13,"remainingConfigurations":444},{"removed":"omniscience","score":0.8730962818383223,"rank":12,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8481915913909237,"rank":13,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8509044580933066,"rank":13,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8500618941936505,"rank":13,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8644556406602492,"rank":14,"remainingConfigurations":444},{"removed":"deepswe","score":0.8347997507454831,"rank":12,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8501262608432111,"rank":13,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8472654443558508,"rank":13,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8472472418107732,"rank":13,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8506614778195928,"rank":13,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8487345099948341,"rank":14,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8498420294751892,"rank":13,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8483377700233556,"rank":13,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8492730001887837,"rank":13,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.849503191118646,"rank":13,"remainingConfigurations":444},{"removed":"livebench-language","score":0.851874419034819,"rank":13,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8511855894275314,"rank":13,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8481186996364117,"rank":13,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8496318070822996,"rank":13,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.851234808642825,"rank":13,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8480144181696705,"rank":13,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8497448528653804,"rank":13,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8476956781403264,"rank":13,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8518560944736272,"rank":13,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.847047072769142,"rank":13,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8528312018469699,"rank":13,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8461733903962868,"rank":13,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8528360167878762,"rank":13,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8554063304885785,"rank":13,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8459219487286562,"rank":13,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6.1-sol--effort-xhigh":{"score":0.8404179303166387,"rank":14,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8607646918290458,"rank":15,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8471031395550765,"rank":18,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8246208258904982,"rank":16,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.840421194865554,"rank":14,"remainingConfigurations":444},{"removed":"Scale","score":0.846618345882992,"rank":15,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8378285634405684,"rank":14,"remainingConfigurations":444},{"removed":"Cognition","score":0.7922026406835508,"rank":21,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8674164507158572,"rank":12,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.838640709887542,"rank":15,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8365805349293801,"rank":17,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8354742548045303,"rank":14,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8400024896268542,"rank":13,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8397786590502112,"rank":14,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8393468536305898,"rank":14,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8404179303166387,"rank":14,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8237422377663725,"rank":15,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8207136167345926,"rank":15,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.840432467717226,"rank":14,"remainingConfigurations":444},{"removed":"briefcase","score":0.841793922761438,"rank":14,"remainingConfigurations":444},{"removed":"aime","score":0.8399141578923257,"rank":14,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8407527247867413,"rank":14,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8433109401084572,"rank":14,"remainingConfigurations":444},{"removed":"automationbench","score":0.8381470468393303,"rank":15,"remainingConfigurations":444},{"removed":"critpt","score":0.8405179149669775,"rank":15,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8405165000149833,"rank":14,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8396203853572062,"rank":15,"remainingConfigurations":444},{"removed":"gdpval","score":0.8434737783829361,"rank":14,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8403123171039181,"rank":14,"remainingConfigurations":444},{"removed":"gpqa","score":0.838480758679483,"rank":15,"remainingConfigurations":444},{"removed":"harvey","score":0.8399355215960709,"rank":13,"remainingConfigurations":444},{"removed":"hle","score":0.8433454123628795,"rank":14,"remainingConfigurations":444},{"removed":"ifbench","score":0.838442237918303,"rank":14,"remainingConfigurations":444},{"removed":"itbench","score":0.8404210249246823,"rank":14,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8402033580741753,"rank":14,"remainingConfigurations":444},{"removed":"math500","score":0.840309120307174,"rank":14,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8423597400359452,"rank":14,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8440463242134116,"rank":14,"remainingConfigurations":444},{"removed":"omniscience","score":0.8416328348181863,"rank":14,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8394256718291538,"rank":14,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8394081790373068,"rank":14,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8373979995808071,"rank":14,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8609194551705537,"rank":16,"remainingConfigurations":444},{"removed":"deepswe","score":0.8254408561982837,"rank":16,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8400117441022029,"rank":14,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8410352850410744,"rank":14,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7922026406835508,"rank":21,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8411202456843597,"rank":14,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8387279621033357,"rank":15,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8409413249889198,"rank":14,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8392481858650735,"rank":15,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8404136156899445,"rank":14,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8420785159670817,"rank":14,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8384494681110614,"rank":15,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8373771062996008,"rank":15,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8411261746520386,"rank":14,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8386379227318025,"rank":14,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8449081072298043,"rank":14,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.838640709887542,"rank":15,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8386302717390756,"rank":15,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8384219658465869,"rank":14,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8424586447380017,"rank":15,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.840681695782351,"rank":14,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8399668616712054,"rank":14,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8403918363300784,"rank":14,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8400000950557512,"rank":14,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8395035592334154,"rank":14,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8403686575075197,"rank":14,"remainingConfigurations":444}],"sharedOrderConflicts":2},"claude-fable-5-1--effort-xhigh":{"score":0.8383805128572343,"rank":15,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8436994720349968,"rank":17,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8449525029966741,"rank":19,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8305889876619011,"rank":15,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8383573730472121,"rank":15,"remainingConfigurations":444},{"removed":"Scale","score":0.7858352972111401,"rank":24,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.836702679832445,"rank":15,"remainingConfigurations":444},{"removed":"Cognition","score":0.8623703294000143,"rank":10,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8463478645750717,"rank":16,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8363802655346779,"rank":16,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8478567572695201,"rank":14,"remainingConfigurations":431},{"removed":"Vals AI","score":0.829679517370379,"rank":15,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.838492854117081,"rank":14,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8366408015430474,"rank":15,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8379748847494589,"rank":15,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8383805128572343,"rank":15,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8382002799859535,"rank":13,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8361915754621864,"rank":12,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8383131982499137,"rank":15,"remainingConfigurations":444},{"removed":"briefcase","score":0.8360158885516729,"rank":15,"remainingConfigurations":444},{"removed":"aime","score":0.837129090521682,"rank":15,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8386750073865329,"rank":15,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8398069923844297,"rank":15,"remainingConfigurations":444},{"removed":"automationbench","score":0.8410788634798765,"rank":14,"remainingConfigurations":444},{"removed":"critpt","score":0.8410187944013084,"rank":14,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8383439974682498,"rank":15,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.84025738979387,"rank":14,"remainingConfigurations":444},{"removed":"gdpval","score":0.8376785524022577,"rank":15,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8379235471497105,"rank":15,"remainingConfigurations":444},{"removed":"gpqa","score":0.8408265179189226,"rank":14,"remainingConfigurations":444},{"removed":"harvey","score":0.8387948787924983,"rank":14,"remainingConfigurations":444},{"removed":"hle","score":0.8397939072891609,"rank":15,"remainingConfigurations":444},{"removed":"ifbench","score":0.8363424592572084,"rank":15,"remainingConfigurations":444},{"removed":"itbench","score":0.8388548135119023,"rank":15,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8379522149796889,"rank":15,"remainingConfigurations":444},{"removed":"math500","score":0.838145606853328,"rank":15,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8393621499280804,"rank":15,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8419211658533045,"rank":15,"remainingConfigurations":444},{"removed":"omniscience","score":0.8391276618892448,"rank":15,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8376540855154495,"rank":15,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8376167032885705,"rank":15,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8353794383724672,"rank":15,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8366004099389849,"rank":20,"remainingConfigurations":444},{"removed":"deepswe","score":0.8307617609647518,"rank":14,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8383966849531687,"rank":15,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8357813842250073,"rank":15,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8623703294000143,"rank":10,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8309742161180759,"rank":15,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8586617854328372,"rank":12,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8120266241942776,"rank":18,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8458607666156283,"rank":14,"remainingConfigurations":444},{"removed":"livebench-math","score":0.837543389983837,"rank":15,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8357738953746949,"rank":15,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8395714400107446,"rank":14,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8394301263730456,"rank":14,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.838240830703659,"rank":15,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8378605530079338,"rank":15,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8403010521298647,"rank":15,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8363802655346779,"rank":16,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8386615825281623,"rank":14,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8365850511822143,"rank":15,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8459514147745696,"rank":14,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8384776051972768,"rank":15,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.838153494166712,"rank":15,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8378770560009254,"rank":15,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8380971583467206,"rank":15,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8378251764267329,"rank":15,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8379028775191708,"rank":15,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5--effort-medium":{"score":0.8319049535030567,"rank":16,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8838015800325653,"rank":11,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8513468189040446,"rank":17,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8316795526244269,"rank":14,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8318419854614026,"rank":16,"remainingConfigurations":444},{"removed":"Scale","score":0.839024650641418,"rank":16,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8288307604158098,"rank":16,"remainingConfigurations":444},{"removed":"Cognition","score":0.6871572602134925,"rank":34,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8402318215235454,"rank":17,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8300834239743095,"rank":17,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8400962917667458,"rank":15,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8258309382334095,"rank":16,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8311081268553163,"rank":16,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8298840384258016,"rank":16,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8316164711628539,"rank":16,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8319049535030567,"rank":16,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8307807712022499,"rank":14,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8276986836675936,"rank":14,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8312195890786165,"rank":16,"remainingConfigurations":444},{"removed":"briefcase","score":0.8323091177741256,"rank":16,"remainingConfigurations":444},{"removed":"aime","score":0.8297738080525957,"rank":16,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8320829780561422,"rank":16,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8312096783087101,"rank":16,"remainingConfigurations":444},{"removed":"automationbench","score":0.8354798533946851,"rank":16,"remainingConfigurations":444},{"removed":"critpt","score":0.8320038608956919,"rank":16,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8313993419655527,"rank":16,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8355415382130884,"rank":16,"remainingConfigurations":444},{"removed":"gdpval","score":0.8336478801354511,"rank":16,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8315788386356934,"rank":16,"remainingConfigurations":444},{"removed":"gpqa","score":0.8355356387709981,"rank":16,"remainingConfigurations":444},{"removed":"harvey","score":0.831912521745585,"rank":16,"remainingConfigurations":444},{"removed":"hle","score":0.8334217965880532,"rank":16,"remainingConfigurations":444},{"removed":"ifbench","score":0.8287227810399694,"rank":16,"remainingConfigurations":444},{"removed":"itbench","score":0.8321052688738789,"rank":16,"remainingConfigurations":444},{"removed":"livecodebench","score":0.831238961040103,"rank":16,"remainingConfigurations":444},{"removed":"math500","score":0.8315958123702435,"rank":16,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8329705015747274,"rank":16,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8377617798515679,"rank":16,"remainingConfigurations":444},{"removed":"omniscience","score":0.8322991361579942,"rank":16,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8312050934135424,"rank":16,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8302543324176069,"rank":16,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8284620691928118,"rank":16,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8480263741393413,"rank":17,"remainingConfigurations":444},{"removed":"deepswe","score":0.8318805942399946,"rank":13,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.831932961921345,"rank":16,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8291345572630453,"rank":16,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6871572602134925,"rank":34,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8305591312346458,"rank":16,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8304122590487779,"rank":16,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8308502692317034,"rank":15,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8299417430116659,"rank":16,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8313066471157828,"rank":16,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8298657378981907,"rank":16,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8332906491395016,"rank":16,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8329979713397252,"rank":16,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8307812301001453,"rank":16,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8311384071581608,"rank":16,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8339822356227202,"rank":16,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8300834239743095,"rank":17,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8310823932132209,"rank":16,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.830482552941907,"rank":16,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8335251037485092,"rank":16,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8319619617828096,"rank":17,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8317530750513056,"rank":16,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8313773579851654,"rank":16,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8315988014669253,"rank":16,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8312954199048965,"rank":16,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.831426337684244,"rank":16,"remainingConfigurations":444}],"sharedOrderConflicts":3},"gpt-6.1-sol--effort-medium":{"score":0.8238506927309873,"rank":17,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8535826685570466,"rank":16,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8569478680624849,"rank":16,"remainingConfigurations":444},{"removed":"Datacurve","score":0.8057624084886384,"rank":17,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8238649314087336,"rank":17,"remainingConfigurations":444},{"removed":"Scale","score":0.8310682816802816,"rank":17,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8213436909011613,"rank":17,"remainingConfigurations":444},{"removed":"Cognition","score":0.7583225869351663,"rank":24,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8299411329846634,"rank":18,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8221702090415789,"rank":18,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8220002713946957,"rank":18,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8203029775406637,"rank":17,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8236383651629656,"rank":17,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8225716017671587,"rank":17,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8234675917083797,"rank":17,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8238506927309873,"rank":17,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8219052001122532,"rank":16,"remainingConfigurations":444},{"removed":"All provider reports","score":0.819941685972606,"rank":16,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8239077336717612,"rank":17,"remainingConfigurations":444},{"removed":"briefcase","score":0.8284891724420743,"rank":17,"remainingConfigurations":444},{"removed":"aime","score":0.8230789209489675,"rank":17,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8242699334144735,"rank":17,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8243738819055465,"rank":18,"remainingConfigurations":444},{"removed":"automationbench","score":0.8266742374053225,"rank":17,"remainingConfigurations":444},{"removed":"critpt","score":0.8257610482373079,"rank":17,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8238341701835844,"rank":17,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8273875746022719,"rank":17,"remainingConfigurations":444},{"removed":"gdpval","score":0.8276380326193854,"rank":17,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8236938300253125,"rank":17,"remainingConfigurations":444},{"removed":"gpqa","score":0.8213513790649878,"rank":19,"remainingConfigurations":444},{"removed":"harvey","score":0.8230903035333821,"rank":17,"remainingConfigurations":444},{"removed":"hle","score":0.8268227982054012,"rank":17,"remainingConfigurations":444},{"removed":"ifbench","score":0.8215185883165775,"rank":17,"remainingConfigurations":444},{"removed":"itbench","score":0.8236865360178092,"rank":17,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8235015006540741,"rank":17,"remainingConfigurations":444},{"removed":"math500","score":0.8236705724873463,"rank":17,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.826044940172587,"rank":17,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8284496127536035,"rank":17,"remainingConfigurations":444},{"removed":"omniscience","score":0.8243190028382181,"rank":18,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8227427578767944,"rank":17,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8280865626423032,"rank":17,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.8202856482564586,"rank":17,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8630802750323087,"rank":15,"remainingConfigurations":444},{"removed":"deepswe","score":0.7856713928078723,"rank":20,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8238582761939418,"rank":17,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8177551210010495,"rank":18,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7583225869351663,"rank":24,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8247573870344609,"rank":17,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8227654049424467,"rank":17,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.823663219929677,"rank":16,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.822423920366966,"rank":17,"remainingConfigurations":444},{"removed":"livebench-math","score":0.823810307268606,"rank":17,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8231392915672927,"rank":18,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8246710065378933,"rank":17,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8237292516346519,"rank":17,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8226191317036298,"rank":18,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8233046950407802,"rank":17,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8256644674726433,"rank":18,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8221702090415789,"rank":18,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8216686127191344,"rank":17,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8216489478184136,"rank":17,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8274535002796523,"rank":17,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8241970357432323,"rank":18,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8232147806490072,"rank":17,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8238598906591461,"rank":18,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8233566407132941,"rank":17,"remainingConfigurations":444},{"removed":"vibe-code","score":0.822947013799659,"rank":17,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8238388561533716,"rank":18,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-6.1-sol--effort-max":{"score":0.8231507026285795,"rank":18,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8263275143779528,"rank":20,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8246721873845267,"rank":20,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7978528113949537,"rank":18,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.823125237192016,"rank":18,"remainingConfigurations":444},{"removed":"Scale","score":0.8281396133334252,"rank":18,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7951913475623321,"rank":19,"remainingConfigurations":444},{"removed":"Cognition","score":0.8086209567608523,"rank":19,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8510306811201266,"rank":15,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8201232669784014,"rank":19,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8204289436381184,"rank":19,"remainingConfigurations":431},{"removed":"Vals AI","score":0.8607617820659713,"rank":12,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8222319509587702,"rank":18,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.8214055566214898,"rank":18,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8216311885296497,"rank":18,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8231507026285795,"rank":18,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8110631014416169,"rank":17,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8065242227990871,"rank":18,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8236116468256552,"rank":18,"remainingConfigurations":444},{"removed":"briefcase","score":0.8228942200095779,"rank":18,"remainingConfigurations":444},{"removed":"aime","score":0.8230242552889822,"rank":18,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8233847756035132,"rank":18,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.8249093429010373,"rank":17,"remainingConfigurations":444},{"removed":"automationbench","score":0.8239126655611955,"rank":18,"remainingConfigurations":444},{"removed":"critpt","score":0.823763826410028,"rank":18,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8235675360603878,"rank":18,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8147999118202546,"rank":18,"remainingConfigurations":444},{"removed":"gdpval","score":0.8242280044657012,"rank":18,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8231234494353186,"rank":18,"remainingConfigurations":444},{"removed":"gpqa","score":0.8218153460000998,"rank":18,"remainingConfigurations":444},{"removed":"harvey","score":0.8225819791887939,"rank":18,"remainingConfigurations":444},{"removed":"hle","score":0.8257864073142654,"rank":18,"remainingConfigurations":444},{"removed":"ifbench","score":0.8214037888670492,"rank":18,"remainingConfigurations":444},{"removed":"itbench","score":0.8233644317463799,"rank":18,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8230811296947017,"rank":18,"remainingConfigurations":444},{"removed":"math500","score":0.8231384343897895,"rank":18,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8233483355732562,"rank":18,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8267640389226685,"rank":18,"remainingConfigurations":444},{"removed":"omniscience","score":0.8257143241997577,"rank":17,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8219612570921816,"rank":18,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.8223710079175622,"rank":18,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.791916861741549,"rank":19,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8400363253762118,"rank":19,"remainingConfigurations":444},{"removed":"deepswe","score":0.8005410995743502,"rank":17,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8231561804136915,"rank":18,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8225000581574747,"rank":17,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8086209567608523,"rank":19,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.8234854196537462,"rank":18,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8213979912358188,"rank":18,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8228477865418947,"rank":17,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.8214044856770327,"rank":18,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8219656525205058,"rank":18,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8240544996603836,"rank":17,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8216330365147506,"rank":18,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8203403790998802,"rank":18,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.826142202033695,"rank":17,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8218210608147333,"rank":18,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8262600711684008,"rank":17,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8201232669784014,"rank":19,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8207084833921218,"rank":18,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8211933660742187,"rank":18,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8269273299208085,"rank":18,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.8326736717372198,"rank":16,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8143436922287469,"rank":18,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.8310321770049257,"rank":17,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.8192384441888788,"rank":18,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8152200120200584,"rank":18,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.8305212092296005,"rank":17,"remainingConfigurations":444}],"sharedOrderConflicts":3},"claude-fable-5-1--effort-high":{"score":0.8079007312147191,"rank":19,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8294148787391257,"rank":19,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8151804951695759,"rank":22,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7957009314060945,"rank":19,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.8078921770594301,"rank":19,"remainingConfigurations":444},{"removed":"Scale","score":0.8167239580960901,"rank":19,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.8055595442913456,"rank":18,"remainingConfigurations":444},{"removed":"Cognition","score":0.8097939077752869,"rank":18,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8175604023284472,"rank":21,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.8063268081424392,"rank":20,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8163399497591216,"rank":20,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7837675953642265,"rank":23,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.8082974590357953,"rank":19,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.805637482981112,"rank":19,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.8071320086176139,"rank":19,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.8079007312147191,"rank":19,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.8078344520354669,"rank":19,"remainingConfigurations":444},{"removed":"All provider reports","score":0.8052349409750246,"rank":19,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.8076712934639697,"rank":19,"remainingConfigurations":444},{"removed":"briefcase","score":0.8053918085888174,"rank":19,"remainingConfigurations":444},{"removed":"aime","score":0.8059654712551808,"rank":19,"remainingConfigurations":444},{"removed":"apex-agents","score":0.8082760279729341,"rank":19,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.808304477647613,"rank":19,"remainingConfigurations":444},{"removed":"automationbench","score":0.8126148900645466,"rank":19,"remainingConfigurations":444},{"removed":"critpt","score":0.8114196679302662,"rank":19,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.8076598543048846,"rank":19,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.8085348476829793,"rank":19,"remainingConfigurations":444},{"removed":"gdpval","score":0.808021067825908,"rank":19,"remainingConfigurations":444},{"removed":"gmmlu","score":0.8076197408456179,"rank":19,"remainingConfigurations":444},{"removed":"gpqa","score":0.8133060464001458,"rank":20,"remainingConfigurations":444},{"removed":"harvey","score":0.8083481316138235,"rank":19,"remainingConfigurations":444},{"removed":"hle","score":0.8113042165706972,"rank":20,"remainingConfigurations":444},{"removed":"ifbench","score":0.8047905789432441,"rank":19,"remainingConfigurations":444},{"removed":"itbench","score":0.8083251906927006,"rank":19,"remainingConfigurations":444},{"removed":"livecodebench","score":0.8073446853502828,"rank":19,"remainingConfigurations":444},{"removed":"math500","score":0.8076229350266328,"rank":19,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.8094015448655147,"rank":19,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.812318312899909,"rank":19,"remainingConfigurations":444},{"removed":"omniscience","score":0.8090885670853144,"rank":19,"remainingConfigurations":444},{"removed":"tau-bench","score":0.8075733384424796,"rank":19,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.806883609130062,"rank":19,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7857614033174997,"rank":23,"remainingConfigurations":444},{"removed":"arc-agi","score":0.805610713124317,"rank":24,"remainingConfigurations":444},{"removed":"deepswe","score":0.7958980211345995,"rank":18,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.8079257551360327,"rank":19,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.8053031808079735,"rank":19,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8097939077752869,"rank":18,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.807119143212638,"rank":19,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.8058495604823394,"rank":19,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8077514402672726,"rank":19,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.805290874543224,"rank":19,"remainingConfigurations":444},{"removed":"livebench-math","score":0.8072741556671708,"rank":19,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.8058241737865615,"rank":19,"remainingConfigurations":444},{"removed":"livebench-language","score":0.8094249875885566,"rank":19,"remainingConfigurations":444},{"removed":"livebench-data","score":0.8089642382808151,"rank":19,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.8065114896134576,"rank":19,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.8071043115699751,"rank":19,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.8102219705600032,"rank":19,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.8063268081424392,"rank":20,"remainingConfigurations":444},{"removed":"frontiermath","score":0.8081389498061293,"rank":19,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.8066129371001395,"rank":19,"remainingConfigurations":444},{"removed":"simpleqa","score":0.8101827089285786,"rank":19,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.808693362285709,"rank":19,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.8081760783368468,"rank":19,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.807829886036387,"rank":19,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.808082859700452,"rank":19,"remainingConfigurations":444},{"removed":"vibe-code","score":0.8076240837627863,"rank":19,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.80781746920043,"rank":19,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-fable-5--effort-high":{"score":0.7974003321637468,"rank":20,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7891968548755021,"rank":24,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8097467588908707,"rank":23,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7881813994398268,"rank":20,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7973950519682211,"rank":20,"remainingConfigurations":444},{"removed":"Scale","score":0.7692738086285469,"rank":28,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7871061941163754,"rank":23,"remainingConfigurations":444},{"removed":"Cognition","score":0.7586454419849096,"rank":23,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8010207938683259,"rank":23,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.844131025189255,"rank":14,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8385486663302415,"rank":16,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7915868020803772,"rank":20,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7965440032170904,"rank":20,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7980846035712078,"rank":20,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7973595216354693,"rank":20,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7974003321637468,"rank":20,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7966980072121457,"rank":20,"remainingConfigurations":444},{"removed":"All provider reports","score":0.796425256094551,"rank":20,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7972457394010378,"rank":20,"remainingConfigurations":444},{"removed":"briefcase","score":0.7965933844477876,"rank":21,"remainingConfigurations":444},{"removed":"aime","score":0.7784510520409712,"rank":25,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7975912383668665,"rank":20,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.797691066057797,"rank":20,"remainingConfigurations":444},{"removed":"automationbench","score":0.7976527589161431,"rank":21,"remainingConfigurations":444},{"removed":"critpt","score":0.7987243206258632,"rank":20,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7973960898000771,"rank":20,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7987891952545181,"rank":20,"remainingConfigurations":444},{"removed":"gdpval","score":0.7973761560934726,"rank":20,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7974097930712597,"rank":20,"remainingConfigurations":444},{"removed":"gpqa","score":0.8265955105867694,"rank":17,"remainingConfigurations":444},{"removed":"harvey","score":0.7975885096449842,"rank":21,"remainingConfigurations":444},{"removed":"hle","score":0.7999037620848207,"rank":21,"remainingConfigurations":444},{"removed":"ifbench","score":0.7960752050660703,"rank":20,"remainingConfigurations":444},{"removed":"itbench","score":0.7974413614810348,"rank":20,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7973787142750351,"rank":20,"remainingConfigurations":444},{"removed":"math500","score":0.7973933833071905,"rank":20,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7982432183964304,"rank":20,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.8002760553516731,"rank":20,"remainingConfigurations":444},{"removed":"omniscience","score":0.7979046879356796,"rank":20,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7961446020522015,"rank":20,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7970922237403135,"rank":20,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7870079358022637,"rank":22,"remainingConfigurations":444},{"removed":"arc-agi","score":0.809695035392597,"rank":23,"remainingConfigurations":444},{"removed":"deepswe","score":0.7881502106420335,"rank":19,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7973578533904183,"rank":20,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.792375741218346,"rank":20,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7586454419849096,"rank":23,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7650314467340534,"rank":26,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.796246723610461,"rank":20,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.797017930709713,"rank":22,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7986215072012728,"rank":20,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7972304516986477,"rank":20,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7963008857612351,"rank":20,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7978984736637873,"rank":20,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7982038032379806,"rank":20,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7966266054789243,"rank":20,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7969991356498487,"rank":20,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7985691409076043,"rank":20,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.844131025189255,"rank":14,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7941480644047193,"rank":21,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7932971595696325,"rank":20,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7980141443114496,"rank":20,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7973186713266563,"rank":20,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7973207413886954,"rank":20,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7970396110719848,"rank":20,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7972249848631593,"rank":20,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7972830240841929,"rank":20,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7970746377712254,"rank":20,"remainingConfigurations":444}],"sharedOrderConflicts":3},"claude-fable-5-1--effort-medium":{"score":0.7948008948322135,"rank":21,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.821420576370795,"rank":21,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.820463950494338,"rank":21,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7838351876453946,"rank":21,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7947128390539722,"rank":21,"remainingConfigurations":444},{"removed":"Scale","score":0.8016558227816608,"rank":21,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7925124445819326,"rank":21,"remainingConfigurations":444},{"removed":"Cognition","score":0.7224629402969384,"rank":31,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8026524466513433,"rank":22,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7926692108788395,"rank":21,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8047825299314942,"rank":22,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7870846153303993,"rank":22,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.795182330922537,"rank":21,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7923629175655825,"rank":22,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7943248609956859,"rank":21,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7948008948322135,"rank":21,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7948298478242598,"rank":21,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7923334176590385,"rank":21,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7944665097689496,"rank":21,"remainingConfigurations":444},{"removed":"briefcase","score":0.79259587779323,"rank":23,"remainingConfigurations":444},{"removed":"aime","score":0.7926260354216206,"rank":20,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7951797704443783,"rank":21,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7940369879764112,"rank":21,"remainingConfigurations":444},{"removed":"automationbench","score":0.799413300329397,"rank":20,"remainingConfigurations":444},{"removed":"critpt","score":0.7985148458446597,"rank":21,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7944204795115603,"rank":21,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7947904735455844,"rank":21,"remainingConfigurations":444},{"removed":"gdpval","score":0.7971816940804647,"rank":21,"remainingConfigurations":444},{"removed":"gmmlu","score":0.794467767095188,"rank":21,"remainingConfigurations":444},{"removed":"gpqa","score":0.8025460451001095,"rank":21,"remainingConfigurations":444},{"removed":"harvey","score":0.7948969395865655,"rank":22,"remainingConfigurations":444},{"removed":"hle","score":0.7962960921449981,"rank":22,"remainingConfigurations":444},{"removed":"ifbench","score":0.791255306382495,"rank":22,"remainingConfigurations":444},{"removed":"itbench","score":0.7951463898338228,"rank":21,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7940668098253948,"rank":21,"remainingConfigurations":444},{"removed":"math500","score":0.7944689316371356,"rank":21,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7961882812494564,"rank":21,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7993628049813362,"rank":21,"remainingConfigurations":444},{"removed":"omniscience","score":0.7955515098218968,"rank":21,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7942124508504723,"rank":22,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7935227514544461,"rank":21,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.790553241905366,"rank":20,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8117950414523735,"rank":22,"remainingConfigurations":444},{"removed":"deepswe","score":0.7840264395644111,"rank":21,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7948218806633239,"rank":21,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7902128007542721,"rank":21,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7224629402969384,"rank":31,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7936560694835532,"rank":21,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7926333780053861,"rank":21,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7945936120833142,"rank":23,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7920911278727717,"rank":22,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7941199967961957,"rank":21,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7925103462284993,"rank":21,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7964146427560662,"rank":21,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7958593979997941,"rank":21,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7933741791534784,"rank":21,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7939169505767459,"rank":21,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.797415619227445,"rank":21,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7926692108788395,"rank":21,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7950380308690891,"rank":20,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.793093896752353,"rank":21,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7969180225867118,"rank":23,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7948947697607407,"rank":21,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7944842118632729,"rank":21,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7941992314975336,"rank":21,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7944322387509928,"rank":21,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7940366240316749,"rank":21,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7942343972500164,"rank":21,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-sol--effort-xhigh":{"score":0.7927595850485814,"rank":22,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8329148702716993,"rank":18,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7917938742472875,"rank":26,"remainingConfigurations":444},{"removed":"Datacurve","score":0.751635728146927,"rank":24,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7927568844141563,"rank":23,"remainingConfigurations":444},{"removed":"Scale","score":0.7850517267090745,"rank":25,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7932320703324128,"rank":20,"remainingConfigurations":444},{"removed":"Cognition","score":0.7977611600230358,"rank":20,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7995659541600516,"rank":25,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.790351612036296,"rank":22,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7982381538120098,"rank":24,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7934646684128053,"rank":19,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7927676572419929,"rank":23,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7946866155451892,"rank":21,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7925268981769391,"rank":22,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7927595850485814,"rank":22,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7898893215746705,"rank":22,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7914394650224291,"rank":22,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7926075334032795,"rank":23,"remainingConfigurations":444},{"removed":"briefcase","score":0.7933726091216128,"rank":22,"remainingConfigurations":444},{"removed":"aime","score":0.7916414257753112,"rank":22,"remainingConfigurations":444},{"removed":"apex-agents","score":0.792965015724131,"rank":23,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7936472891431962,"rank":22,"remainingConfigurations":444},{"removed":"automationbench","score":0.7935013285238569,"rank":22,"remainingConfigurations":444},{"removed":"critpt","score":0.7943846267367257,"rank":22,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7924611216912236,"rank":23,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7904616187935994,"rank":23,"remainingConfigurations":444},{"removed":"gdpval","score":0.7936762514582077,"rank":23,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7925635625955433,"rank":23,"remainingConfigurations":444},{"removed":"gpqa","score":0.7902979239720258,"rank":24,"remainingConfigurations":444},{"removed":"harvey","score":0.7921691422953598,"rank":23,"remainingConfigurations":444},{"removed":"hle","score":0.7950196637532364,"rank":24,"remainingConfigurations":444},{"removed":"ifbench","score":0.7960003721316133,"rank":21,"remainingConfigurations":444},{"removed":"itbench","score":0.7924994314770708,"rank":23,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7923744694653946,"rank":23,"remainingConfigurations":444},{"removed":"math500","score":0.792572956231668,"rank":23,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7947984152110287,"rank":23,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7972883517196904,"rank":22,"remainingConfigurations":444},{"removed":"omniscience","score":0.7921471194126012,"rank":23,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7960691344941025,"rank":21,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7924235452510158,"rank":23,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7943700029798716,"rank":18,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7924985147723564,"rank":26,"remainingConfigurations":444},{"removed":"deepswe","score":0.7514873354742662,"rank":25,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7938680555622525,"rank":22,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.790053566585204,"rank":22,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7977611600230358,"rank":20,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7936483907643218,"rank":22,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7741237703041198,"rank":24,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7975307450070606,"rank":21,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7965221584595823,"rank":21,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7928966527102405,"rank":22,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7920068457517755,"rank":22,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7934802083776636,"rank":23,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7925205176187253,"rank":23,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7915267413246424,"rank":22,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.792048921045151,"rank":23,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7948308409039502,"rank":23,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.790351612036296,"rank":22,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7922457459392619,"rank":22,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7903435636636246,"rank":23,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7976489640518647,"rank":22,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7931204580451091,"rank":22,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7919834453278428,"rank":23,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7926413313293926,"rank":23,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7921955287555456,"rank":23,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7917803247796354,"rank":23,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7928067889521829,"rank":22,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-6-astra--effort-low":{"score":0.7927593849681646,"rank":23,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8026140833174106,"rank":22,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7723234022739837,"rank":31,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7783133394052314,"rank":22,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7927633972195761,"rank":22,"remainingConfigurations":444},{"removed":"Scale","score":0.800223824479091,"rank":22,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.785687565316965,"rank":24,"remainingConfigurations":444},{"removed":"Cognition","score":0.8108927327141312,"rank":17,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7999685681506742,"rank":24,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7899723980955154,"rank":23,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7915624804656635,"rank":25,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7892443203997107,"rank":21,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7927744878279878,"rank":22,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7915402201674681,"rank":23,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7924714415662192,"rank":23,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7927593849681646,"rank":23,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.731867934548367,"rank":34,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7302291383251743,"rank":33,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7929098392581878,"rank":22,"remainingConfigurations":444},{"removed":"briefcase","score":0.7967813778718339,"rank":20,"remainingConfigurations":444},{"removed":"aime","score":0.7921978329951461,"rank":21,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7932927945307305,"rank":22,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7932659722088481,"rank":23,"remainingConfigurations":444},{"removed":"automationbench","score":0.7920646555817918,"rank":24,"remainingConfigurations":444},{"removed":"critpt","score":0.7931750243697494,"rank":23,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7928685393252018,"rank":22,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7898742150519382,"rank":24,"remainingConfigurations":444},{"removed":"gdpval","score":0.795732905400949,"rank":22,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7927850713298873,"rank":22,"remainingConfigurations":444},{"removed":"gpqa","score":0.7906937092018019,"rank":23,"remainingConfigurations":444},{"removed":"harvey","score":0.7919506807613682,"rank":24,"remainingConfigurations":444},{"removed":"hle","score":0.7957156477333643,"rank":23,"remainingConfigurations":444},{"removed":"ifbench","score":0.7907817499453347,"rank":23,"remainingConfigurations":444},{"removed":"itbench","score":0.7925490591210503,"rank":22,"remainingConfigurations":444},{"removed":"livecodebench","score":0.792679568450421,"rank":22,"remainingConfigurations":444},{"removed":"math500","score":0.792717439505271,"rank":22,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7952750778941017,"rank":22,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7963973197997382,"rank":23,"remainingConfigurations":444},{"removed":"omniscience","score":0.7923783443808784,"rank":22,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7931990716252991,"rank":23,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7930937179871846,"rank":22,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7853114209637243,"rank":24,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8450127191711841,"rank":18,"remainingConfigurations":444},{"removed":"deepswe","score":0.7773996297331006,"rank":22,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7927595423594197,"rank":23,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7623993365476439,"rank":26,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8108927327141312,"rank":17,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7930397798066312,"rank":23,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7904085323292658,"rank":22,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7926620106249912,"rank":24,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7912714668280306,"rank":23,"remainingConfigurations":444},{"removed":"livebench-math","score":0.792808254112177,"rank":23,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7918925776185852,"rank":23,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7937025162197259,"rank":22,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7926295459587501,"rank":22,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7912883296114862,"rank":23,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7920822226352523,"rank":22,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7948876586269726,"rank":22,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7899723980955154,"rank":23,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7886282599298773,"rank":24,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7906136436058467,"rank":22,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7979006509926134,"rank":21,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7930539188320989,"rank":23,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7920952217132186,"rank":22,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7927248953600947,"rank":22,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7922241110820026,"rank":22,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7918095762555443,"rank":22,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7927584383654459,"rank":23,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5--effort-high":{"score":0.790553136546194,"rank":24,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8015213473452346,"rank":23,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7850070371381425,"rank":29,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7514436091062974,"rank":25,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7905309785289901,"rank":24,"remainingConfigurations":444},{"removed":"Scale","score":0.7994491362138164,"rank":23,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.790487879248345,"rank":22,"remainingConfigurations":444},{"removed":"Cognition","score":0.8412326672658877,"rank":14,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7976420917926094,"rank":27,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7551963913629524,"rank":28,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8028573943934348,"rank":23,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7835611040658104,"rank":24,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.789979737991022,"rank":24,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7884452654545236,"rank":24,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7903115249091442,"rank":24,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.790553136546194,"rank":24,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7891135938218671,"rank":23,"remainingConfigurations":444},{"removed":"All provider reports","score":0.786209333304999,"rank":23,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7903960931085326,"rank":24,"remainingConfigurations":444},{"removed":"briefcase","score":0.7886183299666413,"rank":24,"remainingConfigurations":444},{"removed":"aime","score":0.7877146861907726,"rank":23,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7909625478286132,"rank":24,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7917184922785575,"rank":24,"remainingConfigurations":444},{"removed":"automationbench","score":0.7925788763042361,"rank":23,"remainingConfigurations":444},{"removed":"critpt","score":0.791117447656267,"rank":24,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.790502231002737,"rank":24,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7933373209223477,"rank":22,"remainingConfigurations":444},{"removed":"gdpval","score":0.7911646295231126,"rank":24,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7904350532379426,"rank":24,"remainingConfigurations":444},{"removed":"gpqa","score":0.792531476205486,"rank":22,"remainingConfigurations":444},{"removed":"harvey","score":0.7902307810945278,"rank":25,"remainingConfigurations":444},{"removed":"hle","score":0.7936957070431339,"rank":25,"remainingConfigurations":444},{"removed":"ifbench","score":0.788255925587647,"rank":24,"remainingConfigurations":444},{"removed":"itbench","score":0.7906194015648885,"rank":24,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7903030162014685,"rank":24,"remainingConfigurations":444},{"removed":"math500","score":0.7904292980876783,"rank":24,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7922856626758236,"rank":24,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.795880458642812,"rank":24,"remainingConfigurations":444},{"removed":"omniscience","score":0.7913672458938111,"rank":24,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7892302402420451,"rank":24,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7899816500118221,"rank":24,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7896436934125172,"rank":21,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8244173179036571,"rank":21,"remainingConfigurations":444},{"removed":"deepswe","score":0.7516373165129114,"rank":24,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7905691158613811,"rank":24,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7776437112662187,"rank":24,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8412326672658877,"rank":14,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7907030213917438,"rank":24,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7890629510957768,"rank":23,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.789913969786053,"rank":25,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.788752859972595,"rank":24,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7901774789523972,"rank":24,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7889992714745314,"rank":24,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7918300271056604,"rank":24,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7914036972714301,"rank":24,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7890356814698513,"rank":24,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7897665437923439,"rank":24,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7926662723834578,"rank":24,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7551963913629524,"rank":28,"remainingConfigurations":444},{"removed":"frontiermath","score":0.790172953660574,"rank":23,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7882336141907577,"rank":24,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7939979823051487,"rank":25,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7907184069870831,"rank":24,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7902487792022205,"rank":24,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7901790478361329,"rank":24,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7902340367956562,"rank":24,"remainingConfigurations":444},{"removed":"vibe-code","score":0.789836120040218,"rank":24,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7901519809560661,"rank":24,"remainingConfigurations":444}],"sharedOrderConflicts":3},"claude-opus-5--effort-xhigh":{"score":0.7852468407834232,"rank":25,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7862179054911328,"rank":25,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.8094143671872978,"rank":24,"remainingConfigurations":444},{"removed":"Datacurve","score":0.741384323701015,"rank":29,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7851998683002192,"rank":25,"remainingConfigurations":444},{"removed":"Scale","score":0.7205351945695769,"rank":40,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7691790134901381,"rank":25,"remainingConfigurations":444},{"removed":"Cognition","score":0.8573481723763864,"rank":12,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7979508651334909,"rank":26,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7818594310244854,"rank":24,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.8082315093110116,"rank":21,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7761802518280788,"rank":25,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7826472657541309,"rank":26,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7824839539486396,"rank":25,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7848515217200634,"rank":25,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7852468407834232,"rank":25,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7844159140834276,"rank":24,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7786680636062163,"rank":25,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7846379921185296,"rank":25,"remainingConfigurations":444},{"removed":"briefcase","score":0.7821559138305384,"rank":25,"remainingConfigurations":444},{"removed":"aime","score":0.7839095793122017,"rank":24,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7855947551190114,"rank":25,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7856010308161844,"rank":25,"remainingConfigurations":444},{"removed":"automationbench","score":0.7872330266746702,"rank":25,"remainingConfigurations":444},{"removed":"critpt","score":0.7863515330717182,"rank":25,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7853871896493295,"rank":25,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7881860635895942,"rank":25,"remainingConfigurations":444},{"removed":"gdpval","score":0.7837929324301226,"rank":25,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7851127824453918,"rank":25,"remainingConfigurations":444},{"removed":"gpqa","score":0.7876681990233542,"rank":25,"remainingConfigurations":444},{"removed":"harvey","score":0.7885760088699826,"rank":26,"remainingConfigurations":444},{"removed":"hle","score":0.7878251937092388,"rank":26,"remainingConfigurations":444},{"removed":"ifbench","score":0.7830720499610866,"rank":25,"remainingConfigurations":444},{"removed":"itbench","score":0.7865049674313918,"rank":25,"remainingConfigurations":444},{"removed":"livecodebench","score":0.784979543356552,"rank":25,"remainingConfigurations":444},{"removed":"math500","score":0.7851305732954647,"rank":25,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7872714112719459,"rank":25,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7908249687719024,"rank":25,"remainingConfigurations":444},{"removed":"omniscience","score":0.7870334689137555,"rank":25,"remainingConfigurations":444},{"removed":"tau-bench","score":0.783969658032758,"rank":25,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7843240602049216,"rank":25,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7680165241795622,"rank":26,"remainingConfigurations":444},{"removed":"arc-agi","score":0.8001834529633506,"rank":25,"remainingConfigurations":444},{"removed":"deepswe","score":0.7418808520207083,"rank":28,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.785261974439618,"rank":25,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7818253495016728,"rank":23,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8573481723763864,"rank":12,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7966077609679857,"rank":20,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7712123052400605,"rank":27,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.8027896965995654,"rank":20,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7675297521716503,"rank":26,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7840585936019466,"rank":25,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7820255538818941,"rank":25,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7867600642174297,"rank":25,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7879785358211847,"rank":25,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.783389456506292,"rank":25,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7840230971603342,"rank":25,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7885213773125889,"rank":25,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7818594310244854,"rank":24,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7846295466822064,"rank":25,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7855253527941004,"rank":25,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7957478270383445,"rank":24,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7853721870285408,"rank":25,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7846776885098413,"rank":25,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7839965578419359,"rank":25,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7843890828301335,"rank":25,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7839185311985365,"rank":25,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7841309953045696,"rank":25,"remainingConfigurations":444}],"sharedOrderConflicts":3},"claude-sonnet-5-5--effort-max":{"score":0.7752346952613443,"rank":26,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7773756058865874,"rank":26,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.79785213014779,"rank":25,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7476513607378078,"rank":26,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7751738830888749,"rank":26,"remainingConfigurations":444},{"removed":"Scale","score":0.7750259586671224,"rank":26,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6891190412967211,"rank":40,"remainingConfigurations":444},{"removed":"Cognition","score":0.8260612630377615,"rank":16,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8213331810507706,"rank":20,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7706254918481669,"rank":25,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7874104044699729,"rank":26,"remainingConfigurations":431},{"removed":"Vals AI","score":0.74713443092387,"rank":29,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7724024690497275,"rank":27,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.771896453183639,"rank":26,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7733022900850223,"rank":26,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7752346952613443,"rank":26,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7744953437225582,"rank":25,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7664012844357186,"rank":26,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7718754846747139,"rank":26,"remainingConfigurations":444},{"removed":"briefcase","score":0.7722383466578923,"rank":26,"remainingConfigurations":444},{"removed":"aime","score":0.7744106529537279,"rank":26,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7755245391533574,"rank":26,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7751863939186291,"rank":26,"remainingConfigurations":444},{"removed":"automationbench","score":0.7736400526099608,"rank":26,"remainingConfigurations":444},{"removed":"critpt","score":0.7764504098820724,"rank":26,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7756364837487991,"rank":26,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7774588202226043,"rank":26,"remainingConfigurations":444},{"removed":"gdpval","score":0.7739711380468544,"rank":26,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7751289292982224,"rank":26,"remainingConfigurations":444},{"removed":"gpqa","score":0.7773106737348311,"rank":26,"remainingConfigurations":444},{"removed":"harvey","score":0.7997956797203094,"rank":20,"remainingConfigurations":444},{"removed":"hle","score":0.7780760013521459,"rank":27,"remainingConfigurations":444},{"removed":"ifbench","score":0.7729652751189202,"rank":26,"remainingConfigurations":444},{"removed":"itbench","score":0.7767311835059881,"rank":26,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7750076504517964,"rank":26,"remainingConfigurations":444},{"removed":"math500","score":0.7751552971398713,"rank":26,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7774946981895257,"rank":26,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7809672534815809,"rank":26,"remainingConfigurations":444},{"removed":"omniscience","score":0.7798057708297099,"rank":26,"remainingConfigurations":444},{"removed":"tau-bench","score":0.773315331279144,"rank":26,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7729437299877455,"rank":26,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6920785583058375,"rank":40,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7881254937084664,"rank":27,"remainingConfigurations":444},{"removed":"deepswe","score":0.748135785767602,"rank":26,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.775257804514537,"rank":26,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7724908423694531,"rank":25,"remainingConfigurations":444},{"removed":"frontiercode","score":0.8260612630377615,"rank":16,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.776053609979027,"rank":25,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7726697695740277,"rank":26,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7762510273983634,"rank":26,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7713459629487701,"rank":25,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7693099276790464,"rank":26,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7623082432850525,"rank":27,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7783535161199903,"rank":26,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7877546435422492,"rank":26,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7718022844741365,"rank":27,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7689216773422781,"rank":26,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.787832443734553,"rank":26,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7706254918481669,"rank":25,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7736874436854907,"rank":26,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7725707697895032,"rank":26,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7782561093661311,"rank":26,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7760141906060117,"rank":26,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7690927055621829,"rank":26,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7749103590016427,"rank":26,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7692656412229697,"rank":26,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7681959088269762,"rank":26,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7720837024535756,"rank":26,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5-pro--effort-xhigh":{"score":0.7645221009807254,"rank":27,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7697148548617827,"rank":27,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.79134328327735,"rank":27,"remainingConfigurations":444},{"removed":"Datacurve","score":0.741393104687703,"rank":28,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7646656992515712,"rank":27,"remainingConfigurations":444},{"removed":"Scale","score":0.7721095942675298,"rank":27,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7635755532339638,"rank":26,"remainingConfigurations":444},{"removed":"Cognition","score":0.7475141258617114,"rank":25,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7689805515753664,"rank":29,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7615623187922008,"rank":26,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7601411277898741,"rank":29,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7585406321682977,"rank":26,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7640565698392905,"rank":28,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7614988534751778,"rank":27,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7642526674987052,"rank":27,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7645221009807254,"rank":27,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7634678814087468,"rank":26,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7597449911194056,"rank":27,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7649568760740003,"rank":27,"remainingConfigurations":444},{"removed":"briefcase","score":0.7642236237102482,"rank":27,"remainingConfigurations":444},{"removed":"aime","score":0.7650168887964682,"rank":27,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7651171839666254,"rank":27,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7640184107509486,"rank":28,"remainingConfigurations":444},{"removed":"automationbench","score":0.7640512262804338,"rank":27,"remainingConfigurations":444},{"removed":"critpt","score":0.7733125510683619,"rank":27,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7645822733859844,"rank":27,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7667289642413905,"rank":27,"remainingConfigurations":444},{"removed":"gdpval","score":0.7646944027256711,"rank":27,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7641834410040679,"rank":27,"remainingConfigurations":444},{"removed":"gpqa","score":0.7652163031605848,"rank":27,"remainingConfigurations":444},{"removed":"harvey","score":0.7638929061083991,"rank":27,"remainingConfigurations":444},{"removed":"hle","score":0.7679209030573803,"rank":28,"remainingConfigurations":444},{"removed":"ifbench","score":0.7611577851661111,"rank":28,"remainingConfigurations":444},{"removed":"itbench","score":0.7645406381864633,"rank":27,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7639080992625903,"rank":27,"remainingConfigurations":444},{"removed":"math500","score":0.7641985050639092,"rank":27,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.766288551487948,"rank":27,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7698117442232242,"rank":27,"remainingConfigurations":444},{"removed":"omniscience","score":0.7648404838938033,"rank":28,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7619046777479094,"rank":27,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7648498118454367,"rank":27,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7635554514687551,"rank":27,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7822817425972274,"rank":29,"remainingConfigurations":444},{"removed":"deepswe","score":0.741836654019683,"rank":29,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.764519922403839,"rank":27,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7501749969458859,"rank":28,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7475141258617114,"rank":25,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7639811687041268,"rank":27,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.762910462270808,"rank":29,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7640210577037839,"rank":27,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7626478678311609,"rank":27,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7643728031891701,"rank":27,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7634522791691788,"rank":26,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7655244810626706,"rank":27,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7650932938442455,"rank":28,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7627710478937808,"rank":28,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7639081975182141,"rank":28,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.76650252445289,"rank":27,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7615623187922008,"rank":26,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7592093408804055,"rank":28,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7621331562408219,"rank":27,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7759602595218139,"rank":27,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7645629240135076,"rank":27,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7642957847401499,"rank":27,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7639546709159513,"rank":27,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7641458670648339,"rank":27,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7636629893619444,"rank":27,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7641594595738398,"rank":27,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-sonnet-5-5--effort-xhigh":{"score":0.7625670719788503,"rank":28,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7679059271504709,"rank":28,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7714684213092781,"rank":32,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7417394426974978,"rank":27,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7624969374674313,"rank":28,"remainingConfigurations":444},{"removed":"Scale","score":0.8156799706105691,"rank":20,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7577847771230489,"rank":28,"remainingConfigurations":444},{"removed":"Cognition","score":0.6308637022582735,"rank":41,"remainingConfigurations":444},{"removed":"LiveBench","score":0.8242662700313458,"rank":19,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7602432679577769,"rank":27,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7614014201523566,"rank":28,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7469922574370793,"rank":30,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7618932022893633,"rank":29,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7605289523095946,"rank":28,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7609961474893364,"rank":28,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7625670719788503,"rank":28,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7624313368263774,"rank":27,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7581533863217939,"rank":28,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7628492530183683,"rank":28,"remainingConfigurations":444},{"removed":"briefcase","score":0.7588791655244224,"rank":28,"remainingConfigurations":444},{"removed":"aime","score":0.7614914742116113,"rank":28,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7629135642213732,"rank":28,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.767327681690256,"rank":27,"remainingConfigurations":444},{"removed":"automationbench","score":0.762425466958144,"rank":28,"remainingConfigurations":444},{"removed":"critpt","score":0.7636074188804948,"rank":28,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7627533299936657,"rank":28,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7655441612190287,"rank":28,"remainingConfigurations":444},{"removed":"gdpval","score":0.7616884570052457,"rank":28,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7616550044688847,"rank":28,"remainingConfigurations":444},{"removed":"gpqa","score":0.7643457045876701,"rank":28,"remainingConfigurations":444},{"removed":"harvey","score":0.7622298384846844,"rank":28,"remainingConfigurations":444},{"removed":"hle","score":0.8135252116417311,"rank":19,"remainingConfigurations":444},{"removed":"ifbench","score":0.7611865904261405,"rank":27,"remainingConfigurations":444},{"removed":"itbench","score":0.7631912089521244,"rank":28,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7621263118715911,"rank":28,"remainingConfigurations":444},{"removed":"math500","score":0.7622962350374669,"rank":28,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7640026784043105,"rank":28,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7680320005945188,"rank":28,"remainingConfigurations":444},{"removed":"omniscience","score":0.7654023984114199,"rank":27,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7607651472867886,"rank":28,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7594336948550083,"rank":28,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7558189696201542,"rank":29,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7610006880532305,"rank":30,"remainingConfigurations":444},{"removed":"deepswe","score":0.7419357093142183,"rank":27,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7625946908609734,"rank":28,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.760094495028144,"rank":27,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6308637022582735,"rank":41,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7332453127999622,"rank":33,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7631182146699547,"rank":28,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7433097441894345,"rank":30,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7607291421572314,"rank":28,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7568842461604532,"rank":28,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7453573663327581,"rank":29,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7650526682731863,"rank":28,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7659746220600675,"rank":27,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7753375091516905,"rank":26,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7639916862691898,"rank":27,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7652721617869789,"rank":28,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7602432679577769,"rank":27,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7618739534544477,"rank":27,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7603927984099389,"rank":28,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7636346058142348,"rank":28,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7625423624593578,"rank":28,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7625321086145043,"rank":28,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7620409589053961,"rank":28,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7623620890455026,"rank":28,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7617407921734977,"rank":28,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7621408981055747,"rank":28,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-fable-5--effort-medium":{"score":0.7531156528332978,"rank":29,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.751694445957445,"rank":30,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7878176960685374,"rank":28,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7651827026782279,"rank":23,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7531369089221776,"rank":29,"remainingConfigurations":444},{"removed":"Scale","score":0.760126910848047,"rank":29,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7511904565142385,"rank":29,"remainingConfigurations":444},{"removed":"Cognition","score":0.6660476790613233,"rank":38,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7626917720254681,"rank":32,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7491555550467779,"rank":29,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7630531608419583,"rank":27,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7445060679359253,"rank":31,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7520273135176163,"rank":30,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7502673803197207,"rank":29,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7529342760567953,"rank":29,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7531156528332978,"rank":29,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7524254145451037,"rank":28,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7483469571265156,"rank":29,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7530176429536989,"rank":29,"remainingConfigurations":444},{"removed":"briefcase","score":0.7513839457690773,"rank":29,"remainingConfigurations":444},{"removed":"aime","score":0.7519053584981105,"rank":29,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7536902230651483,"rank":29,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7535291686410113,"rank":29,"remainingConfigurations":444},{"removed":"automationbench","score":0.7537064272373191,"rank":29,"remainingConfigurations":444},{"removed":"critpt","score":0.7512851361329339,"rank":29,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7531032498429836,"rank":29,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7548376073206909,"rank":29,"remainingConfigurations":444},{"removed":"gdpval","score":0.7534070065109132,"rank":29,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7530248063658079,"rank":29,"remainingConfigurations":444},{"removed":"gpqa","score":0.7540328359993417,"rank":29,"remainingConfigurations":444},{"removed":"harvey","score":0.7534221515382177,"rank":29,"remainingConfigurations":444},{"removed":"hle","score":0.756664202672531,"rank":29,"remainingConfigurations":444},{"removed":"ifbench","score":0.7506142216565989,"rank":29,"remainingConfigurations":444},{"removed":"itbench","score":0.7534491506660643,"rank":29,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7529358328131326,"rank":29,"remainingConfigurations":444},{"removed":"math500","score":0.753020571792825,"rank":29,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7556275890461861,"rank":29,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.759105616538939,"rank":29,"remainingConfigurations":444},{"removed":"omniscience","score":0.7540276131940834,"rank":29,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7516136013708955,"rank":29,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7519799243692652,"rank":29,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7501890115541859,"rank":31,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7835369509242548,"rank":28,"remainingConfigurations":444},{"removed":"deepswe","score":0.7653808407715976,"rank":23,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7531493709887748,"rank":29,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7473362064544551,"rank":29,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6660476790613233,"rank":38,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7524648671221774,"rank":28,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7500459077402715,"rank":30,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7522696954842377,"rank":28,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7510357266867073,"rank":29,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7525074718659398,"rank":29,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7506604319373295,"rank":28,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7548690145917143,"rank":30,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7543096979772718,"rank":29,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7513713713477767,"rank":29,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.752044690678679,"rank":29,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7560458397850888,"rank":29,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7491555550467779,"rank":29,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7512398655858211,"rank":29,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7516765609598579,"rank":29,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7578126607044178,"rank":29,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.753070862964722,"rank":29,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7528593237950023,"rank":30,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7524197478099817,"rank":29,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7527065396733654,"rank":29,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7523227235358209,"rank":29,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7524953091257666,"rank":29,"remainingConfigurations":444}],"sharedOrderConflicts":2},"muse-spark-1.3--effort-xhigh":{"score":0.7427064995842336,"rank":30,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7447254021288932,"rank":33,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7694174913331361,"rank":33,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7169000822184639,"rank":31,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7425854525903001,"rank":30,"remainingConfigurations":444},{"removed":"Scale","score":0.750461546614536,"rank":31,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7422709110446064,"rank":31,"remainingConfigurations":444},{"removed":"Cognition","score":0.7390452714638912,"rank":28,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7333674374486523,"rank":39,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7384008989733696,"rank":30,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7387222071807223,"rank":36,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7557986815200374,"rank":27,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7421373101458851,"rank":32,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7399900500234499,"rank":30,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6560720123973566,"rank":44,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7427064995842336,"rank":30,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7421532854883522,"rank":29,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6520598117519161,"rank":45,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7427380016866677,"rank":30,"remainingConfigurations":444},{"removed":"briefcase","score":0.7412493060740551,"rank":30,"remainingConfigurations":444},{"removed":"aime","score":0.7433212499575633,"rank":30,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7429969268742892,"rank":30,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7426486509227482,"rank":30,"remainingConfigurations":444},{"removed":"automationbench","score":0.7432129660604385,"rank":30,"remainingConfigurations":444},{"removed":"critpt","score":0.7429720701251533,"rank":31,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7422631642620595,"rank":31,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7428665546224805,"rank":31,"remainingConfigurations":444},{"removed":"gdpval","score":0.7404293249343858,"rank":32,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7427434726130788,"rank":30,"remainingConfigurations":444},{"removed":"gpqa","score":0.7403914848951723,"rank":32,"remainingConfigurations":444},{"removed":"harvey","score":0.7244359857448889,"rank":37,"remainingConfigurations":444},{"removed":"hle","score":0.745701696195557,"rank":30,"remainingConfigurations":444},{"removed":"ifbench","score":0.7401933023880876,"rank":31,"remainingConfigurations":444},{"removed":"itbench","score":0.7426497422383157,"rank":30,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7426421081153879,"rank":30,"remainingConfigurations":444},{"removed":"math500","score":0.74275413930916,"rank":30,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7445506446451543,"rank":31,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7493383865457925,"rank":30,"remainingConfigurations":444},{"removed":"omniscience","score":0.7502290876983619,"rank":30,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7396875106861166,"rank":31,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.74286538300428,"rank":30,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7539390170056931,"rank":30,"remainingConfigurations":444},{"removed":"arc-agi","score":0.758536552406531,"rank":33,"remainingConfigurations":444},{"removed":"deepswe","score":0.7171263590931992,"rank":31,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7427853419660438,"rank":30,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7404508359426724,"rank":31,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7390452714638912,"rank":28,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7430783883044741,"rank":30,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7407636263800956,"rank":31,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7422483048065528,"rank":31,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7404426599759223,"rank":30,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7425214529953529,"rank":31,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7440085751742987,"rank":30,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7552063575156701,"rank":29,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7452721539903496,"rank":31,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7334471370462342,"rank":33,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7449456465556472,"rank":30,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7336159495399966,"rank":36,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7384008989733696,"rank":30,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7431364170132101,"rank":30,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7398192641691058,"rank":30,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7411478640637695,"rank":34,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7307774090850199,"rank":36,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7603374840309644,"rank":29,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7439189848181899,"rank":30,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7522517346778388,"rank":30,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7395975795486113,"rank":32,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7366397223649012,"rank":33,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.6-sol--effort-max":{"score":0.741123875720382,"rank":31,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7451926541214045,"rank":32,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7584940423022534,"rank":36,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6953639520874974,"rank":36,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.741081561772896,"rank":31,"remainingConfigurations":444},{"removed":"Scale","score":0.7505994456201542,"rank":30,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7605351124304148,"rank":27,"remainingConfigurations":444},{"removed":"Cognition","score":0.7222090105531357,"rank":32,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7530198259475399,"rank":34,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7350320119593176,"rank":31,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7418030109314255,"rank":35,"remainingConfigurations":431},{"removed":"Vals AI","score":0.750437219739041,"rank":28,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.741016790238285,"rank":33,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7354979862765605,"rank":33,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.740255375367747,"rank":31,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.741123875720382,"rank":31,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7401300294462453,"rank":31,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7329293477541851,"rank":32,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7411124417278239,"rank":31,"remainingConfigurations":444},{"removed":"briefcase","score":0.7406097054200069,"rank":31,"remainingConfigurations":444},{"removed":"aime","score":0.7408942991493696,"rank":31,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7412431151460922,"rank":32,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7414581998817343,"rank":31,"remainingConfigurations":444},{"removed":"automationbench","score":0.7405441276059254,"rank":33,"remainingConfigurations":444},{"removed":"critpt","score":0.7413625612727898,"rank":32,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7431922588663369,"rank":30,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7418487137554446,"rank":32,"remainingConfigurations":444},{"removed":"gdpval","score":0.7409680927406911,"rank":30,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7411476395303233,"rank":31,"remainingConfigurations":444},{"removed":"gpqa","score":0.7340024756192429,"rank":34,"remainingConfigurations":444},{"removed":"harvey","score":0.7459357206197194,"rank":30,"remainingConfigurations":444},{"removed":"hle","score":0.7418677556035415,"rank":33,"remainingConfigurations":444},{"removed":"ifbench","score":0.7402679961146252,"rank":30,"remainingConfigurations":444},{"removed":"itbench","score":0.739433202566928,"rank":33,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7410986207661746,"rank":31,"remainingConfigurations":444},{"removed":"math500","score":0.7411483326309534,"rank":31,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7461277726261045,"rank":30,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.739530019729477,"rank":33,"remainingConfigurations":444},{"removed":"omniscience","score":0.7433372042993902,"rank":32,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7401904145913353,"rank":30,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7402375037114372,"rank":31,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.757924600142378,"rank":28,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7587953336813323,"rank":32,"remainingConfigurations":444},{"removed":"deepswe","score":0.689300789144216,"rank":37,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7408882225243127,"rank":32,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7449110919169474,"rank":30,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7222090105531357,"rank":32,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7417420016524526,"rank":31,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7389651254483803,"rank":32,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7403233351220088,"rank":32,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7400134641836518,"rank":31,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7428332567202522,"rank":30,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7361176106500061,"rank":32,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7407747655623981,"rank":33,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7423368697522243,"rank":33,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.741950035631854,"rank":30,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7385418192319083,"rank":33,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7453761481704912,"rank":30,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7350320119593176,"rank":31,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7356260829299828,"rank":32,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7378000106146695,"rank":32,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7501803279953866,"rank":30,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7447281470511626,"rank":30,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7392584463806271,"rank":33,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.738922430402957,"rank":32,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.736796893462086,"rank":33,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7400156009937522,"rank":31,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7405144401863808,"rank":30,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-fable-5--effort-xhigh":{"score":0.7409165255600528,"rank":32,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.74246602103098,"rank":34,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7414944000652218,"rank":40,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7049378859700622,"rank":33,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7409529712056061,"rank":32,"remainingConfigurations":444},{"removed":"Scale","score":0.8759396799027722,"rank":12,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7153947750274986,"rank":37,"remainingConfigurations":444},{"removed":"Cognition","score":0.6866110045169638,"rank":35,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7501332568394593,"rank":35,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7348982586131179,"rank":32,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7532768332739614,"rank":30,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7324438786201778,"rank":32,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7401393177842234,"rank":34,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7383967185070265,"rank":31,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7407221111146468,"rank":30,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7409165255600528,"rank":32,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7402907362897745,"rank":30,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7368232769569646,"rank":31,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.740676445459821,"rank":32,"remainingConfigurations":444},{"removed":"briefcase","score":0.738929867169405,"rank":32,"remainingConfigurations":444},{"removed":"aime","score":0.7390303803241688,"rank":32,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7414326575849616,"rank":31,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7414286332655536,"rank":32,"remainingConfigurations":444},{"removed":"automationbench","score":0.7419130195120909,"rank":31,"remainingConfigurations":444},{"removed":"critpt","score":0.7434900051151452,"rank":30,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7410173622771049,"rank":32,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7430659518923252,"rank":30,"remainingConfigurations":444},{"removed":"gdpval","score":0.7404710930213886,"rank":31,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7408231546469509,"rank":32,"remainingConfigurations":444},{"removed":"gpqa","score":0.7411291227611821,"rank":31,"remainingConfigurations":444},{"removed":"harvey","score":0.7417760046977823,"rank":33,"remainingConfigurations":444},{"removed":"hle","score":0.7449289046291625,"rank":31,"remainingConfigurations":444},{"removed":"ifbench","score":0.7388765738289038,"rank":33,"remainingConfigurations":444},{"removed":"itbench","score":0.7411356951924951,"rank":31,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7408012817107258,"rank":32,"remainingConfigurations":444},{"removed":"math500","score":0.7408384155724481,"rank":32,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.742949358888935,"rank":32,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7466462595138683,"rank":31,"remainingConfigurations":444},{"removed":"omniscience","score":0.7418195353089226,"rank":33,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7394934589231749,"rank":32,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7401225213257767,"rank":32,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7146593591505058,"rank":37,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7327619960321247,"rank":40,"remainingConfigurations":444},{"removed":"deepswe","score":0.7050932302035434,"rank":33,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7409357727794007,"rank":31,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.73754356749759,"rank":32,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6866110045169638,"rank":35,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7448933127303494,"rank":29,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7736633432357766,"rank":25,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7502184743638347,"rank":29,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7091036503122939,"rank":40,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7403294835223361,"rank":32,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7383026943250809,"rank":31,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7424543344737881,"rank":32,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7423514991160923,"rank":32,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7392190882619079,"rank":31,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7397950506116476,"rank":32,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7439661694761708,"rank":32,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7348982586131179,"rank":32,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7424574023445634,"rank":31,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7379765781678462,"rank":31,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7434550310876027,"rank":32,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7409327945982479,"rank":32,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7404931118182958,"rank":31,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.740102361075583,"rank":31,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7403908420637011,"rank":31,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7402418327461016,"rank":30,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.740129451431832,"rank":31,"remainingConfigurations":444}],"sharedOrderConflicts":2},"claude-fable-5--effort-max":{"score":0.7395803680955662,"rank":33,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7510765954493134,"rank":31,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7569439859451447,"rank":37,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7025404077064951,"rank":35,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7395497009113244,"rank":33,"remainingConfigurations":444},{"removed":"Scale","score":0.7447771291578786,"rank":32,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7504282126985933,"rank":30,"remainingConfigurations":444},{"removed":"Cognition","score":0.7247903586859298,"rank":30,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7644075484119374,"rank":31,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7348651086223307,"rank":33,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7520000150959069,"rank":31,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7190615135363266,"rank":35,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7897124299420465,"rank":25,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7359578149848387,"rank":32,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.73848029287296,"rank":32,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7395803680955662,"rank":33,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7385409785893833,"rank":32,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7844242960154478,"rank":24,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.738528771650568,"rank":33,"remainingConfigurations":444},{"removed":"briefcase","score":0.7374246207713018,"rank":33,"remainingConfigurations":444},{"removed":"aime","score":0.7302155758607901,"rank":35,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7398904201921782,"rank":33,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7393483977863364,"rank":33,"remainingConfigurations":444},{"removed":"automationbench","score":0.7304673528120622,"rank":36,"remainingConfigurations":444},{"removed":"critpt","score":0.7406396369204779,"rank":33,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7386429602487116,"rank":33,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7413191919356782,"rank":33,"remainingConfigurations":444},{"removed":"gdpval","score":0.738779478559774,"rank":33,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7395389291665753,"rank":33,"remainingConfigurations":444},{"removed":"gpqa","score":0.7529401187765906,"rank":30,"remainingConfigurations":444},{"removed":"harvey","score":0.7451994569927867,"rank":31,"remainingConfigurations":444},{"removed":"hle","score":0.7423000387491686,"rank":32,"remainingConfigurations":444},{"removed":"ifbench","score":0.739949099719233,"rank":32,"remainingConfigurations":444},{"removed":"itbench","score":0.7403608694120253,"rank":32,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7394843455692693,"rank":33,"remainingConfigurations":444},{"removed":"math500","score":0.7395609137994553,"rank":33,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7409712244275757,"rank":33,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7460068128668583,"rank":32,"remainingConfigurations":444},{"removed":"omniscience","score":0.7417324947782342,"rank":34,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7380983118519734,"rank":33,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7389062724569916,"rank":33,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7701668542248417,"rank":25,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7473690237525336,"rank":36,"remainingConfigurations":444},{"removed":"deepswe","score":0.7031070326058716,"rank":35,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.739594495056192,"rank":33,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7361843053128191,"rank":34,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7247903586859298,"rank":30,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7404318348905955,"rank":32,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7369724558366566,"rank":33,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7398423858670004,"rank":33,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7368368655764831,"rank":32,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7375856369398898,"rank":33,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7348478669868634,"rank":34,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7396313759694375,"rank":34,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7459901795606257,"rank":30,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7340663229886023,"rank":32,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7407681093257593,"rank":31,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7442760135107301,"rank":31,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7348651086223307,"rank":33,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7336928708413817,"rank":33,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7358604620270152,"rank":33,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7457543659777084,"rank":31,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.742441796961796,"rank":31,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7400753403989602,"rank":32,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7365445253073917,"rank":33,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7359950772498055,"rank":34,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7358558151144811,"rank":33,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7388346770681963,"rank":32,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gemini-4-argon--effort-low":{"score":0.7328455654459817,"rank":34,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7399213755478261,"rank":36,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9736424693011694,"rank":2,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6949679738835676,"rank":37,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7331231006084118,"rank":34,"remainingConfigurations":444},{"removed":"Scale","score":0.7410943262987152,"rank":33,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7328629114116335,"rank":34,"remainingConfigurations":444},{"removed":"Cognition","score":0.572388095402122,"rank":49,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7449870255260688,"rank":36,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7295157011322865,"rank":34,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.736716023729063,"rank":37,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7280394132371891,"rank":33,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7326093564893852,"rank":35,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7299438044681424,"rank":34,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7325201460877014,"rank":33,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7328455654459817,"rank":34,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7324542604145939,"rank":33,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7290197272806943,"rank":34,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7328674990298643,"rank":35,"remainingConfigurations":444},{"removed":"briefcase","score":0.7328129775651302,"rank":34,"remainingConfigurations":444},{"removed":"aime","score":0.7317214118979103,"rank":34,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7334891592905252,"rank":34,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7326995706881504,"rank":36,"remainingConfigurations":444},{"removed":"automationbench","score":0.7313251513292363,"rank":35,"remainingConfigurations":444},{"removed":"critpt","score":0.732495188674349,"rank":35,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.732769400396816,"rank":34,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7337039330505792,"rank":34,"remainingConfigurations":444},{"removed":"gdpval","score":0.733364909085806,"rank":34,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7328131296324923,"rank":34,"remainingConfigurations":444},{"removed":"gpqa","score":0.7298871094958946,"rank":37,"remainingConfigurations":444},{"removed":"harvey","score":0.7315499470377212,"rank":34,"remainingConfigurations":444},{"removed":"hle","score":0.7379308685913201,"rank":35,"remainingConfigurations":444},{"removed":"ifbench","score":0.7302938382575542,"rank":34,"remainingConfigurations":444},{"removed":"itbench","score":0.7325557023925291,"rank":35,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7330188914025267,"rank":34,"remainingConfigurations":444},{"removed":"math500","score":0.7328116011215151,"rank":34,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7360752695548415,"rank":35,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7386173195009292,"rank":35,"remainingConfigurations":444},{"removed":"omniscience","score":0.7333195958228461,"rank":36,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7313685160054485,"rank":34,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7329582091578789,"rank":34,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7333973466775521,"rank":33,"remainingConfigurations":444},{"removed":"arc-agi","score":0.9412479645188938,"rank":3,"remainingConfigurations":444},{"removed":"deepswe","score":0.6949740230009326,"rank":36,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.732855017782211,"rank":34,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.49773819122290347,"rank":68,"remainingConfigurations":444},{"removed":"frontiercode","score":0.572388095402122,"rank":49,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7322809926138746,"rank":34,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7307525966442227,"rank":34,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7325443932232562,"rank":34,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7309589388376162,"rank":33,"remainingConfigurations":444},{"removed":"livebench-math","score":0.732825712325444,"rank":34,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7324023141053413,"rank":35,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7336702763893305,"rank":35,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7336297788230853,"rank":35,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.730759491606405,"rank":34,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7320946575516055,"rank":34,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7345223543592084,"rank":35,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7295157011322865,"rank":34,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7325492336000693,"rank":34,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7295582613782239,"rank":34,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7374617543756369,"rank":35,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.732432769594822,"rank":35,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7325562755981534,"rank":34,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7327024913662301,"rank":34,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7324730736418946,"rank":35,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7320282623336821,"rank":35,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7324850227555665,"rank":34,"remainingConfigurations":444}],"sharedOrderConflicts":2},"muse-wonder--effort-max":{"score":0.7321209992509411,"rank":35,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7223541682651119,"rank":40,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.762230757649363,"rank":35,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7029958680201386,"rank":34,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7319616180368796,"rank":35,"remainingConfigurations":444},{"removed":"Scale","score":0.7385637752603111,"rank":37,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7329890456218463,"rank":33,"remainingConfigurations":444},{"removed":"Cognition","score":0.7299871057932216,"rank":29,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7773898128848565,"rank":28,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7275185584380338,"rank":35,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7350485462583815,"rank":38,"remainingConfigurations":431},{"removed":"Vals AI","score":0.70716979721893,"rank":40,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7312150124212131,"rank":36,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.729188099493681,"rank":35,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7276805196102676,"rank":36,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7321209992509411,"rank":35,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7312839337007371,"rank":35,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7230415149484721,"rank":36,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7329692860852685,"rank":34,"remainingConfigurations":444},{"removed":"briefcase","score":0.7268656527292038,"rank":37,"remainingConfigurations":444},{"removed":"aime","score":0.7318890502840701,"rank":33,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7324562455343436,"rank":35,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7392486131070237,"rank":34,"remainingConfigurations":444},{"removed":"automationbench","score":0.7275674601014136,"rank":38,"remainingConfigurations":444},{"removed":"critpt","score":0.7349395791906352,"rank":34,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7325603333881481,"rank":35,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7303367008823565,"rank":36,"remainingConfigurations":444},{"removed":"gdpval","score":0.7286663886657877,"rank":37,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7320737373599381,"rank":35,"remainingConfigurations":444},{"removed":"gpqa","score":0.7305355291827215,"rank":36,"remainingConfigurations":444},{"removed":"harvey","score":0.7177106265723535,"rank":39,"remainingConfigurations":444},{"removed":"hle","score":0.7383902244844732,"rank":34,"remainingConfigurations":444},{"removed":"ifbench","score":0.7293288472505338,"rank":35,"remainingConfigurations":444},{"removed":"itbench","score":0.733035912985656,"rank":34,"remainingConfigurations":444},{"removed":"livecodebench","score":0.731929399144088,"rank":35,"remainingConfigurations":444},{"removed":"math500","score":0.7321228272878063,"rank":35,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7362963614275166,"rank":34,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7388584140419007,"rank":34,"remainingConfigurations":444},{"removed":"omniscience","score":0.7486786164047275,"rank":31,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7300047427726887,"rank":35,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.732905408076339,"rank":35,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7353451361141904,"rank":32,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7507412908441952,"rank":35,"remainingConfigurations":444},{"removed":"deepswe","score":0.7032154085936747,"rank":34,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7321815655649409,"rank":35,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7302066600653707,"rank":35,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7299871057932216,"rank":29,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7319177620877685,"rank":35,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7301447113760225,"rank":35,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.731538579498117,"rank":35,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7290786090728346,"rank":34,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7234250511526087,"rank":38,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.735862227915732,"rank":33,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7473862338875897,"rank":31,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7334798048331503,"rank":36,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7186589740050463,"rank":38,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7311649560121184,"rank":35,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7349275827279543,"rank":34,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7275185584380338,"rank":35,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7315931675002698,"rank":35,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7289554362357943,"rank":35,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7344855144402858,"rank":36,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7354305490226619,"rank":33,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7254547239468344,"rank":38,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7255096617059484,"rank":37,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.738087389987656,"rank":32,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7329533723109724,"rank":34,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7309185115038269,"rank":35,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5--effort-max":{"score":0.7308935047612021,"rank":36,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7351846383476337,"rank":38,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7387228612049128,"rank":41,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6802917693511773,"rank":38,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7308724411729459,"rank":36,"remainingConfigurations":444},{"removed":"Scale","score":0.7400951899847197,"rank":34,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7342449970102405,"rank":32,"remainingConfigurations":444},{"removed":"Cognition","score":0.7407655099385156,"rank":27,"remainingConfigurations":444},{"removed":"LiveBench","score":0.766336150592427,"rank":30,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7265898247144844,"rank":37,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7442035116154058,"rank":33,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7072183700328231,"rank":39,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7511742281972754,"rank":31,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7277547344466457,"rank":36,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7296918124921546,"rank":34,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7308935047612021,"rank":36,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7297604113383892,"rank":36,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7462308546745738,"rank":30,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7292099838820736,"rank":36,"remainingConfigurations":444},{"removed":"briefcase","score":0.7286874722297987,"rank":35,"remainingConfigurations":444},{"removed":"aime","score":0.728676443311041,"rank":36,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7312228295693628,"rank":36,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7316480992933695,"rank":37,"remainingConfigurations":444},{"removed":"automationbench","score":0.7416858837620682,"rank":32,"remainingConfigurations":444},{"removed":"critpt","score":0.7321467271829568,"rank":36,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7311400685031434,"rank":36,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7332488770154809,"rank":35,"remainingConfigurations":444},{"removed":"gdpval","score":0.7299860445002322,"rank":36,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7308547626686103,"rank":36,"remainingConfigurations":444},{"removed":"gpqa","score":0.7333566921929014,"rank":35,"remainingConfigurations":444},{"removed":"harvey","score":0.7417890658927258,"rank":32,"remainingConfigurations":444},{"removed":"hle","score":0.7346530925999097,"rank":36,"remainingConfigurations":444},{"removed":"ifbench","score":0.7292757179933947,"rank":36,"remainingConfigurations":444},{"removed":"itbench","score":0.7314418211125436,"rank":36,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7308095827103472,"rank":36,"remainingConfigurations":444},{"removed":"math500","score":0.7308754768484674,"rank":36,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7311600733197031,"rank":37,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7370509806580903,"rank":36,"remainingConfigurations":444},{"removed":"omniscience","score":0.7334535030039699,"rank":35,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7295805990953941,"rank":36,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7293879656926361,"rank":36,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7185728204056203,"rank":35,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7277441375141028,"rank":42,"remainingConfigurations":444},{"removed":"deepswe","score":0.6805288744496062,"rank":38,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7309165070878052,"rank":36,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7276042509865049,"rank":36,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7407655099385156,"rank":27,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7312090873278237,"rank":36,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7290240920489998,"rank":36,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7307139626383496,"rank":36,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7282978791430036,"rank":35,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7276113803636756,"rank":36,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7255992917602153,"rank":38,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7295247365635142,"rank":37,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7391530637318869,"rank":34,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7226030220098352,"rank":37,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7286145251254568,"rank":36,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7430922920991921,"rank":33,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7265898247144844,"rank":37,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7266281511276995,"rank":38,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7228761670490806,"rank":38,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7432244690845797,"rank":33,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7328394127514826,"rank":34,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7308761086323665,"rank":35,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7252801719112959,"rank":38,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7271431518052406,"rank":37,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7301400563695507,"rank":36,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7266513255741865,"rank":37,"remainingConfigurations":444}],"sharedOrderConflicts":3},"claude-fable-5-1--effort-low":{"score":0.7291458038537506,"rank":37,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.752309014463461,"rank":29,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7665751157179127,"rank":34,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7150797565513702,"rank":32,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7291217486090021,"rank":37,"remainingConfigurations":444},{"removed":"Scale","score":0.7394251507547388,"rank":35,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7267800837423642,"rank":35,"remainingConfigurations":444},{"removed":"Cognition","score":0.6403426840522733,"rank":40,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7394178044079552,"rank":37,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.72722763249811,"rank":36,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7424031146063039,"rank":34,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7201375723256493,"rank":34,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7295968922315668,"rank":37,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7260417582662958,"rank":37,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7286225588752799,"rank":35,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7291458038537506,"rank":37,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7295216321463766,"rank":37,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7263918266183499,"rank":35,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7289205698690658,"rank":37,"remainingConfigurations":444},{"removed":"briefcase","score":0.7273165866588678,"rank":36,"remainingConfigurations":444},{"removed":"aime","score":0.7265453269789853,"rank":37,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7297628542067672,"rank":37,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7295222054159897,"rank":38,"remainingConfigurations":444},{"removed":"automationbench","score":0.7338104460069843,"rank":34,"remainingConfigurations":444},{"removed":"critpt","score":0.7262813894133116,"rank":38,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7288333543431245,"rank":37,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7276752196433955,"rank":37,"remainingConfigurations":444},{"removed":"gdpval","score":0.7312580832731372,"rank":35,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7288542265523036,"rank":37,"remainingConfigurations":444},{"removed":"gpqa","score":0.7375128388231665,"rank":33,"remainingConfigurations":444},{"removed":"harvey","score":0.7288914276691997,"rank":35,"remainingConfigurations":444},{"removed":"hle","score":0.7328258030157911,"rank":37,"remainingConfigurations":444},{"removed":"ifbench","score":0.7253360962937907,"rank":37,"remainingConfigurations":444},{"removed":"itbench","score":0.7294389429758557,"rank":37,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7284806880348077,"rank":37,"remainingConfigurations":444},{"removed":"math500","score":0.7288182275455908,"rank":37,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7312146989381544,"rank":36,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7352764244423818,"rank":37,"remainingConfigurations":444},{"removed":"omniscience","score":0.7297804171896051,"rank":38,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7283764871307511,"rank":37,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7277534875739541,"rank":37,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7243793363460852,"rank":34,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7565111332051847,"rank":34,"remainingConfigurations":444},{"removed":"deepswe","score":0.7152805922543397,"rank":32,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7291714281013046,"rank":37,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7246010784216149,"rank":37,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6403426840522733,"rank":40,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7277866914960901,"rank":37,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7265240964247798,"rank":37,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7289134516314539,"rank":37,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7262865647685389,"rank":36,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7284353797241397,"rank":35,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7264305058120746,"rank":37,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7311997619596883,"rank":36,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7302611585551299,"rank":38,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7272352183535845,"rank":35,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7280360863008131,"rank":37,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.73239788519401,"rank":37,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.72722763249811,"rank":36,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7275364339709439,"rank":37,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7272386503089768,"rank":36,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7324070226126946,"rank":37,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7291611703846211,"rank":37,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7287499563833023,"rank":36,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7284377589402329,"rank":35,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7287267550774144,"rank":36,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7282281006541135,"rank":37,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7284944785562689,"rank":36,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5-5--effort-high":{"score":0.7259972540368528,"rank":38,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7397472473170795,"rank":37,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7537915419952174,"rank":38,"remainingConfigurations":444},{"removed":"Datacurve","score":0.7169570831463137,"rank":30,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7259295823314865,"rank":38,"remainingConfigurations":444},{"removed":"Scale","score":0.7389567127505453,"rank":36,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7254239425250931,"rank":36,"remainingConfigurations":444},{"removed":"Cognition","score":0.6834143114320678,"rank":36,"remainingConfigurations":444},{"removed":"LiveBench","score":0.738609105828466,"rank":38,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7245300126951308,"rank":38,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7445746328073498,"rank":32,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7085497185962382,"rank":37,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7253851721248242,"rank":38,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7229957291996426,"rank":38,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7250774053871399,"rank":37,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7259972540368528,"rank":38,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7264027978680794,"rank":38,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7219084179952429,"rank":37,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7261241818909686,"rank":38,"remainingConfigurations":444},{"removed":"briefcase","score":0.7198143733674193,"rank":38,"remainingConfigurations":444},{"removed":"aime","score":0.723127334205948,"rank":38,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7266432185353812,"rank":38,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7335712913823985,"rank":35,"remainingConfigurations":444},{"removed":"automationbench","score":0.727597708154652,"rank":37,"remainingConfigurations":444},{"removed":"critpt","score":0.7292352248816796,"rank":37,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7260386367417843,"rank":38,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7274766826201642,"rank":38,"remainingConfigurations":444},{"removed":"gdpval","score":0.7285721304211878,"rank":38,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7256498886564096,"rank":38,"remainingConfigurations":444},{"removed":"gpqa","score":0.7288860050682594,"rank":38,"remainingConfigurations":444},{"removed":"harvey","score":0.726482044096821,"rank":36,"remainingConfigurations":444},{"removed":"hle","score":0.7323554938489507,"rank":38,"remainingConfigurations":444},{"removed":"ifbench","score":0.7220847550108842,"rank":38,"remainingConfigurations":444},{"removed":"itbench","score":0.726656522477802,"rank":38,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7251995037702431,"rank":38,"remainingConfigurations":444},{"removed":"math500","score":0.7256372622564892,"rank":38,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7282579114141404,"rank":38,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7325473375833772,"rank":38,"remainingConfigurations":444},{"removed":"omniscience","score":0.7308987923487469,"rank":37,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7231652418493303,"rank":38,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7207059340856695,"rank":38,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7136766024756872,"rank":38,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7419455534759205,"rank":37,"remainingConfigurations":444},{"removed":"deepswe","score":0.717187781368504,"rank":30,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7260335084539493,"rank":38,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7240602039779335,"rank":38,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6834143114320678,"rank":36,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7252839587642548,"rank":38,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7240672397254208,"rank":38,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7254655691290223,"rank":38,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7232993786573179,"rank":37,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7253294219266674,"rank":37,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7233995011290298,"rank":39,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7282830416709857,"rank":38,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7272252374025908,"rank":39,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.723680432970935,"rank":36,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7248522751832945,"rank":38,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.729198809286307,"rank":38,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7245300126951308,"rank":38,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7252133796666028,"rank":39,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7257302670707785,"rank":37,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7294627459220674,"rank":38,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7283651995581052,"rank":38,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7268572255399625,"rank":37,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7262311878230494,"rank":36,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.726662730160274,"rank":38,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7261765986142977,"rank":38,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7262377866775568,"rank":38,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.8-flash--effort-high":{"score":0.7184744919870086,"rank":39,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7289012150525415,"rank":39,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7462556232918299,"rank":39,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6423532494648447,"rank":40,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7185110741420337,"rank":39,"remainingConfigurations":444},{"removed":"Scale","score":0.727473315361963,"rank":38,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6605903769409334,"rank":43,"remainingConfigurations":444},{"removed":"Cognition","score":0.7463211502439305,"rank":26,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7605128563165894,"rank":33,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7134916108882536,"rank":39,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7286301415845884,"rank":39,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7178629700449571,"rank":36,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7179719542806712,"rank":39,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7153473750818709,"rank":39,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7177941664255424,"rank":38,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7184744919870086,"rank":39,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7175107363547509,"rank":40,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7132049776573991,"rank":39,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7173960685003898,"rank":39,"remainingConfigurations":444},{"removed":"briefcase","score":0.7190223944951354,"rank":39,"remainingConfigurations":444},{"removed":"aime","score":0.7184140366730718,"rank":39,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7188055475165435,"rank":39,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7192282098566739,"rank":39,"remainingConfigurations":444},{"removed":"automationbench","score":0.7162251509982475,"rank":39,"remainingConfigurations":444},{"removed":"critpt","score":0.7195374904454855,"rank":39,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.7186432014945181,"rank":39,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7200478136729127,"rank":39,"remainingConfigurations":444},{"removed":"gdpval","score":0.7184703425884629,"rank":39,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7184825108299598,"rank":39,"remainingConfigurations":444},{"removed":"gpqa","score":0.7108389094323545,"rank":39,"remainingConfigurations":444},{"removed":"harvey","score":0.7209817674145135,"rank":38,"remainingConfigurations":444},{"removed":"hle","score":0.721921462361547,"rank":39,"remainingConfigurations":444},{"removed":"ifbench","score":0.7162672542043446,"rank":39,"remainingConfigurations":444},{"removed":"itbench","score":0.7164645160864941,"rank":39,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7185253482246865,"rank":39,"remainingConfigurations":444},{"removed":"math500","score":0.7185002474036325,"rank":39,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7192604055576498,"rank":39,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7236100142853461,"rank":39,"remainingConfigurations":444},{"removed":"omniscience","score":0.7202706240825921,"rank":39,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7162297431611103,"rank":39,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7187761307941005,"rank":39,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6603017905059385,"rank":43,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7384414006765762,"rank":38,"remainingConfigurations":444},{"removed":"deepswe","score":0.6424832947754088,"rank":40,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7185132063866192,"rank":39,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7177428769253966,"rank":39,"remainingConfigurations":444},{"removed":"frontiercode","score":0.7463211502439305,"rank":26,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7190317277777023,"rank":39,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7162679266427725,"rank":39,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7182115721058047,"rank":39,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7166078925640379,"rank":38,"remainingConfigurations":444},{"removed":"livebench-math","score":0.716914113781161,"rank":39,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7299217790233422,"rank":36,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7123510045043826,"rank":40,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7315436706250797,"rank":37,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7151619501482175,"rank":39,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7158534471383852,"rank":39,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7076442161191907,"rank":40,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7134916108882536,"rank":39,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7312180348840395,"rank":36,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.7136200674617287,"rank":39,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7161171689078275,"rank":40,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7116442539719827,"rank":39,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7250201195450439,"rank":39,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7224156973440551,"rank":39,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7146095177190513,"rank":39,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7207354206635478,"rank":39,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.718814441449345,"rank":39,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.8-flash--effort-medium":{"score":0.7113553355969322,"rank":40,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7407934765383439,"rank":35,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7817533079942511,"rank":30,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6011507106727315,"rank":45,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7114670819841208,"rank":40,"remainingConfigurations":444},{"removed":"Scale","score":0.7218450940469383,"rank":39,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7132021747801925,"rank":38,"remainingConfigurations":444},{"removed":"Cognition","score":0.71966919500032,"rank":33,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7211834654658541,"rank":40,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.7063260329279726,"rank":40,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7219352580823214,"rank":40,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7080812949682338,"rank":38,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7114989369379904,"rank":40,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.7080406726850458,"rank":40,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7113015851535724,"rank":39,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7113553355969322,"rank":40,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7097659440688227,"rank":41,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7065837492406715,"rank":40,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7114212678487974,"rank":40,"remainingConfigurations":444},{"removed":"briefcase","score":0.7150617217993608,"rank":40,"remainingConfigurations":444},{"removed":"aime","score":0.7098183116269051,"rank":40,"remainingConfigurations":444},{"removed":"apex-agents","score":0.7118669226173205,"rank":40,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7097254022769285,"rank":40,"remainingConfigurations":444},{"removed":"automationbench","score":0.7076976940480265,"rank":40,"remainingConfigurations":444},{"removed":"critpt","score":0.7149040763664375,"rank":40,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.711161652975124,"rank":40,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7119758287932715,"rank":40,"remainingConfigurations":444},{"removed":"gdpval","score":0.7133479149952242,"rank":40,"remainingConfigurations":444},{"removed":"gmmlu","score":0.711241249397264,"rank":40,"remainingConfigurations":444},{"removed":"gpqa","score":0.7077713163261912,"rank":40,"remainingConfigurations":444},{"removed":"harvey","score":0.7096865036323988,"rank":40,"remainingConfigurations":444},{"removed":"hle","score":0.7172643651436047,"rank":40,"remainingConfigurations":444},{"removed":"ifbench","score":0.708600499418338,"rank":40,"remainingConfigurations":444},{"removed":"itbench","score":0.7110490387423652,"rank":40,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7113180016137202,"rank":40,"remainingConfigurations":444},{"removed":"math500","score":0.7113001983801602,"rank":40,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7147403891578908,"rank":40,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.7164840045251627,"rank":40,"remainingConfigurations":444},{"removed":"omniscience","score":0.7124704971588693,"rank":40,"remainingConfigurations":444},{"removed":"tau-bench","score":0.7086124110323982,"rank":40,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7113205133152108,"rank":40,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7150176617458177,"rank":36,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7600076147877247,"rank":31,"remainingConfigurations":444},{"removed":"deepswe","score":0.6013125408652455,"rank":45,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7113940642258402,"rank":40,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.697316544471784,"rank":40,"remainingConfigurations":444},{"removed":"frontiercode","score":0.71966919500032,"rank":33,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7117019120225345,"rank":40,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.7089596451060274,"rank":40,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7112902702961753,"rank":40,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.7094790028538845,"rank":39,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7114681932113996,"rank":40,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.710536707573222,"rank":40,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7124967962203312,"rank":39,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7122672457883636,"rank":40,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.7090139661107221,"rank":40,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7105660548016232,"rank":40,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7131244103006046,"rank":39,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.7063260329279726,"rank":40,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7109017137570919,"rank":40,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.707849165237353,"rank":40,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7173877951604707,"rank":39,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7105857403749812,"rank":40,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7112416846400506,"rank":40,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7108155507902593,"rank":40,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7112598026905493,"rank":40,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7106347719650629,"rank":40,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7107826747139457,"rank":40,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4.1-flash--effort-high":{"score":0.7015963097002348,"rank":41,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6978518759419566,"rank":43,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.9043078900652581,"rank":10,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6498230198553157,"rank":39,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.7019451408822442,"rank":41,"remainingConfigurations":444},{"removed":"Scale","score":0.7106351328540862,"rank":41,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.7020836245025303,"rank":39,"remainingConfigurations":444},{"removed":"Cognition","score":0.4422786049500829,"rank":76,"remainingConfigurations":444},{"removed":"LiveBench","score":0.7134878227958749,"rank":41,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6963982362931068,"rank":41,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.7135275023610888,"rank":41,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6988235435533242,"rank":42,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.7013441055290377,"rank":41,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6983339164333008,"rank":41,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.7012727676228679,"rank":40,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.7015963097002348,"rank":41,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7017132357969667,"rank":42,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6979132201288795,"rank":41,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.7016571411823586,"rank":41,"remainingConfigurations":444},{"removed":"briefcase","score":0.7017006506294831,"rank":41,"remainingConfigurations":444},{"removed":"aime","score":0.7004501936048958,"rank":41,"remainingConfigurations":444},{"removed":"apex-agents","score":0.702268824798059,"rank":41,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.7016258437470908,"rank":41,"remainingConfigurations":444},{"removed":"automationbench","score":0.6997195682780574,"rank":41,"remainingConfigurations":444},{"removed":"critpt","score":0.7010383859338498,"rank":41,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.701461116971467,"rank":41,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.7027491430175982,"rank":41,"remainingConfigurations":444},{"removed":"gdpval","score":0.7021238592554114,"rank":41,"remainingConfigurations":444},{"removed":"gmmlu","score":0.7015684126065564,"rank":41,"remainingConfigurations":444},{"removed":"gpqa","score":0.6978307806569143,"rank":41,"remainingConfigurations":444},{"removed":"harvey","score":0.6999810210011287,"rank":41,"remainingConfigurations":444},{"removed":"hle","score":0.707159054649641,"rank":41,"remainingConfigurations":444},{"removed":"ifbench","score":0.6989735702735432,"rank":41,"remainingConfigurations":444},{"removed":"itbench","score":0.7012785397994801,"rank":41,"remainingConfigurations":444},{"removed":"livecodebench","score":0.7018615568019843,"rank":41,"remainingConfigurations":444},{"removed":"math500","score":0.7015772038414947,"rank":41,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.7055209370034046,"rank":41,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.707768200508844,"rank":41,"remainingConfigurations":444},{"removed":"omniscience","score":0.7021115909608205,"rank":41,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6999579622897164,"rank":41,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.7016197368492021,"rank":41,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.7031056554621681,"rank":39,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7296102941438397,"rank":41,"remainingConfigurations":444},{"removed":"deepswe","score":0.649824770496808,"rank":39,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.7016206858616739,"rank":41,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.7369009864852462,"rank":33,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4422786049500829,"rank":76,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.7008734205961202,"rank":41,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6993071268005849,"rank":41,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.7013332760017835,"rank":41,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6996463406816064,"rank":41,"remainingConfigurations":444},{"removed":"livebench-math","score":0.7016803455101591,"rank":41,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.7014594185063391,"rank":41,"remainingConfigurations":444},{"removed":"livebench-language","score":0.7022127157800044,"rank":41,"remainingConfigurations":444},{"removed":"livebench-data","score":0.7031231135970083,"rank":41,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6992728398072586,"rank":41,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.7007735321995288,"rank":41,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.7026489956706947,"rank":41,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6963982362931068,"rank":41,"remainingConfigurations":444},{"removed":"frontiermath","score":0.7010018701933683,"rank":41,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6984540064183397,"rank":41,"remainingConfigurations":444},{"removed":"simpleqa","score":0.7061550957101104,"rank":41,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.7002057990256795,"rank":41,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.7016667232086972,"rank":41,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.7012918917916927,"rank":41,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.7014153818509031,"rank":41,"remainingConfigurations":444},{"removed":"vibe-code","score":0.7010645118833759,"rank":41,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.7008377752980387,"rank":41,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-sol--effort-high":{"score":0.689000896442018,"rank":42,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7162443690149014,"rank":41,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.698493290272134,"rank":46,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6386833661305925,"rank":41,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6889728584604423,"rank":42,"remainingConfigurations":444},{"removed":"Scale","score":0.6973416121034642,"rank":42,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6849503086854373,"rank":41,"remainingConfigurations":444},{"removed":"Cognition","score":0.6816394721960725,"rank":37,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6984756240033728,"rank":43,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6887101646142845,"rank":42,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.700978719047991,"rank":42,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6887719939100015,"rank":43,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6889614174990722,"rank":42,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6872166551543746,"rank":42,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.688852441596994,"rank":41,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.689000896442018,"rank":42,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6882657250228009,"rank":44,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6862814506770585,"rank":43,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6889312144837375,"rank":42,"remainingConfigurations":444},{"removed":"briefcase","score":0.6901623363503339,"rank":42,"remainingConfigurations":444},{"removed":"aime","score":0.6854846689939539,"rank":42,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6892870695830594,"rank":42,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6896953804865126,"rank":42,"remainingConfigurations":444},{"removed":"automationbench","score":0.6885223075203104,"rank":42,"remainingConfigurations":444},{"removed":"critpt","score":0.688614696444192,"rank":42,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6886104845950921,"rank":42,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6863961161578763,"rank":42,"remainingConfigurations":444},{"removed":"gdpval","score":0.6893625093310379,"rank":42,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6888991305727231,"rank":42,"remainingConfigurations":444},{"removed":"gpqa","score":0.6900682492772394,"rank":42,"remainingConfigurations":444},{"removed":"harvey","score":0.688050192707698,"rank":42,"remainingConfigurations":444},{"removed":"hle","score":0.6967057129114176,"rank":42,"remainingConfigurations":444},{"removed":"ifbench","score":0.6917042245510593,"rank":42,"remainingConfigurations":444},{"removed":"itbench","score":0.6886720958499444,"rank":42,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6887041765577853,"rank":42,"remainingConfigurations":444},{"removed":"math500","score":0.6888709755142517,"rank":42,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6913644321615289,"rank":42,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6947822527957817,"rank":42,"remainingConfigurations":444},{"removed":"omniscience","score":0.6883998901133518,"rank":42,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6917590374660615,"rank":42,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6890211684806132,"rank":42,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6851396781449246,"rank":41,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7105662684316663,"rank":44,"remainingConfigurations":444},{"removed":"deepswe","score":0.6385726179514564,"rank":41,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.688989729605718,"rank":42,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6934020642567081,"rank":41,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6816394721960725,"rank":37,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6856669340359712,"rank":42,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.688750499275212,"rank":42,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6891001046735091,"rank":42,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6926643440412418,"rank":42,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6890847058344991,"rank":42,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.688071027516245,"rank":42,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6896934800784847,"rank":42,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6892663277551835,"rank":42,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6874510476455864,"rank":42,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6884947707882092,"rank":42,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6909424958707028,"rank":42,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6887101646142845,"rank":42,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6882864319511265,"rank":42,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6883544670654542,"rank":42,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6932797648569871,"rank":42,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6886332431188346,"rank":42,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6886183592068242,"rank":42,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6890740405697263,"rank":42,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6884620970606335,"rank":42,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6882119567251138,"rank":42,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.68920065339421,"rank":42,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k3--effort-max":{"score":0.6647155773036123,"rank":43,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6574677935451216,"rank":46,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7197936693588245,"rank":44,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5851642363638727,"rank":47,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6646626250725849,"rank":43,"remainingConfigurations":444},{"removed":"Scale","score":0.6758679416296478,"rank":43,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6710382317846632,"rank":42,"remainingConfigurations":444},{"removed":"Cognition","score":0.652529484098789,"rank":39,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6725581971680992,"rank":44,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6578805121720824,"rank":43,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6808239476586125,"rank":44,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6660562639944128,"rank":44,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.664629343836251,"rank":43,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5708026707644934,"rank":60,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6645963571643748,"rank":42,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6647155773036123,"rank":43,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6641659605044921,"rank":46,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5712382789832925,"rank":60,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6666286120768731,"rank":43,"remainingConfigurations":444},{"removed":"briefcase","score":0.6632756584400777,"rank":43,"remainingConfigurations":444},{"removed":"aime","score":0.664325712457232,"rank":43,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6643476846387317,"rank":43,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.664101674969192,"rank":44,"remainingConfigurations":444},{"removed":"automationbench","score":0.6591383894746691,"rank":44,"remainingConfigurations":444},{"removed":"critpt","score":0.6651549010572807,"rank":43,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6658262479927515,"rank":43,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6663697333850718,"rank":43,"remainingConfigurations":444},{"removed":"gdpval","score":0.6644108526897111,"rank":43,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6647508113465755,"rank":43,"remainingConfigurations":444},{"removed":"gpqa","score":0.6652441403155928,"rank":43,"remainingConfigurations":444},{"removed":"harvey","score":0.658095413334785,"rank":44,"remainingConfigurations":444},{"removed":"hle","score":0.6803959364077491,"rank":43,"remainingConfigurations":444},{"removed":"ifbench","score":0.6631500207408648,"rank":43,"remainingConfigurations":444},{"removed":"itbench","score":0.6636848122230784,"rank":43,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6647006656572919,"rank":43,"remainingConfigurations":444},{"removed":"math500","score":0.6647555944505409,"rank":43,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6723219383656053,"rank":43,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6751467850797375,"rank":43,"remainingConfigurations":444},{"removed":"omniscience","score":0.6677682391440625,"rank":43,"remainingConfigurations":444},{"removed":"tau-bench","score":0.662479839806721,"rank":43,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6649107623828743,"rank":43,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6735179623287105,"rank":42,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7117264701568442,"rank":43,"remainingConfigurations":444},{"removed":"deepswe","score":0.588443399103325,"rank":47,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6644876686579103,"rank":43,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6602151561270796,"rank":43,"remainingConfigurations":444},{"removed":"frontiercode","score":0.652529484098789,"rank":39,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6650430614716085,"rank":43,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6620145852902252,"rank":43,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6639014935725314,"rank":43,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6637124682037762,"rank":43,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6646595229464913,"rank":43,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6621191223144198,"rank":43,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6662451409684692,"rank":43,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6666330983232004,"rank":43,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6629547308173475,"rank":44,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6633465606401594,"rank":43,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6670828665403241,"rank":44,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6578805121720824,"rank":43,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6597765968625415,"rank":43,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.664469058509791,"rank":43,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6749134428972097,"rank":43,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6675550973606263,"rank":44,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6739202396820011,"rank":43,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6597299338165717,"rank":44,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.663417055046743,"rank":43,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6596457032248279,"rank":43,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6608174413603695,"rank":44,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-sol--effort-max":{"score":0.6623840158950337,"rank":44,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.675365939119802,"rank":44,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6826141725430951,"rank":48,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6193623631372539,"rank":42,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6623435017334248,"rank":44,"remainingConfigurations":444},{"removed":"Scale","score":0.6726727388322011,"rank":44,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6419166697479,"rank":46,"remainingConfigurations":444},{"removed":"Cognition","score":0.6194733635649948,"rank":43,"remainingConfigurations":444},{"removed":"LiveBench","score":0.702410015270786,"rank":42,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6575326948704557,"rank":44,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6546682112629907,"rank":45,"remainingConfigurations":431},{"removed":"Vals AI","score":0.7041427693885659,"rank":41,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6614736375358542,"rank":44,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6594167218164915,"rank":43,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6608545224329779,"rank":43,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6623840158950337,"rank":44,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.7253895022195777,"rank":39,"remainingConfigurations":444},{"removed":"All provider reports","score":0.7205974835699523,"rank":38,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6627671385686719,"rank":44,"remainingConfigurations":444},{"removed":"briefcase","score":0.6620291572635443,"rank":44,"remainingConfigurations":444},{"removed":"aime","score":0.6609874797338137,"rank":44,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6627957696844634,"rank":44,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6650152173861771,"rank":43,"remainingConfigurations":444},{"removed":"automationbench","score":0.6604920169541454,"rank":43,"remainingConfigurations":444},{"removed":"critpt","score":0.6630507072225998,"rank":44,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6628838030543995,"rank":44,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6625705551951315,"rank":44,"remainingConfigurations":444},{"removed":"gdpval","score":0.663270611700562,"rank":44,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6623276354060522,"rank":44,"remainingConfigurations":444},{"removed":"gpqa","score":0.6617156652669499,"rank":44,"remainingConfigurations":444},{"removed":"harvey","score":0.6619168392404792,"rank":43,"remainingConfigurations":444},{"removed":"hle","score":0.667911140229458,"rank":44,"remainingConfigurations":444},{"removed":"ifbench","score":0.6603685415471139,"rank":44,"remainingConfigurations":444},{"removed":"itbench","score":0.6616096943445652,"rank":44,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6622463672528401,"rank":44,"remainingConfigurations":444},{"removed":"math500","score":0.662352535832676,"rank":44,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.664496482472673,"rank":44,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6696968980161778,"rank":44,"remainingConfigurations":444},{"removed":"omniscience","score":0.6655569068282163,"rank":44,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6608473664306149,"rank":44,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6602525561753554,"rank":44,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6340091592137641,"rank":47,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6846584066253397,"rank":49,"remainingConfigurations":444},{"removed":"deepswe","score":0.6192534919615854,"rank":42,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6623922488454913,"rank":44,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6665627760900061,"rank":42,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6194733635649948,"rank":43,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6622629926736061,"rank":44,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6597952460905193,"rank":44,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6619816309521658,"rank":44,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6605609675205963,"rank":44,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6610931628517304,"rank":44,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6586825527859913,"rank":44,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6613557320946574,"rank":44,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6575341042650996,"rank":44,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6652903046891309,"rank":43,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6625379695110449,"rank":44,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6703092106805402,"rank":43,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6575326948704557,"rank":44,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6549989170393428,"rank":44,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6588900356103331,"rank":44,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6725835166638583,"rank":44,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6744703097325777,"rank":43,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6527689882373008,"rank":44,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6736465830065027,"rank":43,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6550248165654201,"rank":44,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6519106384685021,"rank":44,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6730124227450007,"rank":43,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gpt-6-sol--effort-xhigh":{"score":0.6411878464125557,"rank":45,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6678631772582317,"rank":45,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7019171936604028,"rank":45,"remainingConfigurations":444},{"removed":"Datacurve","score":0.604212940451443,"rank":43,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.641220476474253,"rank":45,"remainingConfigurations":444},{"removed":"Scale","score":0.6554018852211317,"rank":45,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6392876853537632,"rank":47,"remainingConfigurations":444},{"removed":"Cognition","score":0.540838586110766,"rank":58,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6606483581147217,"rank":45,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6397558281860453,"rank":45,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6425351432451282,"rank":47,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6365178393926509,"rank":45,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6408551878241947,"rank":45,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.638924030217288,"rank":45,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6403524113168247,"rank":45,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6411878464125557,"rank":45,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.695585281248197,"rank":43,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6924980018362347,"rank":42,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6415445452726412,"rank":45,"remainingConfigurations":444},{"removed":"briefcase","score":0.64482979798656,"rank":45,"remainingConfigurations":444},{"removed":"aime","score":0.6390567098635999,"rank":45,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6420579102490779,"rank":45,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6434990989315211,"rank":45,"remainingConfigurations":444},{"removed":"automationbench","score":0.6379020445779308,"rank":45,"remainingConfigurations":444},{"removed":"critpt","score":0.6402116594139585,"rank":45,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6412720309144564,"rank":45,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6396543610422994,"rank":45,"remainingConfigurations":444},{"removed":"gdpval","score":0.6447887848007784,"rank":45,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6409163810934456,"rank":45,"remainingConfigurations":444},{"removed":"gpqa","score":0.6373455844510582,"rank":46,"remainingConfigurations":444},{"removed":"harvey","score":0.6397355744464028,"rank":45,"remainingConfigurations":444},{"removed":"hle","score":0.6494069033470167,"rank":45,"remainingConfigurations":444},{"removed":"ifbench","score":0.638012509876159,"rank":45,"remainingConfigurations":444},{"removed":"itbench","score":0.6409966973180884,"rank":46,"remainingConfigurations":444},{"removed":"livecodebench","score":0.640474378814201,"rank":45,"remainingConfigurations":444},{"removed":"math500","score":0.6408212711789921,"rank":45,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6453788969170383,"rank":45,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6508326349997993,"rank":45,"remainingConfigurations":444},{"removed":"omniscience","score":0.643075802446681,"rank":45,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6395983377251652,"rank":45,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.639949600074697,"rank":45,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6390484016789314,"rank":46,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6855597043887421,"rank":48,"remainingConfigurations":444},{"removed":"deepswe","score":0.6039616171146777,"rank":43,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6409637556192468,"rank":45,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6488067869973443,"rank":44,"remainingConfigurations":444},{"removed":"frontiercode","score":0.540838586110766,"rank":58,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6417837355053172,"rank":45,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.638586407009606,"rank":45,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6412636055020825,"rank":45,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6398725271846827,"rank":45,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6412326922803105,"rank":45,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6406368368570229,"rank":45,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6417980101894087,"rank":45,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6398566154199571,"rank":45,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6393891834789381,"rank":45,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6397151207851728,"rank":45,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6456945215385396,"rank":45,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6397558281860453,"rank":45,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6390910947280785,"rank":45,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6373284296877197,"rank":45,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6473619164983163,"rank":45,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6414655797261851,"rank":45,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6401776796561037,"rank":45,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6410917190823491,"rank":45,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6404024663802274,"rank":45,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6396299390403436,"rank":45,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6411034170676823,"rank":45,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5-5--effort-low":{"score":0.6310526155160828,"rank":46,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6312912426955491,"rank":48,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6700916312135975,"rank":52,"remainingConfigurations":444},{"removed":"Datacurve","score":0.6033840232453657,"rank":44,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6311545457384476,"rank":46,"remainingConfigurations":444},{"removed":"Scale","score":0.6432190797231129,"rank":46,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6329909524545558,"rank":48,"remainingConfigurations":444},{"removed":"Cognition","score":0.5675563241627951,"rank":52,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6438531340622898,"rank":47,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6285732693094847,"rank":46,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6471406956030178,"rank":46,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6186449783806557,"rank":48,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6307715166455884,"rank":46,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6271015022471489,"rank":46,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6305047297941747,"rank":46,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6310526155160828,"rank":46,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6320336565652985,"rank":48,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6272993437579014,"rank":48,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6313072647752923,"rank":46,"remainingConfigurations":444},{"removed":"briefcase","score":0.6324154164813134,"rank":47,"remainingConfigurations":444},{"removed":"aime","score":0.6280693908877594,"rank":46,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6320638757470071,"rank":46,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6323867021995925,"rank":46,"remainingConfigurations":444},{"removed":"automationbench","score":0.6341293871902172,"rank":46,"remainingConfigurations":444},{"removed":"critpt","score":0.6316885373875433,"rank":46,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6309800354705043,"rank":46,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6300572457783821,"rank":46,"remainingConfigurations":444},{"removed":"gdpval","score":0.637622479577008,"rank":46,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6308974841837193,"rank":46,"remainingConfigurations":444},{"removed":"gpqa","score":0.6330978428977495,"rank":47,"remainingConfigurations":444},{"removed":"harvey","score":0.63018634253324,"rank":46,"remainingConfigurations":444},{"removed":"hle","score":0.6375806149138749,"rank":46,"remainingConfigurations":444},{"removed":"ifbench","score":0.6274432742517645,"rank":46,"remainingConfigurations":444},{"removed":"itbench","score":0.6311698477777711,"rank":47,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6306601902537289,"rank":46,"remainingConfigurations":444},{"removed":"math500","score":0.630800236410385,"rank":46,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6336713767730994,"rank":46,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6392892677363246,"rank":46,"remainingConfigurations":444},{"removed":"omniscience","score":0.6311268243367824,"rank":47,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6285855323104378,"rank":46,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6248399327082467,"rank":48,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6299262718016326,"rank":48,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6577111059577713,"rank":53,"remainingConfigurations":444},{"removed":"deepswe","score":0.6035732100983201,"rank":44,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6310828727843257,"rank":46,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6252594831209248,"rank":45,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5675563241627951,"rank":52,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6292490791273283,"rank":46,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6283462508703676,"rank":46,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6302003632409808,"rank":46,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6285744752212915,"rank":46,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6303713222945851,"rank":46,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6278653553865626,"rank":46,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6336538954468633,"rank":46,"remainingConfigurations":444},{"removed":"livebench-data","score":0.632137639082096,"rank":46,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6284665018179015,"rank":46,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6296686860045969,"rank":46,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6351411310150518,"rank":46,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6285732693094847,"rank":46,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6297187768329525,"rank":46,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6297179311650364,"rank":46,"remainingConfigurations":444},{"removed":"simpleqa","score":0.636027023137478,"rank":46,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6309525988224838,"rank":46,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6305529144209171,"rank":46,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6302441175054629,"rank":46,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6305670340884494,"rank":46,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6299515907138235,"rank":46,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6303254596967613,"rank":46,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6.1-sol--effort-low":{"score":0.6276461507445094,"rank":47,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6496098587512985,"rank":47,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6273973016644857,"rank":56,"remainingConfigurations":444},{"removed":"Datacurve","score":0.595105845563814,"rank":46,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6276780711103552,"rank":47,"remainingConfigurations":444},{"removed":"Scale","score":0.6407661646938863,"rank":47,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6203608015349728,"rank":50,"remainingConfigurations":444},{"removed":"Cognition","score":0.609234698474472,"rank":44,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6386276419594488,"rank":49,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6264946311509596,"rank":47,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6256584832590962,"rank":52,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6228314311322865,"rank":46,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6275084887184589,"rank":47,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6247984514539247,"rank":47,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6271569698440268,"rank":47,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6276461507445094,"rank":47,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6732473493784782,"rank":45,"remainingConfigurations":444},{"removed":"All provider reports","score":0.670008118987492,"rank":44,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6280475111948866,"rank":47,"remainingConfigurations":444},{"removed":"briefcase","score":0.6339659789565115,"rank":46,"remainingConfigurations":444},{"removed":"aime","score":0.6259100862657747,"rank":47,"remainingConfigurations":444},{"removed":"apex-agents","score":0.628701666885819,"rank":47,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.626250344974867,"rank":48,"remainingConfigurations":444},{"removed":"automationbench","score":0.6274904294588602,"rank":47,"remainingConfigurations":444},{"removed":"critpt","score":0.6269992402078041,"rank":47,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6277256797875884,"rank":47,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.622970178281089,"rank":48,"remainingConfigurations":444},{"removed":"gdpval","score":0.6322845086129392,"rank":47,"remainingConfigurations":444},{"removed":"gmmlu","score":0.627619943915828,"rank":47,"remainingConfigurations":444},{"removed":"gpqa","score":0.6244622239373286,"rank":48,"remainingConfigurations":444},{"removed":"harvey","score":0.6260341128094697,"rank":47,"remainingConfigurations":444},{"removed":"hle","score":0.6351502200264691,"rank":47,"remainingConfigurations":444},{"removed":"ifbench","score":0.6250143701059124,"rank":47,"remainingConfigurations":444},{"removed":"itbench","score":0.6272583094260274,"rank":48,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6273430288878038,"rank":47,"remainingConfigurations":444},{"removed":"math500","score":0.6274652126777842,"rank":47,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6323296955006483,"rank":47,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.635621400697269,"rank":47,"remainingConfigurations":444},{"removed":"omniscience","score":0.6267277652695195,"rank":49,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6266569390018379,"rank":47,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6276186767768072,"rank":46,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6205899393038902,"rank":50,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7099723198405558,"rank":45,"remainingConfigurations":444},{"removed":"deepswe","score":0.5954116691131782,"rank":46,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6276562477898189,"rank":47,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5909301904007692,"rank":51,"remainingConfigurations":444},{"removed":"frontiercode","score":0.609234698474472,"rank":44,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6272406054606536,"rank":47,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6239834384541477,"rank":47,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6273799104138239,"rank":47,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.626182997941872,"rank":47,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6277485393004846,"rank":47,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6261311752327733,"rank":47,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6294139855572957,"rank":47,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6273377618112091,"rank":47,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.624972724907687,"rank":47,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6267037920083353,"rank":47,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6311434391495384,"rank":47,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6264946311509596,"rank":47,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6208419881589649,"rank":48,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6238930529684498,"rank":47,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6345689119013692,"rank":47,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6278095699481343,"rank":47,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.62668762802727,"rank":47,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6275234297987353,"rank":47,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.626885103852235,"rank":47,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6261835750416705,"rank":47,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6275390752850888,"rank":47,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.6--effort-medium":{"score":0.6251983967534925,"rank":48,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6256155776116236,"rank":50,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7369023672890727,"rank":42,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5425832961844482,"rank":56,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6252807210799823,"rank":48,"remainingConfigurations":444},{"removed":"Scale","score":0.6385403038766505,"rank":48,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6255574512419312,"rank":49,"remainingConfigurations":444},{"removed":"Cognition","score":0.5504560862480464,"rank":56,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6404339209187156,"rank":48,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.62041625452841,"rank":48,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.633324105692742,"rank":49,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6195042809716286,"rank":47,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6253024628556197,"rank":48,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6211482188043425,"rank":48,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6250466865526557,"rank":48,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6251983967534925,"rank":48,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6254724306584692,"rank":49,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6214231166655462,"rank":49,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6245497621101449,"rank":48,"remainingConfigurations":444},{"removed":"briefcase","score":0.621720490483184,"rank":48,"remainingConfigurations":444},{"removed":"aime","score":0.6229559758276534,"rank":48,"remainingConfigurations":444},{"removed":"apex-agents","score":0.626113811573772,"rank":48,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6270901486350208,"rank":47,"remainingConfigurations":444},{"removed":"automationbench","score":0.619246300499915,"rank":48,"remainingConfigurations":444},{"removed":"critpt","score":0.6257280302342167,"rank":48,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.625207973786947,"rank":48,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6295232208398088,"rank":47,"remainingConfigurations":444},{"removed":"gdpval","score":0.6219366422043382,"rank":48,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6250545226010388,"rank":48,"remainingConfigurations":444},{"removed":"gpqa","score":0.6222370137451848,"rank":49,"remainingConfigurations":444},{"removed":"harvey","score":0.6217865223359075,"rank":48,"remainingConfigurations":444},{"removed":"hle","score":0.6342776402077465,"rank":48,"remainingConfigurations":444},{"removed":"ifbench","score":0.6218290844359365,"rank":48,"remainingConfigurations":444},{"removed":"itbench","score":0.6251958649638182,"rank":49,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6248983815201061,"rank":48,"remainingConfigurations":444},{"removed":"math500","score":0.624995592108519,"rank":48,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6285058672981522,"rank":48,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6337116659910706,"rank":48,"remainingConfigurations":444},{"removed":"omniscience","score":0.6303728124281831,"rank":48,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6230306667513644,"rank":48,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6264245772099005,"rank":47,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6292150154090811,"rank":49,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7376963329769399,"rank":39,"remainingConfigurations":444},{"removed":"deepswe","score":0.5426328653327478,"rank":56,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6252522590400211,"rank":48,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6130757853513269,"rank":46,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5504560862480464,"rank":56,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6244005761951043,"rank":48,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6224204454193614,"rank":48,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6250633891078735,"rank":48,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6233615664507208,"rank":48,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6247568301551197,"rank":48,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6242943372101369,"rank":48,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6274078686798266,"rank":48,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6257871978775218,"rank":48,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6220874048329171,"rank":48,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6248278687598764,"rank":48,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6271658280038968,"rank":48,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.62041625452841,"rank":48,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6252999780352625,"rank":47,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6204149322071251,"rank":48,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6323045263617356,"rank":48,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6256634160275193,"rank":48,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.624955642724257,"rank":48,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6241057368493005,"rank":48,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6255135315612749,"rank":48,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6240243916502741,"rank":48,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6243108819934206,"rank":48,"remainingConfigurations":444}],"sharedOrderConflicts":2},"grok-4.7--effort-xhigh":{"score":0.6181766255704918,"rank":49,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6130161048098621,"rank":53,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6813511893627792,"rank":49,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5792878299343286,"rank":48,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6181613268379901,"rank":49,"remainingConfigurations":444},{"removed":"Scale","score":0.6303100875339426,"rank":49,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5458403233184254,"rank":64,"remainingConfigurations":444},{"removed":"Cognition","score":0.6266035767675495,"rank":42,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6547873333123831,"rank":46,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6138196418274219,"rank":49,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6301390293724712,"rank":50,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5962726774538116,"rank":50,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6178488625810189,"rank":49,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.614393223998743,"rank":49,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6169865437481601,"rank":49,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6181766255704918,"rank":49,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6184886642590265,"rank":50,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6132084242461623,"rank":50,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6163156285684123,"rank":49,"remainingConfigurations":444},{"removed":"briefcase","score":0.6145314803524001,"rank":49,"remainingConfigurations":444},{"removed":"aime","score":0.6168852011386444,"rank":49,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6187685204389407,"rank":49,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6234873224215222,"rank":49,"remainingConfigurations":444},{"removed":"automationbench","score":0.614081088446845,"rank":49,"remainingConfigurations":444},{"removed":"critpt","score":0.620507428749052,"rank":49,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6181593075780122,"rank":49,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6206253999667463,"rank":49,"remainingConfigurations":444},{"removed":"gdpval","score":0.6155785481143786,"rank":49,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6181972029233312,"rank":49,"remainingConfigurations":444},{"removed":"gpqa","score":0.6138034869780254,"rank":50,"remainingConfigurations":444},{"removed":"harvey","score":0.6056106224966776,"rank":50,"remainingConfigurations":444},{"removed":"hle","score":0.625489769634763,"rank":49,"remainingConfigurations":444},{"removed":"ifbench","score":0.6154820547670805,"rank":49,"remainingConfigurations":444},{"removed":"itbench","score":0.6201174110227213,"rank":50,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6181415281037282,"rank":49,"remainingConfigurations":444},{"removed":"math500","score":0.6181870541202286,"rank":49,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6213610857303487,"rank":49,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6268549206493962,"rank":49,"remainingConfigurations":444},{"removed":"omniscience","score":0.6223193356973441,"rank":50,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6157967325075901,"rank":49,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6225915509627548,"rank":49,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5521290644631781,"rank":63,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6729653788515702,"rank":50,"remainingConfigurations":444},{"removed":"deepswe","score":0.5794311533642427,"rank":48,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6182395806285426,"rank":49,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6082756775593742,"rank":48,"remainingConfigurations":444},{"removed":"frontiercode","score":0.6266035767675495,"rank":42,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6176368650583625,"rank":49,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6156926670710535,"rank":49,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6178230217122648,"rank":49,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6161748003205006,"rank":49,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6124665842385272,"rank":49,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.622371418392557,"rank":49,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6238428434986941,"rank":49,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6198287363249076,"rank":49,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6131643102803871,"rank":49,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6236182997929753,"rank":49,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6120519702602903,"rank":50,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6138196418274219,"rank":49,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6186372535352745,"rank":49,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6138277439981141,"rank":49,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6253752536120377,"rank":50,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6255185711508915,"rank":49,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6176312697301348,"rank":49,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6140119168371013,"rank":49,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6205565683013249,"rank":49,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6131675189209745,"rank":50,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6160889937255928,"rank":49,"remainingConfigurations":444}],"sharedOrderConflicts":1},"grok-4.6--effort-high":{"score":0.6133733610287327,"rank":50,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6130335740254751,"rank":52,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6760654714846063,"rank":51,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5624162975324111,"rank":50,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6133740152791446,"rank":50,"remainingConfigurations":444},{"removed":"Scale","score":0.625916137936798,"rank":50,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.656541264576239,"rank":44,"remainingConfigurations":444},{"removed":"Cognition","score":0.5437583712994306,"rank":57,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6314753717487828,"rank":50,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.609789766913519,"rank":50,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6228162705325059,"rank":54,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5919377404553919,"rank":53,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6132323405377117,"rank":50,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.609051114130754,"rank":50,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6130788669130082,"rank":50,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6133733610287327,"rank":50,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6135144211255882,"rank":51,"remainingConfigurations":444},{"removed":"All provider reports","score":0.608794059802337,"rank":51,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6143066308927951,"rank":50,"remainingConfigurations":444},{"removed":"briefcase","score":0.6099470437257903,"rank":51,"remainingConfigurations":444},{"removed":"aime","score":0.6130169374795071,"rank":50,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6139998871699014,"rank":50,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6178686358036957,"rank":50,"remainingConfigurations":444},{"removed":"automationbench","score":0.6089569245017875,"rank":50,"remainingConfigurations":444},{"removed":"critpt","score":0.6152365559802946,"rank":50,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6115636063266322,"rank":50,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6164513764476501,"rank":50,"remainingConfigurations":444},{"removed":"gdpval","score":0.6110930690781236,"rank":51,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6134102656907601,"rank":50,"remainingConfigurations":444},{"removed":"gpqa","score":0.6037628278917889,"rank":52,"remainingConfigurations":444},{"removed":"harvey","score":0.6038473175355357,"rank":51,"remainingConfigurations":444},{"removed":"hle","score":0.6204784702885747,"rank":50,"remainingConfigurations":444},{"removed":"ifbench","score":0.6108446336490689,"rank":50,"remainingConfigurations":444},{"removed":"itbench","score":0.6135053249324577,"rank":51,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6133739961000388,"rank":50,"remainingConfigurations":444},{"removed":"math500","score":0.6133936326338562,"rank":50,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6171068185913383,"rank":50,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6220266820437534,"rank":50,"remainingConfigurations":444},{"removed":"omniscience","score":0.6163494243410697,"rank":51,"remainingConfigurations":444},{"removed":"tau-bench","score":0.609790764445081,"rank":50,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6171763067367317,"rank":50,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.655642122567823,"rank":44,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6620440455450896,"rank":52,"remainingConfigurations":444},{"removed":"deepswe","score":0.5625926818750405,"rank":50,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6134295428516907,"rank":50,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6066219384600943,"rank":49,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5437583712994306,"rank":57,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6128492374095829,"rank":50,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6107426393034022,"rank":50,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6131522523130039,"rank":50,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6115610532907213,"rank":50,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6122882507578008,"rank":50,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6130616104400356,"rank":50,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6160269979212449,"rank":50,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6145960414104508,"rank":50,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6099077633964841,"rank":50,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6137181444819645,"rank":50,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6140198999964351,"rank":49,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.609789766913519,"rank":50,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6132311127266244,"rank":50,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.6068938154266378,"rank":50,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6274638139390173,"rank":49,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6187752498882295,"rank":50,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.613401327701728,"rank":50,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.607796344931855,"rank":51,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6201351979436809,"rank":50,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6160474463652479,"rank":49,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6081670115225508,"rank":51,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gemini-3.7-flash--effort-medium":{"score":0.6090790624154763,"rank":51,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6259900165895482,"rank":49,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.7291281810095877,"rank":43,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5427513728027801,"rank":55,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6092773925624204,"rank":51,"remainingConfigurations":444},{"removed":"Scale","score":0.6227862027177352,"rank":51,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6082881268719079,"rank":51,"remainingConfigurations":444},{"removed":"Cognition","score":0.5369598142943471,"rank":59,"remainingConfigurations":444},{"removed":"LiveBench","score":0.618647444990977,"rank":51,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.6028850511691182,"rank":51,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6237669341936517,"rank":53,"remainingConfigurations":431},{"removed":"Vals AI","score":0.6032842157524535,"rank":49,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6092721929093781,"rank":51,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6047837320087157,"rank":51,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6091593898267845,"rank":51,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6090790624154763,"rank":51,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6085741362832161,"rank":52,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6046047741750067,"rank":52,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6094371798668308,"rank":51,"remainingConfigurations":444},{"removed":"briefcase","score":0.6079058728690044,"rank":52,"remainingConfigurations":444},{"removed":"aime","score":0.6067708224549097,"rank":51,"remainingConfigurations":444},{"removed":"apex-agents","score":0.609852254895095,"rank":51,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6076762260750396,"rank":51,"remainingConfigurations":444},{"removed":"automationbench","score":0.6069633834873536,"rank":52,"remainingConfigurations":444},{"removed":"critpt","score":0.6141117981323335,"rank":51,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6015323912458915,"rank":52,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6107087335570504,"rank":51,"remainingConfigurations":444},{"removed":"gdpval","score":0.6126296316379515,"rank":50,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6089834278828138,"rank":51,"remainingConfigurations":444},{"removed":"gpqa","score":0.6075011622232243,"rank":51,"remainingConfigurations":444},{"removed":"harvey","score":0.6069536616907248,"rank":49,"remainingConfigurations":444},{"removed":"hle","score":0.6191011255180943,"rank":51,"remainingConfigurations":444},{"removed":"ifbench","score":0.6061439198194185,"rank":51,"remainingConfigurations":444},{"removed":"itbench","score":0.6085760053810195,"rank":52,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6091214125786818,"rank":51,"remainingConfigurations":444},{"removed":"math500","score":0.609026299226881,"rank":51,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6135306504014292,"rank":51,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6153031626882718,"rank":51,"remainingConfigurations":444},{"removed":"omniscience","score":0.6090113692062262,"rank":53,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6088397549352765,"rank":51,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6093960805220193,"rank":51,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6103503840341026,"rank":51,"remainingConfigurations":444},{"removed":"arc-agi","score":0.7042426991178927,"rank":46,"remainingConfigurations":444},{"removed":"deepswe","score":0.5428702646609133,"rank":55,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6091310604761048,"rank":51,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5924891326567794,"rank":50,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5369598142943471,"rank":59,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6085022480271766,"rank":51,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.606249894842786,"rank":51,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.6090200833863365,"rank":51,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6073270324550563,"rank":51,"remainingConfigurations":444},{"removed":"livebench-math","score":0.6092671554914967,"rank":51,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6079926644985952,"rank":51,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6105405846328521,"rank":51,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6101500008241382,"rank":51,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.606190988254982,"rank":51,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6080202478159603,"rank":51,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6113452991630529,"rank":51,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.6028850511691182,"rank":51,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6087950486730506,"rank":51,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.604474293104679,"rank":51,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6166695610334783,"rank":51,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6078922043756124,"rank":51,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6090667857127567,"rank":51,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6082089615030334,"rank":50,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6090568625018674,"rank":51,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6083003505488566,"rank":51,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6081774804231422,"rank":50,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gemini-3.8-flash--effort-low":{"score":0.6038706084766922,"rank":52,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7135082560194704,"rank":42,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.40094620398739855,"rank":98,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5591723496341864,"rank":52,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.6038547255493414,"rank":52,"remainingConfigurations":444},{"removed":"Scale","score":0.6177643160175165,"rank":52,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6015341396940227,"rank":52,"remainingConfigurations":444},{"removed":"Cognition","score":0.5646416662390279,"rank":54,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6160423331848833,"rank":52,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.600425719724278,"rank":52,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6070114453316398,"rank":55,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5954608837960016,"rank":51,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.6036350447120318,"rank":52,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.599669717666859,"rank":52,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.6031987743033822,"rank":52,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.6038706084766922,"rank":52,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6055471892094871,"rank":53,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6004917648781777,"rank":53,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.6034806655095959,"rank":52,"remainingConfigurations":444},{"removed":"briefcase","score":0.6115774853856225,"rank":50,"remainingConfigurations":444},{"removed":"aime","score":0.6015377158501067,"rank":52,"remainingConfigurations":444},{"removed":"apex-agents","score":0.6047202572226951,"rank":52,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.6002416634503025,"rank":52,"remainingConfigurations":444},{"removed":"automationbench","score":0.6081289793369452,"rank":51,"remainingConfigurations":444},{"removed":"critpt","score":0.6131854735198746,"rank":52,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.6028719950598526,"rank":51,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.6034358545125702,"rank":52,"remainingConfigurations":444},{"removed":"gdpval","score":0.6068078750281962,"rank":52,"remainingConfigurations":444},{"removed":"gmmlu","score":0.6035369893416379,"rank":52,"remainingConfigurations":444},{"removed":"gpqa","score":0.5991122341496263,"rank":53,"remainingConfigurations":444},{"removed":"harvey","score":0.6012958272076318,"rank":52,"remainingConfigurations":444},{"removed":"hle","score":0.6131511830283224,"rank":52,"remainingConfigurations":444},{"removed":"ifbench","score":0.5989908435038803,"rank":52,"remainingConfigurations":444},{"removed":"itbench","score":0.6031555355439174,"rank":54,"remainingConfigurations":444},{"removed":"livecodebench","score":0.6030440901284354,"rank":52,"remainingConfigurations":444},{"removed":"math500","score":0.6034866101997461,"rank":52,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6070896588234861,"rank":52,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6081319097433436,"rank":53,"remainingConfigurations":444},{"removed":"omniscience","score":0.6015792402988231,"rank":54,"remainingConfigurations":444},{"removed":"tau-bench","score":0.6009343582977655,"rank":52,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.6037034057798797,"rank":52,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6014817715102084,"rank":52,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6944002237515893,"rank":47,"remainingConfigurations":444},{"removed":"deepswe","score":0.559013732472005,"rank":51,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.6038854490933151,"rank":52,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5526170737439912,"rank":61,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5646416662390279,"rank":54,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.6028308441638728,"rank":52,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.6012672300981011,"rank":52,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.603438647457711,"rank":52,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.6021021118555256,"rank":52,"remainingConfigurations":444},{"removed":"livebench-math","score":0.603771985791528,"rank":52,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.6023463074146121,"rank":52,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6059278271196605,"rank":52,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6038758100422781,"rank":52,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.6007868376917928,"rank":52,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.6029240555389855,"rank":52,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6073881087871804,"rank":52,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.600425719724278,"rank":52,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6023449547123433,"rank":52,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5983531294140004,"rank":52,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6107439354902443,"rank":53,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.6039538202125602,"rank":52,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.6030843906395286,"rank":52,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.6035191282137925,"rank":52,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.6033804041462829,"rank":52,"remainingConfigurations":444},{"removed":"vibe-code","score":0.6024165510256417,"rank":52,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.6035606597166708,"rank":52,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-sol--effort-high":{"score":0.5988679090143599,"rank":53,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6221468403797271,"rank":51,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6891811524671545,"rank":47,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5593236949789474,"rank":51,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5989104241891501,"rank":53,"remainingConfigurations":444},{"removed":"Scale","score":0.614742784566075,"rank":53,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5968807229484346,"rank":53,"remainingConfigurations":444},{"removed":"Cognition","score":0.4791657941266519,"rank":69,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6113222758279926,"rank":53,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.597226488407797,"rank":53,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.603243907242634,"rank":56,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5947632612205528,"rank":52,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5986210379798375,"rank":53,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5958889851234435,"rank":53,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5982841093719204,"rank":53,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5988679090143599,"rank":53,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.6491276084189369,"rank":47,"remainingConfigurations":444},{"removed":"All provider reports","score":0.6456759684546086,"rank":46,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.599354750133637,"rank":53,"remainingConfigurations":444},{"removed":"briefcase","score":0.6033215194488423,"rank":53,"remainingConfigurations":444},{"removed":"aime","score":0.5964844780949157,"rank":53,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5998897037882142,"rank":53,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5990291697420986,"rank":53,"remainingConfigurations":444},{"removed":"automationbench","score":0.5956250569783227,"rank":53,"remainingConfigurations":444},{"removed":"critpt","score":0.5989727396156289,"rank":54,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5989576337698047,"rank":53,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5960893021227256,"rank":54,"remainingConfigurations":444},{"removed":"gdpval","score":0.6031679547457561,"rank":53,"remainingConfigurations":444},{"removed":"gmmlu","score":0.598628320460629,"rank":53,"remainingConfigurations":444},{"removed":"gpqa","score":0.5951516595228723,"rank":54,"remainingConfigurations":444},{"removed":"harvey","score":0.5971841753671834,"rank":53,"remainingConfigurations":444},{"removed":"hle","score":0.6080179021047564,"rank":53,"remainingConfigurations":444},{"removed":"ifbench","score":0.5958167036215923,"rank":53,"remainingConfigurations":444},{"removed":"itbench","score":0.5986130806048583,"rank":55,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5981953905859905,"rank":53,"remainingConfigurations":444},{"removed":"math500","score":0.5985113291804223,"rank":53,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.6036589876280217,"rank":53,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.609641110383514,"rank":52,"remainingConfigurations":444},{"removed":"omniscience","score":0.6002631573661422,"rank":55,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5976193825899173,"rank":53,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5971456310058322,"rank":53,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5972858450335695,"rank":53,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6521902225985727,"rank":54,"remainingConfigurations":444},{"removed":"deepswe","score":0.5586723414313203,"rank":52,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5988747880235762,"rank":53,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.6120777937839393,"rank":47,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4791657941266519,"rank":69,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.59943438070678,"rank":53,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5962638647242442,"rank":53,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5985939330166657,"rank":53,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5975233596347556,"rank":53,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5989158618473968,"rank":53,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5973080974776347,"rank":53,"remainingConfigurations":444},{"removed":"livebench-language","score":0.6006513293193821,"rank":53,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5986005081659506,"rank":54,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5961212488073766,"rank":53,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5977854162382576,"rank":53,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.6026528792600078,"rank":53,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.597226488407797,"rank":53,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5969068915187237,"rank":54,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.594954147480608,"rank":53,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6060910686307314,"rank":55,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5991109924139437,"rank":53,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.597763061406172,"rank":53,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5987619095816842,"rank":53,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5980247523755099,"rank":53,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5972414765576967,"rank":53,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5987750576982026,"rank":53,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.6--effort-xhigh":{"score":0.5932497693964965,"rank":54,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5968465449574495,"rank":55,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6297250832183255,"rank":55,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5181112201848597,"rank":59,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5931950021685192,"rank":54,"remainingConfigurations":444},{"removed":"Scale","score":0.6073277733444106,"rank":54,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5908220889866312,"rank":55,"remainingConfigurations":444},{"removed":"Cognition","score":0.5751078547904346,"rank":47,"remainingConfigurations":444},{"removed":"LiveBench","score":0.600275560061681,"rank":55,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5866826494702401,"rank":55,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6276952992526241,"rank":51,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5830438000094565,"rank":55,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5932403838065045,"rank":54,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5888356861032448,"rank":54,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5934537933240337,"rank":54,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5932497693964965,"rank":54,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5931222054927849,"rank":54,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5889498924110954,"rank":54,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5935487475085334,"rank":55,"remainingConfigurations":444},{"removed":"briefcase","score":0.589748563058179,"rank":55,"remainingConfigurations":444},{"removed":"aime","score":0.5843512069923846,"rank":56,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5941077729174213,"rank":54,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5942910232952746,"rank":55,"remainingConfigurations":444},{"removed":"automationbench","score":0.587524636816788,"rank":55,"remainingConfigurations":444},{"removed":"critpt","score":0.5954713603256216,"rank":55,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5934270419465151,"rank":54,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5983583289509872,"rank":53,"remainingConfigurations":444},{"removed":"gdpval","score":0.590529240711206,"rank":54,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5931554437539641,"rank":54,"remainingConfigurations":444},{"removed":"gpqa","score":0.584173875485976,"rank":56,"remainingConfigurations":444},{"removed":"harvey","score":0.5915183638324554,"rank":54,"remainingConfigurations":444},{"removed":"hle","score":0.601080028030538,"rank":55,"remainingConfigurations":444},{"removed":"ifbench","score":0.5909199073867503,"rank":54,"remainingConfigurations":444},{"removed":"itbench","score":0.5928760321041413,"rank":56,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5929144234693572,"rank":54,"remainingConfigurations":444},{"removed":"math500","score":0.5930984116864233,"rank":54,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5969975487324516,"rank":54,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6023780388679565,"rank":54,"remainingConfigurations":444},{"removed":"omniscience","score":0.598060941945964,"rank":56,"remainingConfigurations":444},{"removed":"tau-bench","score":0.591460851373447,"rank":54,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5937345133821605,"rank":54,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5930383260165989,"rank":54,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6518942374394108,"rank":55,"remainingConfigurations":444},{"removed":"deepswe","score":0.518242728994664,"rank":58,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5932781362835257,"rank":54,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5691111084606354,"rank":58,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5751078547904346,"rank":47,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5926439101976984,"rank":54,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5902703362242834,"rank":54,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5931015544703814,"rank":54,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5917396804158641,"rank":54,"remainingConfigurations":444},{"removed":"livebench-math","score":0.593338670613486,"rank":54,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5914782281358637,"rank":55,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5951639974961734,"rank":54,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5941404578696167,"rank":55,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5900949887697354,"rank":54,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5921119948941802,"rank":54,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.596374490671408,"rank":54,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5866826494702401,"rank":55,"remainingConfigurations":444},{"removed":"frontiermath","score":0.6001201636336733,"rank":53,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5882055889860429,"rank":54,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6077074401972801,"rank":54,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5927903845988699,"rank":54,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.592949646800989,"rank":55,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5925795520775984,"rank":55,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5927996027219338,"rank":54,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5920990147013281,"rank":54,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5929618597607552,"rank":55,"remainingConfigurations":444}],"sharedOrderConflicts":2},"qwen-3.8-max-0902--effort-reasoning":{"score":0.5901081449562977,"rank":55,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6434947749382139,"rank":54,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5515384922051171,"rank":53,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5891270651684927,"rank":55,"remainingConfigurations":444},{"removed":"Scale","score":0.6052561078489767,"rank":55,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5919829589372423,"rank":54,"remainingConfigurations":444},{"removed":"Cognition","score":0.5742993983585648,"rank":48,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5970884683022045,"rank":57,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5914874377876517,"rank":54,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5929066127115408,"rank":57,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5825232557274017,"rank":56,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5898207472286844,"rank":55,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5844644868785966,"rank":56,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5891216820561073,"rank":55,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5901081449562977,"rank":55,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5915287142543989,"rank":55,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5846961310413724,"rank":55,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5863672819998135,"rank":57,"remainingConfigurations":444},{"removed":"briefcase","score":0.5714461486589166,"rank":58,"remainingConfigurations":444},{"removed":"aime","score":0.5895809896993891,"rank":55,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5817661396761818,"rank":59,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5969594013220516,"rank":54,"remainingConfigurations":444},{"removed":"automationbench","score":0.5942134997696341,"rank":54,"remainingConfigurations":444},{"removed":"critpt","score":0.6004210305108036,"rank":53,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5813074277585946,"rank":59,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.590467318084413,"rank":55,"remainingConfigurations":444},{"removed":"gdpval","score":0.5774515182703405,"rank":58,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5900689580022841,"rank":55,"remainingConfigurations":444},{"removed":"gpqa","score":0.5892430651714866,"rank":55,"remainingConfigurations":444},{"removed":"harvey","score":0.5873033715552963,"rank":55,"remainingConfigurations":444},{"removed":"hle","score":0.6024752165404925,"rank":54,"remainingConfigurations":444},{"removed":"ifbench","score":0.5832849755295278,"rank":57,"remainingConfigurations":444},{"removed":"itbench","score":0.6051951276642288,"rank":53,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5890186492067767,"rank":55,"remainingConfigurations":444},{"removed":"math500","score":0.5900333378940587,"rank":55,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5935561745709593,"rank":56,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.6022582015264998,"rank":55,"remainingConfigurations":444},{"removed":"omniscience","score":0.635734929566434,"rank":46,"remainingConfigurations":444},{"removed":"tau-bench","score":0.580531030859659,"rank":57,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5807828119360747,"rank":58,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5820309461598627,"rank":56,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6317569727632583,"rank":56,"remainingConfigurations":444},{"removed":"deepswe","score":0.5517983401066041,"rank":53,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5901579387010454,"rank":55,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5863306760472508,"rank":52,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5742993983585648,"rank":48,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.589222161335475,"rank":55,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5875022710526336,"rank":55,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5896707317344504,"rank":55,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5884161384105513,"rank":55,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5899822564536127,"rank":55,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5885932164724319,"rank":56,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5927325385349487,"rank":55,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5903962011827831,"rank":56,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5868007458503867,"rank":55,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5891815255994725,"rank":55,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5929397690301443,"rank":55,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5914874377876517,"rank":54,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5902611995691023,"rank":56,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.582387438562245,"rank":56,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5975601341819307,"rank":57,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5897466260094424,"rank":55,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5897130363472981,"rank":56,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5892727018632197,"rank":56,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5901070669093532,"rank":55,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5889459857875406,"rank":56,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5895080708109356,"rank":56,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.7-flash--effort-high":{"score":0.5884455537670358,"rank":56,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5929737249438681,"rank":56,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6110451306281907,"rank":58,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5221950341466896,"rank":57,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5885121344373454,"rank":56,"remainingConfigurations":444},{"removed":"Scale","score":0.6022703127297206,"rank":56,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.6511907247109766,"rank":45,"remainingConfigurations":444},{"removed":"Cognition","score":0.5638742086032528,"rank":55,"remainingConfigurations":444},{"removed":"LiveBench","score":0.6045987886911058,"rank":54,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5827198937196545,"rank":58,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5890434151721047,"rank":58,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5874648333005094,"rank":54,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5882682406756626,"rank":56,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5845413658164851,"rank":55,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.587880336561216,"rank":56,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5884455537670358,"rank":56,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5881369831256166,"rank":56,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5835028393872642,"rank":56,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5836352328630444,"rank":58,"remainingConfigurations":444},{"removed":"briefcase","score":0.590039878404885,"rank":54,"remainingConfigurations":444},{"removed":"aime","score":0.5920962548974656,"rank":54,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5889588353411944,"rank":55,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5906483546807245,"rank":56,"remainingConfigurations":444},{"removed":"automationbench","score":0.5855724557177852,"rank":57,"remainingConfigurations":444},{"removed":"critpt","score":0.5905474951605132,"rank":56,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5886135474320434,"rank":55,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5894156367526082,"rank":56,"remainingConfigurations":444},{"removed":"gdpval","score":0.5890265008187392,"rank":55,"remainingConfigurations":444},{"removed":"gmmlu","score":0.588454569539941,"rank":56,"remainingConfigurations":444},{"removed":"gpqa","score":0.581564230780554,"rank":57,"remainingConfigurations":444},{"removed":"harvey","score":0.5852197121799357,"rank":57,"remainingConfigurations":444},{"removed":"hle","score":0.5946159852208491,"rank":57,"remainingConfigurations":444},{"removed":"ifbench","score":0.5863520113961346,"rank":55,"remainingConfigurations":444},{"removed":"itbench","score":0.5877278855091442,"rank":57,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5885118756405386,"rank":56,"remainingConfigurations":444},{"removed":"math500","score":0.5884719598097099,"rank":56,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.58850136074853,"rank":58,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5964458690695741,"rank":56,"remainingConfigurations":444},{"removed":"omniscience","score":0.5903022861932684,"rank":58,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5874289676339792,"rank":55,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5887417032064987,"rank":55,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.6510371395253479,"rank":45,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5999945185118273,"rank":59,"remainingConfigurations":444},{"removed":"deepswe","score":0.5223522077043903,"rank":57,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5885007829132907,"rank":56,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5837012380896939,"rank":53,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5638742086032528,"rank":55,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.588585674394236,"rank":56,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5858193286238293,"rank":56,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5881637042650415,"rank":56,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5867893520965097,"rank":56,"remainingConfigurations":444},{"removed":"livebench-math","score":0.589489603576752,"rank":56,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5936584143473919,"rank":54,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5851655091440019,"rank":58,"remainingConfigurations":444},{"removed":"livebench-data","score":0.6018100552351608,"rank":53,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5810940721904038,"rank":57,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5885329503892184,"rank":56,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5795725438866852,"rank":59,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5827198937196545,"rank":58,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5945807007830345,"rank":55,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5849698514908849,"rank":55,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5869712340324693,"rank":60,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5794051937739297,"rank":58,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5944998812917301,"rank":54,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5934736368682959,"rank":54,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5835210365386374,"rank":58,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5920545334202603,"rank":55,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5933347153942083,"rank":54,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-fable-5--effort-low":{"score":0.5864641046398065,"rank":57,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5696886572525738,"rank":60,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5862778369195659,"rank":63,"remainingConfigurations":444},{"removed":"Datacurve","score":0.568238748204834,"rank":49,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5866757482374442,"rank":57,"remainingConfigurations":444},{"removed":"Scale","score":0.6022141972300328,"rank":57,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5887098359518033,"rank":56,"remainingConfigurations":444},{"removed":"Cognition","score":0.4880058160656821,"rank":67,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5974329935111772,"rank":56,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5828470771910043,"rank":57,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6898036761762975,"rank":43,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5730994185168589,"rank":60,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.585786155295074,"rank":57,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5821858678459336,"rank":57,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5864221515957927,"rank":57,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5864641046398065,"rank":57,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5866687593764718,"rank":57,"remainingConfigurations":444},{"removed":"All provider reports","score":0.581723668462129,"rank":57,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5865444495267869,"rank":56,"remainingConfigurations":444},{"removed":"briefcase","score":0.5845080543943996,"rank":56,"remainingConfigurations":444},{"removed":"aime","score":0.5407929214097054,"rank":64,"remainingConfigurations":444},{"removed":"apex-agents","score":0.587408528306559,"rank":56,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5867367956440194,"rank":57,"remainingConfigurations":444},{"removed":"automationbench","score":0.586403464228651,"rank":56,"remainingConfigurations":444},{"removed":"critpt","score":0.5855681380621128,"rank":58,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5864594074860997,"rank":57,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5882100605501668,"rank":57,"remainingConfigurations":444},{"removed":"gdpval","score":0.5862356419190199,"rank":56,"remainingConfigurations":444},{"removed":"gmmlu","score":0.586491299807902,"rank":57,"remainingConfigurations":444},{"removed":"gpqa","score":0.6616612606653945,"rank":45,"remainingConfigurations":444},{"removed":"harvey","score":0.5856058083039168,"rank":56,"remainingConfigurations":444},{"removed":"hle","score":0.5949490581093337,"rank":56,"remainingConfigurations":444},{"removed":"ifbench","score":0.5843520652517957,"rank":56,"remainingConfigurations":444},{"removed":"itbench","score":0.5863406522580988,"rank":58,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5865884406313931,"rank":57,"remainingConfigurations":444},{"removed":"math500","score":0.5864315408217918,"rank":57,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5899547770750604,"rank":57,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5960345654159066,"rank":58,"remainingConfigurations":444},{"removed":"omniscience","score":0.5868060078807439,"rank":59,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5847947933020813,"rank":56,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5856531774616223,"rank":56,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5883565392927815,"rank":55,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5780620954655548,"rank":63,"remainingConfigurations":444},{"removed":"deepswe","score":0.5684750495128531,"rank":49,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.586509776937251,"rank":57,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5830076024221215,"rank":54,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4880058160656821,"rank":67,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5858950699987108,"rank":57,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5825810685333448,"rank":57,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5858256395527057,"rank":57,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5846901101049289,"rank":57,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5861351320403639,"rank":57,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.58338002003401,"rank":57,"remainingConfigurations":444},{"removed":"livebench-language","score":0.589013300506022,"rank":56,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5876378571318711,"rank":57,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.583558270533602,"rank":56,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5849329006845781,"rank":57,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5905320241288253,"rank":56,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5828470771910043,"rank":57,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5760493218567084,"rank":59,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5740683495680751,"rank":58,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5899917102482526,"rank":59,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5860452497413992,"rank":56,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5860814946035933,"rank":57,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5855415124058466,"rank":57,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5860617557300863,"rank":57,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5854649146186827,"rank":57,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5857269207255132,"rank":57,"remainingConfigurations":444}],"sharedOrderConflicts":0},"muse-spark-1.3--effort-max":{"score":0.5831429105105554,"rank":58,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6454527634858953,"rank":53,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5462786636779674,"rank":54,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5822621541529595,"rank":58,"remainingConfigurations":444},{"removed":"Scale","score":0.5989488446537522,"rank":58,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5847049820375815,"rank":57,"remainingConfigurations":444},{"removed":"Cognition","score":0.5680955866075913,"rank":51,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5937894198649765,"rank":59,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5845234395489065,"rank":56,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5874388635511412,"rank":59,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5739404226723464,"rank":59,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5825340961196049,"rank":58,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5775062945391719,"rank":58,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5826691965231902,"rank":58,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5831429105105554,"rank":58,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5849611345932377,"rank":58,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5783163356753896,"rank":58,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5968191130197406,"rank":54,"remainingConfigurations":444},{"removed":"briefcase","score":0.5657646027001996,"rank":61,"remainingConfigurations":444},{"removed":"aime","score":0.5814216800649978,"rank":58,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5834350724813403,"rank":57,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5759785408719348,"rank":59,"remainingConfigurations":444},{"removed":"automationbench","score":0.5791045295469895,"rank":58,"remainingConfigurations":444},{"removed":"critpt","score":0.5873681835974351,"rank":57,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5842535815140676,"rank":58,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5761123627077486,"rank":59,"remainingConfigurations":444},{"removed":"gdpval","score":0.5700721620430667,"rank":59,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5821904174769567,"rank":58,"remainingConfigurations":444},{"removed":"gpqa","score":0.5787725222390759,"rank":58,"remainingConfigurations":444},{"removed":"harvey","score":0.5517992291209178,"rank":63,"remainingConfigurations":444},{"removed":"hle","score":0.591647662994447,"rank":58,"remainingConfigurations":444},{"removed":"ifbench","score":0.5745021033693319,"rank":59,"remainingConfigurations":444},{"removed":"itbench","score":0.6542678516111137,"rank":45,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5811641579448187,"rank":59,"remainingConfigurations":444},{"removed":"math500","score":0.5825338611165514,"rank":58,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.585801139318152,"rank":59,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5962865185457086,"rank":57,"remainingConfigurations":444},{"removed":"omniscience","score":0.6109006903683103,"rank":52,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5708618530439261,"rank":59,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5781098780016835,"rank":59,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5816836333807834,"rank":57,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6293387929606838,"rank":57,"remainingConfigurations":444},{"removed":"deepswe","score":0.546476409731547,"rank":54,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5831919817390903,"rank":58,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.580266833523516,"rank":56,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5680955866075913,"rank":51,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5823189393549237,"rank":59,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5806723668285163,"rank":58,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5826497006745348,"rank":58,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5814414136186198,"rank":58,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5827819287188309,"rank":58,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.581424315290146,"rank":58,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5858494062923228,"rank":57,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5835337512640552,"rank":59,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5797616210096477,"rank":58,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5821657760860971,"rank":58,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5863574071071816,"rank":57,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5845234395489065,"rank":56,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5835502108633214,"rank":57,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5757694411499957,"rank":57,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5907115625640638,"rank":58,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5830702636856632,"rank":57,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5824417277456294,"rank":58,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5823204559223074,"rank":58,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5829757211208048,"rank":59,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5818849374008935,"rank":58,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5825635769769635,"rank":58,"remainingConfigurations":444}],"sharedOrderConflicts":1},"glm-5.3--effort-max":{"score":0.5818778215067574,"rank":59,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6008239990374871,"rank":54,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6239652932797481,"rank":57,"remainingConfigurations":444},{"removed":"Datacurve","score":0.46653692930199275,"rank":70,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5818842681552182,"rank":59,"remainingConfigurations":444},{"removed":"Scale","score":0.5912540324890249,"rank":59,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5675748188542155,"rank":60,"remainingConfigurations":444},{"removed":"Cognition","score":0.5787697586228306,"rank":46,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5946583049167051,"rank":58,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5760341075943828,"rank":59,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.6395800358889923,"rank":48,"remainingConfigurations":431},{"removed":"Vals AI","score":0.577770878845845,"rank":58,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5808173696711593,"rank":59,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5762294358977417,"rank":59,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.581978010777109,"rank":59,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5818778215067574,"rank":59,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5816853039977535,"rank":59,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5751490455006529,"rank":59,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5825534263244326,"rank":59,"remainingConfigurations":444},{"removed":"briefcase","score":0.578937621009204,"rank":57,"remainingConfigurations":444},{"removed":"aime","score":0.5828514200061584,"rank":57,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5823376398471394,"rank":58,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5806278720767305,"rank":58,"remainingConfigurations":444},{"removed":"automationbench","score":0.5780297494862254,"rank":59,"remainingConfigurations":444},{"removed":"critpt","score":0.5823817802906563,"rank":59,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5866162066223531,"rank":56,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5865330197724127,"rank":58,"remainingConfigurations":444},{"removed":"gdpval","score":0.5792039048252121,"rank":57,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5818747522949268,"rank":59,"remainingConfigurations":444},{"removed":"gpqa","score":0.5762794349671418,"rank":59,"remainingConfigurations":444},{"removed":"harvey","score":0.5828383998325609,"rank":58,"remainingConfigurations":444},{"removed":"hle","score":0.5875184598678344,"rank":59,"remainingConfigurations":444},{"removed":"ifbench","score":0.5798128324394237,"rank":58,"remainingConfigurations":444},{"removed":"itbench","score":0.58129431030165,"rank":59,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5818806330553637,"rank":58,"remainingConfigurations":444},{"removed":"math500","score":0.5819010728279725,"rank":59,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5941158134238417,"rank":55,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5911599274555163,"rank":59,"remainingConfigurations":444},{"removed":"omniscience","score":0.5859684316606053,"rank":60,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5777923240765951,"rank":58,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5812881396242789,"rank":57,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5726832226595148,"rank":60,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6050219515609004,"rank":58,"remainingConfigurations":444},{"removed":"deepswe","score":0.46712654698238937,"rank":70,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5819416230137071,"rank":59,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.575972540322936,"rank":57,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5787697586228306,"rank":46,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5825996014520102,"rank":58,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5786210338528176,"rank":59,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5825592149176556,"rank":59,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5791587181595959,"rank":59,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5814969395665995,"rank":59,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5798224049597653,"rank":59,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5835133520699146,"rank":59,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5848766477077444,"rank":58,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5785760720281526,"rank":59,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5806008225756634,"rank":59,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5842689220821993,"rank":58,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5760341075943828,"rank":59,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5774228979140927,"rank":58,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5735075312041977,"rank":59,"remainingConfigurations":444},{"removed":"simpleqa","score":0.599329712767661,"rank":56,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5785067538357876,"rank":59,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5814614364532041,"rank":59,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5735321531044989,"rank":59,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.58810854268533,"rank":56,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5814590063100206,"rank":59,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5733107722173876,"rank":59,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5--effort-xhigh":{"score":0.5686822678550768,"rank":60,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5776609723835645,"rank":57,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5938422760716643,"rank":62,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5219201029481503,"rank":58,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5686362544271683,"rank":60,"remainingConfigurations":444},{"removed":"Scale","score":0.588550835887845,"rank":60,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5636180612722911,"rank":61,"remainingConfigurations":444},{"removed":"Cognition","score":0.5700739783046005,"rank":50,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5722417501767084,"rank":62,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5489049428587455,"rank":63,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5714098871919943,"rank":60,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5814826642010652,"rank":57,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5686796483642148,"rank":60,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.6451336187860727,"rank":44,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5682766658556563,"rank":60,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5686822678550768,"rank":60,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5669129015357782,"rank":60,"remainingConfigurations":444},{"removed":"All provider reports","score":0.64085513858274,"rank":47,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5676569196399338,"rank":60,"remainingConfigurations":444},{"removed":"briefcase","score":0.5687210626343197,"rank":59,"remainingConfigurations":444},{"removed":"aime","score":0.5683703123470519,"rank":59,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5688208619516657,"rank":60,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5688736720705821,"rank":60,"remainingConfigurations":444},{"removed":"automationbench","score":0.5697888172085631,"rank":60,"remainingConfigurations":444},{"removed":"critpt","score":0.5687536027483037,"rank":60,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5691651093934478,"rank":61,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5697791661712227,"rank":60,"remainingConfigurations":444},{"removed":"gdpval","score":0.5687666495909515,"rank":60,"remainingConfigurations":444},{"removed":"gmmlu","score":0.568727566033111,"rank":60,"remainingConfigurations":444},{"removed":"gpqa","score":0.5582480730673385,"rank":61,"remainingConfigurations":444},{"removed":"harvey","score":0.5689686987825645,"rank":60,"remainingConfigurations":444},{"removed":"hle","score":0.5802107758974862,"rank":60,"remainingConfigurations":444},{"removed":"ifbench","score":0.5677545936770981,"rank":60,"remainingConfigurations":444},{"removed":"itbench","score":0.567855937870056,"rank":60,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5686412237664468,"rank":60,"remainingConfigurations":444},{"removed":"math500","score":0.5687083119884203,"rank":60,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5738987499644258,"rank":60,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5748445451108285,"rank":61,"remainingConfigurations":444},{"removed":"omniscience","score":0.5702224761521568,"rank":61,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5675252936672867,"rank":60,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5687640441237974,"rank":61,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5679535149630724,"rank":61,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5861232195549,"rank":61,"remainingConfigurations":444},{"removed":"deepswe","score":0.516611940574277,"rank":59,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5662968486711994,"rank":61,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5668596473217694,"rank":59,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5700739783046005,"rank":50,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5690781651903777,"rank":60,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5636642535960267,"rank":61,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5624312467045937,"rank":61,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5771766194938808,"rank":60,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5710648907586836,"rank":60,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5639627957247432,"rank":61,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5683072609690714,"rank":61,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5680648591129863,"rank":60,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5686132485375424,"rank":60,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.567086661186682,"rank":60,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.573706529597785,"rank":61,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5489049428587455,"rank":63,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5633975951249537,"rank":60,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5659439291891757,"rank":60,"remainingConfigurations":444},{"removed":"simpleqa","score":0.576915648438454,"rank":62,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5701635531627745,"rank":60,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5653536887069411,"rank":60,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.566082470883517,"rank":60,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5668330679598252,"rank":60,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5686323800301281,"rank":60,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5689665753710796,"rank":60,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-max":{"score":0.5669778610965056,"rank":61,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.573549028686067,"rank":59,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6005121440598656,"rank":60,"remainingConfigurations":444},{"removed":"Datacurve","score":0.48736032375352556,"rank":64,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5669353982500097,"rank":61,"remainingConfigurations":444},{"removed":"Scale","score":0.5812713168008781,"rank":61,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5780773117859052,"rank":58,"remainingConfigurations":444},{"removed":"Cognition","score":0.5653966316989619,"rank":53,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5860578068284829,"rank":60,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5595730598369507,"rank":60,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.570909936959463,"rank":61,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5678791136762189,"rank":61,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5670921267289369,"rank":61,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.566132702642209,"rank":61,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5661324502235952,"rank":61,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5669778610965056,"rank":61,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5660665399777821,"rank":61,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5643624521269328,"rank":61,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5670208982403167,"rank":61,"remainingConfigurations":444},{"removed":"briefcase","score":0.5669585870687299,"rank":60,"remainingConfigurations":444},{"removed":"aime","score":0.5626932138067224,"rank":60,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5667574135310478,"rank":61,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5668638019015589,"rank":62,"remainingConfigurations":444},{"removed":"automationbench","score":0.5649902751992769,"rank":61,"remainingConfigurations":444},{"removed":"critpt","score":0.5670993221097104,"rank":61,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5713071686240153,"rank":60,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5671640938635272,"rank":61,"remainingConfigurations":444},{"removed":"gdpval","score":0.56700611657268,"rank":61,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5670172732460502,"rank":61,"remainingConfigurations":444},{"removed":"gpqa","score":0.5631894937813333,"rank":60,"remainingConfigurations":444},{"removed":"harvey","score":0.5745331729505664,"rank":59,"remainingConfigurations":444},{"removed":"hle","score":0.57428034867305,"rank":61,"remainingConfigurations":444},{"removed":"ifbench","score":0.5666096288973893,"rank":61,"remainingConfigurations":444},{"removed":"itbench","score":0.5644193489175277,"rank":61,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5669223579150856,"rank":61,"remainingConfigurations":444},{"removed":"math500","score":0.5669946240359575,"rank":61,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5714172930358928,"rank":61,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.575918701532734,"rank":60,"remainingConfigurations":444},{"removed":"omniscience","score":0.569272857219124,"rank":62,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5664788355829985,"rank":61,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5650503924550713,"rank":62,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5753642090442417,"rank":59,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5834869149958911,"rank":62,"remainingConfigurations":444},{"removed":"deepswe","score":0.4872619269695376,"rank":65,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5669362625093431,"rank":60,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5814792374739,"rank":55,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5653966316989619,"rank":53,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5670120296747311,"rank":61,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5643287992692301,"rank":60,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5665889807955325,"rank":60,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.56559980619064,"rank":61,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5679047699132744,"rank":61,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.566848949712521,"rank":60,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5704120462069523,"rank":60,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5630251493935373,"rank":61,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5630549360657099,"rank":61,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5594276977239808,"rank":62,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5781473943509665,"rank":60,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5595730598369507,"rank":60,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5580735454131837,"rank":62,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5637470076879564,"rank":61,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5847179074388089,"rank":61,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5663631978944262,"rank":61,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5614857386374142,"rank":61,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5659829346811128,"rank":61,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5659938022156051,"rank":61,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5680342623907025,"rank":61,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5651494948388941,"rank":61,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.7--effort-high":{"score":0.5607762355448137,"rank":62,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.548192022299286,"rank":61,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6788403988175883,"rank":50,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4996725739638283,"rank":62,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5608216850802539,"rank":62,"remainingConfigurations":444},{"removed":"Scale","score":0.5763747973705056,"rank":62,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5624892408249863,"rank":62,"remainingConfigurations":444},{"removed":"Cognition","score":0.48440805608284593,"rank":68,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5733515419886269,"rank":61,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5579658149042805,"rank":61,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5607322933005662,"rank":62,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5462729156734559,"rank":62,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5606350583972396,"rank":62,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5562357403713912,"rank":62,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5603337054000316,"rank":62,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5607762355448137,"rank":62,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5623026882510536,"rank":62,"remainingConfigurations":444},{"removed":"All provider reports","score":0.557230478190282,"rank":62,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5550473896187316,"rank":63,"remainingConfigurations":444},{"removed":"briefcase","score":0.5537776338787586,"rank":63,"remainingConfigurations":444},{"removed":"aime","score":0.558684878677878,"rank":61,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5620778452204248,"rank":62,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5683243360466775,"rank":61,"remainingConfigurations":444},{"removed":"automationbench","score":0.5541049270438423,"rank":63,"remainingConfigurations":444},{"removed":"critpt","score":0.5646386394912285,"rank":62,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5611838311121925,"rank":62,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5615844110645304,"rank":62,"remainingConfigurations":444},{"removed":"gdpval","score":0.5556246070842267,"rank":63,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5607015529621732,"rank":62,"remainingConfigurations":444},{"removed":"gpqa","score":0.5566956451649198,"rank":62,"remainingConfigurations":444},{"removed":"harvey","score":0.5572620714608495,"rank":61,"remainingConfigurations":444},{"removed":"hle","score":0.5732947583447531,"rank":62,"remainingConfigurations":444},{"removed":"ifbench","score":0.5571143548756468,"rank":62,"remainingConfigurations":444},{"removed":"itbench","score":0.5609386741118766,"rank":62,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5604614650107094,"rank":62,"remainingConfigurations":444},{"removed":"math500","score":0.5605914917546596,"rank":62,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5645750439223849,"rank":62,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.571655226200119,"rank":62,"remainingConfigurations":444},{"removed":"omniscience","score":0.5662361684569058,"rank":63,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5587225922408393,"rank":62,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5634808449492172,"rank":63,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5658811449629714,"rank":62,"remainingConfigurations":444},{"removed":"arc-agi","score":0.6642167239767695,"rank":51,"remainingConfigurations":444},{"removed":"deepswe","score":0.4996719660281483,"rank":62,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5608103562901242,"rank":62,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5336948726470401,"rank":64,"remainingConfigurations":444},{"removed":"frontiercode","score":0.48440805608284593,"rank":68,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.559573228653072,"rank":62,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5580151359632557,"rank":62,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5604482017527875,"rank":62,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5590648542879612,"rank":62,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5605606948612173,"rank":62,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5594029947905405,"rank":62,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5630982356079876,"rank":62,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5610951262951241,"rank":62,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5573522582193225,"rank":62,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5600080954657035,"rank":61,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5638323370902747,"rank":62,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5579658149042805,"rank":61,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5609658958861101,"rank":61,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5551911386975639,"rank":62,"remainingConfigurations":444},{"removed":"simpleqa","score":0.569021042576687,"rank":63,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5615175175762396,"rank":62,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5602093319386627,"rank":62,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5597408314791293,"rank":62,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5613642554469483,"rank":62,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5598739721843732,"rank":62,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5596420272722318,"rank":62,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.5--effort-high":{"score":0.5556196744964845,"rank":63,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5744282480153785,"rank":58,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.547978116162364,"rank":67,"remainingConfigurations":444},{"removed":"Datacurve","score":0.49563014531331984,"rank":63,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5556018348360485,"rank":63,"remainingConfigurations":444},{"removed":"Scale","score":0.5730859945277444,"rank":63,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5546136099449218,"rank":63,"remainingConfigurations":444},{"removed":"Cognition","score":0.597627612177595,"rank":45,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5675304517525449,"rank":63,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5519034480845236,"rank":62,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5542951406476007,"rank":63,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5436481067052799,"rank":63,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.555751775730556,"rank":63,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5510496179954841,"rank":63,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5553061072514657,"rank":63,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5556196744964845,"rank":63,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5563182009404052,"rank":63,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5516321434814895,"rank":63,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5561410113401607,"rank":62,"remainingConfigurations":444},{"removed":"briefcase","score":0.5588253340410119,"rank":62,"remainingConfigurations":444},{"removed":"aime","score":0.555261868074778,"rank":62,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5566004605335471,"rank":63,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5530561796079446,"rank":63,"remainingConfigurations":444},{"removed":"automationbench","score":0.5567216586392636,"rank":62,"remainingConfigurations":444},{"removed":"critpt","score":0.5550760545679646,"rank":63,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5556281753402278,"rank":63,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5535928725790626,"rank":64,"remainingConfigurations":444},{"removed":"gdpval","score":0.5569098933802229,"rank":62,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5556434915914791,"rank":63,"remainingConfigurations":444},{"removed":"gpqa","score":0.5524872655636348,"rank":63,"remainingConfigurations":444},{"removed":"harvey","score":0.5545320019077741,"rank":62,"remainingConfigurations":444},{"removed":"hle","score":0.5629914349015569,"rank":63,"remainingConfigurations":444},{"removed":"ifbench","score":0.5568883548459131,"rank":63,"remainingConfigurations":444},{"removed":"itbench","score":0.5551291680247729,"rank":63,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5555293824729429,"rank":63,"remainingConfigurations":444},{"removed":"math500","score":0.5556140311027004,"rank":63,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5607932813987991,"rank":63,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5648024428249679,"rank":63,"remainingConfigurations":444},{"removed":"omniscience","score":0.5542492617493062,"rank":64,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5555697742273096,"rank":63,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5561188022520898,"rank":64,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5492299534604926,"rank":64,"remainingConfigurations":444},{"removed":"arc-agi","score":0.543727784230617,"rank":68,"remainingConfigurations":444},{"removed":"deepswe","score":0.49560750907678025,"rank":63,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5556889142385638,"rank":63,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5531110217318654,"rank":60,"remainingConfigurations":444},{"removed":"frontiercode","score":0.597627612177595,"rank":45,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5555920178504795,"rank":63,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5521981549968957,"rank":63,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5556450123951097,"rank":63,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5544569546578705,"rank":63,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5558885525120558,"rank":63,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5538752479140661,"rank":63,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5575790752753339,"rank":63,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5556534056349255,"rank":63,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5526232158289183,"rank":63,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5545087315796868,"rank":63,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5591546402947039,"rank":63,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5519034480845236,"rank":62,"remainingConfigurations":444},{"removed":"frontiermath","score":0.556321319766804,"rank":63,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5402062279903407,"rank":63,"remainingConfigurations":444},{"removed":"simpleqa","score":0.565287882575705,"rank":65,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.556132652937444,"rank":63,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5559056650896032,"rank":63,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.556215005808776,"rank":63,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5558316227576836,"rank":63,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5551334730618426,"rank":63,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5561992223030726,"rank":63,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2.6-pro--effort-reasoning":{"score":0.5451296693325177,"rank":64,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.600224930354301,"rank":61,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5042585059259709,"rank":61,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5441865912122293,"rank":64,"remainingConfigurations":444},{"removed":"Scale","score":0.5622429113794495,"rank":64,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5446316481047311,"rank":65,"remainingConfigurations":444},{"removed":"Cognition","score":0.524270448241375,"rank":61,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5545734860420615,"rank":64,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5465978727143134,"rank":64,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5489249377125861,"rank":64,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5356215375320943,"rank":64,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5448307600765272,"rank":64,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.539638614896628,"rank":64,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5441890922645075,"rank":64,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5451296693325177,"rank":64,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5471264845037105,"rank":64,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5404725538976483,"rank":64,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5524075167572513,"rank":64,"remainingConfigurations":444},{"removed":"briefcase","score":0.5240759326572909,"rank":66,"remainingConfigurations":444},{"removed":"aime","score":0.5429020856041026,"rank":63,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5471489537873241,"rank":64,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5435890580004026,"rank":64,"remainingConfigurations":444},{"removed":"automationbench","score":0.532856921631783,"rank":64,"remainingConfigurations":444},{"removed":"critpt","score":0.5429571537069813,"rank":64,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5470205629805983,"rank":64,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5550115961491854,"rank":63,"remainingConfigurations":444},{"removed":"gdpval","score":0.5197727668202942,"rank":66,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5443855813831054,"rank":64,"remainingConfigurations":444},{"removed":"gpqa","score":0.5400265513854657,"rank":65,"remainingConfigurations":444},{"removed":"harvey","score":0.5412906006936011,"rank":64,"remainingConfigurations":444},{"removed":"hle","score":0.5491289927095788,"rank":64,"remainingConfigurations":444},{"removed":"ifbench","score":0.5375315882160299,"rank":64,"remainingConfigurations":444},{"removed":"itbench","score":0.5465610753259736,"rank":64,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5427589547347245,"rank":64,"remainingConfigurations":444},{"removed":"math500","score":0.5443309126073202,"rank":64,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5475694686536813,"rank":64,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5587657195744146,"rank":64,"remainingConfigurations":444},{"removed":"omniscience","score":0.5980251547539461,"rank":57,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5411841317966406,"rank":64,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5723467908813489,"rank":60,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5319297463832772,"rank":66,"remainingConfigurations":444},{"removed":"arc-agi","score":0.590043550038215,"rank":60,"remainingConfigurations":444},{"removed":"deepswe","score":0.5044397302302619,"rank":61,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5451891195869808,"rank":64,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.541538146361754,"rank":62,"remainingConfigurations":444},{"removed":"frontiercode","score":0.524270448241375,"rank":61,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5440401570524626,"rank":64,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5424126520813634,"rank":64,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5446412998737059,"rank":64,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5435723218509695,"rank":64,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5449162156935414,"rank":64,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.543259723549057,"rank":64,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5480009209940612,"rank":64,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5454793116866459,"rank":64,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5415472447513057,"rank":64,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5440857335977326,"rank":64,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5484879442672882,"rank":64,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5465978727143134,"rank":64,"remainingConfigurations":444},{"removed":"frontiermath","score":0.545690885764674,"rank":64,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5374762578415321,"rank":64,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5530830228906383,"rank":66,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5447955297039355,"rank":64,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5445766244007032,"rank":64,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5443281660238802,"rank":64,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5450289770746611,"rank":64,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5438404242245579,"rank":64,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5445370438474401,"rank":64,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-8--effort-max":{"score":0.5292818767033628,"rank":65,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5388708620060948,"rank":62,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5650490461509086,"rank":64,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4765481338658595,"rank":66,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.529185641157859,"rank":65,"remainingConfigurations":444},{"removed":"Scale","score":0.5422351203843353,"rank":66,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5701322028677991,"rank":59,"remainingConfigurations":444},{"removed":"Cognition","score":0.5085417211026496,"rank":63,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5398397345493976,"rank":65,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5225213373424734,"rank":66,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5423822481446002,"rank":65,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4987330154647151,"rank":67,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5303261867622872,"rank":65,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5110663944800966,"rank":67,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5285731777760686,"rank":65,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5292818767033628,"rank":65,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5290947073185625,"rank":65,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5120549036841743,"rank":67,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.527970649747544,"rank":65,"remainingConfigurations":444},{"removed":"briefcase","score":0.5277781747893598,"rank":64,"remainingConfigurations":444},{"removed":"aime","score":0.5376013968578256,"rank":65,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5295905337236776,"rank":65,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5291098775699731,"rank":65,"remainingConfigurations":444},{"removed":"automationbench","score":0.5283333336773625,"rank":65,"remainingConfigurations":444},{"removed":"critpt","score":0.5293428014351618,"rank":65,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5302517697629985,"rank":65,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5299597604750402,"rank":65,"remainingConfigurations":444},{"removed":"gdpval","score":0.5282898252448821,"rank":64,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5292989788598129,"rank":65,"remainingConfigurations":444},{"removed":"gpqa","score":0.5409111937871366,"rank":64,"remainingConfigurations":444},{"removed":"harvey","score":0.5283559766989886,"rank":65,"remainingConfigurations":444},{"removed":"hle","score":0.524449100803503,"rank":67,"remainingConfigurations":444},{"removed":"ifbench","score":0.5305347612694382,"rank":65,"remainingConfigurations":444},{"removed":"itbench","score":0.5289624945073921,"rank":65,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5291495834329017,"rank":65,"remainingConfigurations":444},{"removed":"math500","score":0.529289340530825,"rank":65,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5336922863644604,"rank":65,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5495965134569043,"rank":65,"remainingConfigurations":444},{"removed":"omniscience","score":0.5320886286076584,"rank":65,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5279599708973338,"rank":65,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5290323780280727,"rank":65,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5766022144096089,"rank":58,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5549444364922624,"rank":65,"remainingConfigurations":444},{"removed":"deepswe","score":0.4832949969790916,"rank":66,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5290504856154673,"rank":65,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.527490993959758,"rank":65,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5085417211026496,"rank":63,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5290930468223606,"rank":65,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5260730153163751,"rank":65,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5288257162166152,"rank":65,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5278873870338086,"rank":65,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5249721340792528,"rank":66,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5215783003986244,"rank":66,"remainingConfigurations":444},{"removed":"livebench-language","score":0.53414764283366,"rank":65,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5371550796770131,"rank":65,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.529077464768931,"rank":65,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5260550531294418,"rank":65,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5320481793755306,"rank":65,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5225213373424734,"rank":66,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5200400018404363,"rank":66,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5239134908009503,"rank":65,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5375922306129742,"rank":67,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5311302310256006,"rank":65,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5282782842461026,"rank":65,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5267621820704038,"rank":65,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5267289109959838,"rank":65,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5264709800743869,"rank":65,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5285256045915181,"rank":65,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen-3.8-max-0902--effort-xhigh":{"score":0.5256484128461368,"rank":66,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5241016080281579,"rank":64,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5615597641235204,"rank":65,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4869340391989116,"rank":65,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5256397980903317,"rank":66,"remainingConfigurations":444},{"removed":"Scale","score":0.5412359018283069,"rank":67,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5310159283246202,"rank":66,"remainingConfigurations":444},{"removed":"Cognition","score":0.5288514027819426,"rank":60,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5222041262106747,"rank":67,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5226488484794554,"rank":65,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5132784764474735,"rank":65,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5252647708551642,"rank":66,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5206522350423922,"rank":65,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.527776609414868,"rank":66,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.5256484128461368,"rank":66,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5263734401717972,"rank":66,"remainingConfigurations":444},{"removed":"All provider reports","score":0.523184792779315,"rank":65,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5260848515874007,"rank":66,"remainingConfigurations":444},{"removed":"briefcase","score":0.524375634993628,"rank":65,"remainingConfigurations":444},{"removed":"aime","score":0.46713040488475094,"rank":70,"remainingConfigurations":444},{"removed":"apex-agents","score":0.5264763733634438,"rank":66,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.5257690260600238,"rank":66,"remainingConfigurations":444},{"removed":"automationbench","score":0.5246354881442928,"rank":66,"remainingConfigurations":444},{"removed":"critpt","score":0.5260160651428222,"rank":66,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5257065061671752,"rank":66,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.5283772719662685,"rank":66,"remainingConfigurations":444},{"removed":"gdpval","score":0.5244032996798649,"rank":65,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5258807223952858,"rank":66,"remainingConfigurations":444},{"removed":"gpqa","score":0.5183633263664754,"rank":66,"remainingConfigurations":444},{"removed":"harvey","score":0.5227536287740037,"rank":66,"remainingConfigurations":444},{"removed":"hle","score":0.5337741880834571,"rank":65,"remainingConfigurations":444},{"removed":"ifbench","score":0.5251250887685432,"rank":66,"remainingConfigurations":444},{"removed":"itbench","score":0.5247780039712686,"rank":66,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5258955457704773,"rank":66,"remainingConfigurations":444},{"removed":"math500","score":0.5257940560538006,"rank":66,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5300186355404056,"rank":66,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5360754389777642,"rank":66,"remainingConfigurations":444},{"removed":"omniscience","score":0.5254759526052242,"rank":66,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5218054979121365,"rank":66,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.5263765288652121,"rank":66,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5328312233802189,"rank":65,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5516793420215372,"rank":66,"remainingConfigurations":444},{"removed":"deepswe","score":0.48744170316331853,"rank":64,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5256596635968859,"rank":66,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5211546840427367,"rank":66,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5288514027819426,"rank":60,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5251285785328839,"rank":67,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5227692384985236,"rank":66,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.5252159318974038,"rank":66,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5242151030137361,"rank":66,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5258892715989757,"rank":65,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5227419585593734,"rank":65,"remainingConfigurations":444},{"removed":"livebench-language","score":0.528502351641781,"rank":66,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5267855027701444,"rank":66,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5225821405352639,"rank":66,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5242482489879855,"rank":66,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5287100639073666,"rank":66,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5226488484794554,"rank":65,"remainingConfigurations":444},{"removed":"frontiermath","score":0.5416644022060021,"rank":65,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5095499317628767,"rank":66,"remainingConfigurations":444},{"removed":"simpleqa","score":0.6111997984028364,"rank":52,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.524742265275911,"rank":66,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5257917305512,"rank":66,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.524433356656206,"rank":66,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.5258515579926867,"rank":66,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5247369950059658,"rank":66,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.5253032230319331,"rank":66,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen-3.8-max--effort-xhigh":{"score":0.519623962509007,"rank":67,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5248307916454519,"rank":63,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.552216246864231,"rank":66,"remainingConfigurations":444},{"removed":"Datacurve","score":0.5103968485265504,"rank":60,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.5195874530701597,"rank":67,"remainingConfigurations":444},{"removed":"Scale","score":0.5376972115847903,"rank":68,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.5226125133675014,"rank":67,"remainingConfigurations":444},{"removed":"Cognition","score":0.5108950817702161,"rank":62,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5295687541788573,"rank":66,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5104909491398937,"rank":67,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5158463061338522,"rank":66,"remainingConfigurations":431},{"removed":"Vals AI","score":0.5123291349470173,"rank":66,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.5199867910303412,"rank":67,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.5148675019193077,"rank":66,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.521130160294084,"rank":67,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.519623962509007,"rank":67,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5188748852425812,"rank":67,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5160418221493336,"rank":66,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.5197955566281541,"rank":67,"remainingConfigurations":444},{"removed":"briefcase","score":0.5187700838424396,"rank":67,"remainingConfigurations":444},{"removed":"aime","score":0.5058117827539621,"rank":66,"remainingConfigurations":444},{"removed":"apex-agents","score":0.520257632639403,"rank":67,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.519841335634733,"rank":67,"remainingConfigurations":444},{"removed":"automationbench","score":0.5183162918267286,"rank":67,"remainingConfigurations":444},{"removed":"critpt","score":0.519998490810452,"rank":67,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.5195889527419645,"rank":67,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.521676033692219,"rank":67,"remainingConfigurations":444},{"removed":"gdpval","score":0.5188840980172632,"rank":67,"remainingConfigurations":444},{"removed":"gmmlu","score":0.5197226353682675,"rank":67,"remainingConfigurations":444},{"removed":"gpqa","score":0.5146682597198098,"rank":67,"remainingConfigurations":444},{"removed":"harvey","score":0.5171946699929536,"rank":67,"remainingConfigurations":444},{"removed":"hle","score":0.5269143241462748,"rank":66,"remainingConfigurations":444},{"removed":"ifbench","score":0.5187897801286345,"rank":67,"remainingConfigurations":444},{"removed":"itbench","score":0.5189309069527474,"rank":67,"remainingConfigurations":444},{"removed":"livecodebench","score":0.5196730960823432,"rank":67,"remainingConfigurations":444},{"removed":"math500","score":0.5196851895369667,"rank":67,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.5241680213801011,"rank":67,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5294610692732106,"rank":67,"remainingConfigurations":444},{"removed":"omniscience","score":0.5200512346627388,"rank":67,"remainingConfigurations":444},{"removed":"tau-bench","score":0.5174621139445131,"rank":67,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.519978407938798,"rank":67,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.5250355368257639,"rank":67,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5439996759942072,"rank":67,"remainingConfigurations":444},{"removed":"deepswe","score":0.5108391439685979,"rank":60,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.5196992486228298,"rank":67,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5158601176289661,"rank":67,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5108950817702161,"rank":62,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.520206978145303,"rank":68,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.5162046730318267,"rank":67,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.519764912281031,"rank":67,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.5189894247798081,"rank":67,"remainingConfigurations":444},{"removed":"livebench-math","score":0.5201331175599038,"rank":67,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.5176782916668731,"rank":67,"remainingConfigurations":444},{"removed":"livebench-language","score":0.5216256094796831,"rank":67,"remainingConfigurations":444},{"removed":"livebench-data","score":0.5210250974376432,"rank":67,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.5162376735743631,"rank":67,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.5183141772383054,"rank":67,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.5223200548874184,"rank":67,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5104909491398937,"rank":67,"remainingConfigurations":444},{"removed":"frontiermath","score":0.512981179617528,"rank":67,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.5011314808511618,"rank":67,"remainingConfigurations":444},{"removed":"simpleqa","score":0.5653419193076643,"rank":64,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.5182773060640521,"rank":67,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.5199559076342292,"rank":67,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.5184212085142562,"rank":67,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.519663148450927,"rank":67,"remainingConfigurations":444},{"removed":"vibe-code","score":0.5189529188452615,"rank":67,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.519180816112713,"rank":67,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4.1-flash--effort-max":{"score":0.48742540131088097,"rank":68,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.49541563758823043,"rank":65,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5330910070429224,"rank":68,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4387458869017535,"rank":71,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.48723067685578964,"rank":68,"remainingConfigurations":444},{"removed":"Scale","score":0.5054321092652577,"rank":69,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.48471367922158315,"rank":68,"remainingConfigurations":444},{"removed":"Cognition","score":0.45684840046802,"rank":73,"remainingConfigurations":444},{"removed":"LiveBench","score":0.49723180504501646,"rank":69,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4856786075266147,"rank":69,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.49422097655578395,"rank":69,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4781970665851995,"rank":68,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4870858057569529,"rank":68,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4820774046800702,"rank":69,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.486767457926127,"rank":69,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.48742540131088097,"rank":68,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4902506450543414,"rank":69,"remainingConfigurations":444},{"removed":"All provider reports","score":0.48396403235621666,"rank":71,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.49446478584663417,"rank":68,"remainingConfigurations":444},{"removed":"briefcase","score":0.4842954985496251,"rank":70,"remainingConfigurations":444},{"removed":"aime","score":0.4854096946132858,"rank":67,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4885730829793828,"rank":68,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4810701906846407,"rank":70,"remainingConfigurations":444},{"removed":"automationbench","score":0.47201361559287713,"rank":70,"remainingConfigurations":444},{"removed":"critpt","score":0.49104668923381767,"rank":68,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4874533974585507,"rank":68,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.49950254807993577,"rank":68,"remainingConfigurations":444},{"removed":"gdpval","score":0.48270979327551755,"rank":70,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4872912799899389,"rank":68,"remainingConfigurations":444},{"removed":"gpqa","score":0.4831721830665409,"rank":69,"remainingConfigurations":444},{"removed":"harvey","score":0.4876831337659135,"rank":68,"remainingConfigurations":444},{"removed":"hle","score":0.5009655766788002,"rank":68,"remainingConfigurations":444},{"removed":"ifbench","score":0.48274127989422494,"rank":69,"remainingConfigurations":444},{"removed":"itbench","score":0.48139959375528446,"rank":69,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4870487200989399,"rank":68,"remainingConfigurations":444},{"removed":"math500","score":0.4873648937421993,"rank":68,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.49203277891324165,"rank":68,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.5089517684318885,"rank":68,"remainingConfigurations":444},{"removed":"omniscience","score":0.4936620996798445,"rank":69,"remainingConfigurations":444},{"removed":"tau-bench","score":0.48505439753115137,"rank":68,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.48636204903100033,"rank":68,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.48267206587974937,"rank":69,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4964102851939615,"rank":72,"remainingConfigurations":444},{"removed":"deepswe","score":0.4386896593830141,"rank":71,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4874538457726758,"rank":68,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.5363127475230155,"rank":63,"remainingConfigurations":444},{"removed":"frontiercode","score":0.45684840046802,"rank":73,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.48579165535155716,"rank":69,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4846396722603202,"rank":68,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4870492186913524,"rank":69,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.48591333057796926,"rank":69,"remainingConfigurations":444},{"removed":"livebench-math","score":0.48729218338171104,"rank":68,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4856041233614028,"rank":68,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4900314151207629,"rank":68,"remainingConfigurations":444},{"removed":"livebench-data","score":0.48756357983563525,"rank":68,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.48364876756654424,"rank":68,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4863259780326363,"rank":68,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4914298108745825,"rank":68,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4856786075266147,"rank":69,"remainingConfigurations":444},{"removed":"frontiermath","score":0.486594612978493,"rank":68,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.48107976533207203,"rank":68,"remainingConfigurations":444},{"removed":"simpleqa","score":0.49556744739445846,"rank":69,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4873076314030107,"rank":68,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4865869445219803,"rank":68,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4868711508933025,"rank":68,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4869517502026193,"rank":68,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4858574347857198,"rank":68,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.48697694420864607,"rank":68,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-8--effort-xhigh":{"score":0.4861014858027099,"rank":69,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.46897814824310396,"rank":69,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5159817296484009,"rank":70,"remainingConfigurations":444},{"removed":"Datacurve","score":0.47130638540378006,"rank":67,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4861186015670729,"rank":69,"remainingConfigurations":444},{"removed":"Scale","score":0.5495566140986349,"rank":65,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.48368592100907265,"rank":69,"remainingConfigurations":444},{"removed":"Cognition","score":0.4675750523992828,"rank":71,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4958991083702399,"rank":70,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4409476868861655,"rank":77,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.49869761363490067,"rank":68,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4737997323024597,"rank":70,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.48577859860562606,"rank":69,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.48522680772575333,"rank":68,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.48607366536757973,"rank":70,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4861014858027099,"rank":69,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.48596736626336917,"rank":70,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4846918205678085,"rank":70,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.48608099632033275,"rank":69,"remainingConfigurations":444},{"removed":"briefcase","score":0.48486881075196003,"rank":69,"remainingConfigurations":444},{"removed":"aime","score":0.4833663942465378,"rank":68,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4870157953356107,"rank":69,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4866158645360514,"rank":68,"remainingConfigurations":444},{"removed":"automationbench","score":0.4863315616595099,"rank":68,"remainingConfigurations":444},{"removed":"critpt","score":0.4864239837933971,"rank":69,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4860541408433838,"rank":69,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.48774002681114714,"rank":69,"remainingConfigurations":444},{"removed":"gdpval","score":0.48536689216173623,"rank":68,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4862561937415812,"rank":69,"remainingConfigurations":444},{"removed":"gpqa","score":0.48669665518297006,"rank":68,"remainingConfigurations":444},{"removed":"harvey","score":0.4855908840304937,"rank":69,"remainingConfigurations":444},{"removed":"hle","score":0.49473655375119,"rank":69,"remainingConfigurations":444},{"removed":"ifbench","score":0.48495891560616217,"rank":68,"remainingConfigurations":444},{"removed":"itbench","score":0.48597986138508514,"rank":68,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4861537405135716,"rank":69,"remainingConfigurations":444},{"removed":"math500","score":0.48613027899659755,"rank":69,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.49016874870981453,"rank":69,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4962072835893035,"rank":69,"remainingConfigurations":444},{"removed":"omniscience","score":0.48569409655675216,"rank":70,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4848082974365906,"rank":69,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4855874646248388,"rank":69,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.48406899618383276,"rank":68,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5095187747019275,"rank":70,"remainingConfigurations":444},{"removed":"deepswe","score":0.47125168233560055,"rank":67,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4860548940217176,"rank":69,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4837100730683323,"rank":70,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4675750523992828,"rank":71,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.5270627998467613,"rank":66,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4316130991012117,"rank":82,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4940121087751958,"rank":68,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4942454734278199,"rank":68,"remainingConfigurations":444},{"removed":"livebench-math","score":0.48601067361226313,"rank":69,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4830158686287383,"rank":69,"remainingConfigurations":444},{"removed":"livebench-language","score":0.48777714424876334,"rank":69,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4875596150802182,"rank":69,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4834030118933567,"rank":69,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4844070721684899,"rank":69,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.49051879417791633,"rank":69,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4409476868861655,"rank":77,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4857565783087334,"rank":69,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4761762921912091,"rank":70,"remainingConfigurations":444},{"removed":"simpleqa","score":0.49681257572218146,"rank":68,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4852353751724974,"rank":69,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.48572387722546884,"rank":69,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.48521087357502274,"rank":69,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4855206751923848,"rank":69,"remainingConfigurations":444},{"removed":"vibe-code","score":0.485237693159753,"rank":69,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4855436265693657,"rank":69,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-sol--effort-medium":{"score":0.48158702169889733,"rank":70,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.49349962245443835,"rank":66,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.6017485161434182,"rank":59,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4348712706583364,"rank":72,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4816520160772768,"rank":70,"remainingConfigurations":444},{"removed":"Scale","score":0.5004897736810475,"rank":70,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.47809558370465677,"rank":70,"remainingConfigurations":444},{"removed":"Cognition","score":0.36651960745362483,"rank":96,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4939078224223503,"rank":71,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.48129662209616036,"rank":70,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.48724785893694067,"rank":70,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4753665046485324,"rank":69,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.48139728944149507,"rank":70,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4777926686931029,"rank":70,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.48104336476057896,"rank":71,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.48158702169889733,"rank":70,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.5156608877007268,"rank":68,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5112946065545879,"rank":68,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.48223087421584093,"rank":70,"remainingConfigurations":444},{"removed":"briefcase","score":0.4857251847562505,"rank":68,"remainingConfigurations":444},{"removed":"aime","score":0.47890819069135054,"rank":69,"remainingConfigurations":444},{"removed":"apex-agents","score":0.48293523444934033,"rank":70,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.48124162114287206,"rank":69,"remainingConfigurations":444},{"removed":"automationbench","score":0.4775057439507209,"rank":69,"remainingConfigurations":444},{"removed":"critpt","score":0.48126571842250104,"rank":70,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.48176154488056905,"rank":70,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.47827954212424917,"rank":70,"remainingConfigurations":444},{"removed":"gdpval","score":0.48448540494882847,"rank":69,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4815357531899196,"rank":70,"remainingConfigurations":444},{"removed":"gpqa","score":0.4780968889389629,"rank":70,"remainingConfigurations":444},{"removed":"harvey","score":0.4794146651045917,"rank":70,"remainingConfigurations":444},{"removed":"hle","score":0.4936115751816103,"rank":70,"remainingConfigurations":444},{"removed":"ifbench","score":0.4790236336439307,"rank":70,"remainingConfigurations":444},{"removed":"itbench","score":0.481124010826492,"rank":70,"remainingConfigurations":444},{"removed":"livecodebench","score":0.48113086114956943,"rank":70,"remainingConfigurations":444},{"removed":"math500","score":0.48131286824267727,"rank":70,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4878339466875831,"rank":70,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4941016139450871,"rank":70,"remainingConfigurations":444},{"removed":"omniscience","score":0.4814232894282853,"rank":72,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4810079062807751,"rank":70,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4826916180163467,"rank":70,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4799171754342726,"rank":70,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5705590240685708,"rank":64,"remainingConfigurations":444},{"removed":"deepswe","score":0.433796083956375,"rank":72,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.48159935693138967,"rank":70,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.48077007779304903,"rank":71,"remainingConfigurations":444},{"removed":"frontiercode","score":0.36651960745362483,"rank":96,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.480624542537025,"rank":70,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.47810850849419806,"rank":69,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.481328348645716,"rank":70,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4805013791753298,"rank":70,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4817317486460371,"rank":70,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4796402122878806,"rank":70,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4838294051292335,"rank":70,"remainingConfigurations":444},{"removed":"livebench-data","score":0.48126139368723253,"rank":70,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.47818435893187344,"rank":70,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4803868960633302,"rank":70,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4860373867169256,"rank":70,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.48129662209616036,"rank":70,"remainingConfigurations":444},{"removed":"frontiermath","score":0.47945720769309313,"rank":70,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.47781551858107063,"rank":69,"remainingConfigurations":444},{"removed":"simpleqa","score":0.49011929134125953,"rank":70,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.48157828957228843,"rank":70,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.48045375355241116,"rank":70,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.48137091544107663,"rank":70,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4807073811804126,"rank":70,"remainingConfigurations":444},{"removed":"vibe-code","score":0.479843115903529,"rank":70,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.48139671441424436,"rank":70,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-8--effort-high":{"score":0.4633704486064592,"rank":71,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.45720150995495423,"rank":70,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4285899550763262,"rank":92,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4701070612876747,"rank":68,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4635854224521419,"rank":71,"remainingConfigurations":444},{"removed":"Scale","score":0.49036257341512096,"rank":71,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4420022938659843,"rank":79,"remainingConfigurations":444},{"removed":"Cognition","score":0.47832769628715427,"rank":70,"remainingConfigurations":444},{"removed":"LiveBench","score":0.47049607451143044,"rank":73,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4660650443552394,"rank":71,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.48034068380908446,"rank":71,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4487479952058609,"rank":73,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.46333391368363125,"rank":71,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4589378944705098,"rank":71,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.463332032904373,"rank":72,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4633704486064592,"rank":71,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.46368301478200585,"rank":71,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4592228360946687,"rank":72,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.463297301386804,"rank":71,"remainingConfigurations":444},{"removed":"briefcase","score":0.46122952185986077,"rank":71,"remainingConfigurations":444},{"removed":"aime","score":0.4602599610011225,"rank":71,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4644954769938763,"rank":71,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4638152728279274,"rank":72,"remainingConfigurations":444},{"removed":"automationbench","score":0.46299261744632325,"rank":71,"remainingConfigurations":444},{"removed":"critpt","score":0.46363888818363885,"rank":71,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4633161782759269,"rank":71,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4651066844234604,"rank":71,"remainingConfigurations":444},{"removed":"gdpval","score":0.4629206099358836,"rank":71,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4634121492926245,"rank":71,"remainingConfigurations":444},{"removed":"gpqa","score":0.4656611605055829,"rank":71,"remainingConfigurations":444},{"removed":"harvey","score":0.4620230048600866,"rank":71,"remainingConfigurations":444},{"removed":"hle","score":0.4739230683027653,"rank":71,"remainingConfigurations":444},{"removed":"ifbench","score":0.46187807278474063,"rank":72,"remainingConfigurations":444},{"removed":"itbench","score":0.46281545143659547,"rank":71,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4634759377152909,"rank":71,"remainingConfigurations":444},{"removed":"math500","score":0.4633267835420199,"rank":71,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4674276594226505,"rank":72,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.47485002783864944,"rank":72,"remainingConfigurations":444},{"removed":"omniscience","score":0.4634554196426353,"rank":74,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4624463661096591,"rank":72,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.46265106023188735,"rank":72,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4420975726565987,"rank":78,"remainingConfigurations":444},{"removed":"arc-agi","score":0.42610185154535496,"rank":90,"remainingConfigurations":444},{"removed":"deepswe","score":0.4702401921201241,"rank":68,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4634184485357204,"rank":71,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.46021327109884447,"rank":72,"remainingConfigurations":444},{"removed":"frontiercode","score":0.47832769628715427,"rank":70,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4619421161071877,"rank":71,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.463666985888827,"rank":70,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.463823076972626,"rank":71,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4581525068651375,"rank":72,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4631869556922113,"rank":71,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.46014637324730945,"rank":71,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4661413142608007,"rank":72,"remainingConfigurations":444},{"removed":"livebench-data","score":0.46444688020837144,"rank":71,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.45991645805686693,"rank":71,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.46171231159487186,"rank":71,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4680017962370014,"rank":71,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4660650443552394,"rank":71,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4614983162530873,"rank":71,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4617354790560316,"rank":71,"remainingConfigurations":444},{"removed":"simpleqa","score":0.46785179520216263,"rank":72,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.46294471593151715,"rank":71,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4627142131780975,"rank":72,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.46254897719265675,"rank":71,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.46292721942404036,"rank":72,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4625404865477784,"rank":71,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.46247387815630153,"rank":71,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-xhigh":{"score":0.4609407036999364,"rank":72,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4740488502391827,"rank":68,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.44451641685834326,"rank":89,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3830489750164287,"rank":84,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.46096569461842957,"rank":72,"remainingConfigurations":444},{"removed":"Scale","score":0.48023795586270746,"rank":72,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4558055207913645,"rank":72,"remainingConfigurations":444},{"removed":"Cognition","score":0.5047167387565487,"rank":64,"remainingConfigurations":444},{"removed":"LiveBench","score":0.46807964187660506,"rank":74,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.45790947979603863,"rank":72,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.46913680870941676,"rank":73,"remainingConfigurations":431},{"removed":"Vals AI","score":0.46662213620390974,"rank":72,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.46102763891582604,"rank":72,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.45683114496104144,"rank":72,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4609761761336308,"rank":73,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4609407036999364,"rank":72,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4629427055124616,"rank":72,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4589879983471586,"rank":73,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.46154927523795325,"rank":72,"remainingConfigurations":444},{"removed":"briefcase","score":0.46001255285994125,"rank":72,"remainingConfigurations":444},{"removed":"aime","score":0.45832735771739824,"rank":72,"remainingConfigurations":444},{"removed":"apex-agents","score":0.46216018014046406,"rank":72,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.459634623587951,"rank":73,"remainingConfigurations":444},{"removed":"automationbench","score":0.46058804596455444,"rank":72,"remainingConfigurations":444},{"removed":"critpt","score":0.45753004140741105,"rank":72,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4607809047295519,"rank":72,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4565980237991558,"rank":74,"remainingConfigurations":444},{"removed":"gdpval","score":0.4596781898833117,"rank":72,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4609738696744672,"rank":72,"remainingConfigurations":444},{"removed":"gpqa","score":0.45830351996953517,"rank":73,"remainingConfigurations":444},{"removed":"harvey","score":0.4559899038306363,"rank":72,"remainingConfigurations":444},{"removed":"hle","score":0.4707679193053936,"rank":72,"remainingConfigurations":444},{"removed":"ifbench","score":0.4656551704676975,"rank":71,"remainingConfigurations":444},{"removed":"itbench","score":0.4603794974798232,"rank":72,"remainingConfigurations":444},{"removed":"livecodebench","score":0.46075230491375035,"rank":72,"remainingConfigurations":444},{"removed":"math500","score":0.4608409747672017,"rank":72,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4816557987185232,"rank":71,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4723636106279727,"rank":73,"remainingConfigurations":444},{"removed":"omniscience","score":0.4604458166126975,"rank":78,"remainingConfigurations":444},{"removed":"tau-bench","score":0.46548130766932205,"rank":71,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4617438318731748,"rank":73,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.45448217919402345,"rank":73,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4396004229123249,"rank":88,"remainingConfigurations":444},{"removed":"deepswe","score":0.38285473666167835,"rank":84,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.460983475589114,"rank":72,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4600227484039145,"rank":73,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5047167387565487,"rank":64,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4600144444474062,"rank":72,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4576094900872289,"rank":71,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4608887878612453,"rank":72,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4597055793602794,"rank":71,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4613110920758785,"rank":72,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4589590269480046,"rank":73,"remainingConfigurations":444},{"removed":"livebench-language","score":0.46312203139727126,"rank":74,"remainingConfigurations":444},{"removed":"livebench-data","score":0.46088225645374736,"rank":72,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4575259908835963,"rank":72,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.45981239571021226,"rank":72,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4649215027965328,"rank":72,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.45790947979603863,"rank":72,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4594262060234681,"rank":72,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.45455688975164216,"rank":72,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4697431718173934,"rank":71,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.45896746845126857,"rank":72,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4577686373631651,"rank":73,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4586376086072745,"rank":72,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4585018856374359,"rank":73,"remainingConfigurations":444},{"removed":"vibe-code","score":0.45705104861724194,"rank":72,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.45900310578741027,"rank":73,"remainingConfigurations":444}],"sharedOrderConflicts":0},"muse-spark-1.2--effort-xhigh":{"score":0.4564649514260552,"rank":73,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4878621689359373,"rank":67,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.492006724664716,"rank":74,"remainingConfigurations":444},{"removed":"Datacurve","score":0.4160062145439903,"rank":74,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.45633021967271575,"rank":73,"remainingConfigurations":444},{"removed":"Scale","score":0.47390642848403935,"rank":73,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4582315777238397,"rank":71,"remainingConfigurations":444},{"removed":"Cognition","score":0.45415975722892526,"rank":74,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4611033841801775,"rank":76,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.45023376319579494,"rank":74,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4478331555170592,"rank":80,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4457624218982983,"rank":74,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.45636060973169706,"rank":73,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4516413981831633,"rank":73,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.5150217072610046,"rank":68,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4564649514260552,"rank":73,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.45648438284451665,"rank":73,"remainingConfigurations":444},{"removed":"All provider reports","score":0.5104080296082782,"rank":69,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.45654895923649313,"rank":73,"remainingConfigurations":444},{"removed":"briefcase","score":0.45525053851946246,"rank":73,"remainingConfigurations":444},{"removed":"aime","score":0.4573751884029349,"rank":73,"remainingConfigurations":444},{"removed":"apex-agents","score":0.45701046605311374,"rank":73,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.45620666566498524,"rank":76,"remainingConfigurations":444},{"removed":"automationbench","score":0.45737984506066104,"rank":74,"remainingConfigurations":444},{"removed":"critpt","score":0.4571002750006474,"rank":73,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4538459739496372,"rank":74,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4580846975009936,"rank":73,"remainingConfigurations":444},{"removed":"gdpval","score":0.45460599737219604,"rank":73,"remainingConfigurations":444},{"removed":"gmmlu","score":0.45647795596210156,"rank":73,"remainingConfigurations":444},{"removed":"gpqa","score":0.4574006770101214,"rank":74,"remainingConfigurations":444},{"removed":"harvey","score":0.4382991161427852,"rank":80,"remainingConfigurations":444},{"removed":"hle","score":0.46447864917475773,"rank":74,"remainingConfigurations":444},{"removed":"ifbench","score":0.45420386280872055,"rank":74,"remainingConfigurations":444},{"removed":"itbench","score":0.45599412432007796,"rank":73,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4562972732745274,"rank":73,"remainingConfigurations":444},{"removed":"math500","score":0.45648439083815434,"rank":73,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4619212032216819,"rank":73,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.46815725176061695,"rank":74,"remainingConfigurations":444},{"removed":"omniscience","score":0.4610096469879515,"rank":76,"remainingConfigurations":444},{"removed":"tau-bench","score":0.45414636846820994,"rank":74,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.45695974993956695,"rank":74,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4703452477716386,"rank":71,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4806235750935938,"rank":75,"remainingConfigurations":444},{"removed":"deepswe","score":0.4163042689439571,"rank":74,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4566130951231471,"rank":73,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4547363323125238,"rank":74,"remainingConfigurations":444},{"removed":"frontiercode","score":0.45415975722892526,"rank":74,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.45614366877991724,"rank":73,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.45388009160394716,"rank":72,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4562698446289955,"rank":73,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4543510862376392,"rank":73,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4611539168929772,"rank":73,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.45920807957972304,"rank":72,"remainingConfigurations":444},{"removed":"livebench-language","score":0.46312569249536456,"rank":73,"remainingConfigurations":444},{"removed":"livebench-data","score":0.45783014042488196,"rank":73,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.44663532285610913,"rank":75,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4560858170879709,"rank":74,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.45137803504358076,"rank":76,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.45023376319579494,"rank":74,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4589321272009426,"rank":74,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.45252764320077016,"rank":73,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4454539167001728,"rank":81,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.44179965125127146,"rank":79,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4684862727369375,"rank":71,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.45312395275341905,"rank":74,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.46387294582694655,"rank":71,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4544269841586119,"rank":73,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.46113864868856186,"rank":72,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-5-5--effort-xhigh":{"score":0.45399371763893637,"rank":74,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4481359476294957,"rank":72,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.48473572895012523,"rank":78,"remainingConfigurations":444},{"removed":"Datacurve","score":0.41210243275283354,"rank":75,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.45414384248594813,"rank":74,"remainingConfigurations":444},{"removed":"Scale","score":0.4731235579135396,"rank":74,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.45162280172697367,"rank":73,"remainingConfigurations":444},{"removed":"Cognition","score":0.39345137818695625,"rank":86,"remainingConfigurations":444},{"removed":"LiveBench","score":0.5108885285820329,"rank":68,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4492989849425735,"rank":75,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4660319036732618,"rank":74,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4367484526507536,"rank":77,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.45383241200453345,"rank":74,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.44953945283103547,"rank":75,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4528859608893829,"rank":75,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.45399371763893637,"rank":74,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.45502789443611696,"rank":75,"remainingConfigurations":444},{"removed":"All provider reports","score":0.449340565209368,"rank":75,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.4548252097656631,"rank":74,"remainingConfigurations":444},{"removed":"briefcase","score":0.4478946115333426,"rank":75,"remainingConfigurations":444},{"removed":"aime","score":0.45076646791698444,"rank":74,"remainingConfigurations":444},{"removed":"apex-agents","score":0.45519482959101104,"rank":74,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.45675216583048345,"rank":74,"remainingConfigurations":444},{"removed":"automationbench","score":0.4569701396963626,"rank":75,"remainingConfigurations":444},{"removed":"critpt","score":0.45334852745244664,"rank":74,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4543316985178849,"rank":73,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4561393987043288,"rank":75,"remainingConfigurations":444},{"removed":"gdpval","score":0.45273299425700836,"rank":75,"remainingConfigurations":444},{"removed":"gmmlu","score":0.45394058510945756,"rank":74,"remainingConfigurations":444},{"removed":"gpqa","score":0.45547280665514456,"rank":75,"remainingConfigurations":444},{"removed":"harvey","score":0.45251974665255595,"rank":73,"remainingConfigurations":444},{"removed":"hle","score":0.46513516125601445,"rank":73,"remainingConfigurations":444},{"removed":"ifbench","score":0.4511062816584362,"rank":75,"remainingConfigurations":444},{"removed":"itbench","score":0.4542590281698547,"rank":74,"remainingConfigurations":444},{"removed":"livecodebench","score":0.45382768365528664,"rank":74,"remainingConfigurations":444},{"removed":"math500","score":0.4538456606401615,"rank":74,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.458263692583805,"rank":75,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4663865471574396,"rank":75,"remainingConfigurations":444},{"removed":"omniscience","score":0.46053765380217987,"rank":77,"remainingConfigurations":444},{"removed":"tau-bench","score":0.45257925260229875,"rank":75,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4477144666835257,"rank":77,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4514871060287593,"rank":74,"remainingConfigurations":444},{"removed":"arc-agi","score":0.47446710271149145,"rank":79,"remainingConfigurations":444},{"removed":"deepswe","score":0.4122888961443145,"rank":75,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.45405528403649126,"rank":74,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.44914399487161094,"rank":75,"remainingConfigurations":444},{"removed":"frontiercode","score":0.39345137818695625,"rank":86,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.45190388211332017,"rank":74,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4510444262268516,"rank":73,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.45335371480838305,"rank":74,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.45163349623130955,"rank":75,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4481665140557664,"rank":75,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.45267252820559273,"rank":74,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4668564982810975,"rank":71,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4508513726035084,"rank":75,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4468551357635464,"rank":74,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4564465586080852,"rank":73,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4561617419147453,"rank":74,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4492989849425735,"rank":75,"remainingConfigurations":444},{"removed":"frontiermath","score":0.45303151019971805,"rank":75,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.45209577313172367,"rank":74,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4585988788678919,"rank":74,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4533303897785788,"rank":73,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4535531602747424,"rank":74,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4533011610773634,"rank":73,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4534705809198019,"rank":74,"remainingConfigurations":444},{"removed":"vibe-code","score":0.45254196144326125,"rank":74,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.45340682395878623,"rank":74,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.6-sol--effort-medium":{"score":0.45344336908165067,"rank":75,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4562189425166838,"rank":71,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4728941814592104,"rank":82,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3718304513225972,"rank":87,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4533774400819704,"rank":75,"remainingConfigurations":444},{"removed":"Scale","score":0.4720212686804482,"rank":75,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.44654668727039354,"rank":75,"remainingConfigurations":444},{"removed":"Cognition","score":0.43712611437589555,"rank":77,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4643767319668652,"rank":75,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.5036938254396929,"rank":68,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4650092281245506,"rank":75,"remainingConfigurations":431},{"removed":"Vals AI","score":0.44017887671114764,"rank":75,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.45342217513581806,"rank":75,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.44955415460568443,"rank":74,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.45335491676341766,"rank":74,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.45344336908165067,"rank":75,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4553517084634135,"rank":74,"remainingConfigurations":444},{"removed":"All provider reports","score":0.45138997533153263,"rank":74,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.45407766113801157,"rank":75,"remainingConfigurations":444},{"removed":"briefcase","score":0.4534677669619717,"rank":74,"remainingConfigurations":444},{"removed":"aime","score":0.44997973160781246,"rank":75,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4547895261589918,"rank":75,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4546921037013418,"rank":77,"remainingConfigurations":444},{"removed":"automationbench","score":0.4521801776819085,"rank":76,"remainingConfigurations":444},{"removed":"critpt","score":0.4524323577455272,"rank":75,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.45356762297366454,"rank":75,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4502256453105708,"rank":77,"remainingConfigurations":444},{"removed":"gdpval","score":0.45275895886678724,"rank":74,"remainingConfigurations":444},{"removed":"gmmlu","score":0.45361472572367617,"rank":75,"remainingConfigurations":444},{"removed":"gpqa","score":0.45119704706668423,"rank":76,"remainingConfigurations":444},{"removed":"harvey","score":0.45088458224936495,"rank":74,"remainingConfigurations":444},{"removed":"hle","score":0.46394262068994535,"rank":75,"remainingConfigurations":444},{"removed":"ifbench","score":0.45608052366069396,"rank":73,"remainingConfigurations":444},{"removed":"itbench","score":0.4529269151732324,"rank":75,"remainingConfigurations":444},{"removed":"livecodebench","score":0.45330323442247406,"rank":75,"remainingConfigurations":444},{"removed":"math500","score":0.4534038605368014,"rank":75,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.45845121594906574,"rank":74,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.46434318789262935,"rank":76,"remainingConfigurations":444},{"removed":"omniscience","score":0.45148381552393174,"rank":79,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4561101589861587,"rank":73,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4541815054327329,"rank":75,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.44695770792568124,"rank":76,"remainingConfigurations":444},{"removed":"arc-agi","score":0.502170572035615,"rank":71,"remainingConfigurations":444},{"removed":"deepswe","score":0.3716893634441432,"rank":87,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.453462118929934,"rank":75,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4476739503518343,"rank":76,"remainingConfigurations":444},{"removed":"frontiercode","score":0.43712611437589555,"rank":77,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.45043309654091174,"rank":75,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.45017898735283063,"rank":74,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4533432530779211,"rank":75,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4523557691629793,"rank":74,"remainingConfigurations":444},{"removed":"livebench-math","score":0.45367171771523324,"rank":74,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4513487704072725,"rank":75,"remainingConfigurations":444},{"removed":"livebench-language","score":0.45576662319016875,"rank":75,"remainingConfigurations":444},{"removed":"livebench-data","score":0.45347139933899366,"rank":74,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4499492894484094,"rank":73,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4521910304302812,"rank":75,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.45765671381473383,"rank":73,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.5036938254396929,"rank":68,"remainingConfigurations":444},{"removed":"frontiermath","score":0.452113194063316,"rank":76,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4501036578081257,"rank":75,"remainingConfigurations":444},{"removed":"simpleqa","score":0.46263309380975626,"rank":73,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4532742669508614,"rank":74,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4526140328689859,"rank":75,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.45303107983194657,"rank":75,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.45300771607414086,"rank":75,"remainingConfigurations":444},{"removed":"vibe-code","score":0.45208470144750845,"rank":75,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4530020688859526,"rank":75,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen-3.8-max--effort-reasoning":{"score":0.44740837675919964,"rank":76,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5071994684207682,"rank":72,"remainingConfigurations":444},{"removed":"Datacurve","score":0.40464313423019843,"rank":76,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4461903938065837,"rank":76,"remainingConfigurations":444},{"removed":"Scale","score":0.4684724844834551,"rank":76,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4494183535953529,"rank":74,"remainingConfigurations":444},{"removed":"Cognition","score":0.43339158224433577,"rank":78,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4559791157091184,"rank":77,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.45153237227049603,"rank":73,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.45312297479285085,"rank":77,"remainingConfigurations":431},{"removed":"Vals AI","score":0.43998568606406896,"rank":76,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4472610097922321,"rank":76,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4413792847386078,"rank":76,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.44656591256559874,"rank":76,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.44740837675919964,"rank":76,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.44915277727442565,"rank":76,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4422177922334591,"rank":76,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.45000646441001396,"rank":76,"remainingConfigurations":444},{"removed":"briefcase","score":0.4439988609303312,"rank":76,"remainingConfigurations":444},{"removed":"aime","score":0.44589042105131854,"rank":76,"remainingConfigurations":444},{"removed":"apex-agents","score":0.45010516189441824,"rank":76,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4565529716035425,"rank":75,"remainingConfigurations":444},{"removed":"automationbench","score":0.45780385125011697,"rank":73,"remainingConfigurations":444},{"removed":"critpt","score":0.44571075805641325,"rank":76,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.44843955468552094,"rank":76,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.44055863318577737,"rank":80,"remainingConfigurations":444},{"removed":"gdpval","score":0.4326585020459201,"rank":82,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4472725262416762,"rank":76,"remainingConfigurations":444},{"removed":"gpqa","score":0.44090353725610404,"rank":79,"remainingConfigurations":444},{"removed":"harvey","score":0.4441209063163412,"rank":75,"remainingConfigurations":444},{"removed":"hle","score":0.4565831044519842,"rank":76,"remainingConfigurations":444},{"removed":"ifbench","score":0.4415321842203867,"rank":78,"remainingConfigurations":444},{"removed":"itbench","score":0.44741190343696474,"rank":76,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4455717588219441,"rank":76,"remainingConfigurations":444},{"removed":"math500","score":0.44695631234566074,"rank":76,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.45105565648371626,"rank":77,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.45599492172498496,"rank":78,"remainingConfigurations":444},{"removed":"omniscience","score":0.4937432178679597,"rank":68,"remainingConfigurations":444},{"removed":"tau-bench","score":0.42160137208387155,"rank":82,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.45081172127192365,"rank":76,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.45120046588931806,"rank":75,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4963229730471559,"rank":73,"remainingConfigurations":444},{"removed":"deepswe","score":0.4048571231883879,"rank":76,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4474778839608069,"rank":76,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4436883232604627,"rank":77,"remainingConfigurations":444},{"removed":"frontiercode","score":0.43339158224433577,"rank":78,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4460917721739923,"rank":76,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4446562910707643,"rank":75,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4470740807571818,"rank":76,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4462284672831435,"rank":76,"remainingConfigurations":444},{"removed":"livebench-math","score":0.44746596659121635,"rank":76,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.44556732928808757,"rank":76,"remainingConfigurations":444},{"removed":"livebench-language","score":0.45043026982651874,"rank":76,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4475315836336587,"rank":76,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.44352591601134783,"rank":76,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4462664738437736,"rank":76,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4509467923473238,"rank":77,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.45153237227049603,"rank":73,"remainingConfigurations":444},{"removed":"frontiermath","score":0.44821782319939535,"rank":77,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4384703711848003,"rank":77,"remainingConfigurations":444},{"removed":"simpleqa","score":0.45631104841736475,"rank":75,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.44675026548252056,"rank":75,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4469086068706367,"rank":76,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.44660562278099186,"rank":76,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.44731684977374325,"rank":77,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4461555561552984,"rank":76,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4468278333393416,"rank":76,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-pro--effort-max":{"score":0.4439700523849441,"rank":77,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.44361964973678975,"rank":73,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.49059448708642767,"rank":75,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3911714737849825,"rank":81,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.44393883406036405,"rank":77,"remainingConfigurations":444},{"removed":"Scale","score":0.46082150302364777,"rank":80,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4435533298764393,"rank":77,"remainingConfigurations":444},{"removed":"Cognition","score":0.4327892951124635,"rank":79,"remainingConfigurations":444},{"removed":"LiveBench","score":0.45080306879917975,"rank":79,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4398908250887051,"rank":79,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.41974765383243606,"rank":84,"remainingConfigurations":431},{"removed":"Vals AI","score":0.46897235462870807,"rank":71,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.44379888478885937,"rank":77,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4384872245689686,"rank":78,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.44367124301866906,"rank":77,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4439700523849441,"rank":77,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.44526239362374914,"rank":77,"remainingConfigurations":444},{"removed":"All provider reports","score":0.43936940149120235,"rank":77,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.4445797701205197,"rank":78,"remainingConfigurations":444},{"removed":"briefcase","score":0.4438712812245438,"rank":77,"remainingConfigurations":444},{"removed":"aime","score":0.4394768186432911,"rank":79,"remainingConfigurations":444},{"removed":"apex-agents","score":0.44489887589627203,"rank":78,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.44437595037180966,"rank":78,"remainingConfigurations":444},{"removed":"automationbench","score":0.44066160138666893,"rank":81,"remainingConfigurations":444},{"removed":"critpt","score":0.443887345141643,"rank":77,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4369943555753845,"rank":82,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4515474635383326,"rank":76,"remainingConfigurations":444},{"removed":"gdpval","score":0.44262789485447024,"rank":77,"remainingConfigurations":444},{"removed":"gmmlu","score":0.44401501744190924,"rank":77,"remainingConfigurations":444},{"removed":"gpqa","score":0.4442009651903589,"rank":77,"remainingConfigurations":444},{"removed":"harvey","score":0.43331199847184343,"rank":82,"remainingConfigurations":444},{"removed":"hle","score":0.4534962998909174,"rank":77,"remainingConfigurations":444},{"removed":"ifbench","score":0.4418443763139322,"rank":77,"remainingConfigurations":444},{"removed":"itbench","score":0.44335731690244146,"rank":77,"remainingConfigurations":444},{"removed":"livecodebench","score":0.44402217649963077,"rank":77,"remainingConfigurations":444},{"removed":"math500","score":0.4440508278311637,"rank":77,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.454232241420782,"rank":76,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4558659771220102,"rank":79,"remainingConfigurations":444},{"removed":"omniscience","score":0.44585995581637583,"rank":82,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4408581257934141,"rank":78,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4465109587139983,"rank":78,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.45775323313780286,"rank":72,"remainingConfigurations":444},{"removed":"arc-agi","score":0.48002947865405643,"rank":76,"remainingConfigurations":444},{"removed":"deepswe","score":0.39144131880347927,"rank":80,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.44403510477824476,"rank":77,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4394305625382382,"rank":81,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4327892951124635,"rank":79,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.44269669688615004,"rank":77,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4412775992590467,"rank":76,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4436654135808811,"rank":77,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.44227842561488506,"rank":77,"remainingConfigurations":444},{"removed":"livebench-math","score":0.44420455617853677,"rank":77,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.44200660395907193,"rank":77,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4464243277427576,"rank":79,"remainingConfigurations":444},{"removed":"livebench-data","score":0.44487393648456136,"rank":77,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4402480931356891,"rank":77,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4429514694789836,"rank":77,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4470296802631886,"rank":79,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4398908250887051,"rank":79,"remainingConfigurations":444},{"removed":"frontiermath","score":0.45941468014012465,"rank":73,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4252770143649853,"rank":82,"remainingConfigurations":444},{"removed":"simpleqa","score":0.44674251066872633,"rank":80,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4466827179405169,"rank":76,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4387263772265309,"rank":81,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.43575335235665524,"rank":82,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4513630843097582,"rank":76,"remainingConfigurations":444},{"removed":"vibe-code","score":0.43263446092803415,"rank":82,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.44627014878988275,"rank":77,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-5--effort-low":{"score":0.4435690955310805,"rank":78,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.43661440520521516,"rank":75,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4740536449254433,"rank":81,"remainingConfigurations":444},{"removed":"Datacurve","score":0.383724467610896,"rank":83,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.44340199079478454,"rank":78,"remainingConfigurations":444},{"removed":"Scale","score":0.46397632146510365,"rank":79,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.44225074641874645,"rank":78,"remainingConfigurations":444},{"removed":"Cognition","score":0.41803067216260104,"rank":81,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4497422221163419,"rank":80,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.43989366511804523,"rank":78,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.5077733366820592,"rank":67,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4260172775011828,"rank":81,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4434196142829792,"rank":78,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.43863850094952017,"rank":77,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.44351933615516853,"rank":78,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4435690955310805,"rank":78,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4440797459749764,"rank":79,"remainingConfigurations":444},{"removed":"All provider reports","score":0.43901251550175074,"rank":78,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.44405610155268693,"rank":79,"remainingConfigurations":444},{"removed":"briefcase","score":0.4429361084638422,"rank":79,"remainingConfigurations":444},{"removed":"aime","score":0.4433720531897205,"rank":77,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4449785333395792,"rank":77,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4408821648049372,"rank":79,"remainingConfigurations":444},{"removed":"automationbench","score":0.44333543296732153,"rank":78,"remainingConfigurations":444},{"removed":"critpt","score":0.4422952907945524,"rank":78,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4436494939735929,"rank":77,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.44594600359207504,"rank":78,"remainingConfigurations":444},{"removed":"gdpval","score":0.4449855529581728,"rank":76,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4437284141347552,"rank":78,"remainingConfigurations":444},{"removed":"gpqa","score":0.46352832606522626,"rank":72,"remainingConfigurations":444},{"removed":"harvey","score":0.44171284199156097,"rank":76,"remainingConfigurations":444},{"removed":"hle","score":0.45325500742023356,"rank":78,"remainingConfigurations":444},{"removed":"ifbench","score":0.44146639585187003,"rank":79,"remainingConfigurations":444},{"removed":"itbench","score":0.44325761787352436,"rank":78,"remainingConfigurations":444},{"removed":"livecodebench","score":0.44326780328130266,"rank":78,"remainingConfigurations":444},{"removed":"math500","score":0.4434909511113652,"rank":78,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.44764001541899007,"rank":78,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.45602342169800386,"rank":77,"remainingConfigurations":444},{"removed":"omniscience","score":0.44284546930072993,"rank":83,"remainingConfigurations":444},{"removed":"tau-bench","score":0.44253704292303614,"rank":76,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.44326912804556445,"rank":79,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.44236840753406553,"rank":77,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4677890397797439,"rank":82,"remainingConfigurations":444},{"removed":"deepswe","score":0.38399778670305,"rank":83,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.44362835940254297,"rank":78,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.44112003390388527,"rank":78,"remainingConfigurations":444},{"removed":"frontiercode","score":0.41803067216260104,"rank":81,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.442312952830689,"rank":79,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4401377774694903,"rank":78,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4430797549596927,"rank":78,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4422075456508073,"rank":78,"remainingConfigurations":444},{"removed":"livebench-math","score":0.443488442592096,"rank":78,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4400540671426341,"rank":79,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4467392341376813,"rank":78,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4446289280412221,"rank":78,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.44005312379794564,"rank":78,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.44177120713502865,"rank":79,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.44818535630443607,"rank":78,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.43989366511804523,"rank":78,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4392592020609655,"rank":80,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.43526941522591617,"rank":80,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4472711804377621,"rank":78,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4428881878450897,"rank":77,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.44309308269267583,"rank":77,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4426083631472195,"rank":77,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4432274599667457,"rank":78,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4425127444905263,"rank":77,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.44285659112085596,"rank":78,"remainingConfigurations":444}],"sharedOrderConflicts":0},"step-5-preview--effort-reasoning":{"score":0.44330647820745145,"rank":79,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5021773957809975,"rank":73,"remainingConfigurations":444},{"removed":"Datacurve","score":0.39898598899919874,"rank":78,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4421705726303093,"rank":79,"remainingConfigurations":444},{"removed":"Scale","score":0.4641897000614897,"rank":78,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.44448479345658826,"rank":76,"remainingConfigurations":444},{"removed":"Cognition","score":0.4275369311764541,"rank":80,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4517824031868294,"rank":78,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.445703485073001,"rank":76,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4485309719150578,"rank":79,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4350970085917707,"rank":78,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.44311485547720286,"rank":79,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.43688372887882315,"rank":80,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4426335221017195,"rank":79,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.44330647820745145,"rank":79,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.44524350358622694,"rank":78,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4380404776431707,"rank":80,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.44993878865221854,"rank":77,"remainingConfigurations":444},{"removed":"briefcase","score":0.4346250912195729,"rank":82,"remainingConfigurations":444},{"removed":"aime","score":0.4421765665633742,"rank":78,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4331250117097816,"rank":82,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4372450899938334,"rank":82,"remainingConfigurations":444},{"removed":"automationbench","score":0.44542979621264095,"rank":77,"remainingConfigurations":444},{"removed":"critpt","score":0.4408282150401,"rank":80,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.43360273436296,"rank":83,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4606376165198536,"rank":72,"remainingConfigurations":444},{"removed":"gdpval","score":0.4339180609842302,"rank":81,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4434988717104214,"rank":79,"remainingConfigurations":444},{"removed":"gpqa","score":0.4376394225183811,"rank":82,"remainingConfigurations":444},{"removed":"harvey","score":0.44041520534430934,"rank":77,"remainingConfigurations":444},{"removed":"hle","score":0.4487303839817572,"rank":82,"remainingConfigurations":444},{"removed":"ifbench","score":0.436527584485025,"rank":81,"remainingConfigurations":444},{"removed":"itbench","score":0.4191599090373573,"rank":83,"remainingConfigurations":444},{"removed":"livecodebench","score":0.44215509035273287,"rank":79,"remainingConfigurations":444},{"removed":"math500","score":0.4433502603713886,"rank":79,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.44762352718384885,"rank":79,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4787014075690572,"rank":71,"remainingConfigurations":444},{"removed":"omniscience","score":0.461780649518686,"rank":75,"remainingConfigurations":444},{"removed":"tau-bench","score":0.44046361825058483,"rank":79,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.47647656061443167,"rank":71,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4330639336641014,"rank":82,"remainingConfigurations":444},{"removed":"arc-agi","score":0.491148769952172,"rank":74,"remainingConfigurations":444},{"removed":"deepswe","score":0.3991948974387039,"rank":78,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4433576751059161,"rank":79,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.44036632596914943,"rank":80,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4275369311764541,"rank":80,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4417457331790397,"rank":80,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4405757573182605,"rank":77,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4429339859846922,"rank":79,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4421105065664679,"rank":79,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4433050600012301,"rank":79,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4414375569021238,"rank":78,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4463192059333864,"rank":80,"remainingConfigurations":444},{"removed":"livebench-data","score":0.44341770018596643,"rank":79,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.43944484589212435,"rank":79,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.44218356616287036,"rank":78,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4469208139866487,"rank":80,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.445703485073001,"rank":76,"remainingConfigurations":444},{"removed":"frontiermath","score":0.44344429466523755,"rank":78,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.4346764733930056,"rank":81,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4520133573435458,"rank":76,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4428083961752602,"rank":78,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4426843672930354,"rank":78,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.44246941531565415,"rank":78,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4431528480929588,"rank":79,"remainingConfigurations":444},{"removed":"vibe-code","score":0.44199980534359923,"rank":78,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.44272769204033086,"rank":79,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5--effort-medium":{"score":0.441367680834683,"rank":80,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.42945608924691214,"rank":76,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4470775272965648,"rank":88,"remainingConfigurations":444},{"removed":"Datacurve","score":0.420215856756007,"rank":73,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4414299712272083,"rank":80,"remainingConfigurations":444},{"removed":"Scale","score":0.46430209943831785,"rank":77,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.43756237729629505,"rank":80,"remainingConfigurations":444},{"removed":"Cognition","score":0.5009285726896321,"rank":66,"remainingConfigurations":444},{"removed":"LiveBench","score":0.44935480839831077,"rank":81,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3956914111716734,"rank":86,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4473232829488283,"rank":81,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4290294094460747,"rank":79,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.44142554911688264,"rank":80,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.43710864166526764,"rank":79,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.44131466099987704,"rank":80,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.441367680834683,"rank":80,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.44297059256609356,"rank":80,"remainingConfigurations":444},{"removed":"All provider reports","score":0.43875548448540047,"rank":79,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.44205523830147625,"rank":80,"remainingConfigurations":444},{"removed":"briefcase","score":0.44351431267817326,"rank":78,"remainingConfigurations":444},{"removed":"aime","score":0.43863778828322125,"rank":80,"remainingConfigurations":444},{"removed":"apex-agents","score":0.44266202978147984,"rank":79,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.43941645323423656,"rank":81,"remainingConfigurations":444},{"removed":"automationbench","score":0.44144782236400837,"rank":80,"remainingConfigurations":444},{"removed":"critpt","score":0.4401528904634832,"rank":81,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4409264245323341,"rank":79,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4396188827586305,"rank":82,"remainingConfigurations":444},{"removed":"gdpval","score":0.44222050220219516,"rank":78,"remainingConfigurations":444},{"removed":"gmmlu","score":0.44155117111337766,"rank":80,"remainingConfigurations":444},{"removed":"gpqa","score":0.43798344665509076,"rank":81,"remainingConfigurations":444},{"removed":"harvey","score":0.4392156422740224,"rank":79,"remainingConfigurations":444},{"removed":"hle","score":0.4514863680561958,"rank":79,"remainingConfigurations":444},{"removed":"ifbench","score":0.44258998280413137,"rank":76,"remainingConfigurations":444},{"removed":"itbench","score":0.440804181521591,"rank":79,"remainingConfigurations":444},{"removed":"livecodebench","score":0.44148048996842176,"rank":80,"remainingConfigurations":444},{"removed":"math500","score":0.4414224557194402,"rank":80,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4467649486143728,"rank":80,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4522184182493831,"rank":80,"remainingConfigurations":444},{"removed":"omniscience","score":0.4387797277589749,"rank":86,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4421401034539108,"rank":77,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4420936728364872,"rank":80,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4390236054672325,"rank":79,"remainingConfigurations":444},{"removed":"arc-agi","score":0.44182597715382066,"rank":86,"remainingConfigurations":444},{"removed":"deepswe","score":0.42011485798011616,"rank":73,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.44141025950202056,"rank":80,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.44059660359909897,"rank":79,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5009285726896321,"rank":66,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.44234843058870815,"rank":78,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4353619518688802,"rank":81,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.441710293893325,"rank":80,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.44082587095279485,"rank":80,"remainingConfigurations":444},{"removed":"livebench-math","score":0.44169017928080795,"rank":80,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4392158902075775,"rank":80,"remainingConfigurations":444},{"removed":"livebench-language","score":0.44339578343206193,"rank":81,"remainingConfigurations":444},{"removed":"livebench-data","score":0.44139415598753834,"rank":81,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4380242954430434,"rank":80,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4398817148126115,"rank":80,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.44591864736014836,"rank":81,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3956914111716734,"rank":86,"remainingConfigurations":444},{"removed":"frontiermath","score":0.44032039847211885,"rank":79,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.436294896650933,"rank":79,"remainingConfigurations":444},{"removed":"simpleqa","score":0.44998574042909834,"rank":77,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.44074931065034223,"rank":80,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4406092671328388,"rank":79,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.44088578174431464,"rank":79,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4407321509918775,"rank":80,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4399370366764175,"rank":79,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4410636103634033,"rank":80,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-8--effort-medium":{"score":0.43954724096982045,"rank":81,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4164096540950692,"rank":79,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.37630661067018845,"rank":104,"remainingConfigurations":444},{"removed":"Datacurve","score":0.46820053066240325,"rank":69,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4399151182137316,"rank":81,"remainingConfigurations":444},{"removed":"Scale","score":0.45582390080100316,"rank":82,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4354577471700017,"rank":82,"remainingConfigurations":444},{"removed":"Cognition","score":0.462221173032798,"rank":72,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4417481037280115,"rank":82,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4331823805528903,"rank":81,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.45278301578095176,"rank":78,"remainingConfigurations":431},{"removed":"Vals AI","score":0.42277611451109576,"rank":82,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.43956029486266734,"rank":81,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4348801722585726,"rank":81,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.43950170873988087,"rank":81,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.43954724096982045,"rank":81,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4401776233695546,"rank":81,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4355288323071411,"rank":81,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.43976768008004524,"rank":81,"remainingConfigurations":444},{"removed":"briefcase","score":0.43747560564744675,"rank":80,"remainingConfigurations":444},{"removed":"aime","score":0.43582294556230233,"rank":81,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4407267231600773,"rank":80,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.43980967810711763,"rank":80,"remainingConfigurations":444},{"removed":"automationbench","score":0.439019343353279,"rank":82,"remainingConfigurations":444},{"removed":"critpt","score":0.4391055816262126,"rank":82,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4394447939997245,"rank":81,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.44068674374055306,"rank":79,"remainingConfigurations":444},{"removed":"gdpval","score":0.43931419916264747,"rank":79,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4395583434579396,"rank":81,"remainingConfigurations":444},{"removed":"gpqa","score":0.44134882729014085,"rank":78,"remainingConfigurations":444},{"removed":"harvey","score":0.4379646998855689,"rank":81,"remainingConfigurations":444},{"removed":"hle","score":0.4506958707096873,"rank":81,"remainingConfigurations":444},{"removed":"ifbench","score":0.43755195246100803,"rank":80,"remainingConfigurations":444},{"removed":"itbench","score":0.4392431952255511,"rank":80,"remainingConfigurations":444},{"removed":"livecodebench","score":0.43977536874099665,"rank":81,"remainingConfigurations":444},{"removed":"math500","score":0.4394936684071337,"rank":81,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.444004193765132,"rank":81,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4515683549481489,"rank":82,"remainingConfigurations":444},{"removed":"omniscience","score":0.43934245529199784,"rank":85,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4387788388711744,"rank":80,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4386619384258607,"rank":81,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.43559842982480884,"rank":81,"remainingConfigurations":444},{"removed":"arc-agi","score":0.37385571226238445,"rank":99,"remainingConfigurations":444},{"removed":"deepswe","score":0.4683285797200416,"rank":69,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4396002418311111,"rank":81,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.43757653200094476,"rank":82,"remainingConfigurations":444},{"removed":"frontiercode","score":0.462221173032798,"rank":72,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4372822817827556,"rank":81,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4366979461108777,"rank":79,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.43913489423917146,"rank":81,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4369901007448392,"rank":81,"remainingConfigurations":444},{"removed":"livebench-math","score":0.43937571102293366,"rank":81,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.43628905373194365,"rank":81,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4424746300681434,"rank":82,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4404534610502058,"rank":82,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4360017366897689,"rank":81,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.43783755674256647,"rank":81,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.44435691054623394,"rank":82,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4331823805528903,"rank":81,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4383594522297316,"rank":81,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.43869285714188155,"rank":76,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4468132385149271,"rank":79,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4388691518135892,"rank":81,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.43904257764721066,"rank":80,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4386395319579463,"rank":80,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.43906402802428324,"rank":81,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4383563904560004,"rank":80,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.43882024461549024,"rank":81,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-5-5--effort-max":{"score":0.4388976713672646,"rank":82,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.41224267285919863,"rank":80,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5140591025155966,"rank":71,"remainingConfigurations":444},{"removed":"Datacurve","score":0.394155031707565,"rank":79,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.43882638308512445,"rank":82,"remainingConfigurations":444},{"removed":"Scale","score":0.45907217666210515,"rank":81,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4371456560910352,"rank":81,"remainingConfigurations":444},{"removed":"Cognition","score":0.35313154662290064,"rank":101,"remainingConfigurations":444},{"removed":"LiveBench","score":0.48448700081823737,"rank":72,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4344783828018663,"rank":80,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.45330131167104687,"rank":76,"remainingConfigurations":431},{"removed":"Vals AI","score":0.4269610620654545,"rank":80,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.43869410145182314,"rank":82,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.43444961802606824,"rank":82,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.43785900126471516,"rank":82,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4388976713672646,"rank":82,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.44000072766697257,"rank":82,"remainingConfigurations":444},{"removed":"All provider reports","score":0.43435360613923146,"rank":82,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.43041688439482795,"rank":82,"remainingConfigurations":444},{"removed":"briefcase","score":0.43513695337471403,"rank":81,"remainingConfigurations":444},{"removed":"aime","score":0.4355310437823194,"rank":82,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4402288607548512,"rank":81,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4358914809249152,"rank":83,"remainingConfigurations":444},{"removed":"automationbench","score":0.4421248264405204,"rank":79,"remainingConfigurations":444},{"removed":"critpt","score":0.4415141531179399,"rank":79,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4396261414845306,"rank":80,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4401275730069866,"rank":81,"remainingConfigurations":444},{"removed":"gdpval","score":0.4375759176160729,"rank":80,"remainingConfigurations":444},{"removed":"gmmlu","score":0.43891220584686236,"rank":82,"remainingConfigurations":444},{"removed":"gpqa","score":0.4398481372828877,"rank":80,"remainingConfigurations":444},{"removed":"harvey","score":0.44026987926989575,"rank":78,"remainingConfigurations":444},{"removed":"hle","score":0.4512782661776173,"rank":80,"remainingConfigurations":444},{"removed":"ifbench","score":0.4363896109532819,"rank":82,"remainingConfigurations":444},{"removed":"itbench","score":0.439174280804538,"rank":81,"remainingConfigurations":444},{"removed":"livecodebench","score":0.43855915324283495,"rank":82,"remainingConfigurations":444},{"removed":"math500","score":0.4387701213485619,"rank":82,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4433083168986387,"rank":82,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.45185187372039487,"rank":81,"remainingConfigurations":444},{"removed":"omniscience","score":0.446657723132924,"rank":81,"remainingConfigurations":444},{"removed":"tau-bench","score":0.43820077071363667,"rank":81,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.43457320591593573,"rank":82,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4383878356412507,"rank":80,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4770655965600479,"rank":78,"remainingConfigurations":444},{"removed":"deepswe","score":0.3942868481243127,"rank":79,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.43894799368819276,"rank":82,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4922387816429478,"rank":69,"remainingConfigurations":444},{"removed":"frontiercode","score":0.35313154662290064,"rank":101,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.43724491201624777,"rank":82,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.43589872110998634,"rank":80,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.43838477215032573,"rank":82,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.43690421848382294,"rank":82,"remainingConfigurations":444},{"removed":"livebench-math","score":0.43784198586720685,"rank":82,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.43319614755242947,"rank":82,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4480861823024019,"rank":77,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4415381819339487,"rank":80,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4223788709846696,"rank":82,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.43582875037228175,"rank":82,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4533816340634835,"rank":75,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4344783828018663,"rank":80,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4377106117750676,"rank":82,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.43738736901176106,"rank":78,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4445875851335676,"rank":82,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4386340273473044,"rank":82,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4381806171701795,"rank":82,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4385416518684457,"rank":81,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4381290780618777,"rank":82,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4371853217672474,"rank":81,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.43854308561042993,"rank":82,"remainingConfigurations":444}],"sharedOrderConflicts":1},"qwen3.8-2.4t-a95b--effort-reasoning":{"score":0.42429541929465603,"rank":83,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4837510407914873,"rank":79,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3815112625414448,"rank":85,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.42309115958279464,"rank":83,"remainingConfigurations":444},{"removed":"Scale","score":0.44578129420615825,"rank":83,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.426454856946522,"rank":83,"remainingConfigurations":444},{"removed":"Cognition","score":0.41091256332578774,"rank":82,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4328828421799204,"rank":83,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.42753742587163385,"rank":82,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.42932063928228387,"rank":83,"remainingConfigurations":431},{"removed":"Vals AI","score":0.41696287152281203,"rank":83,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4241955572673142,"rank":83,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4180904819636641,"rank":83,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4236496117889222,"rank":83,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.42429541929465603,"rank":83,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4260139855257626,"rank":83,"remainingConfigurations":444},{"removed":"All provider reports","score":0.4191488781227479,"rank":83,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.42758672565725925,"rank":83,"remainingConfigurations":444},{"removed":"briefcase","score":0.40986076183973325,"rank":83,"remainingConfigurations":444},{"removed":"aime","score":0.4223561899288606,"rank":83,"remainingConfigurations":444},{"removed":"apex-agents","score":0.42709955463106647,"rank":83,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.47667857858119816,"rank":71,"remainingConfigurations":444},{"removed":"automationbench","score":0.4072382616035212,"rank":83,"remainingConfigurations":444},{"removed":"critpt","score":0.4207031801577716,"rank":83,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.40560259064367316,"rank":85,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.43823701905386536,"rank":83,"remainingConfigurations":444},{"removed":"gdpval","score":0.40465255015783846,"rank":84,"remainingConfigurations":444},{"removed":"gmmlu","score":0.424180359975557,"rank":83,"remainingConfigurations":444},{"removed":"gpqa","score":0.4100250671139356,"rank":83,"remainingConfigurations":444},{"removed":"harvey","score":0.42133967791502475,"rank":83,"remainingConfigurations":444},{"removed":"hle","score":0.4340586970322724,"rank":83,"remainingConfigurations":444},{"removed":"ifbench","score":0.41729503556416764,"rank":84,"remainingConfigurations":444},{"removed":"itbench","score":0.4248040067056302,"rank":82,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4222096506659025,"rank":83,"remainingConfigurations":444},{"removed":"math500","score":0.42370340052904115,"rank":83,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4278106284836773,"rank":83,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4385639845640725,"rank":83,"remainingConfigurations":444},{"removed":"omniscience","score":0.4690918285699642,"rank":73,"remainingConfigurations":444},{"removed":"tau-bench","score":0.40163180750274724,"rank":84,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4284489034623085,"rank":83,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4308641991377855,"rank":84,"remainingConfigurations":444},{"removed":"arc-agi","score":0.473118253721168,"rank":81,"remainingConfigurations":444},{"removed":"deepswe","score":0.38173418693414535,"rank":85,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4243632159603019,"rank":83,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.42072812719483044,"rank":83,"remainingConfigurations":444},{"removed":"frontiercode","score":0.41091256332578774,"rank":82,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4227741054946468,"rank":83,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4215511936048806,"rank":83,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4239725476910828,"rank":83,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.42319990255136086,"rank":83,"remainingConfigurations":444},{"removed":"livebench-math","score":0.42437187659120457,"rank":83,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.42241719812420947,"rank":83,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4273675939312005,"rank":83,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4244205974881134,"rank":83,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.42034333517355044,"rank":83,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4231256059774331,"rank":83,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4279074545575043,"rank":83,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.42753742587163385,"rank":82,"remainingConfigurations":444},{"removed":"frontiermath","score":0.42512018733232465,"rank":83,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.41505012025891347,"rank":83,"remainingConfigurations":444},{"removed":"simpleqa","score":0.43343686903830503,"rank":83,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.42362131318416524,"rank":83,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.42377672110401426,"rank":83,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.42344625942291353,"rank":83,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4242176045050681,"rank":83,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4230293073078017,"rank":83,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4237188052121965,"rank":83,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-6--effort-max":{"score":0.40815199969711724,"rank":84,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.44264841866434357,"rank":74,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3854182500464427,"rank":100,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3599274001549551,"rank":90,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4080087796749159,"rank":84,"remainingConfigurations":444},{"removed":"Scale","score":0.37918351894645036,"rank":98,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4047384945245886,"rank":87,"remainingConfigurations":444},{"removed":"Cognition","score":0.38784717786324374,"rank":91,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4104605334443725,"rank":87,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4059719307760259,"rank":85,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4799252147706597,"rank":72,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3933332292169039,"rank":86,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4079488813128839,"rank":84,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.4032255179592079,"rank":84,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4080882754542423,"rank":84,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.40815199969711724,"rank":84,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.4096686369622648,"rank":84,"remainingConfigurations":444},{"removed":"All provider reports","score":0.40452882744457225,"rank":84,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.40870712714873086,"rank":85,"remainingConfigurations":444},{"removed":"briefcase","score":0.4066788359188536,"rank":85,"remainingConfigurations":444},{"removed":"aime","score":0.4112231743804677,"rank":84,"remainingConfigurations":444},{"removed":"apex-agents","score":0.40567754016899954,"rank":86,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.40830336324671773,"rank":84,"remainingConfigurations":444},{"removed":"automationbench","score":0.40672252075981713,"rank":84,"remainingConfigurations":444},{"removed":"critpt","score":0.4060775181298193,"rank":86,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4077354257792483,"rank":84,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4103924219365443,"rank":86,"remainingConfigurations":444},{"removed":"gdpval","score":0.4073630930850216,"rank":83,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4049798473823949,"rank":85,"remainingConfigurations":444},{"removed":"gpqa","score":0.40872760919159745,"rank":84,"remainingConfigurations":444},{"removed":"harvey","score":0.4058894762835657,"rank":85,"remainingConfigurations":444},{"removed":"hle","score":0.36760301121477945,"rank":99,"remainingConfigurations":444},{"removed":"ifbench","score":0.42149173960247005,"rank":83,"remainingConfigurations":444},{"removed":"itbench","score":0.40719356525453415,"rank":84,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4080932810036626,"rank":84,"remainingConfigurations":444},{"removed":"math500","score":0.4080471840755339,"rank":84,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4128214807780406,"rank":84,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4240563560316477,"rank":84,"remainingConfigurations":444},{"removed":"omniscience","score":0.39973279084098307,"rank":88,"remainingConfigurations":444},{"removed":"tau-bench","score":0.4086029345551851,"rank":83,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.40917894065303834,"rank":85,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.40308392359331774,"rank":87,"remainingConfigurations":444},{"removed":"arc-agi","score":0.37672560688561935,"rank":98,"remainingConfigurations":444},{"removed":"deepswe","score":0.3601246564813778,"rank":90,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4081687297213963,"rank":84,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.407035724671442,"rank":85,"remainingConfigurations":444},{"removed":"frontiercode","score":0.38784717786324374,"rank":91,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.39200120642850633,"rank":88,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4062249470740707,"rank":84,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.40422652597618747,"rank":86,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4072976961462831,"rank":84,"remainingConfigurations":444},{"removed":"livebench-math","score":0.40800893501172686,"rank":85,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.40523006110892507,"rank":84,"remainingConfigurations":444},{"removed":"livebench-language","score":0.41039748906654316,"rank":85,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4087503939965204,"rank":84,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4059083391509888,"rank":84,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.40729582265682945,"rank":84,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4113863446281762,"rank":84,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4059719307760259,"rank":85,"remainingConfigurations":444},{"removed":"frontiermath","score":0.40126733023766287,"rank":87,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.40218402724531094,"rank":84,"remainingConfigurations":444},{"removed":"simpleqa","score":0.41382314586033025,"rank":86,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.40751158061944986,"rank":84,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4077337848517097,"rank":85,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.4072897948179319,"rank":84,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4079441074692283,"rank":85,"remainingConfigurations":444},{"removed":"vibe-code","score":0.40706406514873955,"rank":84,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.40771564268606353,"rank":84,"remainingConfigurations":444}],"sharedOrderConflicts":1},"glm-5.3-flash--effort-reasoning":{"score":0.4063006062730237,"rank":85,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4634782900986816,"rank":86,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3609169678037069,"rank":88,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4051773791602314,"rank":85,"remainingConfigurations":444},{"removed":"Scale","score":0.4279668786763871,"rank":84,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4066737036494053,"rank":85,"remainingConfigurations":444},{"removed":"Cognition","score":0.39074468454184935,"rank":88,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4154830376559869,"rank":85,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.4086144927107549,"rank":83,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4123174885452831,"rank":87,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3976993205865926,"rank":84,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4060523718967019,"rank":85,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.39984213524412554,"rank":85,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4056512864902799,"rank":85,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4063006062730237,"rank":85,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.40808886765178415,"rank":85,"remainingConfigurations":444},{"removed":"All provider reports","score":0.40081588933720824,"rank":85,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.4176558761087556,"rank":84,"remainingConfigurations":444},{"removed":"briefcase","score":0.3914496826375484,"rank":87,"remainingConfigurations":444},{"removed":"aime","score":0.4051176833070926,"rank":85,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4082876938464844,"rank":84,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.39331310741808273,"rank":88,"remainingConfigurations":444},{"removed":"automationbench","score":0.38405406388124125,"rank":89,"remainingConfigurations":444},{"removed":"critpt","score":0.4103820396088449,"rank":85,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.44280133327287957,"rank":78,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.41683428107260495,"rank":84,"remainingConfigurations":444},{"removed":"gdpval","score":0.3864371915684491,"rank":88,"remainingConfigurations":444},{"removed":"gmmlu","score":0.4063384046475443,"rank":84,"remainingConfigurations":444},{"removed":"gpqa","score":0.40308881337349445,"rank":85,"remainingConfigurations":444},{"removed":"harvey","score":0.4098412210160583,"rank":84,"remainingConfigurations":444},{"removed":"hle","score":0.4196602479271227,"rank":85,"remainingConfigurations":444},{"removed":"ifbench","score":0.3991596471714389,"rank":86,"remainingConfigurations":444},{"removed":"itbench","score":0.3863216368239164,"rank":89,"remainingConfigurations":444},{"removed":"livecodebench","score":0.40529194305150273,"rank":85,"remainingConfigurations":444},{"removed":"math500","score":0.4063814023852661,"rank":85,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4109139911860948,"rank":85,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.4205722331652035,"rank":85,"remainingConfigurations":444},{"removed":"omniscience","score":0.44764337584013586,"rank":80,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3925648878837525,"rank":87,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.41794004383903127,"rank":84,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.39519627125624907,"rank":88,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4540084374468801,"rank":84,"remainingConfigurations":444},{"removed":"deepswe","score":0.3611360839050006,"rank":88,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.4063607445741176,"rank":86,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.40372332739831185,"rank":86,"remainingConfigurations":444},{"removed":"frontiercode","score":0.39074468454184935,"rank":88,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.4047758492364588,"rank":84,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.40363089457437895,"rank":86,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.4059800797255531,"rank":85,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4052266288979988,"rank":85,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4062608882272442,"rank":86,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.40437265212554024,"rank":86,"remainingConfigurations":444},{"removed":"livebench-language","score":0.40942083053898587,"rank":86,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4064797689702036,"rank":85,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.4022789480150826,"rank":85,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4051466072477463,"rank":85,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.41004671424932,"rank":85,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.4086144927107549,"rank":83,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4064054890240225,"rank":84,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.39772978450171365,"rank":86,"remainingConfigurations":444},{"removed":"simpleqa","score":0.4152872185259069,"rank":84,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4057860875376224,"rank":85,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.40566086264167267,"rank":86,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.40544077889079494,"rank":85,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4061552717122168,"rank":86,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4049485481415749,"rank":85,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.40571296630735526,"rank":85,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.8-flash-next--effort-reasoning":{"score":0.4032547970350735,"rank":86,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4644032958254562,"rank":84,"remainingConfigurations":444},{"removed":"Datacurve","score":0.36007883882860087,"rank":89,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.4018245716718177,"rank":86,"remainingConfigurations":444},{"removed":"Scale","score":0.42545786619297754,"rank":85,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4053427607353748,"rank":86,"remainingConfigurations":444},{"removed":"Cognition","score":0.39032219825888204,"rank":89,"remainingConfigurations":444},{"removed":"LiveBench","score":0.412017319833547,"rank":86,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.40659525504186167,"rank":84,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4095952692725479,"rank":88,"remainingConfigurations":431},{"removed":"Vals AI","score":0.39642360017402817,"rank":85,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.4031227206698165,"rank":86,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3971496433460577,"rank":87,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.40248210822975233,"rank":86,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.4032547970350735,"rank":86,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.40504171753389134,"rank":86,"remainingConfigurations":444},{"removed":"All provider reports","score":0.39811293988410634,"rank":87,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.40590516928657855,"rank":86,"remainingConfigurations":444},{"removed":"briefcase","score":0.36630595754480416,"rank":94,"remainingConfigurations":444},{"removed":"aime","score":0.4014481322302921,"rank":86,"remainingConfigurations":444},{"removed":"apex-agents","score":0.4059992987394094,"rank":85,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4055191055942891,"rank":85,"remainingConfigurations":444},{"removed":"automationbench","score":0.3926338752724874,"rank":87,"remainingConfigurations":444},{"removed":"critpt","score":0.4153737895764697,"rank":84,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4039624748277646,"rank":86,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4151855273533114,"rank":85,"remainingConfigurations":444},{"removed":"gdpval","score":0.37795656457239923,"rank":91,"remainingConfigurations":444},{"removed":"gmmlu","score":0.40291393091561617,"rank":86,"remainingConfigurations":444},{"removed":"gpqa","score":0.3958669256062282,"rank":88,"remainingConfigurations":444},{"removed":"harvey","score":0.3999816928389393,"rank":87,"remainingConfigurations":444},{"removed":"hle","score":0.42250336393540716,"rank":84,"remainingConfigurations":444},{"removed":"ifbench","score":0.39661485305337596,"rank":87,"remainingConfigurations":444},{"removed":"itbench","score":0.40288844690522785,"rank":85,"remainingConfigurations":444},{"removed":"livecodebench","score":0.4010204084074324,"rank":87,"remainingConfigurations":444},{"removed":"math500","score":0.40267960825639065,"rank":86,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.40683209701314543,"rank":87,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.41980253467450795,"rank":86,"remainingConfigurations":444},{"removed":"omniscience","score":0.48171570009937925,"rank":71,"remainingConfigurations":444},{"removed":"tau-bench","score":0.38835928063957376,"rank":88,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.40680837208065834,"rank":86,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.39270772169325224,"rank":89,"remainingConfigurations":444},{"removed":"arc-agi","score":0.45276072184322197,"rank":85,"remainingConfigurations":444},{"removed":"deepswe","score":0.3602726449863278,"rank":89,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.40332315857478224,"rank":87,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.39967293988830216,"rank":88,"remainingConfigurations":444},{"removed":"frontiercode","score":0.39032219825888204,"rank":89,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.40167977818844897,"rank":86,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.4005747759069689,"rank":87,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.40294278486831286,"rank":87,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.4021766866431446,"rank":86,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4033512356817515,"rank":87,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.4013614367018352,"rank":87,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4063031778841206,"rank":87,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4033294583540126,"rank":86,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.399326014159383,"rank":86,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.4020807725016555,"rank":86,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.40692387346439407,"rank":86,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.40659525504186167,"rank":84,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4042837891294812,"rank":85,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3941071608042574,"rank":89,"remainingConfigurations":444},{"removed":"simpleqa","score":0.412285172646935,"rank":87,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.4025675788634977,"rank":86,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4027178058729682,"rank":87,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.40246912256861284,"rank":87,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4031253587199326,"rank":87,"remainingConfigurations":444},{"removed":"vibe-code","score":0.40200130217376945,"rank":87,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.4026787795386746,"rank":86,"remainingConfigurations":444}],"sharedOrderConflicts":0},"muse-spark-1.1--effort-xhigh":{"score":0.40190957266266264,"rank":87,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4277822811414899,"rank":78,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.44043353688680337,"rank":90,"remainingConfigurations":444},{"removed":"Datacurve","score":0.38580285896259686,"rank":82,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.40173140298728977,"rank":87,"remainingConfigurations":444},{"removed":"Scale","score":0.40401622623330696,"rank":90,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.4042328471909298,"rank":88,"remainingConfigurations":444},{"removed":"Cognition","score":0.40073460961747354,"rank":83,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4018506758256151,"rank":88,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3947993976923123,"rank":87,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4133938979710181,"rank":86,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3697356882002966,"rank":91,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.40207555632063374,"rank":87,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.39775695972952235,"rank":86,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.4023269641744458,"rank":87,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.40190957266266264,"rank":87,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.40221247618781053,"rank":87,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3986673665817286,"rank":86,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.40195527034842016,"rank":87,"remainingConfigurations":444},{"removed":"briefcase","score":0.4073192479394871,"rank":84,"remainingConfigurations":444},{"removed":"aime","score":0.3997261414485684,"rank":87,"remainingConfigurations":444},{"removed":"apex-agents","score":0.40240629663151206,"rank":87,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.4031156147796439,"rank":86,"remainingConfigurations":444},{"removed":"automationbench","score":0.4015546183047504,"rank":85,"remainingConfigurations":444},{"removed":"critpt","score":0.40127926200896163,"rank":87,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.4017647669359195,"rank":87,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.4040343632038399,"rank":87,"remainingConfigurations":444},{"removed":"gdpval","score":0.4023266718211032,"rank":85,"remainingConfigurations":444},{"removed":"gmmlu","score":0.40197084937257516,"rank":87,"remainingConfigurations":444},{"removed":"gpqa","score":0.3990099202723314,"rank":86,"remainingConfigurations":444},{"removed":"harvey","score":0.3844949302145068,"rank":90,"remainingConfigurations":444},{"removed":"hle","score":0.4075108615416456,"rank":86,"remainingConfigurations":444},{"removed":"ifbench","score":0.3996796707854913,"rank":85,"remainingConfigurations":444},{"removed":"itbench","score":0.40134021610083614,"rank":86,"remainingConfigurations":444},{"removed":"livecodebench","score":0.40175511264539404,"rank":86,"remainingConfigurations":444},{"removed":"math500","score":0.40195927339928517,"rank":87,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4045334596542896,"rank":88,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.41352411394646477,"rank":87,"remainingConfigurations":444},{"removed":"omniscience","score":0.4007151242979312,"rank":87,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3994406691074062,"rank":85,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.4025114272628356,"rank":87,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.41497476072107836,"rank":85,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4298088414557335,"rank":89,"remainingConfigurations":444},{"removed":"deepswe","score":0.3860341923441886,"rank":82,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.40707045076948173,"rank":85,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4005085211095369,"rank":87,"remainingConfigurations":444},{"removed":"frontiercode","score":0.40073460961747354,"rank":83,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.40217222341779935,"rank":85,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.40469444375088676,"rank":85,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.40692803679779593,"rank":84,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.38139301602166603,"rank":90,"remainingConfigurations":444},{"removed":"livebench-math","score":0.4100634745261708,"rank":84,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.40518862167761016,"rank":85,"remainingConfigurations":444},{"removed":"livebench-language","score":0.41200673844984576,"rank":84,"remainingConfigurations":444},{"removed":"livebench-data","score":0.4008758425233047,"rank":87,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.38611196464932,"rank":89,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3975689197236358,"rank":87,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.4016386351407371,"rank":88,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3947993976923123,"rank":87,"remainingConfigurations":444},{"removed":"frontiermath","score":0.4017740236117484,"rank":86,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3977271948668977,"rank":87,"remainingConfigurations":444},{"removed":"simpleqa","score":0.40852384201868763,"rank":88,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.390907287101373,"rank":88,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.4083925044096015,"rank":84,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.40506222443768164,"rank":86,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.4088222518993716,"rank":84,"remainingConfigurations":444},{"removed":"vibe-code","score":0.4039316028880764,"rank":86,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.402027774100439,"rank":87,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-max":{"score":0.39711432955620496,"rank":88,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.40058080720876194,"rank":81,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.456580756253566,"rank":87,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3102031780965917,"rank":98,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3970748756429232,"rank":88,"remainingConfigurations":444},{"removed":"Scale","score":0.41651351223195837,"rank":86,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.41818873217984215,"rank":84,"remainingConfigurations":444},{"removed":"Cognition","score":0.3827311029385119,"rank":92,"remainingConfigurations":444},{"removed":"LiveBench","score":0.4170440278582133,"rank":84,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3904735078193497,"rank":88,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.406050364541543,"rank":89,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3812813335821386,"rank":88,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3972622820176516,"rank":88,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3952362005188052,"rank":88,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3967340802710743,"rank":88,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.39711432955620496,"rank":88,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3976409683475688,"rank":88,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3954779533407418,"rank":88,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.39726225171253143,"rank":88,"remainingConfigurations":444},{"removed":"briefcase","score":0.39635133788374804,"rank":86,"remainingConfigurations":444},{"removed":"aime","score":0.3914299856976275,"rank":89,"remainingConfigurations":444},{"removed":"apex-agents","score":0.396879036660667,"rank":88,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3965767448268729,"rank":87,"remainingConfigurations":444},{"removed":"automationbench","score":0.3957756857584976,"rank":86,"remainingConfigurations":444},{"removed":"critpt","score":0.39711332294195345,"rank":88,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3985719052405803,"rank":88,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.39629505780527025,"rank":88,"remainingConfigurations":444},{"removed":"gdpval","score":0.39632958208534136,"rank":86,"remainingConfigurations":444},{"removed":"gmmlu","score":0.39719256229154315,"rank":88,"remainingConfigurations":444},{"removed":"gpqa","score":0.3933864044092867,"rank":89,"remainingConfigurations":444},{"removed":"harvey","score":0.40065436912361596,"rank":86,"remainingConfigurations":444},{"removed":"hle","score":0.40710785202406274,"rank":87,"remainingConfigurations":444},{"removed":"ifbench","score":0.39575719327202785,"rank":88,"remainingConfigurations":444},{"removed":"itbench","score":0.3964297451242608,"rank":87,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3970721491377418,"rank":88,"remainingConfigurations":444},{"removed":"math500","score":0.3971398973178368,"rank":88,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.4101800839879508,"rank":86,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.408735340567725,"rank":89,"remainingConfigurations":444},{"removed":"omniscience","score":0.39870899335319065,"rank":89,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3962742033328042,"rank":86,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.39939066730006706,"rank":88,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4130114670136706,"rank":86,"remainingConfigurations":444},{"removed":"arc-agi","score":0.41501152781886524,"rank":93,"remainingConfigurations":444},{"removed":"deepswe","score":0.3101220156933561,"rank":98,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.39710356118943285,"rank":88,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.4155953908515966,"rank":84,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3827311029385119,"rank":92,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3963671218070017,"rank":87,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.39443880749347277,"rank":88,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.39680281466583356,"rank":88,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3962775985018609,"rank":87,"remainingConfigurations":444},{"removed":"livebench-math","score":0.40107195808541724,"rank":88,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3844903490641925,"rank":88,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4042403264812953,"rank":88,"remainingConfigurations":444},{"removed":"livebench-data","score":0.39027333429773386,"rank":88,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3963414657143138,"rank":87,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.39652547577292746,"rank":88,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.406859998635561,"rank":87,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3904735078193497,"rank":88,"remainingConfigurations":444},{"removed":"frontiermath","score":0.38584848732199184,"rank":90,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.39852960398361975,"rank":85,"remainingConfigurations":444},{"removed":"simpleqa","score":0.41434257415814907,"rank":85,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.39374243326718866,"rank":87,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.39280066818357895,"rank":88,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3995269801104024,"rank":88,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3920907556713762,"rank":88,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3947210504748255,"rank":88,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3987060733417865,"rank":88,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-7--effort-xhigh":{"score":0.38697033423396476,"rank":89,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3815211479766761,"rank":83,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4090490309119324,"rank":95,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3488607034122187,"rank":92,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.38712640657118497,"rank":89,"remainingConfigurations":444},{"removed":"Scale","score":0.40483712706925096,"rank":89,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.38282242813617295,"rank":90,"remainingConfigurations":444},{"removed":"Cognition","score":0.5023903982409653,"rank":65,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3451039735418773,"rank":103,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.38050008143237024,"rank":89,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3876527086584023,"rank":91,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3735213079116888,"rank":89,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3867856778187931,"rank":89,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.38300013471957933,"rank":90,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3868046524483051,"rank":89,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.38697033423396476,"rank":89,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3874814261831603,"rank":89,"remainingConfigurations":444},{"removed":"All provider reports","score":0.38319355091233986,"rank":90,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.38681097156132543,"rank":89,"remainingConfigurations":444},{"removed":"briefcase","score":0.38504791164391516,"rank":88,"remainingConfigurations":444},{"removed":"aime","score":0.3917518159094864,"rank":88,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3877231834291857,"rank":89,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.38784480045042496,"rank":89,"remainingConfigurations":444},{"removed":"automationbench","score":0.3868923065834844,"rank":88,"remainingConfigurations":444},{"removed":"critpt","score":0.3874434057957213,"rank":89,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3869906980221319,"rank":89,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3882771978929161,"rank":89,"remainingConfigurations":444},{"removed":"gdpval","score":0.3865356429345372,"rank":87,"remainingConfigurations":444},{"removed":"gmmlu","score":0.38700037202872206,"rank":89,"remainingConfigurations":444},{"removed":"gpqa","score":0.39671472204958524,"rank":87,"remainingConfigurations":444},{"removed":"harvey","score":0.3846968439912253,"rank":89,"remainingConfigurations":444},{"removed":"hle","score":0.3978979895525943,"rank":89,"remainingConfigurations":444},{"removed":"ifbench","score":0.3851609876221904,"rank":89,"remainingConfigurations":444},{"removed":"itbench","score":0.38678351334999567,"rank":88,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3870194200852662,"rank":89,"remainingConfigurations":444},{"removed":"math500","score":0.386941196915452,"rank":89,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3914119824312617,"rank":89,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3994643502019182,"rank":90,"remainingConfigurations":444},{"removed":"omniscience","score":0.38838921652779473,"rank":90,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3856507826904856,"rank":89,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.38581568940916616,"rank":89,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.38452105804114073,"rank":91,"remainingConfigurations":444},{"removed":"arc-agi","score":0.39842792057112875,"rank":94,"remainingConfigurations":444},{"removed":"deepswe","score":0.3491478509747295,"rank":92,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3870576892200465,"rank":89,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3851488731759913,"rank":89,"remainingConfigurations":444},{"removed":"frontiercode","score":0.5023903982409653,"rank":65,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.38518729419768044,"rank":90,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3841262889153052,"rank":89,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3864409728148406,"rank":89,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.385248540662065,"rank":89,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3791202478910047,"rank":91,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.37091074146847575,"rank":94,"remainingConfigurations":444},{"removed":"livebench-language","score":0.4033755511082095,"rank":89,"remainingConfigurations":444},{"removed":"livebench-data","score":0.38684679371645325,"rank":90,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3913173323831461,"rank":88,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3806932985323321,"rank":90,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.39667635821954117,"rank":89,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.38050008143237024,"rank":89,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3948446179204062,"rank":88,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.38637567411354573,"rank":90,"remainingConfigurations":444},{"removed":"simpleqa","score":0.37197793372720067,"rank":97,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.38574059385587506,"rank":89,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.38702117309065875,"rank":89,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.38631833753197437,"rank":89,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.38663278367931486,"rank":89,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3854832233511127,"rank":89,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.38667630765518773,"rank":89,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash--effort-high":{"score":0.37998464129275683,"rank":90,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3757591560965785,"rank":84,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.38196154045362096,"rank":102,"remainingConfigurations":444},{"removed":"Datacurve","score":0.39947895654458804,"rank":77,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3799616037717228,"rank":90,"remainingConfigurations":444},{"removed":"Scale","score":0.41047312941966924,"rank":87,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.37894379121079064,"rank":92,"remainingConfigurations":444},{"removed":"Cognition","score":0.3775780655391207,"rank":93,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3693717373716172,"rank":94,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.37785675128629664,"rank":90,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.37220576887985285,"rank":98,"remainingConfigurations":431},{"removed":"Vals AI","score":0.36709982881532405,"rank":93,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3800075845590258,"rank":90,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3759318605780144,"rank":91,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3803551922451349,"rank":90,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.37998464129275683,"rank":90,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3805013219152478,"rank":90,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3768725529008227,"rank":91,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3785466185896591,"rank":91,"remainingConfigurations":444},{"removed":"briefcase","score":0.381963839710314,"rank":89,"remainingConfigurations":444},{"removed":"aime","score":0.3778207502757988,"rank":92,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3777451658871101,"rank":93,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3809816156287558,"rank":90,"remainingConfigurations":444},{"removed":"automationbench","score":0.3797408423925756,"rank":91,"remainingConfigurations":444},{"removed":"critpt","score":0.38131024933516006,"rank":91,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3766203709625838,"rank":93,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3807824047514803,"rank":92,"remainingConfigurations":444},{"removed":"gdpval","score":0.38080038331322624,"rank":90,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3800190718189009,"rank":90,"remainingConfigurations":444},{"removed":"gpqa","score":0.3787961469419572,"rank":90,"remainingConfigurations":444},{"removed":"harvey","score":0.3805800199204617,"rank":91,"remainingConfigurations":444},{"removed":"hle","score":0.378139225907747,"rank":95,"remainingConfigurations":444},{"removed":"ifbench","score":0.3791567169267052,"rank":90,"remainingConfigurations":444},{"removed":"itbench","score":0.37951361455578264,"rank":91,"remainingConfigurations":444},{"removed":"livecodebench","score":0.37998176751845875,"rank":90,"remainingConfigurations":444},{"removed":"math500","score":0.3800275102882568,"rank":90,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.37884801361813986,"rank":94,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3899462599115305,"rank":93,"remainingConfigurations":444},{"removed":"omniscience","score":0.3808585168207979,"rank":91,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3793808817722681,"rank":90,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3805946656706245,"rank":90,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3788481367763949,"rank":92,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3731886215731195,"rank":100,"remainingConfigurations":444},{"removed":"deepswe","score":0.3996667181547115,"rank":77,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3800694395913486,"rank":90,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3781619521275374,"rank":91,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3775780655391207,"rank":93,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.39137460125626244,"rank":89,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.382111402776461,"rank":90,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.380008888965748,"rank":91,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3856805246339561,"rank":88,"remainingConfigurations":444},{"removed":"livebench-math","score":0.38104106452809744,"rank":90,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3801187253730364,"rank":90,"remainingConfigurations":444},{"removed":"livebench-language","score":0.374681314890043,"rank":94,"remainingConfigurations":444},{"removed":"livebench-data","score":0.38493241310196846,"rank":91,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3808323810372201,"rank":90,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.38359311040627553,"rank":89,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.37475633466574937,"rank":95,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.37785675128629664,"rank":90,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3920804984405338,"rank":89,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.38307377126925246,"rank":91,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3680582500604755,"rank":98,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3702581452359342,"rank":94,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3842573410532568,"rank":90,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.38213994701127024,"rank":90,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.37916741785158986,"rank":90,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3837075174201021,"rank":90,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3831902361953212,"rank":90,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4--effort-xhigh":{"score":0.37982263109015846,"rank":91,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4281558364215731,"rank":77,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.38157752574998743,"rank":103,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3723879536660902,"rank":86,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.37965794470572684,"rank":91,"remainingConfigurations":444},{"removed":"Scale","score":0.40668102903387665,"rank":88,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.38268416742076333,"rank":91,"remainingConfigurations":444},{"removed":"Cognition","score":0.37662341074938005,"rank":94,"remainingConfigurations":444},{"removed":"LiveBench","score":0.34920607333192244,"rank":102,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.37299469989761863,"rank":92,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3825175846939996,"rank":93,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3924598730775339,"rank":87,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.37991859447397,"rank":91,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.39043942469574594,"rank":89,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.37996766910353025,"rank":91,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.37982263109015846,"rank":91,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.37968847448269116,"rank":91,"remainingConfigurations":444},{"removed":"All provider reports","score":0.390174884529127,"rank":89,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3799157845545129,"rank":90,"remainingConfigurations":444},{"removed":"briefcase","score":0.3815319076833488,"rank":90,"remainingConfigurations":444},{"removed":"aime","score":0.3781421421451115,"rank":91,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3787006453462552,"rank":91,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3771975063573072,"rank":92,"remainingConfigurations":444},{"removed":"automationbench","score":0.38101647781455256,"rank":90,"remainingConfigurations":444},{"removed":"critpt","score":0.3786634304772454,"rank":92,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3805722778177516,"rank":90,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.38176376704234843,"rank":90,"remainingConfigurations":444},{"removed":"gdpval","score":0.3818087510474644,"rank":89,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3795510520201682,"rank":91,"remainingConfigurations":444},{"removed":"gpqa","score":0.3752392907794304,"rank":92,"remainingConfigurations":444},{"removed":"harvey","score":0.38756173343914607,"rank":88,"remainingConfigurations":444},{"removed":"hle","score":0.38338604132566206,"rank":92,"remainingConfigurations":444},{"removed":"ifbench","score":0.3786756961053705,"rank":91,"remainingConfigurations":444},{"removed":"itbench","score":0.3809754051002811,"rank":90,"remainingConfigurations":444},{"removed":"livecodebench","score":0.37921760736657184,"rank":91,"remainingConfigurations":444},{"removed":"math500","score":0.3796373351876261,"rank":91,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.38148533901493137,"rank":93,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3993073557279618,"rank":91,"remainingConfigurations":444},{"removed":"omniscience","score":0.3796839825343928,"rank":93,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3791270683063137,"rank":91,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3805043613022368,"rank":91,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.4321463575017561,"rank":83,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3717457042686765,"rank":103,"remainingConfigurations":444},{"removed":"deepswe","score":0.37213632543960706,"rank":86,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.37893059238924826,"rank":91,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.37829322806428617,"rank":90,"remainingConfigurations":444},{"removed":"frontiercode","score":0.37662341074938005,"rank":94,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.38072814713763137,"rank":91,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3820178932258906,"rank":91,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.38020391936066605,"rank":90,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3757793479042213,"rank":93,"remainingConfigurations":444},{"removed":"livebench-math","score":0.38360638836304495,"rank":89,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3832582877748462,"rank":89,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3795352716246388,"rank":91,"remainingConfigurations":444},{"removed":"livebench-data","score":0.37523614603766436,"rank":93,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.37742286973637046,"rank":91,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3782234053949148,"rank":91,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3814584101486877,"rank":91,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.37299469989761863,"rank":92,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3801812344680176,"rank":91,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3757867193261272,"rank":92,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3852379057986621,"rank":91,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.37714469133873846,"rank":90,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.37870198200962046,"rank":91,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.37766075940160887,"rank":91,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.37839495234844067,"rank":91,"remainingConfigurations":444},{"removed":"vibe-code","score":0.37972695642558757,"rank":91,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3780855234871587,"rank":91,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5--effort-xhigh":{"score":0.37796581882811126,"rank":92,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.38468789762330075,"rank":82,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.40624356446382365,"rank":96,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3582462873111552,"rank":91,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3778885257675649,"rank":92,"remainingConfigurations":444},{"removed":"Scale","score":0.39660168949481034,"rank":92,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3764901066390625,"rank":93,"remainingConfigurations":444},{"removed":"Cognition","score":0.3424005791581331,"rank":104,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3683943748956164,"rank":95,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.371249719777319,"rank":94,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.4196630520401919,"rank":85,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3643949105821164,"rank":95,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3780028199497861,"rank":92,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3737410658481373,"rank":92,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.37799343214265574,"rank":92,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.37796581882811126,"rank":92,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.37850922607117604,"rank":93,"remainingConfigurations":444},{"removed":"All provider reports","score":0.37439149861059623,"rank":93,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.37803512606673095,"rank":92,"remainingConfigurations":444},{"removed":"briefcase","score":0.37553202159742766,"rank":92,"remainingConfigurations":444},{"removed":"aime","score":0.3685088794664633,"rank":96,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3788872773838141,"rank":90,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.37953101017796215,"rank":91,"remainingConfigurations":444},{"removed":"automationbench","score":0.37890715965187316,"rank":92,"remainingConfigurations":444},{"removed":"critpt","score":0.37757084952179926,"rank":93,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3770122264802742,"rank":91,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.38142013204909436,"rank":91,"remainingConfigurations":444},{"removed":"gdpval","score":0.37674271033077367,"rank":92,"remainingConfigurations":444},{"removed":"gmmlu","score":0.37805269003399355,"rank":92,"remainingConfigurations":444},{"removed":"gpqa","score":0.3694963138188199,"rank":93,"remainingConfigurations":444},{"removed":"harvey","score":0.37558573224319064,"rank":92,"remainingConfigurations":444},{"removed":"hle","score":0.3877652812438091,"rank":91,"remainingConfigurations":444},{"removed":"ifbench","score":0.37606307621429874,"rank":92,"remainingConfigurations":444},{"removed":"itbench","score":0.3774474820904688,"rank":92,"remainingConfigurations":444},{"removed":"livecodebench","score":0.37780926661697617,"rank":92,"remainingConfigurations":444},{"removed":"math500","score":0.37793170628701617,"rank":92,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3823749987263712,"rank":92,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3899513118798488,"rank":92,"remainingConfigurations":444},{"removed":"omniscience","score":0.3803899100407726,"rank":92,"remainingConfigurations":444},{"removed":"tau-bench","score":0.37592677347873543,"rank":93,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3776099810616546,"rank":92,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.37878775731913583,"rank":93,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3975787142107263,"rank":95,"remainingConfigurations":444},{"removed":"deepswe","score":0.3584913230232605,"rank":91,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.37805936584402344,"rank":92,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3768401550011595,"rank":93,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3424005791581331,"rank":104,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3769273119942685,"rank":92,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3749095171921677,"rank":92,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3777355098375424,"rank":92,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.37591130400890566,"rank":92,"remainingConfigurations":444},{"removed":"livebench-math","score":0.378705172967839,"rank":92,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.36686881869502996,"rank":95,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3914691955134246,"rank":90,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3878395969635318,"rank":89,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.35874584052498665,"rank":99,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.36873660358065946,"rank":95,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.39369212382373414,"rank":90,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.371249719777319,"rank":94,"remainingConfigurations":444},{"removed":"frontiermath","score":0.37438857765104133,"rank":94,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3714722166950803,"rank":95,"remainingConfigurations":444},{"removed":"simpleqa","score":0.40678204703267,"rank":89,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.37685223994100464,"rank":91,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3778444928017623,"rank":92,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.37730696438760525,"rank":92,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3775808874185294,"rank":92,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3767481775139189,"rank":93,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3775566445274479,"rank":92,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.6-luna--effort-xhigh":{"score":0.3766784260836182,"rank":93,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.36953575937478206,"rank":86,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4725666557934152,"rank":83,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3012082464495119,"rank":102,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.37690981864364764,"rank":93,"remainingConfigurations":444},{"removed":"Scale","score":0.3978706842285587,"rank":91,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3729456108410187,"rank":97,"remainingConfigurations":444},{"removed":"Cognition","score":0.3395361090495424,"rank":106,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3858708183092234,"rank":89,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.37284350077024997,"rank":93,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3834427209150091,"rank":92,"remainingConfigurations":431},{"removed":"Vals AI","score":0.36806617113292633,"rank":92,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.37669103017666233,"rank":93,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.37235171362443925,"rank":93,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.37657176969613443,"rank":93,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3766784260836182,"rank":93,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.37946484012334697,"rank":92,"remainingConfigurations":444},{"removed":"All provider reports","score":0.37508135710378093,"rank":92,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.37749472448980975,"rank":93,"remainingConfigurations":444},{"removed":"briefcase","score":0.3758120675998882,"rank":91,"remainingConfigurations":444},{"removed":"aime","score":0.37388774710616207,"rank":94,"remainingConfigurations":444},{"removed":"apex-agents","score":0.37816940666156634,"rank":92,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.37581056058870116,"rank":93,"remainingConfigurations":444},{"removed":"automationbench","score":0.3761141804798251,"rank":93,"remainingConfigurations":444},{"removed":"critpt","score":0.3749368721154979,"rank":94,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3766426075379781,"rank":92,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.37263184285456313,"rank":94,"remainingConfigurations":444},{"removed":"gdpval","score":0.3758850028835932,"rank":93,"remainingConfigurations":444},{"removed":"gmmlu","score":0.37683473998462585,"rank":93,"remainingConfigurations":444},{"removed":"gpqa","score":0.3755038631236835,"rank":91,"remainingConfigurations":444},{"removed":"harvey","score":0.3742300363911411,"rank":93,"remainingConfigurations":444},{"removed":"hle","score":0.38940475189430757,"rank":90,"remainingConfigurations":444},{"removed":"ifbench","score":0.3748103792927456,"rank":93,"remainingConfigurations":444},{"removed":"itbench","score":0.37612849173649554,"rank":93,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3767983463952356,"rank":93,"remainingConfigurations":444},{"removed":"math500","score":0.3766262885937697,"rank":93,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.38329991316806217,"rank":91,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3898454290241238,"rank":94,"remainingConfigurations":444},{"removed":"omniscience","score":0.3769247410708052,"rank":94,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3771973723456669,"rank":92,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.37753408959131646,"rank":93,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.37571460037877974,"rank":96,"remainingConfigurations":444},{"removed":"arc-agi","score":0.46775859759930793,"rank":83,"remainingConfigurations":444},{"removed":"deepswe","score":0.30096847026712903,"rank":102,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.37671591296154733,"rank":93,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3719296438460827,"rank":94,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3395361090495424,"rank":106,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.37471917273102506,"rank":93,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3731327913782207,"rank":93,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.37659654599948517,"rank":93,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3760220478130179,"rank":91,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3769754979629297,"rank":93,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3747101218538234,"rank":91,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3790169578122396,"rank":92,"remainingConfigurations":444},{"removed":"livebench-data","score":0.37653193093870846,"rank":92,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.37305013327490727,"rank":92,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.37542622733134245,"rank":92,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.38101157298324256,"rank":92,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.37284350077024997,"rank":93,"remainingConfigurations":444},{"removed":"frontiermath","score":0.37574942616386525,"rank":92,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3722316551487703,"rank":94,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3861530174903138,"rank":90,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3761815285296876,"rank":92,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.37586874007060284,"rank":94,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3762156182917507,"rank":93,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.37605902647263373,"rank":93,"remainingConfigurations":444},{"removed":"vibe-code","score":0.37517857885235095,"rank":94,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3763752390821662,"rank":93,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-large-4--effort-reasoning":{"score":0.37383073591914656,"rank":94,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4365796067263077,"rank":91,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3298300952530859,"rank":94,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.37265114065146987,"rank":95,"remainingConfigurations":444},{"removed":"Scale","score":0.39621500852962216,"rank":93,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3740333007240641,"rank":95,"remainingConfigurations":444},{"removed":"Cognition","score":0.3585583602295627,"rank":98,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3833371557979697,"rank":91,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3758342509086656,"rank":91,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3798229123718077,"rank":95,"remainingConfigurations":431},{"removed":"Vals AI","score":0.36509741958119313,"rank":94,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.37361759887716833,"rank":94,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3676555605883642,"rank":94,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3731085320438488,"rank":94,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.37383073591914656,"rank":94,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.37576327917060787,"rank":94,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3687275886805151,"rank":94,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.37698506905283446,"rank":94,"remainingConfigurations":444},{"removed":"briefcase","score":0.35921912100015874,"rank":98,"remainingConfigurations":444},{"removed":"aime","score":0.3718425236705049,"rank":95,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3765305177317424,"rank":94,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3636552821984784,"rank":98,"remainingConfigurations":444},{"removed":"automationbench","score":0.34150456843367466,"rank":105,"remainingConfigurations":444},{"removed":"critpt","score":0.38510776699189453,"rank":90,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.37517303354247605,"rank":94,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.36751891879128634,"rank":96,"remainingConfigurations":444},{"removed":"gdpval","score":0.3666490744119321,"rank":96,"remainingConfigurations":444},{"removed":"gmmlu","score":0.37399329966462364,"rank":94,"remainingConfigurations":444},{"removed":"gpqa","score":0.3683977488034002,"rank":94,"remainingConfigurations":444},{"removed":"harvey","score":0.35049221137423675,"rank":100,"remainingConfigurations":444},{"removed":"hle","score":0.39983133275969185,"rank":88,"remainingConfigurations":444},{"removed":"ifbench","score":0.36734395509172185,"rank":95,"remainingConfigurations":444},{"removed":"itbench","score":0.37440133030935724,"rank":94,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3719126197823825,"rank":95,"remainingConfigurations":444},{"removed":"math500","score":0.37325401131249675,"rank":94,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.37749220497792835,"rank":95,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.409060364255051,"rank":88,"remainingConfigurations":444},{"removed":"omniscience","score":0.43943025853809575,"rank":84,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3706111065844014,"rank":95,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.37733180210708656,"rank":94,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3631969203324838,"rank":102,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4237227101021197,"rank":91,"remainingConfigurations":444},{"removed":"deepswe","score":0.3299889730669729,"rank":94,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3738925828109998,"rank":94,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.37112266638073704,"rank":95,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3585583602295627,"rank":98,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.37208081275921345,"rank":94,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3711627342813386,"rank":94,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3735237019116622,"rank":94,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3727547044270468,"rank":94,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3738162710458272,"rank":94,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.37183621390843996,"rank":92,"remainingConfigurations":444},{"removed":"livebench-language","score":0.37698100937193485,"rank":93,"remainingConfigurations":444},{"removed":"livebench-data","score":0.37393619700226743,"rank":94,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3698073634265368,"rank":94,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.37263872725454594,"rank":93,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3777128332666286,"rank":93,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3758342509086656,"rank":91,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3742922599095597,"rank":95,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.36522214934081526,"rank":96,"remainingConfigurations":444},{"removed":"simpleqa","score":0.38282465959969575,"rank":92,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3732509499236311,"rank":93,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3731915257928981,"rank":95,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.37305497979393126,"rank":94,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3736295486779749,"rank":95,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3725283664065521,"rank":95,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.37325787721159814,"rank":94,"remainingConfigurations":444}],"sharedOrderConflicts":1},"glm-5.3-flash--effort-max":{"score":0.37240665773221826,"rank":95,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.37279529755561663,"rank":85,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.38638950390422416,"rank":99,"remainingConfigurations":444},{"removed":"Datacurve","score":0.25010819197376616,"rank":113,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.37267079422764265,"rank":94,"remainingConfigurations":444},{"removed":"Scale","score":0.3926492689357783,"rank":94,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.37082845613367804,"rank":98,"remainingConfigurations":444},{"removed":"Cognition","score":0.39553708095725276,"rank":85,"remainingConfigurations":444},{"removed":"LiveBench","score":0.38374040061264597,"rank":90,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.36635905967666965,"rank":95,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.43596031798151985,"rank":82,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3714176167758003,"rank":90,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.37244183769558975,"rank":95,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3671209340728189,"rank":95,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.37290391619954316,"rank":95,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.37240665773221826,"rank":95,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.37289270337114555,"rank":95,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3681960849410794,"rank":95,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.37258476193052587,"rank":95,"remainingConfigurations":444},{"removed":"briefcase","score":0.37171271732886924,"rank":93,"remainingConfigurations":444},{"removed":"aime","score":0.3602531641316797,"rank":99,"remainingConfigurations":444},{"removed":"apex-agents","score":0.37319307427374787,"rank":95,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3724682304757274,"rank":94,"remainingConfigurations":444},{"removed":"automationbench","score":0.3708101198236781,"rank":94,"remainingConfigurations":444},{"removed":"critpt","score":0.3731352960735714,"rank":95,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3723466953055889,"rank":95,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.37378732349364685,"rank":93,"remainingConfigurations":444},{"removed":"gdpval","score":0.3718890781220625,"rank":94,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3724415749693299,"rank":95,"remainingConfigurations":444},{"removed":"gpqa","score":0.35770069410870287,"rank":97,"remainingConfigurations":444},{"removed":"harvey","score":0.36573297805930577,"rank":94,"remainingConfigurations":444},{"removed":"hle","score":0.3821238017723653,"rank":93,"remainingConfigurations":444},{"removed":"ifbench","score":0.3712547404783997,"rank":94,"remainingConfigurations":444},{"removed":"itbench","score":0.37167757020753994,"rank":95,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3726611217579448,"rank":94,"remainingConfigurations":444},{"removed":"math500","score":0.3724331182958129,"rank":95,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3841006349800016,"rank":90,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3838381682933482,"rank":95,"remainingConfigurations":444},{"removed":"omniscience","score":0.3724797562223135,"rank":95,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3710007056850955,"rank":94,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.37286443881875236,"rank":95,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.37818470452759895,"rank":94,"remainingConfigurations":444},{"removed":"arc-agi","score":0.36822035415287885,"rank":104,"remainingConfigurations":444},{"removed":"deepswe","score":0.25028962289039564,"rank":113,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3725115703474297,"rank":95,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.36695738144989415,"rank":96,"remainingConfigurations":444},{"removed":"frontiercode","score":0.39553708095725276,"rank":85,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3718245085725376,"rank":95,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3697476305572472,"rank":95,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3723752491740968,"rank":95,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.37093742040599215,"rank":95,"remainingConfigurations":444},{"removed":"livebench-math","score":0.37302017419869316,"rank":95,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.37095994292817536,"rank":93,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3742552813735387,"rank":95,"remainingConfigurations":444},{"removed":"livebench-data","score":0.37379414413820294,"rank":95,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3687036227040818,"rank":95,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3712848550910855,"rank":94,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3748166845246405,"rank":94,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.36635905967666965,"rank":95,"remainingConfigurations":444},{"removed":"frontiermath","score":0.37280575628435325,"rank":96,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.394322850919643,"rank":88,"remainingConfigurations":444},{"removed":"simpleqa","score":0.37795987426598865,"rank":94,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.36007519906738256,"rank":97,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.37672560887505163,"rank":93,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3626659216854147,"rank":98,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3756499035835204,"rank":94,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3785735386558704,"rank":92,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3700873838092212,"rank":95,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.7-flash--effort-low":{"score":0.366381985517889,"rank":96,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3601026212286733,"rank":88,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4642664681697341,"rank":85,"remainingConfigurations":444},{"removed":"Datacurve","score":0.29404244908879545,"rank":105,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3666634285020796,"rank":97,"remainingConfigurations":444},{"removed":"Scale","score":0.38885584896489483,"rank":95,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3628167152337622,"rank":101,"remainingConfigurations":444},{"removed":"Cognition","score":0.33321801208309804,"rank":111,"remainingConfigurations":444},{"removed":"LiveBench","score":0.37706726990139766,"rank":92,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3604922929675751,"rank":97,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.37813268394851746,"rank":96,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3582765579776345,"rank":97,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3664382977960389,"rank":96,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3614015944280801,"rank":96,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3664585754859895,"rank":96,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.366381985517889,"rank":96,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3669745088126947,"rank":97,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3621853757035991,"rank":97,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3669789831391817,"rank":96,"remainingConfigurations":444},{"removed":"briefcase","score":0.3651670473299184,"rank":96,"remainingConfigurations":444},{"removed":"aime","score":0.36349036605767465,"rank":98,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3677321491233078,"rank":96,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.36733042417161893,"rank":95,"remainingConfigurations":444},{"removed":"automationbench","score":0.3644365909638305,"rank":95,"remainingConfigurations":444},{"removed":"critpt","score":0.37123248111572393,"rank":96,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3662145886517129,"rank":96,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3678311226890412,"rank":95,"remainingConfigurations":444},{"removed":"gdpval","score":0.36683275329699944,"rank":95,"remainingConfigurations":444},{"removed":"gmmlu","score":0.36646382285861795,"rank":96,"remainingConfigurations":444},{"removed":"gpqa","score":0.3639857651398913,"rank":95,"remainingConfigurations":444},{"removed":"harvey","score":0.36336205599343,"rank":95,"remainingConfigurations":444},{"removed":"hle","score":0.3802628372502559,"rank":94,"remainingConfigurations":444},{"removed":"ifbench","score":0.3640439149482754,"rank":96,"remainingConfigurations":444},{"removed":"itbench","score":0.3656861359887074,"rank":96,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3666038436473995,"rank":97,"remainingConfigurations":444},{"removed":"math500","score":0.3663629054001803,"rank":96,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3721844013746128,"rank":96,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3736258344862063,"rank":98,"remainingConfigurations":444},{"removed":"omniscience","score":0.36256183147751764,"rank":98,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3663222765381018,"rank":96,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.367150130759059,"rank":96,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.36410744988221566,"rank":101,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4417582471731302,"rank":87,"remainingConfigurations":444},{"removed":"deepswe","score":0.29413068882335286,"rank":105,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3664440517329261,"rank":96,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3551911188827243,"rank":100,"remainingConfigurations":444},{"removed":"frontiercode","score":0.33321801208309804,"rank":111,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3651733521457237,"rank":96,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3634475757264499,"rank":96,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3663420766023772,"rank":96,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3656626643758667,"rank":96,"remainingConfigurations":444},{"removed":"livebench-math","score":0.366754883085177,"rank":97,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.36469521184349474,"rank":96,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3684914516207871,"rank":96,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3671649200180033,"rank":97,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3627270712547784,"rank":97,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.36509679174150006,"rank":96,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3697233141497307,"rank":96,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3604922929675751,"rank":97,"remainingConfigurations":444},{"removed":"frontiermath","score":0.36649177198561134,"rank":97,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3608899837985727,"rank":98,"remainingConfigurations":444},{"removed":"simpleqa","score":0.37448448928273903,"rank":95,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3649834657535275,"rank":95,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.36606764589147117,"rank":97,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3655683407253741,"rank":96,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.36627919130342196,"rank":96,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3653852240269675,"rank":97,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.36547656638093184,"rank":97,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k3--effort-high":{"score":0.3654281932425015,"rank":97,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.34564682865946955,"rank":91,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.5220639518406477,"rank":69,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3112437719001709,"rank":97,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.36669079304684266,"rank":96,"remainingConfigurations":444},{"removed":"Scale","score":0.3853645069151294,"rank":96,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.363156148441855,"rank":100,"remainingConfigurations":444},{"removed":"Cognition","score":0.3583156852491947,"rank":99,"remainingConfigurations":444},{"removed":"LiveBench","score":0.36671600234769236,"rank":96,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.36211752284262877,"rank":96,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.34665226782151043,"rank":104,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3513190960540986,"rank":100,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3653613476545053,"rank":97,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.36086777594799563,"rank":97,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3651888997838079,"rank":97,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3654281932425015,"rank":97,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.36731762441961946,"rank":96,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3624957957813166,"rank":96,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3661979547505356,"rank":97,"remainingConfigurations":444},{"removed":"briefcase","score":0.36393310805687257,"rank":97,"remainingConfigurations":444},{"removed":"aime","score":0.3751868185200015,"rank":93,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3668640829819336,"rank":97,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3645041464340828,"rank":97,"remainingConfigurations":444},{"removed":"automationbench","score":0.36411503517192495,"rank":96,"remainingConfigurations":444},{"removed":"critpt","score":0.3650031560518703,"rank":98,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.36525852319566615,"rank":97,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.36662969958747404,"rank":97,"remainingConfigurations":444},{"removed":"gdpval","score":0.36468544891969423,"rank":97,"remainingConfigurations":444},{"removed":"gmmlu","score":0.36554560669924147,"rank":97,"remainingConfigurations":444},{"removed":"gpqa","score":0.3545113102472854,"rank":99,"remainingConfigurations":444},{"removed":"harvey","score":0.36295952935862924,"rank":96,"remainingConfigurations":444},{"removed":"hle","score":0.3773011689311449,"rank":96,"remainingConfigurations":444},{"removed":"ifbench","score":0.363625149211162,"rank":97,"remainingConfigurations":444},{"removed":"itbench","score":0.36477520041507483,"rank":97,"remainingConfigurations":444},{"removed":"livecodebench","score":0.36671839954447694,"rank":96,"remainingConfigurations":444},{"removed":"math500","score":0.36549825193226737,"rank":97,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.37058623769634064,"rank":97,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3780763433529078,"rank":96,"remainingConfigurations":444},{"removed":"omniscience","score":0.3630723354712193,"rank":97,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3639487659775809,"rank":97,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3663094289858528,"rank":97,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3641604904733044,"rank":100,"remainingConfigurations":444},{"removed":"arc-agi","score":0.5134002229272366,"rank":69,"remainingConfigurations":444},{"removed":"deepswe","score":0.3113054975809662,"rank":97,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3654598855179733,"rank":97,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.35838982290378424,"rank":99,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3583156852491947,"rank":99,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3633790239506638,"rank":98,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3626348173365867,"rank":97,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.365094506872835,"rank":97,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.36419206689814637,"rank":97,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3657477478242432,"rank":98,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.36335642552920544,"rank":98,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3678188072119856,"rank":97,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3653443592645024,"rank":98,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3618932130711305,"rank":98,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.364251781450291,"rank":97,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.36952181498992215,"rank":97,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.36211752284262877,"rank":96,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3660994807175997,"rank":98,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.35245356889263263,"rank":99,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3731875871995221,"rank":96,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.36477497986476104,"rank":96,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3647642708170616,"rank":98,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3647308480508631,"rank":97,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.36509662188369846,"rank":97,"remainingConfigurations":444},{"removed":"vibe-code","score":0.36420258522972776,"rank":98,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.36480622879754804,"rank":98,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.6-flash--effort-high":{"score":0.3643792951636686,"rank":98,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.366428995525031,"rank":87,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4009860715809332,"rank":97,"remainingConfigurations":444},{"removed":"Datacurve","score":0.34126469196592457,"rank":93,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.36444353797503437,"rank":98,"remainingConfigurations":444},{"removed":"Scale","score":0.3834866182230634,"rank":97,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.36431115089589167,"rank":99,"remainingConfigurations":444},{"removed":"Cognition","score":0.3632001271899538,"rank":97,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3592051258757072,"rank":99,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3584481153738945,"rank":98,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3607922821851029,"rank":100,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3527795690661412,"rank":99,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.364424708653501,"rank":98,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3597356152975759,"rank":98,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.36467914891430536,"rank":98,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3643792951636686,"rank":98,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3650106800011885,"rank":98,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3607542343488026,"rank":98,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.36451341480356625,"rank":98,"remainingConfigurations":444},{"removed":"briefcase","score":0.36545488178218055,"rank":95,"remainingConfigurations":444},{"removed":"aime","score":0.36591025083168954,"rank":97,"remainingConfigurations":444},{"removed":"apex-agents","score":0.36513389483642306,"rank":98,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3652496324278985,"rank":96,"remainingConfigurations":444},{"removed":"automationbench","score":0.3622366252331867,"rank":97,"remainingConfigurations":444},{"removed":"critpt","score":0.3658384761453651,"rank":97,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3642740452321682,"rank":98,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3652997131974303,"rank":98,"remainingConfigurations":444},{"removed":"gdpval","score":0.36426366999532994,"rank":98,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3644320264042937,"rank":98,"remainingConfigurations":444},{"removed":"gpqa","score":0.356340496210709,"rank":98,"remainingConfigurations":444},{"removed":"harvey","score":0.36272292524059524,"rank":97,"remainingConfigurations":444},{"removed":"hle","score":0.374055650815103,"rank":97,"remainingConfigurations":444},{"removed":"ifbench","score":0.3627073530085399,"rank":98,"remainingConfigurations":444},{"removed":"itbench","score":0.36372406246907046,"rank":98,"remainingConfigurations":444},{"removed":"livecodebench","score":0.36446117385479754,"rank":98,"remainingConfigurations":444},{"removed":"math500","score":0.36442488363279346,"rank":98,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3652706242192935,"rank":98,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3744977345776817,"rank":97,"remainingConfigurations":444},{"removed":"omniscience","score":0.36437473913359275,"rank":96,"remainingConfigurations":444},{"removed":"tau-bench","score":0.36345089291158766,"rank":98,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.36493759397004116,"rank":98,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3644794290696987,"rank":99,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3854558405859056,"rank":97,"remainingConfigurations":444},{"removed":"deepswe","score":0.3414660112813425,"rank":93,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.36448252729875324,"rank":98,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.36040859797878605,"rank":97,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3632001271899538,"rank":97,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.36344639141931295,"rank":97,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.36188127083323357,"rank":98,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3642539078792315,"rank":98,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3629734753967915,"rank":98,"remainingConfigurations":444},{"removed":"livebench-math","score":0.36953839639737124,"rank":96,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3643163503873403,"rank":97,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3591728529528761,"rank":99,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3697730657296843,"rank":96,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3675288100418041,"rank":96,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3628741064402938,"rank":98,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3575416247469187,"rank":100,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3584481153738945,"rank":98,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3744905632292137,"rank":93,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3631065758256518,"rank":97,"remainingConfigurations":444},{"removed":"simpleqa","score":0.35879288514400304,"rank":101,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.356974115076701,"rank":99,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.36686166733825587,"rank":96,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.368390242119184,"rank":95,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3619254234334756,"rank":98,"remainingConfigurations":444},{"removed":"vibe-code","score":0.36624759248099564,"rank":96,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3682046695545255,"rank":96,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-flash--effort-max":{"score":0.35729123718458095,"rank":99,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.35667688882413867,"rank":89,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.36573063014306845,"rank":108,"remainingConfigurations":444},{"removed":"Datacurve","score":0.32038424901495305,"rank":96,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3572204430113302,"rank":99,"remainingConfigurations":444},{"removed":"Scale","score":0.379174641334652,"rank":99,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.35654593208397384,"rank":104,"remainingConfigurations":444},{"removed":"Cognition","score":0.34808486079543166,"rank":103,"remainingConfigurations":444},{"removed":"LiveBench","score":0.365317330546235,"rank":97,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.35118113958009256,"rank":99,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.38057452584930657,"rank":94,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3461030212879875,"rank":101,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3573275814526576,"rank":99,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3520051573386492,"rank":100,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3581576792475097,"rank":99,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.35729123718458095,"rank":99,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3581200874420214,"rank":99,"remainingConfigurations":444},{"removed":"All provider reports","score":0.35379481212788216,"rank":100,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.35785823056985683,"rank":99,"remainingConfigurations":444},{"removed":"briefcase","score":0.3550954399651942,"rank":99,"remainingConfigurations":444},{"removed":"aime","score":0.35237851035424245,"rank":101,"remainingConfigurations":444},{"removed":"apex-agents","score":0.35842434936232753,"rank":99,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.35873096983637787,"rank":99,"remainingConfigurations":444},{"removed":"automationbench","score":0.35361060817488915,"rank":98,"remainingConfigurations":444},{"removed":"critpt","score":0.35682081957865464,"rank":99,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.35713447847115737,"rank":99,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.36425972913263177,"rank":99,"remainingConfigurations":444},{"removed":"gdpval","score":0.3545485670521891,"rank":99,"remainingConfigurations":444},{"removed":"gmmlu","score":0.35738295540747383,"rank":99,"remainingConfigurations":444},{"removed":"gpqa","score":0.34728750073721293,"rank":103,"remainingConfigurations":444},{"removed":"harvey","score":0.35432339884863606,"rank":98,"remainingConfigurations":444},{"removed":"hle","score":0.36776405424965536,"rank":98,"remainingConfigurations":444},{"removed":"ifbench","score":0.3555229635976657,"rank":100,"remainingConfigurations":444},{"removed":"itbench","score":0.3565248575246352,"rank":99,"remainingConfigurations":444},{"removed":"livecodebench","score":0.35733330657771356,"rank":99,"remainingConfigurations":444},{"removed":"math500","score":0.35738283146957456,"rank":99,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.36229904248930406,"rank":99,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.36942418566720886,"rank":99,"remainingConfigurations":444},{"removed":"omniscience","score":0.359057835788071,"rank":99,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3532572970095549,"rank":101,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.35824704706703336,"rank":99,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.358241632692133,"rank":104,"remainingConfigurations":444},{"removed":"arc-agi","score":0.35935424389644033,"rank":107,"remainingConfigurations":444},{"removed":"deepswe","score":0.32060146856186045,"rank":96,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3573832511619797,"rank":99,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3548101345622962,"rank":101,"remainingConfigurations":444},{"removed":"frontiercode","score":0.34808486079543166,"rank":103,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3568219745971322,"rank":99,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3545445171205856,"rank":99,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3572118974275382,"rank":99,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.35615702086079,"rank":99,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3578032910516408,"rank":99,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3554357071294633,"rank":99,"remainingConfigurations":444},{"removed":"livebench-language","score":0.35959353154268614,"rank":98,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3580769097914578,"rank":99,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.35360654333359826,"rank":100,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.35608213184669646,"rank":100,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.36040954907706224,"rank":99,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.35118113958009256,"rank":99,"remainingConfigurations":444},{"removed":"frontiermath","score":0.36359922327674843,"rank":99,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.33763340426435434,"rank":103,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3819171039018186,"rank":93,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.35584959781382935,"rank":100,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3573457509162899,"rank":99,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3562596106578091,"rank":100,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3573158166819259,"rank":99,"remainingConfigurations":444},{"removed":"vibe-code","score":0.35644091900446656,"rank":99,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3568476813290047,"rank":100,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-max":{"score":0.35430256015619194,"rank":100,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3436417840505383,"rank":92,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4143178250572664,"rank":94,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3026854782449009,"rank":101,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3542736603051526,"rank":100,"remainingConfigurations":444},{"removed":"Scale","score":0.3738816933433216,"rank":102,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3745296394869659,"rank":94,"remainingConfigurations":444},{"removed":"Cognition","score":0.3151864230069154,"rank":113,"remainingConfigurations":444},{"removed":"LiveBench","score":0.37112566155609755,"rank":93,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.35024335897846326,"rank":101,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.37325380745884235,"rank":97,"remainingConfigurations":431},{"removed":"Vals AI","score":0.33180000692311756,"rank":103,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3541633463576892,"rank":100,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3501790044864596,"rank":101,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3538305117970742,"rank":100,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.35430256015619194,"rank":100,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3569425101285347,"rank":100,"remainingConfigurations":444},{"removed":"All provider reports","score":0.352209639485997,"rank":101,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3531267422024898,"rank":102,"remainingConfigurations":444},{"removed":"briefcase","score":0.3539867817722275,"rank":100,"remainingConfigurations":444},{"removed":"aime","score":0.3410798692374826,"rank":104,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3551356284850136,"rank":100,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.35485659054700985,"rank":100,"remainingConfigurations":444},{"removed":"automationbench","score":0.35309420270558545,"rank":99,"remainingConfigurations":444},{"removed":"critpt","score":0.355151293829508,"rank":100,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3547237692266878,"rank":100,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3536995144335769,"rank":101,"remainingConfigurations":444},{"removed":"gdpval","score":0.35410292144089855,"rank":100,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3543699168358155,"rank":100,"remainingConfigurations":444},{"removed":"gpqa","score":0.34934418494296954,"rank":102,"remainingConfigurations":444},{"removed":"harvey","score":0.3498947035109929,"rank":103,"remainingConfigurations":444},{"removed":"hle","score":0.3654899417280828,"rank":100,"remainingConfigurations":444},{"removed":"ifbench","score":0.35296179297738667,"rank":101,"remainingConfigurations":444},{"removed":"itbench","score":0.3537653122225786,"rank":100,"remainingConfigurations":444},{"removed":"livecodebench","score":0.35425484697924653,"rank":100,"remainingConfigurations":444},{"removed":"math500","score":0.3543239817518187,"rank":100,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.35991776747077825,"rank":100,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.366878894582582,"rank":100,"remainingConfigurations":444},{"removed":"omniscience","score":0.35660479005090595,"rank":100,"remainingConfigurations":444},{"removed":"tau-bench","score":0.35342856495388536,"rank":100,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.35372646446287276,"rank":101,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3762773670632258,"rank":95,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3721462009985823,"rank":102,"remainingConfigurations":444},{"removed":"deepswe","score":0.30264903889596234,"rank":101,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.35435092182674516,"rank":100,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.37753679275806107,"rank":92,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3151864230069154,"rank":113,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.35309437353630035,"rank":100,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.35168384179150497,"rank":100,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3540432145804884,"rank":100,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.35323927065998495,"rank":100,"remainingConfigurations":444},{"removed":"livebench-math","score":0.35606451847436366,"rank":100,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3464068247072503,"rank":103,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3553454589051501,"rank":101,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3472867629579833,"rank":102,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3501433641592257,"rank":102,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3572661513824726,"rank":99,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3676296886660191,"rank":98,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.35024335897846326,"rank":101,"remainingConfigurations":444},{"removed":"frontiermath","score":0.33794493453466035,"rank":105,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3743445207196712,"rank":93,"remainingConfigurations":444},{"removed":"simpleqa","score":0.36737633228798233,"rank":99,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.35964765934944243,"rank":98,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.35090988115699445,"rank":102,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.36064945655926994,"rank":99,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3465246288073332,"rank":103,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3474140427449142,"rank":103,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3577411943817339,"rank":99,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-high":{"score":0.35298176806508647,"rank":101,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3543157684318439,"rank":90,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.34130800313085446,"rank":116,"remainingConfigurations":444},{"removed":"Datacurve","score":0.28987252554649096,"rank":107,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3529263687658051,"rank":101,"remainingConfigurations":444},{"removed":"Scale","score":0.3742661905430598,"rank":100,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3500953548102432,"rank":106,"remainingConfigurations":444},{"removed":"Cognition","score":0.3922875310066214,"rank":87,"remainingConfigurations":444},{"removed":"LiveBench","score":0.364558944763844,"rank":98,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3477586208043674,"rank":102,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.36079962202692584,"rank":99,"remainingConfigurations":431},{"removed":"Vals AI","score":0.34325751357179524,"rank":102,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3529843446591119,"rank":101,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3486306034876418,"rank":102,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.35285349719031484,"rank":101,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.35298176806508647,"rank":101,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3560310772640422,"rank":101,"remainingConfigurations":444},{"removed":"All provider reports","score":0.35159001658454864,"rank":102,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3536478119441316,"rank":100,"remainingConfigurations":444},{"removed":"briefcase","score":0.3518293523344707,"rank":101,"remainingConfigurations":444},{"removed":"aime","score":0.3503200862766094,"rank":102,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3544238654160936,"rank":101,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.35409311104291447,"rank":101,"remainingConfigurations":444},{"removed":"automationbench","score":0.35119362936761744,"rank":101,"remainingConfigurations":444},{"removed":"critpt","score":0.3504975229178568,"rank":102,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3529085248020239,"rank":101,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3491270198104724,"rank":102,"remainingConfigurations":444},{"removed":"gdpval","score":0.351423111096598,"rank":101,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3531232892654232,"rank":101,"remainingConfigurations":444},{"removed":"gpqa","score":0.3503049802732318,"rank":101,"remainingConfigurations":444},{"removed":"harvey","score":0.3506194677544265,"rank":99,"remainingConfigurations":444},{"removed":"hle","score":0.364546520103945,"rank":102,"remainingConfigurations":444},{"removed":"ifbench","score":0.3573548797329435,"rank":99,"remainingConfigurations":444},{"removed":"itbench","score":0.35230568016561925,"rank":101,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3527606150087723,"rank":102,"remainingConfigurations":444},{"removed":"math500","score":0.3529105814647317,"rank":101,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.35817028703681103,"rank":101,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3645482513024145,"rank":102,"remainingConfigurations":444},{"removed":"omniscience","score":0.3509856303914316,"rank":101,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3572448764927392,"rank":99,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.35389731087655,"rank":100,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3510677280146896,"rank":106,"remainingConfigurations":444},{"removed":"arc-agi","score":0.39106271296435396,"rank":96,"remainingConfigurations":444},{"removed":"deepswe","score":0.28961483526838755,"rank":107,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.35301619625643826,"rank":101,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.35887195707999703,"rank":98,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3922875310066214,"rank":87,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3509569967727393,"rank":103,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3496338535266867,"rank":101,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.352919171691601,"rank":101,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3524048025800865,"rank":101,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3533097453096807,"rank":101,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.35082138749893393,"rank":101,"remainingConfigurations":444},{"removed":"livebench-language","score":0.35541156145223946,"rank":100,"remainingConfigurations":444},{"removed":"livebench-data","score":0.35281901307538993,"rank":100,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.34933051651720376,"rank":103,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.35180327086932994,"rank":101,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3573627970737925,"rank":101,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3477586208043674,"rank":102,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3519618569813862,"rank":100,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.34649406646606207,"rank":101,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3618055691689736,"rank":100,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.35253295094158194,"rank":101,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.35218983346904814,"rank":100,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3526292011786758,"rank":101,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3523127792943442,"rank":101,"remainingConfigurations":444},{"removed":"vibe-code","score":0.35148327368348453,"rank":101,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3527682257664863,"rank":101,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash--effort-low":{"score":0.3523442460739797,"rank":102,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3257195915795334,"rank":97,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.48871825315269235,"rank":76,"remainingConfigurations":444},{"removed":"Datacurve","score":0.30438586001024964,"rank":100,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.35267856776294976,"rank":102,"remainingConfigurations":444},{"removed":"Scale","score":0.3740387084779481,"rank":101,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3538833014615303,"rank":105,"remainingConfigurations":444},{"removed":"Cognition","score":0.3731182885089437,"rank":95,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3520659475647003,"rank":101,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3502837698916277,"rank":100,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.35447618250106866,"rank":98,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.35229550040652136,"rank":102,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.34730558612639933,"rank":103,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.35222339219203985,"rank":102,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3523442460739797,"rank":102,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3538923669905118,"rank":102,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3487446632492685,"rank":103,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3532536874259004,"rank":101,"remainingConfigurations":444},{"removed":"briefcase","score":0.3509018596170312,"rank":102,"remainingConfigurations":444},{"removed":"aime","score":0.38075446282039466,"rank":90,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3539501882104393,"rank":102,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3518574289049637,"rank":102,"remainingConfigurations":444},{"removed":"automationbench","score":0.35133223996654994,"rank":100,"remainingConfigurations":444},{"removed":"critpt","score":0.35222520095108134,"rank":101,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3524655578178421,"rank":102,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.35422243760262057,"rank":100,"remainingConfigurations":444},{"removed":"gdpval","score":0.3511481650343275,"rank":102,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3528398071448307,"rank":102,"remainingConfigurations":444},{"removed":"gpqa","score":0.35346482548812125,"rank":100,"remainingConfigurations":444},{"removed":"harvey","score":0.3500501614421701,"rank":101,"remainingConfigurations":444},{"removed":"hle","score":0.36491573167226715,"rank":101,"remainingConfigurations":444},{"removed":"ifbench","score":0.35090493049552135,"rank":102,"remainingConfigurations":444},{"removed":"itbench","score":0.35146523752208547,"rank":102,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3529266785421368,"rank":101,"remainingConfigurations":444},{"removed":"math500","score":0.3525809797857979,"rank":102,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3566091139531708,"rank":102,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3649979513832149,"rank":101,"remainingConfigurations":444},{"removed":"omniscience","score":0.34905038815858697,"rank":102,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3485307771424928,"rank":102,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3534542726039809,"rank":102,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3551095892187406,"rank":105,"remainingConfigurations":444},{"removed":"arc-agi","score":0.4777379682394414,"rank":77,"remainingConfigurations":444},{"removed":"deepswe","score":0.3045858239125949,"rank":100,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.35238771288293674,"rank":102,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.34676117766277675,"rank":102,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3731182885089437,"rank":95,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.35114053364091236,"rank":102,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.349548099336559,"rank":102,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.35210346108320745,"rank":102,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.35107495548963374,"rank":102,"remainingConfigurations":444},{"removed":"livebench-math","score":0.35295031433273244,"rank":102,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3497681991121154,"rank":102,"remainingConfigurations":444},{"removed":"livebench-language","score":0.35498413933853473,"rank":102,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3524306083711973,"rank":101,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3489321782615273,"rank":104,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3510251130761946,"rank":102,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3561976826430458,"rank":102,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3502837698916277,"rank":100,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3505014480754976,"rank":101,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.31327274036265124,"rank":111,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3554802456895845,"rank":103,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3518074710016031,"rank":102,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.35214350143219186,"rank":101,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3514714585985141,"rank":102,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3524229310558002,"rank":100,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3516844118181341,"rank":100,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.35152854384460736,"rank":102,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-pro--effort-high":{"score":0.3476286549515228,"rank":103,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3265541210301443,"rank":95,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.37291675465153973,"rank":106,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3912095725817328,"rank":80,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3474417190874158,"rank":103,"remainingConfigurations":444},{"removed":"Scale","score":0.3122958144814148,"rank":113,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.37304739744857857,"rank":96,"remainingConfigurations":444},{"removed":"Cognition","score":0.3400328315167733,"rank":105,"remainingConfigurations":444},{"removed":"LiveBench","score":0.33102830148519663,"rank":109,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.34522479103047615,"rank":103,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3186805971429245,"rank":110,"remainingConfigurations":431},{"removed":"Vals AI","score":0.36248001088413745,"rank":96,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3477046688172963,"rank":103,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.35384545037511567,"rank":99,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.34781552549863287,"rank":103,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3476286549515228,"rank":103,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3480512601951931,"rank":103,"remainingConfigurations":444},{"removed":"All provider reports","score":0.35449571322827267,"rank":99,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3477714841294584,"rank":103,"remainingConfigurations":444},{"removed":"briefcase","score":0.3486081417898053,"rank":103,"remainingConfigurations":444},{"removed":"aime","score":0.3542553700049236,"rank":100,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3462174534230644,"rank":103,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.34648934668556014,"rank":103,"remainingConfigurations":444},{"removed":"automationbench","score":0.34848507503336634,"rank":102,"remainingConfigurations":444},{"removed":"critpt","score":0.34774641537216916,"rank":103,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.34807333712898103,"rank":103,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.34849719941866336,"rank":103,"remainingConfigurations":444},{"removed":"gdpval","score":0.34771688073307844,"rank":103,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3476887201346524,"rank":103,"remainingConfigurations":444},{"removed":"gpqa","score":0.34427059021717765,"rank":105,"remainingConfigurations":444},{"removed":"harvey","score":0.34992680243221536,"rank":102,"remainingConfigurations":444},{"removed":"hle","score":0.3293712187858171,"rank":111,"remainingConfigurations":444},{"removed":"ifbench","score":0.3464177026641999,"rank":103,"remainingConfigurations":444},{"removed":"itbench","score":0.34851245271346015,"rank":103,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3478198857269239,"rank":103,"remainingConfigurations":444},{"removed":"math500","score":0.3478022409437284,"rank":103,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3412079084158206,"rank":105,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3303677193655689,"rank":112,"remainingConfigurations":444},{"removed":"omniscience","score":0.34814469024401284,"rank":103,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3457945964242795,"rank":103,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3483277712874995,"rank":103,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3727627491984767,"rank":97,"remainingConfigurations":444},{"removed":"arc-agi","score":0.36333188002297884,"rank":106,"remainingConfigurations":444},{"removed":"deepswe","score":0.3911871899284196,"rank":81,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3475918218585616,"rank":103,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3463846646444475,"rank":103,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3400328315167733,"rank":105,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.35239094985684094,"rank":101,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.34758251483596087,"rank":103,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.34707681835386484,"rank":103,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.34918314909362086,"rank":103,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3477283384732896,"rank":103,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.35178259923644556,"rank":100,"remainingConfigurations":444},{"removed":"livebench-language","score":0.34416520566071435,"rank":104,"remainingConfigurations":444},{"removed":"livebench-data","score":0.34628679203644513,"rank":103,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.35263249429754673,"rank":101,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.349792917616919,"rank":103,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.34105570789229583,"rank":106,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.34522479103047615,"rank":103,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3502152517957861,"rank":102,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.34991005387851426,"rank":100,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3388684399408503,"rank":107,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3484220409496483,"rank":103,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.34866742761507835,"rank":103,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.348376982237617,"rank":103,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.34861068351532604,"rank":102,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3492475567271076,"rank":102,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.34832546844948836,"rank":103,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-sonnet-5--effort-max":{"score":0.34355582708243687,"rank":104,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3344110874894113,"rank":94,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3738559066326383,"rank":105,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2907975866598905,"rank":106,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.343434763443075,"rank":104,"remainingConfigurations":444},{"removed":"Scale","score":0.3609939132588174,"rank":103,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3897509704629374,"rank":89,"remainingConfigurations":444},{"removed":"Cognition","score":0.3246482451911185,"rank":112,"remainingConfigurations":444},{"removed":"LiveBench","score":0.35785283404721074,"rank":100,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3381863362981162,"rank":104,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3935643097998999,"rank":90,"remainingConfigurations":431},{"removed":"Vals AI","score":0.28492831429310245,"rank":113,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3431520762066554,"rank":104,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3379794804223663,"rank":104,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3434917100283024,"rank":104,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.34355582708243687,"rank":104,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.343896697097843,"rank":104,"remainingConfigurations":444},{"removed":"All provider reports","score":0.33794052685955805,"rank":104,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3396051727095411,"rank":105,"remainingConfigurations":444},{"removed":"briefcase","score":0.3418469648518219,"rank":104,"remainingConfigurations":444},{"removed":"aime","score":0.34749248801274574,"rank":103,"remainingConfigurations":444},{"removed":"apex-agents","score":0.34454002093636943,"rank":104,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.34068025873937047,"rank":105,"remainingConfigurations":444},{"removed":"automationbench","score":0.3437183803739132,"rank":103,"remainingConfigurations":444},{"removed":"critpt","score":0.34444581312272265,"rank":104,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.34279344468780515,"rank":104,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.34699399636796874,"rank":104,"remainingConfigurations":444},{"removed":"gdpval","score":0.34244827550874396,"rank":104,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3436367084006933,"rank":104,"remainingConfigurations":444},{"removed":"gpqa","score":0.35900965740942675,"rank":96,"remainingConfigurations":444},{"removed":"harvey","score":0.3468109476815516,"rank":104,"remainingConfigurations":444},{"removed":"hle","score":0.35296399146065943,"rank":104,"remainingConfigurations":444},{"removed":"ifbench","score":0.34227357088674554,"rank":104,"remainingConfigurations":444},{"removed":"itbench","score":0.34336541468503584,"rank":104,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3434408615818451,"rank":104,"remainingConfigurations":444},{"removed":"math500","score":0.3435889117713223,"rank":104,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.35305772272409675,"rank":103,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.35815800737489845,"rank":103,"remainingConfigurations":444},{"removed":"omniscience","score":0.3464607505464021,"rank":104,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3417914670438338,"rank":104,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3436699845214111,"rank":104,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.38810238169391326,"rank":90,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3653445244815991,"rank":105,"remainingConfigurations":444},{"removed":"deepswe","score":0.2913392374376141,"rank":106,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3436090478006057,"rank":104,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.34177508221992836,"rank":104,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3246482451911185,"rank":112,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.34318262278150313,"rank":104,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3402418281572555,"rank":104,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.34402313421103775,"rank":104,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3419574214859045,"rank":104,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3432440471796631,"rank":104,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3401255737273874,"rank":104,"remainingConfigurations":444},{"removed":"livebench-language","score":0.34621440872335946,"rank":103,"remainingConfigurations":444},{"removed":"livebench-data","score":0.34557050687584173,"rank":104,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3399709246949447,"rank":105,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.34200669379326576,"rank":105,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3477728516456154,"rank":104,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3381863362981162,"rank":104,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3335463108711068,"rank":106,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.32326272836353315,"rank":108,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3566887803556678,"rank":102,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.34246948191111143,"rank":104,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.34098603442166636,"rank":104,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3394769186913102,"rank":105,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.342266070501811,"rank":104,"remainingConfigurations":444},{"removed":"vibe-code","score":0.33992838487895655,"rank":104,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.34491295963469676,"rank":104,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-haiku-5-5--effort-high":{"score":0.34056604028184706,"rank":105,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.30770031995478103,"rank":99,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.48077135014533606,"rank":80,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2979450294814542,"rank":104,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3410275288056626,"rank":105,"remainingConfigurations":444},{"removed":"Scale","score":0.3607452414376769,"rank":104,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3395111521506435,"rank":107,"remainingConfigurations":444},{"removed":"Cognition","score":0.2222918293533972,"rank":132,"remainingConfigurations":444},{"removed":"LiveBench","score":0.34509047981214597,"rank":104,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.337425865281791,"rank":105,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3607252857684719,"rank":101,"remainingConfigurations":431},{"removed":"Vals AI","score":0.32561620787786083,"rank":104,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3404411320065926,"rank":105,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.335522111372899,"rank":105,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.340178829268684,"rank":105,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.34056604028184706,"rank":105,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3419312400956715,"rank":105,"remainingConfigurations":444},{"removed":"All provider reports","score":0.33642988566055454,"rank":105,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.34163917323513937,"rank":104,"remainingConfigurations":444},{"removed":"briefcase","score":0.33422513342437193,"rank":105,"remainingConfigurations":444},{"removed":"aime","score":0.33717767105420043,"rank":106,"remainingConfigurations":444},{"removed":"apex-agents","score":0.34220174724178065,"rank":105,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.34275441423045555,"rank":104,"remainingConfigurations":444},{"removed":"automationbench","score":0.34259172648663333,"rank":104,"remainingConfigurations":444},{"removed":"critpt","score":0.3399062233941001,"rank":105,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.34098220828772857,"rank":105,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.34147500120923047,"rank":105,"remainingConfigurations":444},{"removed":"gdpval","score":0.33898558963175746,"rank":105,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3406436875585037,"rank":105,"remainingConfigurations":444},{"removed":"gpqa","score":0.341920482823357,"rank":106,"remainingConfigurations":444},{"removed":"harvey","score":0.33841248150538156,"rank":105,"remainingConfigurations":444},{"removed":"hle","score":0.35360092576793156,"rank":103,"remainingConfigurations":444},{"removed":"ifbench","score":0.3379588776431342,"rank":106,"remainingConfigurations":444},{"removed":"itbench","score":0.3404839097285606,"rank":105,"remainingConfigurations":444},{"removed":"livecodebench","score":0.34080565990258277,"rank":105,"remainingConfigurations":444},{"removed":"math500","score":0.34045792120845,"rank":105,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.34517229711891256,"rank":104,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.35408948640820026,"rank":104,"remainingConfigurations":444},{"removed":"omniscience","score":0.34525665192345795,"rank":105,"remainingConfigurations":444},{"removed":"tau-bench","score":0.33983144458474007,"rank":105,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3357535757233825,"rank":105,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3392679971943631,"rank":107,"remainingConfigurations":444},{"removed":"arc-agi","score":0.47330042194802785,"rank":80,"remainingConfigurations":444},{"removed":"deepswe","score":0.29809620376616597,"rank":104,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3406021105819028,"rank":105,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.32670711006186454,"rank":108,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2222918293533972,"rank":132,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.33859745503986155,"rank":105,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3374901024149122,"rank":105,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3402020606891005,"rank":105,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3391020731877013,"rank":105,"remainingConfigurations":444},{"removed":"livebench-math","score":0.34044885914010475,"rank":105,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3372407198340836,"rank":105,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3434671444297206,"rank":105,"remainingConfigurations":444},{"removed":"livebench-data","score":0.34118259660650035,"rank":105,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.33725988370673327,"rank":106,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.33880536222893826,"rank":106,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3455353473543701,"rank":105,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.337425865281791,"rank":105,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3400004702484493,"rank":103,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3399207135755355,"rank":102,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3481980142421966,"rank":104,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.34006101791706983,"rank":105,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.33983851535811976,"rank":105,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.33976770648889104,"rank":104,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.34004640788049195,"rank":105,"remainingConfigurations":444},{"removed":"vibe-code","score":0.33929021662774267,"rank":105,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.33982861618435195,"rank":105,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-7--effort-max":{"score":0.33492456408559734,"rank":106,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3261782443571586,"rank":96,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.362898976554487,"rank":109,"remainingConfigurations":444},{"removed":"Datacurve","score":0.29835850326674573,"rank":103,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.33470516792047134,"rank":106,"remainingConfigurations":444},{"removed":"Scale","score":0.3542582399829018,"rank":105,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.35660263275460574,"rank":103,"remainingConfigurations":444},{"removed":"Cognition","score":0.3373155874605514,"rank":110,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3439031920730978,"rank":105,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.33529772619345305,"rank":106,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.35959448957426193,"rank":102,"remainingConfigurations":431},{"removed":"Vals AI","score":0.285493845322182,"rank":112,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.33485553599069445,"rank":106,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3322784661490899,"rank":106,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3346364578286323,"rank":106,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.33492456408559734,"rank":106,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3355453522459353,"rank":106,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3325567270581081,"rank":106,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.33197392404228726,"rank":106,"remainingConfigurations":444},{"removed":"briefcase","score":0.33330547813915457,"rank":106,"remainingConfigurations":444},{"removed":"aime","score":0.3405256382398369,"rank":105,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3359105358771241,"rank":106,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.33586470192210394,"rank":106,"remainingConfigurations":444},{"removed":"automationbench","score":0.334426428441226,"rank":106,"remainingConfigurations":444},{"removed":"critpt","score":0.3359113100915909,"rank":106,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.33506136269961506,"rank":106,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3370952340343969,"rank":106,"remainingConfigurations":444},{"removed":"gdpval","score":0.33413304660041376,"rank":106,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3350831873320222,"rank":106,"remainingConfigurations":444},{"removed":"gpqa","score":0.3451451847651135,"rank":104,"remainingConfigurations":444},{"removed":"harvey","score":0.33357246073493435,"rank":106,"remainingConfigurations":444},{"removed":"hle","score":0.34298966323505137,"rank":105,"remainingConfigurations":444},{"removed":"ifbench","score":0.3396835226193953,"rank":105,"remainingConfigurations":444},{"removed":"itbench","score":0.3303139806392528,"rank":107,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3347849374457483,"rank":106,"remainingConfigurations":444},{"removed":"math500","score":0.3349893383348166,"rank":106,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3305288917577093,"rank":110,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.34578135664949405,"rank":105,"remainingConfigurations":444},{"removed":"omniscience","score":0.3346883332503494,"rank":106,"remainingConfigurations":444},{"removed":"tau-bench","score":0.33451937132979115,"rank":106,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3351556059476258,"rank":106,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3596301660423347,"rank":103,"remainingConfigurations":444},{"removed":"arc-agi","score":0.35490656238334545,"rank":108,"remainingConfigurations":444},{"removed":"deepswe","score":0.298480772141928,"rank":103,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3349203544832948,"rank":106,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.33313626258165746,"rank":106,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3373155874605514,"rank":110,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3334646269842419,"rank":106,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.33331669672222924,"rank":106,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3348565041085913,"rank":106,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.33321561617844264,"rank":106,"remainingConfigurations":444},{"removed":"livebench-math","score":0.33513353196276435,"rank":106,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.33243650913099393,"rank":106,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3371529284517629,"rank":106,"remainingConfigurations":444},{"removed":"livebench-data","score":0.33578334440462604,"rank":106,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3318534216125151,"rank":107,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.333740173814194,"rank":107,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.33835603687763766,"rank":107,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.33529772619345305,"rank":106,"remainingConfigurations":444},{"removed":"frontiermath","score":0.32042973199098373,"rank":111,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3291206813032536,"rank":105,"remainingConfigurations":444},{"removed":"simpleqa","score":0.34096814660574787,"rank":105,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.337005145487719,"rank":106,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.33192976019988146,"rank":106,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.33583247773955494,"rank":106,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.33512731296014936,"rank":107,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3382496242643798,"rank":106,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3324421187380443,"rank":106,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.5--effort-high":{"score":0.3309640230079927,"rank":107,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.31913545317507014,"rank":98,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3852346786681328,"rank":101,"remainingConfigurations":444},{"removed":"Datacurve","score":0.26836489962702087,"rank":111,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.33089894287159,"rank":107,"remainingConfigurations":444},{"removed":"Scale","score":0.3506773820148901,"rank":106,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3604943407075614,"rank":102,"remainingConfigurations":444},{"removed":"Cognition","score":0.3385984524289498,"rank":107,"remainingConfigurations":444},{"removed":"LiveBench","score":0.34337790540555013,"rank":106,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3124417256156843,"rank":110,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3347265530042712,"rank":107,"remainingConfigurations":431},{"removed":"Vals AI","score":0.31030048837411717,"rank":108,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.33090818527594773,"rank":107,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.32620257251839857,"rank":107,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3311877204363985,"rank":107,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3309640230079927,"rank":107,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.33160520655966347,"rank":107,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3270593540967864,"rank":107,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.33186798969840675,"rank":107,"remainingConfigurations":444},{"removed":"briefcase","score":0.32913303885352946,"rank":107,"remainingConfigurations":444},{"removed":"aime","score":0.32578377137065756,"rank":108,"remainingConfigurations":444},{"removed":"apex-agents","score":0.33196582284142495,"rank":107,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3332505098607253,"rank":108,"remainingConfigurations":444},{"removed":"automationbench","score":0.32749307974628183,"rank":108,"remainingConfigurations":444},{"removed":"critpt","score":0.3320990881187605,"rank":107,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3318337991912003,"rank":107,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.331877557210668,"rank":107,"remainingConfigurations":444},{"removed":"gdpval","score":0.32963212755824833,"rank":107,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3310999312787337,"rank":107,"remainingConfigurations":444},{"removed":"gpqa","score":0.32207339960535575,"rank":111,"remainingConfigurations":444},{"removed":"harvey","score":0.31986862626146495,"rank":111,"remainingConfigurations":444},{"removed":"hle","score":0.3416100282241969,"rank":107,"remainingConfigurations":444},{"removed":"ifbench","score":0.3294897549341301,"rank":107,"remainingConfigurations":444},{"removed":"itbench","score":0.3305716289560994,"rank":106,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3309473031461783,"rank":107,"remainingConfigurations":444},{"removed":"math500","score":0.3310065132431477,"rank":107,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3329241644911831,"rank":107,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3431264888506818,"rank":106,"remainingConfigurations":444},{"removed":"omniscience","score":0.33172521547421846,"rank":107,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3286764603581635,"rank":107,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3323635559550978,"rank":107,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.36691008632930733,"rank":98,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3728870379738694,"rank":101,"remainingConfigurations":444},{"removed":"deepswe","score":0.2684942806703337,"rank":111,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.33103571806541937,"rank":107,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.32811168559638754,"rank":107,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3385984524289498,"rank":107,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3293538689859304,"rank":107,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3283199314088244,"rank":107,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.33088616441502655,"rank":107,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3297672735300827,"rank":107,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3307275342659283,"rank":107,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.32958793771140954,"rank":107,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3336650910631295,"rank":107,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3319156678025775,"rank":107,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3270531303892458,"rank":108,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.330481835593877,"rank":108,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3333338344904422,"rank":108,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3124417256156843,"rank":110,"remainingConfigurations":444},{"removed":"frontiermath","score":0.33912583270071295,"rank":104,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.32596325182430935,"rank":106,"remainingConfigurations":444},{"removed":"simpleqa","score":0.34035497310082236,"rank":106,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3351213586341392,"rank":107,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.33078066379303916,"rank":107,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3298622532274738,"rank":107,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3351298165360426,"rank":106,"remainingConfigurations":444},{"removed":"vibe-code","score":0.33157358585714464,"rank":107,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3269781919531563,"rank":108,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-5-20251101--effort-thinking-64k":{"score":0.3289358744880357,"rank":108,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3399904677591284,"rank":93,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3667892894688291,"rank":107,"remainingConfigurations":444},{"removed":"Datacurve","score":0.28859994532359645,"rank":108,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3290607069356034,"rank":108,"remainingConfigurations":444},{"removed":"Scale","score":0.34847511499174266,"rank":107,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.32971042909535925,"rank":108,"remainingConfigurations":444},{"removed":"Cognition","score":0.33756683434749096,"rank":109,"remainingConfigurations":444},{"removed":"LiveBench","score":null,"rank":null,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3203302134382011,"rank":108,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3287834641263705,"rank":108,"remainingConfigurations":431},{"removed":"Vals AI","score":0.32395292630213685,"rank":105,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3289619578788018,"rank":108,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3260954727371106,"rank":108,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.32699560442906356,"rank":108,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3289358744880357,"rank":108,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.32931418464799894,"rank":108,"remainingConfigurations":444},{"removed":"All provider reports","score":0.32454118995682496,"rank":109,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.32847635435085043,"rank":108,"remainingConfigurations":444},{"removed":"briefcase","score":0.32804377156489944,"rank":108,"remainingConfigurations":444},{"removed":"aime","score":0.32671414020878636,"rank":107,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3292538637787817,"rank":108,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3296039154167268,"rank":109,"remainingConfigurations":444},{"removed":"automationbench","score":0.3285287580680826,"rank":107,"remainingConfigurations":444},{"removed":"critpt","score":0.3292227750358691,"rank":108,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3290138826042666,"rank":108,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3297132442888073,"rank":108,"remainingConfigurations":444},{"removed":"gdpval","score":0.3284487290615031,"rank":109,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3289462180922613,"rank":108,"remainingConfigurations":444},{"removed":"gpqa","score":0.3288541913976055,"rank":109,"remainingConfigurations":444},{"removed":"harvey","score":0.3264144888838912,"rank":107,"remainingConfigurations":444},{"removed":"hle","score":0.34200027603674976,"rank":106,"remainingConfigurations":444},{"removed":"ifbench","score":0.32711499223322216,"rank":108,"remainingConfigurations":444},{"removed":"itbench","score":0.3288909938626658,"rank":108,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3289789819260126,"rank":108,"remainingConfigurations":444},{"removed":"math500","score":0.32892884879494827,"rank":108,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3332383610375141,"rank":106,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3410081378221012,"rank":108,"remainingConfigurations":444},{"removed":"omniscience","score":0.3309032549541415,"rank":108,"remainingConfigurations":444},{"removed":"tau-bench","score":0.32789906852232936,"rank":108,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.32848385798638113,"rank":108,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3329503529074885,"rank":108,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3496696207576133,"rank":109,"remainingConfigurations":444},{"removed":"deepswe","score":0.2887427428663523,"rank":108,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3290934518686178,"rank":108,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3351964736522466,"rank":105,"remainingConfigurations":444},{"removed":"frontiercode","score":0.33756683434749096,"rank":109,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.32705083905814747,"rank":109,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.326806200749392,"rank":108,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3283646691896163,"rank":108,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3273354971380513,"rank":108,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3112274932545327,"rank":111,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.288859155595306,"rank":114,"remainingConfigurations":444},{"removed":"livebench-language","score":0.3026964925907101,"rank":112,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3289258974344769,"rank":108,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3704007825319982,"rank":93,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3490213874951158,"rank":104,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.35282547061441316,"rank":103,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3203302134382011,"rank":108,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3286449059808824,"rank":107,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3255458451053239,"rank":107,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3282298214711696,"rank":111,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3271426699044441,"rank":108,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.3292811560472075,"rank":108,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.32896991781682566,"rank":108,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.32845775859727283,"rank":108,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3271895388537662,"rank":108,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3290366908292098,"rank":107,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-7--effort-high":{"score":0.3269609272242716,"rank":109,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2926520888001392,"rank":101,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.34772485007246007,"rank":112,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3052338927791797,"rank":99,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.327127392067506,"rank":109,"remainingConfigurations":444},{"removed":"Scale","score":0.3466416438621993,"rank":109,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3184719950763911,"rank":109,"remainingConfigurations":444},{"removed":"Cognition","score":0.3897024771275863,"rank":90,"remainingConfigurations":444},{"removed":"LiveBench","score":0.33460552095833496,"rank":107,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.27297905322338567,"rank":121,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.34317964484618835,"rank":105,"remainingConfigurations":431},{"removed":"Vals AI","score":0.3162884381353855,"rank":106,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.32687286372806884,"rank":109,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3254148834084619,"rank":109,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.3265633723252343,"rank":109,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3269609272242716,"rank":109,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.32757725288593337,"rank":110,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3255302218823039,"rank":108,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3272515258458285,"rank":110,"remainingConfigurations":444},{"removed":"briefcase","score":0.3258917817789532,"rank":109,"remainingConfigurations":444},{"removed":"aime","score":0.3234042788339037,"rank":109,"remainingConfigurations":444},{"removed":"apex-agents","score":0.32827795611788374,"rank":110,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.32767809276060805,"rank":110,"remainingConfigurations":444},{"removed":"automationbench","score":0.3270087112254529,"rank":109,"remainingConfigurations":444},{"removed":"critpt","score":0.32665314682164526,"rank":110,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.3270359774367307,"rank":110,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3281387354967719,"rank":109,"remainingConfigurations":444},{"removed":"gdpval","score":0.32616223374649317,"rank":110,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3272441901205313,"rank":109,"remainingConfigurations":444},{"removed":"gpqa","score":0.32732738574874004,"rank":110,"remainingConfigurations":444},{"removed":"harvey","score":0.32496209758904815,"rank":109,"remainingConfigurations":444},{"removed":"hle","score":0.3384419491641035,"rank":109,"remainingConfigurations":444},{"removed":"ifbench","score":0.32580002410428827,"rank":109,"remainingConfigurations":444},{"removed":"itbench","score":0.3266003506622106,"rank":110,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3272177089553654,"rank":109,"remainingConfigurations":444},{"removed":"math500","score":0.3270142519308911,"rank":109,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.33217051805313336,"rank":108,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.339625012359349,"rank":109,"remainingConfigurations":444},{"removed":"omniscience","score":0.32558027238874737,"rank":111,"remainingConfigurations":444},{"removed":"tau-bench","score":0.32627534263385555,"rank":110,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.32623836045422605,"rank":109,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3218399579843427,"rank":109,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3429148983687457,"rank":110,"remainingConfigurations":444},{"removed":"deepswe","score":0.30517421868229766,"rank":99,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.3269198301664347,"rank":109,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.32450142563284584,"rank":109,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3897024771275863,"rank":90,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3289823889422672,"rank":108,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3189857606961563,"rank":111,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3272572848013094,"rank":109,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.32639887577702414,"rank":109,"remainingConfigurations":444},{"removed":"livebench-math","score":0.32709760332277327,"rank":108,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.32365713931331475,"rank":108,"remainingConfigurations":444},{"removed":"livebench-language","score":0.32908802516938845,"rank":109,"remainingConfigurations":444},{"removed":"livebench-data","score":0.327886758701828,"rank":109,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.32371836699330636,"rank":109,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3248665200370277,"rank":109,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.33242092338016443,"rank":109,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.27297905322338567,"rank":121,"remainingConfigurations":444},{"removed":"frontiermath","score":0.32594979991079237,"rank":108,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.3216991328468078,"rank":109,"remainingConfigurations":444},{"removed":"simpleqa","score":0.33483221451667916,"rank":109,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3252163552952733,"rank":110,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.326584673953988,"rank":109,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3262934770505108,"rank":109,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.3264825629030788,"rank":109,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3260731816804018,"rank":109,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.32642023432899364,"rank":109,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5-5--effort-medium":{"score":0.32678284268329194,"rank":110,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2664593642589874,"rank":104,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3461417041555202,"rank":114,"remainingConfigurations":444},{"removed":"Datacurve","score":0.28644957320574876,"rank":109,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3266217899757445,"rank":110,"remainingConfigurations":444},{"removed":"Scale","score":0.34741752983676477,"rank":108,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.3177730253637679,"rank":110,"remainingConfigurations":444},{"removed":"Cognition","score":0.4436124250692175,"rank":75,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3313434492558662,"rank":108,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3223620950760717,"rank":107,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.3544986561886048,"rank":103,"remainingConfigurations":431},{"removed":"Vals AI","score":0.31034762185732956,"rank":107,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3266907268610219,"rank":110,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.32179607703266466,"rank":110,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.32638557789982786,"rank":110,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.32678284268329194,"rank":110,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3278698005244104,"rank":109,"remainingConfigurations":444},{"removed":"All provider reports","score":0.322453867454993,"rank":110,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3282371040626069,"rank":109,"remainingConfigurations":444},{"removed":"briefcase","score":0.3195866176924966,"rank":112,"remainingConfigurations":444},{"removed":"aime","score":0.3230492330339714,"rank":110,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3288384817212414,"rank":109,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.33390381476036346,"rank":107,"remainingConfigurations":444},{"removed":"automationbench","score":0.32451898908620214,"rank":110,"remainingConfigurations":444},{"removed":"critpt","score":0.3284791350942935,"rank":109,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.32766844771525916,"rank":109,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.32581119660847185,"rank":110,"remainingConfigurations":444},{"removed":"gdpval","score":0.3287759211409634,"rank":108,"remainingConfigurations":444},{"removed":"gmmlu","score":0.32710763445573804,"rank":110,"remainingConfigurations":444},{"removed":"gpqa","score":0.33072267748986767,"rank":108,"remainingConfigurations":444},{"removed":"harvey","score":0.3254882329733768,"rank":108,"remainingConfigurations":444},{"removed":"hle","score":0.3408185295012081,"rank":108,"remainingConfigurations":444},{"removed":"ifbench","score":0.3245572705832711,"rank":110,"remainingConfigurations":444},{"removed":"itbench","score":0.32708203196776675,"rank":109,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3264502332284587,"rank":110,"remainingConfigurations":444},{"removed":"math500","score":0.32662955274431177,"rank":110,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.33122291398115034,"rank":109,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.34184362754176334,"rank":107,"remainingConfigurations":444},{"removed":"omniscience","score":0.3290480138347006,"rank":110,"remainingConfigurations":444},{"removed":"tau-bench","score":0.3266774025719377,"rank":109,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.3148036283569244,"rank":111,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3169320525583655,"rank":111,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3373828979091095,"rank":114,"remainingConfigurations":444},{"removed":"deepswe","score":0.28665793319162725,"rank":109,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.32682447846954144,"rank":110,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3234877626330867,"rank":110,"remainingConfigurations":444},{"removed":"frontiercode","score":0.4436124250692175,"rank":75,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.325425219249254,"rank":110,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.32351473257711344,"rank":109,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.32661761496601355,"rank":110,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.32524879001166335,"rank":110,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3265438571620352,"rank":109,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3229301325245826,"rank":109,"remainingConfigurations":444},{"removed":"livebench-language","score":0.33026295267246236,"rank":108,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3275847564311697,"rank":110,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.32321032794661714,"rank":110,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.32475653856410214,"rank":110,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3321857050337956,"rank":110,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3223620950760717,"rank":107,"remainingConfigurations":444},{"removed":"frontiermath","score":0.32565462436915255,"rank":109,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.33052493308267444,"rank":104,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3348860776516731,"rank":108,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3262798147240451,"rank":109,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.32606076180589155,"rank":110,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.3259014304081224,"rank":110,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.32624977262251165,"rank":110,"remainingConfigurations":444},{"removed":"vibe-code","score":0.3256077959498736,"rank":110,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3260106674484024,"rank":110,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-8--effort-low":{"score":0.3219597171358646,"rank":111,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3051437834744843,"rank":100,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.29458997397018644,"rank":128,"remainingConfigurations":444},{"removed":"Datacurve","score":0.3238168945718769,"rank":95,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3222497926865248,"rank":111,"remainingConfigurations":444},{"removed":"Scale","score":0.34275184990919594,"rank":110,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.31714990704436546,"rank":111,"remainingConfigurations":444},{"removed":"Cognition","score":0.35065017029103557,"rank":102,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3276671936415096,"rank":110,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.3155649494415628,"rank":109,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.33577907363417997,"rank":106,"remainingConfigurations":431},{"removed":"Vals AI","score":0.30555373701815053,"rank":109,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.32198261207448714,"rank":111,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.31731226219691916,"rank":111,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.32195194415455347,"rank":111,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.3219597171358646,"rank":111,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.3227583016448411,"rank":111,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3181781759884754,"rank":111,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.3223018254399061,"rank":111,"remainingConfigurations":444},{"removed":"briefcase","score":0.3201951041311201,"rank":111,"remainingConfigurations":444},{"removed":"aime","score":0.30789882827385046,"rank":111,"remainingConfigurations":444},{"removed":"apex-agents","score":0.32320722903725957,"rank":111,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.32212761804195117,"rank":111,"remainingConfigurations":444},{"removed":"automationbench","score":0.3212074718166155,"rank":111,"remainingConfigurations":444},{"removed":"critpt","score":0.3221428583658495,"rank":111,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.32190445472525475,"rank":111,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.32297311990617367,"rank":112,"remainingConfigurations":444},{"removed":"gdpval","score":0.3213719527061756,"rank":111,"remainingConfigurations":444},{"removed":"gmmlu","score":0.322098193419695,"rank":111,"remainingConfigurations":444},{"removed":"gpqa","score":0.33527552280387596,"rank":107,"remainingConfigurations":444},{"removed":"harvey","score":0.31997054279515386,"rank":110,"remainingConfigurations":444},{"removed":"hle","score":0.3342357663345405,"rank":110,"remainingConfigurations":444},{"removed":"ifbench","score":0.32085997736653765,"rank":111,"remainingConfigurations":444},{"removed":"itbench","score":0.32142017905140424,"rank":111,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3222523418738542,"rank":111,"remainingConfigurations":444},{"removed":"math500","score":0.321975272519819,"rank":111,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.32706627710224895,"rank":111,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.3343910128729595,"rank":111,"remainingConfigurations":444},{"removed":"omniscience","score":0.3210767798713472,"rank":112,"remainingConfigurations":444},{"removed":"tau-bench","score":0.32086726025886875,"rank":111,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.32163723940280353,"rank":110,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.31812685968818716,"rank":110,"remainingConfigurations":444},{"removed":"arc-agi","score":0.291280305173536,"rank":126,"remainingConfigurations":444},{"removed":"deepswe","score":0.323958825568309,"rank":95,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.32200963138315647,"rank":111,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.3201464822774997,"rank":111,"remainingConfigurations":444},{"removed":"frontiercode","score":0.35065017029103557,"rank":102,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.32028960923262945,"rank":111,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.319363027307939,"rank":110,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.32170733513606564,"rank":111,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.32012944315889286,"rank":111,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3221051794199183,"rank":110,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3188657758493976,"rank":110,"remainingConfigurations":444},{"removed":"livebench-language","score":0.32479072684111726,"rank":110,"remainingConfigurations":444},{"removed":"livebench-data","score":0.32264070350430923,"rank":111,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.3183942310680401,"rank":111,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.3203041773842021,"rank":111,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.32660313446374895,"rank":111,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.3155649494415628,"rank":109,"remainingConfigurations":444},{"removed":"frontiermath","score":0.3215833408385094,"rank":110,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.31935431716179136,"rank":110,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3300691406146633,"rank":110,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3212019275127718,"rank":111,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.32141580562249217,"rank":111,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.32109364826557063,"rank":111,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.32156002716640086,"rank":111,"remainingConfigurations":444},{"removed":"vibe-code","score":0.32088569635252595,"rank":111,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.3212729386094509,"rank":111,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-6--effort-high":{"score":0.31052716939616837,"rank":112,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.28730095420435603,"rank":102,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.289450547742784,"rank":129,"remainingConfigurations":444},{"removed":"Datacurve","score":0.27958703755577813,"rank":110,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.3107739367643057,"rank":112,"remainingConfigurations":444},{"removed":"Scale","score":0.3333287934210443,"rank":111,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.30882335584957943,"rank":112,"remainingConfigurations":444},{"removed":"Cognition","score":0.39869275010270916,"rank":84,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2873334848478046,"rank":114,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.29189753023282355,"rank":113,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.32647242079330274,"rank":109,"remainingConfigurations":431},{"removed":"Vals AI","score":0.30077710738962277,"rank":110,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.3105059686713971,"rank":112,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.3075256822792794,"rank":112,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.31005495679642253,"rank":112,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.31052716939616837,"rank":112,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.31146703021316097,"rank":112,"remainingConfigurations":444},{"removed":"All provider reports","score":0.3079830369993936,"rank":112,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.31079481347603105,"rank":112,"remainingConfigurations":444},{"removed":"briefcase","score":0.30999391568053036,"rank":114,"remainingConfigurations":444},{"removed":"aime","score":0.30756466132399995,"rank":112,"remainingConfigurations":444},{"removed":"apex-agents","score":0.3117460110750105,"rank":112,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.30988354630985265,"rank":112,"remainingConfigurations":444},{"removed":"automationbench","score":0.310063344300606,"rank":112,"remainingConfigurations":444},{"removed":"critpt","score":0.3103755198845845,"rank":112,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.31053510702835946,"rank":112,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3117084527260936,"rank":114,"remainingConfigurations":444},{"removed":"gdpval","score":0.30999402412317656,"rank":112,"remainingConfigurations":444},{"removed":"gmmlu","score":0.3106028331310033,"rank":112,"remainingConfigurations":444},{"removed":"gpqa","score":0.3103897967373565,"rank":112,"remainingConfigurations":444},{"removed":"harvey","score":0.3086356240721037,"rank":112,"remainingConfigurations":444},{"removed":"hle","score":0.322115033276973,"rank":112,"remainingConfigurations":444},{"removed":"ifbench","score":0.30889381611844596,"rank":112,"remainingConfigurations":444},{"removed":"itbench","score":0.3101253526826402,"rank":112,"remainingConfigurations":444},{"removed":"livecodebench","score":0.3107809366880259,"rank":112,"remainingConfigurations":444},{"removed":"math500","score":0.3106038578339962,"rank":112,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.3155419783299392,"rank":112,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.323320415689942,"rank":113,"remainingConfigurations":444},{"removed":"omniscience","score":0.3081848697895022,"rank":113,"remainingConfigurations":444},{"removed":"tau-bench","score":0.31127542750584564,"rank":112,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.31039627500602246,"rank":112,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.3103350202882042,"rank":112,"remainingConfigurations":444},{"removed":"arc-agi","score":0.28207413616865434,"rank":128,"remainingConfigurations":444},{"removed":"deepswe","score":0.27963236493942123,"rank":110,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.31055236000597825,"rank":112,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.31108875298567745,"rank":112,"remainingConfigurations":444},{"removed":"frontiercode","score":0.39869275010270916,"rank":84,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.3105123163047461,"rank":112,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.3056880911537036,"rank":112,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.3105176278184496,"rank":112,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.3095984417968373,"rank":112,"remainingConfigurations":444},{"removed":"livebench-math","score":0.3110445167840366,"rank":112,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.3079573503124448,"rank":111,"remainingConfigurations":444},{"removed":"livebench-language","score":0.30595964966903966,"rank":111,"remainingConfigurations":444},{"removed":"livebench-data","score":0.3120191071302046,"rank":112,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.31004791098454637,"rank":112,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.30406168640228787,"rank":112,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3226550038568516,"rank":112,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.29189753023282355,"rank":113,"remainingConfigurations":444},{"removed":"frontiermath","score":0.30991664994703827,"rank":112,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.30572692287072306,"rank":112,"remainingConfigurations":444},{"removed":"simpleqa","score":0.3179355870377562,"rank":112,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.3096356653368178,"rank":112,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.31004876206274273,"rank":112,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.30992713461364235,"rank":112,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.30997316364447375,"rank":112,"remainingConfigurations":444},{"removed":"vibe-code","score":0.30924715994411534,"rank":112,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.310037551605588,"rank":112,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2.6-flash--effort-reasoning":{"score":0.2918819362435889,"rank":113,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3474212826862681,"rank":113,"remainingConfigurations":444},{"removed":"Datacurve","score":0.25097375407523015,"rank":112,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2907679128226171,"rank":113,"remainingConfigurations":444},{"removed":"Scale","score":0.31479935578496737,"rank":112,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.29165860806392246,"rank":113,"remainingConfigurations":444},{"removed":"Cognition","score":0.27892783080896266,"rank":116,"remainingConfigurations":444},{"removed":"LiveBench","score":0.3008166954308568,"rank":111,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.29446960037731956,"rank":112,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2980105734555018,"rank":111,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2846357343242948,"rank":114,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.29174757358746245,"rank":113,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.28617170920411017,"rank":113,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.29134900896288024,"rank":113,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2918819362435889,"rank":113,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2937946369411788,"rank":113,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2874775168545683,"rank":113,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2944317009286589,"rank":113,"remainingConfigurations":444},{"removed":"briefcase","score":0.2590806084115132,"rank":121,"remainingConfigurations":444},{"removed":"aime","score":0.29004743861669896,"rank":113,"remainingConfigurations":444},{"removed":"apex-agents","score":0.29444323311877696,"rank":113,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.3037829184016521,"rank":113,"remainingConfigurations":444},{"removed":"automationbench","score":0.25121716863210136,"rank":123,"remainingConfigurations":444},{"removed":"critpt","score":0.2913455009882742,"rank":113,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.29239466053686064,"rank":113,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.32415947137141166,"rank":111,"remainingConfigurations":444},{"removed":"gdpval","score":0.26562556103873064,"rank":120,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2918594462273048,"rank":113,"remainingConfigurations":444},{"removed":"gpqa","score":0.2866840531594594,"rank":113,"remainingConfigurations":444},{"removed":"harvey","score":0.2887184617334167,"rank":114,"remainingConfigurations":444},{"removed":"hle","score":0.307643755121669,"rank":113,"remainingConfigurations":444},{"removed":"ifbench","score":0.2855004968904572,"rank":113,"remainingConfigurations":444},{"removed":"itbench","score":0.2913633182810651,"rank":114,"remainingConfigurations":444},{"removed":"livecodebench","score":0.29033456654185896,"rank":113,"remainingConfigurations":444},{"removed":"math500","score":0.2914320367542294,"rank":113,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.29570195747816924,"rank":113,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.33882325973697697,"rank":110,"remainingConfigurations":444},{"removed":"omniscience","score":0.32947221989509023,"rank":109,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2886523224022171,"rank":115,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.30100513956628355,"rank":113,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2835008314041632,"rank":115,"remainingConfigurations":444},{"removed":"arc-agi","score":0.33782733087401007,"rank":113,"remainingConfigurations":444},{"removed":"deepswe","score":0.25109881465903283,"rank":112,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2919366749498562,"rank":113,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.28938209335029796,"rank":113,"remainingConfigurations":444},{"removed":"frontiercode","score":0.27892783080896266,"rank":116,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.28998698589498567,"rank":113,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.28945689230310284,"rank":113,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2916334196253286,"rank":113,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.29093292605366416,"rank":113,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2919629418274738,"rank":113,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.28989692178417675,"rank":113,"remainingConfigurations":444},{"removed":"livebench-language","score":0.29479550546384053,"rank":113,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2919320268806813,"rank":113,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2881256093242905,"rank":113,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.29071230819513955,"rank":113,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.295713720850575,"rank":114,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.29446960037731956,"rank":112,"remainingConfigurations":444},{"removed":"frontiermath","score":0.29237146402225467,"rank":113,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2836347834724909,"rank":114,"remainingConfigurations":444},{"removed":"simpleqa","score":0.30057925101612465,"rank":113,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.29129506161159113,"rank":113,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.29123094841290825,"rank":113,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2911852146856732,"rank":113,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.29162400094170465,"rank":113,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2906263002591267,"rank":113,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2913694689090015,"rank":113,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.2--effort-xhigh":{"score":0.2874149827407689,"rank":114,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.26106483774736416,"rank":105,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3436730610356686,"rank":115,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2414131169420052,"rank":116,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2876678828710575,"rank":114,"remainingConfigurations":444},{"removed":"Scale","score":0.3100379182994174,"rank":114,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2855639521733501,"rank":114,"remainingConfigurations":444},{"removed":"Cognition","score":0.28003418036679023,"rank":115,"remainingConfigurations":444},{"removed":"LiveBench","score":0.28355862357864575,"rank":116,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.28802038959094833,"rank":114,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.29310666587410333,"rank":112,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2766315386775963,"rank":116,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.28734921143243514,"rank":114,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.28242949420422897,"rank":114,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2870993707783192,"rank":114,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2874149827407689,"rank":114,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2891549138872913,"rank":114,"remainingConfigurations":444},{"removed":"All provider reports","score":0.28383396185804427,"rank":114,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2884399603951164,"rank":115,"remainingConfigurations":444},{"removed":"briefcase","score":0.2871513116763513,"rank":116,"remainingConfigurations":444},{"removed":"aime","score":0.28490012725283537,"rank":114,"remainingConfigurations":444},{"removed":"apex-agents","score":0.28948358773854604,"rank":115,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.27901576377731924,"rank":117,"remainingConfigurations":444},{"removed":"automationbench","score":0.2865968740699885,"rank":113,"remainingConfigurations":444},{"removed":"critpt","score":0.2879685927636851,"rank":114,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2875331472995583,"rank":114,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.28930713048281964,"rank":115,"remainingConfigurations":444},{"removed":"gdpval","score":0.28721972768358167,"rank":114,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2872140924787924,"rank":114,"remainingConfigurations":444},{"removed":"gpqa","score":0.2823129101591493,"rank":115,"remainingConfigurations":444},{"removed":"harvey","score":0.2850745666677399,"rank":115,"remainingConfigurations":444},{"removed":"hle","score":0.29897534668036957,"rank":114,"remainingConfigurations":444},{"removed":"ifbench","score":0.28331853733803497,"rank":115,"remainingConfigurations":444},{"removed":"itbench","score":0.28679864852207093,"rank":115,"remainingConfigurations":444},{"removed":"livecodebench","score":0.28844747807937804,"rank":114,"remainingConfigurations":444},{"removed":"math500","score":0.28747133077969383,"rank":114,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.29498268553382995,"rank":114,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.30034169522446513,"rank":114,"remainingConfigurations":444},{"removed":"omniscience","score":0.27773709439765243,"rank":118,"remainingConfigurations":444},{"removed":"tau-bench","score":0.29699305377590907,"rank":114,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2889953716742291,"rank":114,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2871082325634978,"rank":114,"remainingConfigurations":444},{"removed":"arc-agi","score":0.33374485690035754,"rank":115,"remainingConfigurations":444},{"removed":"deepswe","score":0.24148356026077097,"rank":116,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.28745078117352324,"rank":114,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2844493090316072,"rank":115,"remainingConfigurations":444},{"removed":"frontiercode","score":0.28003418036679023,"rank":115,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2853945612345547,"rank":114,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2848656547934082,"rank":114,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2871901575327221,"rank":114,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.286420429834177,"rank":114,"remainingConfigurations":444},{"removed":"livebench-math","score":0.28764624633903163,"rank":114,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2855547606170511,"rank":115,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2895778095817351,"rank":114,"remainingConfigurations":444},{"removed":"livebench-data","score":0.28738653279755744,"rank":114,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.28406283108178393,"rank":114,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.28601418076583823,"rank":115,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2916219178108852,"rank":115,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.28802038959094833,"rank":114,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2878867881848865,"rank":114,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.28394550336272234,"rank":113,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2954116757798642,"rank":114,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.28674811978718046,"rank":114,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.28676758946591757,"rank":114,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2868146610038895,"rank":114,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.28705380845391026,"rank":114,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2861876607832899,"rank":114,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.28686225167268975,"rank":114,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.2--effort-high":{"score":0.28599634195703844,"rank":115,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2824681412291475,"rank":103,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3534926422773494,"rank":111,"remainingConfigurations":444},{"removed":"Datacurve","score":0.24179062237032153,"rank":115,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.28731417633797884,"rank":115,"remainingConfigurations":444},{"removed":"Scale","score":0.30594632118877857,"rank":116,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2852307615948085,"rank":115,"remainingConfigurations":444},{"removed":"Cognition","score":0.2859386881364405,"rank":114,"remainingConfigurations":444},{"removed":"LiveBench","score":0.25756741806015276,"rank":122,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.28191822563874475,"rank":118,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.289197518318748,"rank":113,"remainingConfigurations":431},{"removed":"Vals AI","score":0.27880148149231504,"rank":115,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.28597590612325857,"rank":115,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2821897164988984,"rank":115,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.28506751397502156,"rank":115,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.28599634195703844,"rank":115,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.28711163533050155,"rank":115,"remainingConfigurations":444},{"removed":"All provider reports","score":0.28237408839948436,"rank":115,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2861761492511577,"rank":116,"remainingConfigurations":444},{"removed":"briefcase","score":0.2847825069504637,"rank":117,"remainingConfigurations":444},{"removed":"aime","score":0.28371398517422103,"rank":115,"remainingConfigurations":444},{"removed":"apex-agents","score":0.28683567407663557,"rank":116,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2856019348631252,"rank":116,"remainingConfigurations":444},{"removed":"automationbench","score":0.2850534380702961,"rank":114,"remainingConfigurations":444},{"removed":"critpt","score":0.2866688797905656,"rank":115,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.28589020412055277,"rank":115,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2866648692961303,"rank":117,"remainingConfigurations":444},{"removed":"gdpval","score":0.28553440879643105,"rank":115,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2859638908196234,"rank":115,"remainingConfigurations":444},{"removed":"gpqa","score":0.28506067269420204,"rank":114,"remainingConfigurations":444},{"removed":"harvey","score":0.28357523554626834,"rank":116,"remainingConfigurations":444},{"removed":"hle","score":0.2976387625151206,"rank":115,"remainingConfigurations":444},{"removed":"ifbench","score":0.283903968342215,"rank":114,"remainingConfigurations":444},{"removed":"itbench","score":0.2856924175448479,"rank":116,"remainingConfigurations":444},{"removed":"livecodebench","score":0.287200272114215,"rank":115,"remainingConfigurations":444},{"removed":"math500","score":0.2860015205156993,"rank":115,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2907060966112611,"rank":115,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.29831161347288637,"rank":115,"remainingConfigurations":444},{"removed":"omniscience","score":0.2855264352347527,"rank":116,"remainingConfigurations":444},{"removed":"tau-bench","score":0.28543858822387475,"rank":116,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2862184549988918,"rank":116,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.28748726118651496,"rank":113,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3381199435742223,"rank":112,"remainingConfigurations":444},{"removed":"deepswe","score":0.24186900645531742,"rank":115,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.28608592057507826,"rank":115,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.28470797766076006,"rank":114,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2859386881364405,"rank":114,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.28406556846918013,"rank":115,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.283763444659428,"rank":115,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.28562998653904,"rank":115,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.28472071593481413,"rank":115,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2848216578533876,"rank":115,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.29393277014065594,"rank":112,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2793483179766214,"rank":118,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2700444978405991,"rank":119,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.28045598684117706,"rank":116,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2886835195666107,"rank":114,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.3050177874650304,"rank":113,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.28191822563874475,"rank":118,"remainingConfigurations":444},{"removed":"frontiermath","score":0.28643563153439483,"rank":115,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.27913915556380237,"rank":115,"remainingConfigurations":444},{"removed":"simpleqa","score":0.29082986736591027,"rank":116,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.28479358773273616,"rank":115,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2858073166891856,"rank":115,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2857431417322534,"rank":115,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.2855360241760485,"rank":115,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2845164647812914,"rank":115,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.28575287669645855,"rank":115,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-pro--effort-reasoning":{"score":0.28441574053072055,"rank":116,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.33537896977972786,"rank":119,"remainingConfigurations":444},{"removed":"Datacurve","score":0.24234197002018432,"rank":114,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.28314471457697604,"rank":116,"remainingConfigurations":444},{"removed":"Scale","score":0.30695318914338027,"rank":115,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2840354114899566,"rank":116,"remainingConfigurations":444},{"removed":"Cognition","score":0.273272350462672,"rank":118,"remainingConfigurations":444},{"removed":"LiveBench","score":0.29081497863243166,"rank":112,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2878911908600143,"rank":115,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2885552386510774,"rank":114,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2758493848525851,"rank":117,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2842945320429121,"rank":116,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.27839123139194855,"rank":116,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2840058862377521,"rank":116,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.28441574053072055,"rank":116,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.28592658350156036,"rank":116,"remainingConfigurations":444},{"removed":"All provider reports","score":0.279441663527278,"rank":116,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2732806640626177,"rank":119,"remainingConfigurations":444},{"removed":"briefcase","score":0.3176529032052334,"rank":113,"remainingConfigurations":444},{"removed":"aime","score":0.2836255778083259,"rank":116,"remainingConfigurations":444},{"removed":"apex-agents","score":0.278356294287234,"rank":119,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.27661723436758523,"rank":118,"remainingConfigurations":444},{"removed":"automationbench","score":0.28365113926990176,"rank":115,"remainingConfigurations":444},{"removed":"critpt","score":0.28000246294925524,"rank":117,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.28185321883885284,"rank":117,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2798488225151555,"rank":119,"remainingConfigurations":444},{"removed":"gdpval","score":0.3067289807377109,"rank":113,"remainingConfigurations":444},{"removed":"gmmlu","score":0.28074520001888387,"rank":117,"remainingConfigurations":444},{"removed":"gpqa","score":0.2691360015456294,"rank":118,"remainingConfigurations":444},{"removed":"harvey","score":0.2930931364703858,"rank":113,"remainingConfigurations":444},{"removed":"hle","score":0.28636185088653393,"rank":118,"remainingConfigurations":444},{"removed":"ifbench","score":0.27696149752915317,"rank":117,"remainingConfigurations":444},{"removed":"itbench","score":0.3035495040030662,"rank":113,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2836486014685587,"rank":116,"remainingConfigurations":444},{"removed":"math500","score":0.2847965686115317,"rank":116,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.28915645448821664,"rank":116,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2877885620525187,"rank":118,"remainingConfigurations":444},{"removed":"omniscience","score":0.2771008654788092,"rank":119,"remainingConfigurations":444},{"removed":"tau-bench","score":0.28497899090230966,"rank":117,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2874925553298063,"rank":115,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2828723855762801,"rank":116,"remainingConfigurations":444},{"removed":"arc-agi","score":0.32647799690479523,"rank":116,"remainingConfigurations":444},{"removed":"deepswe","score":0.24251850411040146,"rank":114,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2844649799398315,"rank":116,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.28201795313932615,"rank":116,"remainingConfigurations":444},{"removed":"frontiercode","score":0.273272350462672,"rank":118,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.28245613390062335,"rank":116,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.28207162407339575,"rank":116,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2842004028395158,"rank":116,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2834597950441947,"rank":116,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2845371393463514,"rank":116,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2826368316878119,"rank":116,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2872856276340176,"rank":115,"remainingConfigurations":444},{"removed":"livebench-data","score":0.28437808935396397,"rank":115,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.28069766485622144,"rank":115,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.28330589695077124,"rank":116,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.288034041389867,"rank":116,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2878911908600143,"rank":115,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2845616309032759,"rank":116,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2758053894077372,"rank":116,"remainingConfigurations":444},{"removed":"simpleqa","score":0.29296352545751353,"rank":115,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.28380477143606864,"rank":116,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.28378478463721385,"rank":116,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.28367574183544253,"rank":116,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.284198500820492,"rank":116,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2832557650022716,"rank":116,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2838854505158361,"rank":116,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-pro-0424--effort-max":{"score":0.2820584625224869,"rank":117,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.33086233329323966,"rank":121,"remainingConfigurations":444},{"removed":"Datacurve","score":0.23935334715170056,"rank":117,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2808838072409718,"rank":117,"remainingConfigurations":444},{"removed":"Scale","score":0.3043382127465459,"rank":117,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.28156485981640217,"rank":117,"remainingConfigurations":444},{"removed":"Cognition","score":0.26980494206932154,"rank":119,"remainingConfigurations":444},{"removed":"LiveBench","score":0.28742036393155723,"rank":113,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2851782183607347,"rank":116,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.28529231758996393,"rank":115,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2726739757079469,"rank":118,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.28196454341293103,"rank":117,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.27594481511456864,"rank":117,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2816815464032179,"rank":117,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2820584625224869,"rank":117,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.28360450253075453,"rank":117,"remainingConfigurations":444},{"removed":"All provider reports","score":0.27709147415669055,"rank":117,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2941360351407091,"rank":114,"remainingConfigurations":444},{"removed":"briefcase","score":0.292324417893899,"rank":115,"remainingConfigurations":444},{"removed":"aime","score":0.2811087553403471,"rank":117,"remainingConfigurations":444},{"removed":"apex-agents","score":0.29111581737872055,"rank":114,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.27427632430180743,"rank":119,"remainingConfigurations":444},{"removed":"automationbench","score":0.2631782776290541,"rank":118,"remainingConfigurations":444},{"removed":"critpt","score":0.28144710386918226,"rank":116,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2855292021912221,"rank":116,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2874873441600763,"rank":116,"remainingConfigurations":444},{"removed":"gdpval","score":0.28428915323773113,"rank":116,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2826331393872917,"rank":116,"remainingConfigurations":444},{"removed":"gpqa","score":0.2770841221179224,"rank":116,"remainingConfigurations":444},{"removed":"harvey","score":0.2795624077933969,"rank":117,"remainingConfigurations":444},{"removed":"hle","score":0.2910394160832286,"rank":116,"remainingConfigurations":444},{"removed":"ifbench","score":0.2749887213403039,"rank":118,"remainingConfigurations":444},{"removed":"itbench","score":0.2766861537365115,"rank":118,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2813518972799787,"rank":117,"remainingConfigurations":444},{"removed":"math500","score":0.28214218012349157,"rank":117,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.28673130448358036,"rank":117,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2950884571339501,"rank":116,"remainingConfigurations":444},{"removed":"omniscience","score":0.2857881018380625,"rank":115,"remainingConfigurations":444},{"removed":"tau-bench","score":0.278542925777349,"rank":118,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2850500928182002,"rank":117,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.27887662865004126,"rank":118,"remainingConfigurations":444},{"removed":"arc-agi","score":0.32377731394447795,"rank":119,"remainingConfigurations":444},{"removed":"deepswe","score":0.23952282110829715,"rank":117,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2821052222373727,"rank":117,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.27958232981709913,"rank":117,"remainingConfigurations":444},{"removed":"frontiercode","score":0.26980494206932154,"rank":119,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.28016015992779586,"rank":117,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.27975239930035267,"rank":117,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2818388638413807,"rank":117,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.28113222880816685,"rank":117,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2822004824721187,"rank":117,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.280275563436712,"rank":117,"remainingConfigurations":444},{"removed":"livebench-language","score":0.28490126352300393,"rank":116,"remainingConfigurations":444},{"removed":"livebench-data","score":0.28200949849545404,"rank":116,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2783824267542642,"rank":117,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2809461985051854,"rank":117,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.28566045838573473,"rank":117,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2851782183607347,"rank":116,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2822502023570934,"rank":117,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.27374644712188245,"rank":117,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2905346746623435,"rank":117,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.28144291387981973,"rank":117,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.28143455920482396,"rank":117,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.28132366984045687,"rank":117,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.281838524645102,"rank":117,"remainingConfigurations":444},{"removed":"vibe-code","score":0.28091142771550487,"rank":117,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2815383086260131,"rank":117,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5.3--effort-low":{"score":0.27800965232991565,"rank":118,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.33081675647191144,"rank":122,"remainingConfigurations":444},{"removed":"Datacurve","score":0.23605858172156,"rank":119,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2768788711451185,"rank":118,"remainingConfigurations":444},{"removed":"Scale","score":0.3009191921709741,"rank":118,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.27695905777962876,"rank":118,"remainingConfigurations":444},{"removed":"Cognition","score":0.2616745625327133,"rank":121,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2852334440494178,"rank":115,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.28165374585637276,"rank":119,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2827681458289849,"rank":117,"remainingConfigurations":431},{"removed":"Vals AI","score":0.26894104328553176,"rank":120,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2779064926477138,"rank":118,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2724323256752426,"rank":118,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2775504937779318,"rank":118,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.27800965232991565,"rank":118,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.27998080495173355,"rank":118,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2738973401313406,"rank":118,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.280015669241172,"rank":117,"remainingConfigurations":444},{"removed":"briefcase","score":0.26800174189762377,"rank":118,"remainingConfigurations":444},{"removed":"aime","score":0.27622288722081983,"rank":118,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2808370090336529,"rank":117,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.30060435942592945,"rank":114,"remainingConfigurations":444},{"removed":"automationbench","score":0.2611661345395353,"rank":119,"remainingConfigurations":444},{"removed":"critpt","score":0.2699558363445667,"rank":119,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.27815238948458804,"rank":118,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.3158896921317991,"rank":113,"remainingConfigurations":444},{"removed":"gdpval","score":0.2718650642120316,"rank":118,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2785028896213872,"rank":118,"remainingConfigurations":444},{"removed":"gpqa","score":0.2733378501240561,"rank":117,"remainingConfigurations":444},{"removed":"harvey","score":0.2750706837269267,"rank":118,"remainingConfigurations":444},{"removed":"hle","score":0.28775026932512354,"rank":117,"remainingConfigurations":444},{"removed":"ifbench","score":0.2726696487951781,"rank":119,"remainingConfigurations":444},{"removed":"itbench","score":0.2774467609126005,"rank":117,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2764012484535119,"rank":118,"remainingConfigurations":444},{"removed":"math500","score":0.27746531404776315,"rank":118,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2815567136571395,"rank":118,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2916245694864496,"rank":117,"remainingConfigurations":444},{"removed":"omniscience","score":0.2974144261435942,"rank":114,"remainingConfigurations":444},{"removed":"tau-bench","score":0.274613934576383,"rank":120,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.27957905724579163,"rank":118,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2528198107799334,"rank":123,"remainingConfigurations":444},{"removed":"arc-agi","score":0.32151870112051256,"rank":120,"remainingConfigurations":444},{"removed":"deepswe","score":0.23615207863343488,"rank":119,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.27806288140029833,"rank":118,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.27562136706402857,"rank":119,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2616745625327133,"rank":121,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2761133237202569,"rank":118,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2756485445743154,"rank":118,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.27777646099137376,"rank":118,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.27710247184424197,"rank":118,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2781245111931548,"rank":118,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2760545213573328,"rank":118,"remainingConfigurations":444},{"removed":"livebench-language","score":0.28086186011318476,"rank":117,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2780280715055818,"rank":117,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.27433870763463974,"rank":118,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.27683843971365485,"rank":118,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.28179255191826785,"rank":118,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.28165374585637276,"rank":119,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2783387869444219,"rank":118,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.27017973762284747,"rank":118,"remainingConfigurations":444},{"removed":"simpleqa","score":0.28641878362326717,"rank":118,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.277397516259213,"rank":118,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.27738703099740974,"rank":118,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.27734121691284397,"rank":118,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.27774418873047374,"rank":118,"remainingConfigurations":444},{"removed":"vibe-code","score":0.27682296517350946,"rank":118,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2775092418971969,"rank":118,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash--effort-medium":{"score":0.27610491597542064,"rank":119,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3361174765453567,"rank":118,"remainingConfigurations":444},{"removed":"Datacurve","score":0.23628960122181075,"rank":118,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.27466852108763956,"rank":119,"remainingConfigurations":444},{"removed":"Scale","score":0.3003602492747922,"rank":119,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.27594327668638075,"rank":119,"remainingConfigurations":444},{"removed":"Cognition","score":0.2655072872283603,"rank":120,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2824741868064196,"rank":117,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2827019289286312,"rank":117,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2795901492696514,"rank":118,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2695256696317538,"rank":119,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.27602216869770263,"rank":119,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2705372811298573,"rank":119,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2756882458261174,"rank":119,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.27610491597542064,"rank":119,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2779276000070444,"rank":119,"remainingConfigurations":444},{"removed":"All provider reports","score":0.27191858332046104,"rank":119,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2777631189832984,"rank":118,"remainingConfigurations":444},{"removed":"briefcase","score":0.32572425799496546,"rank":110,"remainingConfigurations":444},{"removed":"aime","score":0.27546761636879685,"rank":119,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2790070388145515,"rank":118,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2866204208659738,"rank":115,"remainingConfigurations":444},{"removed":"automationbench","score":0.2742771264489905,"rank":116,"remainingConfigurations":444},{"removed":"critpt","score":0.2744826247042423,"rank":118,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2763317680351339,"rank":119,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.281178807754326,"rank":118,"remainingConfigurations":444},{"removed":"gdpval","score":0.2757537902823493,"rank":117,"remainingConfigurations":444},{"removed":"gmmlu","score":0.27797094257108457,"rank":119,"remainingConfigurations":444},{"removed":"gpqa","score":0.26053150400440106,"rank":119,"remainingConfigurations":444},{"removed":"harvey","score":0.273781005143585,"rank":119,"remainingConfigurations":444},{"removed":"hle","score":0.2779636848919604,"rank":120,"remainingConfigurations":444},{"removed":"ifbench","score":0.27939281802193955,"rank":116,"remainingConfigurations":444},{"removed":"itbench","score":0.27495387251564074,"rank":119,"remainingConfigurations":444},{"removed":"livecodebench","score":0.274764473055732,"rank":119,"remainingConfigurations":444},{"removed":"math500","score":0.2755960203025232,"rank":119,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.27985205185060413,"rank":119,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2656175127671461,"rank":125,"remainingConfigurations":444},{"removed":"omniscience","score":0.2541822339180223,"rank":123,"remainingConfigurations":444},{"removed":"tau-bench","score":0.27644871911777286,"rank":119,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2785262856468397,"rank":119,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2826733861149762,"rank":117,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3249348800857013,"rank":117,"remainingConfigurations":444},{"removed":"deepswe","score":0.23639882425106362,"rank":118,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2761527082663126,"rank":119,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2730392002083599,"rank":120,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2655072872283603,"rank":120,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.274213715240946,"rank":119,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2738475294273846,"rank":119,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2758887626402489,"rank":119,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2751867876099688,"rank":119,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2762811903191229,"rank":119,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.274245942506479,"rank":119,"remainingConfigurations":444},{"removed":"livebench-language","score":0.27886681213470094,"rank":119,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2760100519625661,"rank":118,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2725295529517276,"rank":119,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.27496539880647247,"rank":119,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2797935785108336,"rank":119,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2827019289286312,"rank":117,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2762970779843035,"rank":119,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.26745410438790906,"rank":119,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2845668939226578,"rank":119,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2754825223064731,"rank":119,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.275471551032593,"rank":119,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2754429257946119,"rank":119,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.27583662520688823,"rank":119,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2749580850884126,"rank":119,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.27559002180489917,"rank":119,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3-flash-preview--effort-reasoning":{"score":0.26763321264031936,"rank":120,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.32261986118168273,"rank":124,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2270414498841704,"rank":120,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2661172426968501,"rank":120,"remainingConfigurations":444},{"removed":"Scale","score":0.29051163594208157,"rank":120,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2675669832365075,"rank":120,"remainingConfigurations":444},{"removed":"Cognition","score":0.2583105974482951,"rank":122,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2723062221159889,"rank":118,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2727900878210613,"rank":122,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2679922322862156,"rank":120,"remainingConfigurations":431},{"removed":"Vals AI","score":0.259667076506266,"rank":121,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.26755666692256985,"rank":120,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.26192715957121104,"rank":120,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.26727563316357844,"rank":120,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.26763321264031936,"rank":120,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2692277270109533,"rank":120,"remainingConfigurations":444},{"removed":"All provider reports","score":0.26315005289526616,"rank":120,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2690290944661807,"rank":120,"remainingConfigurations":444},{"removed":"briefcase","score":0.26746374982103827,"rank":119,"remainingConfigurations":444},{"removed":"aime","score":0.2673091568970873,"rank":121,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2650978067898782,"rank":120,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2705555378794828,"rank":120,"remainingConfigurations":444},{"removed":"automationbench","score":0.2665356791368025,"rank":117,"remainingConfigurations":444},{"removed":"critpt","score":0.26980271962560415,"rank":120,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2671919143925279,"rank":120,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.27211090731543625,"rank":121,"remainingConfigurations":444},{"removed":"gdpval","score":0.26869072112829995,"rank":119,"remainingConfigurations":444},{"removed":"gmmlu","score":0.26312742106868314,"rank":120,"remainingConfigurations":444},{"removed":"gpqa","score":0.2598952869579732,"rank":120,"remainingConfigurations":444},{"removed":"harvey","score":0.2653998540186041,"rank":120,"remainingConfigurations":444},{"removed":"hle","score":0.2780405514887323,"rank":119,"remainingConfigurations":444},{"removed":"ifbench","score":0.2591278833424906,"rank":120,"remainingConfigurations":444},{"removed":"itbench","score":0.26616676416029406,"rank":120,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2664371475365214,"rank":120,"remainingConfigurations":444},{"removed":"math500","score":0.26741202388090135,"rank":120,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2729142268528149,"rank":120,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.27077778274951764,"rank":119,"remainingConfigurations":444},{"removed":"omniscience","score":0.2465002075863062,"rank":125,"remainingConfigurations":444},{"removed":"tau-bench","score":0.29813373805666704,"rank":113,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2704320667658283,"rank":120,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2747066716785305,"rank":119,"remainingConfigurations":444},{"removed":"arc-agi","score":0.31297935660937726,"rank":123,"remainingConfigurations":444},{"removed":"deepswe","score":0.22718078453258583,"rank":121,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2676758957680521,"rank":120,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.26446393193841194,"rank":122,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2583105974482951,"rank":122,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2656147685214242,"rank":120,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.26537906772733905,"rank":120,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2674229332894425,"rank":120,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2666947422020358,"rank":120,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2678472090364017,"rank":120,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.26590094047891494,"rank":120,"remainingConfigurations":444},{"removed":"livebench-language","score":0.27032908090957786,"rank":120,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2674552893724589,"rank":120,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.26414343174313787,"rank":120,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2665440059573965,"rank":120,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.27117246837296355,"rank":120,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2727900878210613,"rank":122,"remainingConfigurations":444},{"removed":"frontiermath","score":0.26815229558605086,"rank":120,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2580527245252041,"rank":122,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2759666623855049,"rank":120,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.26698474368284003,"rank":120,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2670108996709792,"rank":120,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2669665137441862,"rank":120,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.26737611011224577,"rank":120,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2665433999032506,"rank":120,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.26712339505785326,"rank":120,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5--effort-high":{"score":0.25778760194914085,"rank":121,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2468032799864074,"rank":106,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2724044131312166,"rank":133,"remainingConfigurations":444},{"removed":"Datacurve","score":0.21569129572488224,"rank":124,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.25768875577472966,"rank":121,"remainingConfigurations":444},{"removed":"Scale","score":0.2836569327669341,"rank":121,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.24937353306352303,"rank":123,"remainingConfigurations":444},{"removed":"Cognition","score":0.22453494626582005,"rank":130,"remainingConfigurations":444},{"removed":"LiveBench","score":0.26687191713491193,"rank":119,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.28103316443732324,"rank":120,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2832939578045784,"rank":116,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2471436300180634,"rank":122,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.25773864524080004,"rank":121,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2537296895476319,"rank":122,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2577252482138203,"rank":121,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.25778760194914085,"rank":121,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2582382873740086,"rank":121,"remainingConfigurations":444},{"removed":"All provider reports","score":0.25411541669953236,"rank":122,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2580231580665716,"rank":122,"remainingConfigurations":444},{"removed":"briefcase","score":0.25491861365042484,"rank":122,"remainingConfigurations":444},{"removed":"aime","score":0.2547230669271094,"rank":123,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2591552522396441,"rank":121,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2588655129147979,"rank":121,"remainingConfigurations":444},{"removed":"automationbench","score":0.2574119172371298,"rank":121,"remainingConfigurations":444},{"removed":"critpt","score":0.2564465271192153,"rank":121,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.25786732142541874,"rank":121,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2614686024933661,"rank":122,"remainingConfigurations":444},{"removed":"gdpval","score":0.2563202066877401,"rank":121,"remainingConfigurations":444},{"removed":"gmmlu","score":0.258054302977697,"rank":121,"remainingConfigurations":444},{"removed":"gpqa","score":0.2589216530994876,"rank":121,"remainingConfigurations":444},{"removed":"harvey","score":0.25564973199322616,"rank":121,"remainingConfigurations":444},{"removed":"hle","score":0.2684226676336992,"rank":121,"remainingConfigurations":444},{"removed":"ifbench","score":0.2570325953757165,"rank":121,"remainingConfigurations":444},{"removed":"itbench","score":0.2570728444501576,"rank":121,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2577257753111461,"rank":121,"remainingConfigurations":444},{"removed":"math500","score":0.2577884137178566,"rank":121,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.26166292978195055,"rank":121,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.26973996454235244,"rank":120,"remainingConfigurations":444},{"removed":"omniscience","score":0.25786670295070857,"rank":121,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2570089919694657,"rank":122,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.25760294820275026,"rank":122,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2509378016817692,"rank":124,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2720607358367945,"rank":130,"remainingConfigurations":444},{"removed":"deepswe","score":0.21578268262580494,"rank":124,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.25782692094879,"rank":121,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2560687634886686,"rank":123,"remainingConfigurations":444},{"removed":"frontiercode","score":0.22453494626582005,"rank":130,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2560640966949147,"rank":121,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.25629741689564295,"rank":121,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.25814985865442214,"rank":121,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2550971386823027,"rank":121,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2577849841238002,"rank":121,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.25496588112911145,"rank":121,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2603177925262852,"rank":121,"remainingConfigurations":444},{"removed":"livebench-data","score":0.25851995398244404,"rank":121,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2546166095828199,"rank":121,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2562785838602317,"rank":121,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.26208391219589583,"rank":121,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.28103316443732324,"rank":120,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2562533541224094,"rank":121,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2590271526666809,"rank":121,"remainingConfigurations":444},{"removed":"simpleqa","score":0.264488547602934,"rank":121,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2575129052948062,"rank":121,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.25708446473025537,"rank":121,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2571422521293744,"rank":121,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.257548281277688,"rank":121,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2571047891246825,"rank":121,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2569040752057463,"rank":121,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-5-5--effort-medium":{"score":0.2547016862349431,"rank":122,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.21557488395417904,"rank":114,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4220367024804,"rank":93,"remainingConfigurations":444},{"removed":"Datacurve","score":0.21592911316535565,"rank":123,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.255247215410998,"rank":122,"remainingConfigurations":444},{"removed":"Scale","score":0.2757692624232288,"rank":123,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.25351968258983637,"rank":122,"remainingConfigurations":444},{"removed":"Cognition","score":0.13838757225312764,"rank":163,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2585729468907801,"rank":121,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.253447604342358,"rank":124,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2737739303288448,"rank":119,"remainingConfigurations":431},{"removed":"Vals AI","score":0.24198183105093043,"rank":124,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2546140586471551,"rank":122,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.25006664041206716,"rank":123,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2543896788944953,"rank":122,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2547016862349431,"rank":122,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.25593335298816516,"rank":122,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2509455867198441,"rank":123,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.25569254869025687,"rank":123,"remainingConfigurations":444},{"removed":"briefcase","score":0.24949864544127762,"rank":123,"remainingConfigurations":444},{"removed":"aime","score":0.251800651277653,"rank":125,"remainingConfigurations":444},{"removed":"apex-agents","score":0.25636278632703385,"rank":123,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.25531560116920954,"rank":122,"remainingConfigurations":444},{"removed":"automationbench","score":0.25506485699884623,"rank":122,"remainingConfigurations":444},{"removed":"critpt","score":0.25487884178399745,"rank":122,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.25505813585144427,"rank":122,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2554804255607117,"rank":123,"remainingConfigurations":444},{"removed":"gdpval","score":0.2539071191876524,"rank":123,"remainingConfigurations":444},{"removed":"gmmlu","score":0.25490498773204734,"rank":122,"remainingConfigurations":444},{"removed":"gpqa","score":0.25558968528357323,"rank":122,"remainingConfigurations":444},{"removed":"harvey","score":0.2527527929129296,"rank":122,"remainingConfigurations":444},{"removed":"hle","score":0.2680785401507303,"rank":122,"remainingConfigurations":444},{"removed":"ifbench","score":0.2526419713927258,"rank":122,"remainingConfigurations":444},{"removed":"itbench","score":0.2544509133122885,"rank":122,"remainingConfigurations":444},{"removed":"livecodebench","score":0.255170215731963,"rank":122,"remainingConfigurations":444},{"removed":"math500","score":0.2546612217569324,"rank":122,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.25926364602835084,"rank":122,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.26762550907420773,"rank":122,"remainingConfigurations":444},{"removed":"omniscience","score":0.25694087414286965,"rank":122,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2543760066663075,"rank":123,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.25076873039028974,"rank":124,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.25373671682839,"rank":120,"remainingConfigurations":444},{"removed":"arc-agi","score":0.41691596232653994,"rank":92,"remainingConfigurations":444},{"removed":"deepswe","score":0.216047739130346,"rank":123,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.25473580512630145,"rank":122,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.24278530124143902,"rank":129,"remainingConfigurations":444},{"removed":"frontiercode","score":0.13838757225312764,"rank":163,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.25285550611250557,"rank":122,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.25203867661856055,"rank":122,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.25446956743273014,"rank":122,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2535710570653832,"rank":122,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2547219198256814,"rank":122,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2517787699261656,"rank":123,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2573590083474601,"rank":122,"remainingConfigurations":444},{"removed":"livebench-data","score":0.255096033430333,"rank":122,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2516146241272373,"rank":122,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2531139149745643,"rank":122,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2592439018495646,"rank":122,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.253447604342358,"rank":124,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2544137706170005,"rank":122,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2553304037327849,"rank":123,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2619403265342264,"rank":123,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.25417305771334436,"rank":122,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2540144371048723,"rank":122,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2540188040457617,"rank":122,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.2542344310571309,"rank":122,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2535510199852571,"rank":122,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.25404940960171785,"rank":122,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.7-max--effort-reasoning":{"score":0.2537918558669812,"rank":123,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.30285492317997115,"rank":126,"remainingConfigurations":444},{"removed":"Datacurve","score":0.21383159626904372,"rank":125,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2525551196764647,"rank":123,"remainingConfigurations":444},{"removed":"Scale","score":0.27648932707442314,"rank":122,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2536208308922033,"rank":121,"remainingConfigurations":444},{"removed":"Cognition","score":0.2438979210356277,"rank":125,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2601707737238438,"rank":120,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.257710848401196,"rank":123,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2574927215777073,"rank":121,"remainingConfigurations":431},{"removed":"Vals AI","score":0.24543037245305674,"rank":123,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.25370887340608644,"rank":123,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.24813701210997444,"rank":124,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2534230081244176,"rank":123,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2537918558669812,"rank":123,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.25524279537870065,"rank":123,"remainingConfigurations":444},{"removed":"All provider reports","score":0.24920007424367271,"rank":124,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2617992751261297,"rank":121,"remainingConfigurations":444},{"removed":"briefcase","score":0.2606171235132153,"rank":120,"remainingConfigurations":444},{"removed":"aime","score":0.2528834186381981,"rank":124,"remainingConfigurations":444},{"removed":"apex-agents","score":0.256849207930589,"rank":122,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.24810541267251182,"rank":124,"remainingConfigurations":444},{"removed":"automationbench","score":0.2588828208888418,"rank":120,"remainingConfigurations":444},{"removed":"critpt","score":0.25002232649817474,"rank":124,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.23810468973596075,"rank":128,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.27390591159007105,"rank":120,"remainingConfigurations":444},{"removed":"gdpval","score":0.254357325108942,"rank":122,"remainingConfigurations":444},{"removed":"gmmlu","score":0.25432261122907984,"rank":123,"remainingConfigurations":444},{"removed":"gpqa","score":0.2411308944697327,"rank":126,"remainingConfigurations":444},{"removed":"harvey","score":0.25145101930189434,"rank":123,"remainingConfigurations":444},{"removed":"hle","score":0.25881091357284,"rank":125,"remainingConfigurations":444},{"removed":"ifbench","score":0.24159591956376972,"rank":127,"remainingConfigurations":444},{"removed":"itbench","score":0.2366786718153111,"rank":129,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2529710064104198,"rank":123,"remainingConfigurations":444},{"removed":"math500","score":0.254088607331764,"rank":123,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2582581665771238,"rank":123,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2668309654885002,"rank":123,"remainingConfigurations":444},{"removed":"omniscience","score":0.26564520705016764,"rank":120,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2654002519162008,"rank":121,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.25674837795290595,"rank":123,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2529600981564473,"rank":122,"remainingConfigurations":444},{"removed":"arc-agi","score":0.29533255494774774,"rank":125,"remainingConfigurations":444},{"removed":"deepswe","score":0.21398110577531324,"rank":125,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2538416549414842,"rank":123,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2513236638385719,"rank":124,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2438979210356277,"rank":125,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.25196453330969537,"rank":123,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2515792036312497,"rank":123,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.253607167008765,"rank":123,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.25283368941868595,"rank":123,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2539402420397145,"rank":123,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.25203722614834334,"rank":122,"remainingConfigurations":444},{"removed":"livebench-language","score":0.25652198248584246,"rank":123,"remainingConfigurations":444},{"removed":"livebench-data","score":0.25376544746374474,"rank":123,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.25024650185929115,"rank":123,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2527019984528192,"rank":123,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2573139111527933,"rank":123,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.257710848401196,"rank":123,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2539768378284806,"rank":123,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.24534871503993735,"rank":124,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2619063918424808,"rank":124,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2531783429736553,"rank":123,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2531950547755308,"rank":123,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2531046581344531,"rank":123,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.25357414707779496,"rank":123,"remainingConfigurations":444},{"removed":"vibe-code","score":0.25268221793941853,"rank":123,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.25329465811858864,"rank":123,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.8-27b--effort-xhigh":{"score":0.2508713179395796,"rank":124,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.23308127198980955,"rank":108,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.33143475697650654,"rank":120,"remainingConfigurations":444},{"removed":"Datacurve","score":0.20777949966027753,"rank":127,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2518809908414665,"rank":124,"remainingConfigurations":444},{"removed":"Scale","score":0.2728512135573153,"rank":124,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2491452735969819,"rank":124,"remainingConfigurations":444},{"removed":"Cognition","score":0.24310195482171829,"rank":127,"remainingConfigurations":444},{"removed":"LiveBench","score":0.25661489790554043,"rank":123,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.25147816039207704,"rank":125,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.25378698515707715,"rank":122,"remainingConfigurations":431},{"removed":"Vals AI","score":0.24172098823353913,"rank":125,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2508044442393858,"rank":124,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.24592105966958386,"rank":125,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2505989112664831,"rank":124,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2508713179395796,"rank":124,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.25254870514220795,"rank":124,"remainingConfigurations":444},{"removed":"All provider reports","score":0.24730344599823392,"rank":125,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.25225140663402085,"rank":124,"remainingConfigurations":444},{"removed":"briefcase","score":0.24402034435726283,"rank":126,"remainingConfigurations":444},{"removed":"aime","score":0.24856844330899355,"rank":126,"remainingConfigurations":444},{"removed":"apex-agents","score":0.25280479028514874,"rank":124,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.23979522907018425,"rank":127,"remainingConfigurations":444},{"removed":"automationbench","score":0.2478124660495439,"rank":125,"remainingConfigurations":444},{"removed":"critpt","score":0.2538255840397373,"rank":123,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2403800330374415,"rank":127,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2506126804576983,"rank":124,"remainingConfigurations":444},{"removed":"gdpval","score":0.24695255493950471,"rank":124,"remainingConfigurations":444},{"removed":"gmmlu","score":0.25082337834917606,"rank":124,"remainingConfigurations":444},{"removed":"gpqa","score":0.24629873870941696,"rank":123,"remainingConfigurations":444},{"removed":"harvey","score":0.2484218541028775,"rank":124,"remainingConfigurations":444},{"removed":"hle","score":0.2639671787279517,"rank":123,"remainingConfigurations":444},{"removed":"ifbench","score":0.24676766237066117,"rank":124,"remainingConfigurations":444},{"removed":"itbench","score":0.2504878680380392,"rank":123,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2512944909834291,"rank":124,"remainingConfigurations":444},{"removed":"math500","score":0.25062180739263973,"rank":124,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.25502364822172624,"rank":124,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.26617576831716655,"rank":124,"remainingConfigurations":444},{"removed":"omniscience","score":0.28326901620536565,"rank":117,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2443406419891866,"rank":126,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.25863483223993144,"rank":121,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.24923334818846318,"rank":125,"remainingConfigurations":444},{"removed":"arc-agi","score":0.32393131768048083,"rank":118,"remainingConfigurations":444},{"removed":"deepswe","score":0.2078537476023258,"rank":127,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2509070176078735,"rank":124,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2485728913539272,"rank":125,"remainingConfigurations":444},{"removed":"frontiercode","score":0.24310195482171829,"rank":127,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.248852442783859,"rank":124,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.24861604879742952,"rank":124,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2506600265249856,"rank":124,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2500376789936011,"rank":124,"remainingConfigurations":444},{"removed":"livebench-math","score":0.25102471251002406,"rank":124,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.24914180643795958,"rank":124,"remainingConfigurations":444},{"removed":"livebench-language","score":0.25331501506417603,"rank":124,"remainingConfigurations":444},{"removed":"livebench-data","score":0.25072063778269854,"rank":124,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2474260428762799,"rank":124,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.24982027207938884,"rank":124,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2546478427603278,"rank":124,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.25147816039207704,"rank":125,"remainingConfigurations":444},{"removed":"frontiermath","score":0.25164859367644016,"rank":124,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.24194479268292834,"rank":125,"remainingConfigurations":444},{"removed":"simpleqa","score":0.25861104882228475,"rank":125,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2502531976900783,"rank":124,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2502333488883089,"rank":124,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2502874922388097,"rank":124,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.2505329435290187,"rank":124,"remainingConfigurations":444},{"removed":"vibe-code","score":0.24966061259445757,"rank":124,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.25036849612741624,"rank":124,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-sol--effort-low":{"score":0.24707877907960443,"rank":125,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.22541896618992582,"rank":111,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.28410828121403625,"rank":130,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2056718352403283,"rank":128,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.24694138550928912,"rank":125,"remainingConfigurations":444},{"removed":"Scale","score":0.2686884822129854,"rank":125,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.24492004448427115,"rank":126,"remainingConfigurations":444},{"removed":"Cognition","score":0.2734078018444284,"rank":117,"remainingConfigurations":444},{"removed":"LiveBench","score":0.254176088128163,"rank":126,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.24319059628454986,"rank":126,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.23089114628355922,"rank":131,"remainingConfigurations":431},{"removed":"Vals AI","score":0.23877497925521599,"rank":126,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.24707109078971223,"rank":125,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.24293630497673938,"rank":126,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.24698422611092882,"rank":125,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.24707877907960443,"rank":125,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.24925870598246794,"rank":126,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2450502047335881,"rank":127,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2479446929075341,"rank":125,"remainingConfigurations":444},{"removed":"briefcase","score":0.24707867187602614,"rank":124,"remainingConfigurations":444},{"removed":"aime","score":0.2437830739480179,"rank":128,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2486863847894695,"rank":125,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.24738106979787278,"rank":125,"remainingConfigurations":444},{"removed":"automationbench","score":0.2453502381165721,"rank":126,"remainingConfigurations":444},{"removed":"critpt","score":0.2463363642819818,"rank":126,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.24732962056627486,"rank":123,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2441053788178267,"rank":127,"remainingConfigurations":444},{"removed":"gdpval","score":0.24611947465638706,"rank":125,"remainingConfigurations":444},{"removed":"gmmlu","score":0.24746220877104466,"rank":125,"remainingConfigurations":444},{"removed":"gpqa","score":0.24473683694280202,"rank":124,"remainingConfigurations":444},{"removed":"harvey","score":0.24496923165858328,"rank":125,"remainingConfigurations":444},{"removed":"hle","score":0.25858108898938675,"rank":126,"remainingConfigurations":444},{"removed":"ifbench","score":0.24984660553076865,"rank":123,"remainingConfigurations":444},{"removed":"itbench","score":0.24650450676958777,"rank":124,"remainingConfigurations":444},{"removed":"livecodebench","score":0.24715130193978616,"rank":125,"remainingConfigurations":444},{"removed":"math500","score":0.2471868175584109,"rank":125,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2522765594833007,"rank":126,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.25696141319088106,"rank":127,"remainingConfigurations":444},{"removed":"omniscience","score":0.2431908440880279,"rank":127,"remainingConfigurations":444},{"removed":"tau-bench","score":0.24920294479069374,"rank":124,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.24815370865656572,"rank":125,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.2460007924654479,"rank":126,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2962910232292279,"rank":124,"remainingConfigurations":444},{"removed":"deepswe","score":0.20564792236869303,"rank":128,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.24710920017107407,"rank":125,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.24380685953571524,"rank":128,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2734078018444284,"rank":117,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.24570550653816625,"rank":125,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2445481171429532,"rank":125,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2470051069824795,"rank":125,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.24605532937113703,"rank":125,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2474479195665047,"rank":125,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.24503616784982776,"rank":125,"remainingConfigurations":444},{"removed":"livebench-language","score":0.24940544745367355,"rank":125,"remainingConfigurations":444},{"removed":"livebench-data","score":0.24693999639623432,"rank":126,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2437220309031751,"rank":125,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.2459749080218766,"rank":125,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2510454847959458,"rank":125,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.24319059628454986,"rank":126,"remainingConfigurations":444},{"removed":"frontiermath","score":0.24801053629725858,"rank":125,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.24073291665492802,"rank":127,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2554342971494284,"rank":126,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2464974458164666,"rank":126,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.24636710435891718,"rank":125,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2466305277071137,"rank":125,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.24657258914703006,"rank":126,"remainingConfigurations":444},{"removed":"vibe-code","score":0.24584957434192156,"rank":126,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.24676189842727644,"rank":126,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5.2--effort-max":{"score":0.24611727687589333,"rank":126,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2392527366050734,"rank":107,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.27762136269345544,"rank":132,"remainingConfigurations":444},{"removed":"Datacurve","score":0.22691239623122714,"rank":121,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2458310343306522,"rank":127,"remainingConfigurations":444},{"removed":"Scale","score":0.26701114990131064,"rank":126,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.24809370052407934,"rank":125,"remainingConfigurations":444},{"removed":"Cognition","score":0.2435963029948749,"rank":126,"remainingConfigurations":444},{"removed":"LiveBench","score":0.25474408051600855,"rank":125,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.24298947286075867,"rank":128,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.24888308393161207,"rank":124,"remainingConfigurations":431},{"removed":"Vals AI","score":0.22638653293167146,"rank":130,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.24616290334982538,"rank":126,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2606656481654873,"rank":121,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2462685251668161,"rank":126,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.24611727687589333,"rank":126,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2464530447123919,"rank":128,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2616588519744361,"rank":121,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.24663295021073425,"rank":126,"remainingConfigurations":444},{"removed":"briefcase","score":0.24432792023024308,"rank":125,"remainingConfigurations":444},{"removed":"aime","score":0.2480636691331737,"rank":127,"remainingConfigurations":444},{"removed":"apex-agents","score":0.24322925294008926,"rank":127,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.24834459667306874,"rank":123,"remainingConfigurations":444},{"removed":"automationbench","score":0.24921173445608635,"rank":124,"remainingConfigurations":444},{"removed":"critpt","score":0.24447786577938302,"rank":127,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.24460969948251202,"rank":125,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.25049583479338233,"rank":125,"remainingConfigurations":444},{"removed":"gdpval","score":0.24468613257417937,"rank":126,"remainingConfigurations":444},{"removed":"gmmlu","score":0.24632123903198055,"rank":126,"remainingConfigurations":444},{"removed":"gpqa","score":0.22992654140912128,"rank":130,"remainingConfigurations":444},{"removed":"harvey","score":0.23645883811202847,"rank":128,"remainingConfigurations":444},{"removed":"hle","score":0.25337488592465046,"rank":128,"remainingConfigurations":444},{"removed":"ifbench","score":0.24588419758966795,"rank":125,"remainingConfigurations":444},{"removed":"itbench","score":0.241408225221617,"rank":126,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2459605779049275,"rank":127,"remainingConfigurations":444},{"removed":"math500","score":0.24622521369475603,"rank":126,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2524878072428595,"rank":125,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2560979050895902,"rank":128,"remainingConfigurations":444},{"removed":"omniscience","score":0.25238971728170817,"rank":124,"remainingConfigurations":444},{"removed":"tau-bench","score":0.24346190685136956,"rank":127,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.24700841128575488,"rank":127,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.25300058251102,"rank":121,"remainingConfigurations":444},{"removed":"arc-agi","score":0.27183279763278406,"rank":131,"remainingConfigurations":444},{"removed":"deepswe","score":0.23059731901455663,"rank":120,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.24601614130749894,"rank":126,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2446228341462753,"rank":127,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2435963029948749,"rank":126,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.24545759324618902,"rank":126,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2438182883355304,"rank":126,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.24580705953941437,"rank":127,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.24504086875056638,"rank":127,"remainingConfigurations":444},{"removed":"livebench-math","score":0.24649515199213112,"rank":126,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.24365178460426193,"rank":127,"remainingConfigurations":444},{"removed":"livebench-language","score":0.24848461747210818,"rank":126,"remainingConfigurations":444},{"removed":"livebench-data","score":0.24700014614413654,"rank":125,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.24302538869370305,"rank":126,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.24484446965424708,"rank":127,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.24935652641524528,"rank":127,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.24298947286075867,"rank":128,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2397819903778808,"rank":129,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.240270183594448,"rank":128,"remainingConfigurations":444},{"removed":"simpleqa","score":0.26275371083073756,"rank":122,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.24703594222059266,"rank":125,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.24223928514564,"rank":127,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.24503905959209138,"rank":127,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.24734690459189426,"rank":125,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2479927203344008,"rank":125,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2471290232670308,"rank":125,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.5--effort-medium":{"score":0.2459699260047997,"rank":127,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.22930645551854614,"rank":109,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.30054717974909284,"rank":127,"remainingConfigurations":444},{"removed":"Datacurve","score":0.20304702205145508,"rank":129,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.24639994804696672,"rank":126,"remainingConfigurations":444},{"removed":"Scale","score":0.2669782528719716,"rank":127,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.23869165903404954,"rank":127,"remainingConfigurations":444},{"removed":"Cognition","score":0.25096121623955686,"rank":124,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2552364338950031,"rank":124,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2431171608853111,"rank":127,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.252467935398515,"rank":123,"remainingConfigurations":431},{"removed":"Vals AI","score":0.23192968989172294,"rank":128,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.24589569714739304,"rank":127,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.24150270064269705,"rank":127,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.24566626710158734,"rank":127,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.2459699260047997,"rank":127,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.24766180047074815,"rank":127,"remainingConfigurations":444},{"removed":"All provider reports","score":0.24284813497651447,"rank":128,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.24584518650587875,"rank":127,"remainingConfigurations":444},{"removed":"briefcase","score":0.2437300139881401,"rank":127,"remainingConfigurations":444},{"removed":"aime","score":0.24352700952744222,"rank":129,"remainingConfigurations":444},{"removed":"apex-agents","score":0.24727805198875266,"rank":126,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.24645774189112957,"rank":126,"remainingConfigurations":444},{"removed":"automationbench","score":0.2430869669943236,"rank":127,"remainingConfigurations":444},{"removed":"critpt","score":0.24734234617745554,"rank":125,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.24593952690398826,"rank":124,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.24606100625009997,"rank":126,"remainingConfigurations":444},{"removed":"gdpval","score":0.2445065953675254,"rank":127,"remainingConfigurations":444},{"removed":"gmmlu","score":0.24601389611756805,"rank":127,"remainingConfigurations":444},{"removed":"gpqa","score":0.24386809461435652,"rank":125,"remainingConfigurations":444},{"removed":"harvey","score":0.24294886980586758,"rank":126,"remainingConfigurations":444},{"removed":"hle","score":0.2591608219545936,"rank":124,"remainingConfigurations":444},{"removed":"ifbench","score":0.24434966321055307,"rank":126,"remainingConfigurations":444},{"removed":"itbench","score":0.24563376814389293,"rank":125,"remainingConfigurations":444},{"removed":"livecodebench","score":0.24630395734975755,"rank":126,"remainingConfigurations":444},{"removed":"math500","score":0.2459465779050166,"rank":127,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2509061813532587,"rank":127,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.25802129236341803,"rank":126,"remainingConfigurations":444},{"removed":"omniscience","score":0.24533287514232735,"rank":126,"remainingConfigurations":444},{"removed":"tau-bench","score":0.24563959780364975,"rank":125,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.24711716083720822,"rank":126,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.24050728180118305,"rank":127,"remainingConfigurations":444},{"removed":"arc-agi","score":0.3188837405305262,"rank":121,"remainingConfigurations":444},{"removed":"deepswe","score":0.20303271997652508,"rank":129,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.24599922236243424,"rank":127,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.26526007727753126,"rank":121,"remainingConfigurations":444},{"removed":"frontiercode","score":0.25096121623955686,"rank":124,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.24383875692941812,"rank":127,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.24373039233475682,"rank":127,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2458206360917631,"rank":126,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.24509166098103866,"rank":126,"remainingConfigurations":444},{"removed":"livebench-math","score":0.245808228488718,"rank":127,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.24440976329396,"rank":126,"remainingConfigurations":444},{"removed":"livebench-language","score":0.24845832226749798,"rank":127,"remainingConfigurations":444},{"removed":"livebench-data","score":0.24612895158359915,"rank":127,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.24240786454569171,"rank":127,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.24522481459991183,"rank":126,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2493977143088751,"rank":126,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2431171608853111,"rank":127,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2459855724199788,"rank":126,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.24157010786585278,"rank":126,"remainingConfigurations":444},{"removed":"simpleqa","score":0.254100279913491,"rank":127,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.24609185970881753,"rank":127,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.24531215983947294,"rank":126,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.24510855942301657,"rank":126,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.24592198711799465,"rank":127,"remainingConfigurations":444},{"removed":"vibe-code","score":0.24468000563859726,"rank":127,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2452173890417305,"rank":127,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-xhigh":{"score":0.24055108967234728,"rank":128,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.20034742998841967,"rank":117,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.36046674784199323,"rank":110,"remainingConfigurations":444},{"removed":"Datacurve","score":0.20151795007088036,"rank":130,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.24063159882630192,"rank":128,"remainingConfigurations":444},{"removed":"Scale","score":0.2618400011668143,"rank":128,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2364433725232814,"rank":128,"remainingConfigurations":444},{"removed":"Cognition","score":0.18679595741998,"rank":139,"remainingConfigurations":444},{"removed":"LiveBench","score":0.24925153945765763,"rank":127,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2409719308158221,"rank":129,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.24861024015117306,"rank":126,"remainingConfigurations":431},{"removed":"Vals AI","score":0.23260403978148192,"rank":127,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2404608524970977,"rank":128,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.23645237811956496,"rank":128,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.24021872150729437,"rank":128,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.24055108967234728,"rank":128,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.24439310154820457,"rank":129,"remainingConfigurations":444},{"removed":"All provider reports","score":0.23987948859380992,"rank":129,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.24158546035637354,"rank":128,"remainingConfigurations":444},{"removed":"briefcase","score":0.23887684135757037,"rank":129,"remainingConfigurations":444},{"removed":"aime","score":0.2387927626035381,"rank":130,"remainingConfigurations":444},{"removed":"apex-agents","score":0.24226919992168128,"rank":128,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2392419843065843,"rank":128,"remainingConfigurations":444},{"removed":"automationbench","score":0.23857583422207393,"rank":129,"remainingConfigurations":444},{"removed":"critpt","score":0.23966984598756227,"rank":128,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.24100334973367143,"rank":126,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.23764690190137913,"rank":128,"remainingConfigurations":444},{"removed":"gdpval","score":0.23906612193709662,"rank":128,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2409806586643873,"rank":128,"remainingConfigurations":444},{"removed":"gpqa","score":0.23916403424861357,"rank":127,"remainingConfigurations":444},{"removed":"harvey","score":0.2386362955748016,"rank":127,"remainingConfigurations":444},{"removed":"hle","score":0.25480857927724365,"rank":127,"remainingConfigurations":444},{"removed":"ifbench","score":0.23961699174778894,"rank":128,"remainingConfigurations":444},{"removed":"itbench","score":0.24021838415320393,"rank":127,"remainingConfigurations":444},{"removed":"livecodebench","score":0.24073128590794582,"rank":128,"remainingConfigurations":444},{"removed":"math500","score":0.2405675277319909,"rank":128,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.24528325495746242,"rank":128,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2513355892910511,"rank":129,"remainingConfigurations":444},{"removed":"omniscience","score":0.23874652650328967,"rank":128,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2416428461364664,"rank":128,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.24160621713117203,"rank":128,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.23935766897045765,"rank":128,"remainingConfigurations":444},{"removed":"arc-agi","score":0.27102380955764516,"rank":132,"remainingConfigurations":444},{"removed":"deepswe","score":0.20135581576814807,"rank":130,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.24056968186567942,"rank":128,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2767530666260839,"rank":118,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18679595741998,"rank":139,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2384559082457304,"rank":128,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.23811702043296132,"rank":128,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2404162774911306,"rank":128,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.23990880833033415,"rank":128,"remainingConfigurations":444},{"removed":"livebench-math","score":0.24078068156606028,"rank":128,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2387001687326773,"rank":128,"remainingConfigurations":444},{"removed":"livebench-language","score":0.24286105643302439,"rank":128,"remainingConfigurations":444},{"removed":"livebench-data","score":0.24020455736275448,"rank":128,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.23721303581361886,"rank":128,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.23946810187329085,"rank":128,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2446718301518761,"rank":128,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2409719308158221,"rank":129,"remainingConfigurations":444},{"removed":"frontiermath","score":0.24010102449909707,"rank":128,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.23635228488317886,"rank":129,"remainingConfigurations":444},{"removed":"simpleqa","score":0.24847727962570512,"rank":128,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.24015725421121367,"rank":128,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.23968398664879412,"rank":128,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.2402257527793816,"rank":128,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.2399455627382825,"rank":128,"remainingConfigurations":444},{"removed":"vibe-code","score":0.23915460661361831,"rank":128,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.24026513352922832,"rank":128,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3-flash-preview--effort-high":{"score":0.23304171955123917,"rank":129,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.22783080239789733,"rank":110,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2839467000487064,"rank":131,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1918653728676075,"rank":131,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.23368044014164605,"rank":129,"remainingConfigurations":444},{"removed":"Scale","score":0.25283718576977426,"rank":130,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.23223038890087708,"rank":130,"remainingConfigurations":444},{"removed":"Cognition","score":0.23114154119014382,"rank":128,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2354678459424706,"rank":130,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.22978708618237845,"rank":133,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.16867603307670423,"rank":157,"remainingConfigurations":431},{"removed":"Vals AI","score":0.287345731117755,"rank":111,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.2329728746757956,"rank":129,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.22887038603814291,"rank":129,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.23298643076428052,"rank":129,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.23304171955123917,"rank":129,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.23413018535489363,"rank":131,"remainingConfigurations":444},{"removed":"All provider reports","score":0.22988098612109023,"rank":131,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2335421676561851,"rank":130,"remainingConfigurations":444},{"removed":"briefcase","score":0.23204948428799566,"rank":131,"remainingConfigurations":444},{"removed":"aime","score":0.22705983970585586,"rank":134,"remainingConfigurations":444},{"removed":"apex-agents","score":0.23395989530694172,"rank":130,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.23268611528095876,"rank":129,"remainingConfigurations":444},{"removed":"automationbench","score":0.23218717903371056,"rank":130,"remainingConfigurations":444},{"removed":"critpt","score":0.2333974319064552,"rank":130,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2330749140051148,"rank":131,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.23412916363120598,"rank":129,"remainingConfigurations":444},{"removed":"gdpval","score":0.2323698691527536,"rank":130,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2331312644609462,"rank":129,"remainingConfigurations":444},{"removed":"gpqa","score":0.2324816573760852,"rank":128,"remainingConfigurations":444},{"removed":"harvey","score":0.2334784200551608,"rank":129,"remainingConfigurations":444},{"removed":"hle","score":0.2445705178905063,"rank":130,"remainingConfigurations":444},{"removed":"ifbench","score":0.23196810524301456,"rank":129,"remainingConfigurations":444},{"removed":"itbench","score":0.23228758503682465,"rank":131,"remainingConfigurations":444},{"removed":"livecodebench","score":0.23372039958536187,"rank":129,"remainingConfigurations":444},{"removed":"math500","score":0.23311126883433272,"rank":129,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.22342999842706027,"rank":136,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.24440606363087533,"rank":131,"remainingConfigurations":444},{"removed":"omniscience","score":0.2318241610285906,"rank":130,"remainingConfigurations":444},{"removed":"tau-bench","score":0.23177563110867017,"rank":130,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2337181180364641,"rank":130,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.23679525409530724,"rank":129,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2755507041173746,"rank":129,"remainingConfigurations":444},{"removed":"deepswe","score":0.19204769355544074,"rank":131,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.23309827375072656,"rank":129,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.22797897187062643,"rank":132,"remainingConfigurations":444},{"removed":"frontiercode","score":0.23114154119014382,"rank":128,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.23149160378248346,"rank":129,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.23098607139187652,"rank":129,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2329033982506771,"rank":129,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.23151969459007635,"rank":130,"remainingConfigurations":444},{"removed":"livebench-math","score":0.23349427408204224,"rank":129,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2311098687827556,"rank":130,"remainingConfigurations":444},{"removed":"livebench-language","score":0.23538614741211625,"rank":129,"remainingConfigurations":444},{"removed":"livebench-data","score":0.23330780184661296,"rank":129,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2297245845204974,"rank":130,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.23210638637363376,"rank":129,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.23616106392753275,"rank":130,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.22978708618237845,"rank":133,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2412656878061141,"rank":127,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.26561791981688293,"rank":120,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19851103601223763,"rank":141,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.23386305955781592,"rank":129,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2360281484898187,"rank":129,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.23161369896593842,"rank":130,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.23535188372055224,"rank":129,"remainingConfigurations":444},{"removed":"vibe-code","score":0.23535773880190444,"rank":129,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2312618188166801,"rank":130,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.7--effort-low":{"score":0.23260427337761289,"rank":130,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12871817702354219,"rank":133,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.4875453927793007,"rank":77,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1910560115619527,"rank":132,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2325462548550192,"rank":130,"remainingConfigurations":444},{"removed":"Scale","score":0.25440914933235464,"rank":129,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2308137858409478,"rank":131,"remainingConfigurations":444},{"removed":"Cognition","score":0.2140257345547513,"rank":134,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2401607669936957,"rank":128,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.23287090942251962,"rank":130,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.2391955232592287,"rank":128,"remainingConfigurations":431},{"removed":"Vals AI","score":0.2246103937237823,"rank":131,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.23251022069827296,"rank":130,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2279733660144204,"rank":130,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.23224942730400308,"rank":130,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.23260427337761289,"rank":130,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.23503130277584536,"rank":130,"remainingConfigurations":444},{"removed":"All provider reports","score":0.22997737257350492,"rank":130,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.2344086890640442,"rank":129,"remainingConfigurations":444},{"removed":"briefcase","score":0.22363390859175622,"rank":133,"remainingConfigurations":444},{"removed":"aime","score":0.23097105794497666,"rank":132,"remainingConfigurations":444},{"removed":"apex-agents","score":0.23489405435931024,"rank":129,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.23257852330802375,"rank":130,"remainingConfigurations":444},{"removed":"automationbench","score":0.2259800287105422,"rank":132,"remainingConfigurations":444},{"removed":"critpt","score":0.23549648410888782,"rank":129,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2337753554070544,"rank":130,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.22856469614779426,"rank":131,"remainingConfigurations":444},{"removed":"gdpval","score":0.22759830189693675,"rank":132,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2331079492671785,"rank":130,"remainingConfigurations":444},{"removed":"gpqa","score":0.23241418486641172,"rank":129,"remainingConfigurations":444},{"removed":"harvey","score":0.23080957052530673,"rank":131,"remainingConfigurations":444},{"removed":"hle","score":0.24678883063391424,"rank":129,"remainingConfigurations":444},{"removed":"ifbench","score":0.23098497071782498,"rank":130,"remainingConfigurations":444},{"removed":"itbench","score":0.23262192949160665,"rank":130,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2327775288682826,"rank":130,"remainingConfigurations":444},{"removed":"math500","score":0.23270538445692238,"rank":130,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2375135437326932,"rank":129,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.24793288631977736,"rank":130,"remainingConfigurations":444},{"removed":"omniscience","score":0.23169947228500995,"rank":131,"remainingConfigurations":444},{"removed":"tau-bench","score":0.23421423056560564,"rank":129,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2338083130080055,"rank":129,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.23461708990631527,"rank":130,"remainingConfigurations":444},{"removed":"arc-agi","score":0.34062447475958163,"rank":111,"remainingConfigurations":444},{"removed":"deepswe","score":0.191046871731676,"rank":132,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.2326347545686588,"rank":130,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.21972660409636566,"rank":134,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2140257345547513,"rank":134,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2306289587998611,"rank":131,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.23049996632950784,"rank":130,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.23242545127333333,"rank":130,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.23185476898429905,"rank":129,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2327512391803437,"rank":130,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2307710265858974,"rank":131,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2350070269532117,"rank":130,"remainingConfigurations":444},{"removed":"livebench-data","score":0.23252923331782324,"rank":130,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.22917623443842575,"rank":131,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.23153357670194893,"rank":130,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.236486223923294,"rank":129,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.23287090942251962,"rank":130,"remainingConfigurations":444},{"removed":"frontiermath","score":0.23278235552115567,"rank":130,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.22691068492496927,"rank":131,"remainingConfigurations":444},{"removed":"simpleqa","score":0.24030433869359935,"rank":129,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.23211407649189195,"rank":130,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.23190669745383574,"rank":130,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.23215926200313552,"rank":129,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.2321473749025551,"rank":130,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2313549322482473,"rank":130,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.23218979349510652,"rank":129,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k2.6--effort-reasoning":{"score":0.23141342309568821,"rank":131,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2655711914539739,"rank":135,"remainingConfigurations":444},{"removed":"Datacurve","score":0.21206963025224004,"rank":126,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.23065715046354718,"rank":132,"remainingConfigurations":444},{"removed":"Scale","score":0.2416216841479281,"rank":135,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.23560407070484776,"rank":129,"remainingConfigurations":444},{"removed":"Cognition","score":0.2238896730140084,"rank":131,"remainingConfigurations":444},{"removed":"LiveBench","score":0.22871975113551926,"rank":134,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.23271984209338528,"rank":131,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.22896848006688278,"rank":135,"remainingConfigurations":431},{"removed":"Vals AI","score":0.23011983219973883,"rank":129,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.23138757605960902,"rank":131,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2048501524909646,"rank":136,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.23124715113279684,"rank":131,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.23141342309568821,"rank":131,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.23233031222714964,"rank":132,"remainingConfigurations":444},{"removed":"All provider reports","score":0.20584245806693305,"rank":136,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.23234278266644903,"rank":131,"remainingConfigurations":444},{"removed":"briefcase","score":0.23912324619807657,"rank":128,"remainingConfigurations":444},{"removed":"aime","score":0.232044622717182,"rank":131,"remainingConfigurations":444},{"removed":"apex-agents","score":0.22483853434528925,"rank":134,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.22392205814644972,"rank":134,"remainingConfigurations":444},{"removed":"automationbench","score":0.2390246383079698,"rank":128,"remainingConfigurations":444},{"removed":"critpt","score":0.23081251036568196,"rank":131,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.23412543144924955,"rank":129,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.231626848523686,"rank":130,"remainingConfigurations":444},{"removed":"gdpval","score":0.23426097060257256,"rank":129,"remainingConfigurations":444},{"removed":"gmmlu","score":0.23195834179082706,"rank":131,"remainingConfigurations":444},{"removed":"gpqa","score":0.22353756320484816,"rank":133,"remainingConfigurations":444},{"removed":"harvey","score":0.23125719490080487,"rank":130,"remainingConfigurations":444},{"removed":"hle","score":0.23281631481514012,"rank":135,"remainingConfigurations":444},{"removed":"ifbench","score":0.2252040986956448,"rank":132,"remainingConfigurations":444},{"removed":"itbench","score":0.2386848645904903,"rank":128,"remainingConfigurations":444},{"removed":"livecodebench","score":0.231225092407412,"rank":131,"remainingConfigurations":444},{"removed":"math500","score":0.23170493607550427,"rank":131,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.23348059203929905,"rank":131,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2682538450157901,"rank":121,"remainingConfigurations":444},{"removed":"omniscience","score":0.2341314255449453,"rank":129,"remainingConfigurations":444},{"removed":"tau-bench","score":0.22742189568485224,"rank":133,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.23324790767418727,"rank":131,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.18754534790657107,"rank":143,"remainingConfigurations":444},{"removed":"arc-agi","score":0.25826620233914904,"rank":134,"remainingConfigurations":444},{"removed":"deepswe","score":0.2121327585523692,"rank":126,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.231338681148023,"rank":131,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.22965929050174125,"rank":131,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2238896730140084,"rank":131,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2310826785185304,"rank":130,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.2303581043553535,"rank":131,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.23125465387047608,"rank":131,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.23073715862934419,"rank":131,"remainingConfigurations":444},{"removed":"livebench-math","score":0.23193517463636396,"rank":131,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2314398471606848,"rank":129,"remainingConfigurations":444},{"removed":"livebench-language","score":0.23242269956536907,"rank":132,"remainingConfigurations":444},{"removed":"livebench-data","score":0.23064241155628987,"rank":131,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2298817147128448,"rank":129,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.23095196698782838,"rank":131,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2325884190960854,"rank":132,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.23271984209338528,"rank":131,"remainingConfigurations":444},{"removed":"frontiermath","score":0.2320242130185299,"rank":131,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.22634123522913682,"rank":133,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2353977301492366,"rank":131,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.23088010043572305,"rank":131,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2311010859458428,"rank":131,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.23090915437081813,"rank":131,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.23127799045840605,"rank":131,"remainingConfigurations":444},{"removed":"vibe-code","score":0.23101274697415788,"rank":131,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.23105892092709998,"rank":131,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-sol--effort-low":{"score":0.23085843215777854,"rank":132,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.20286775081356587,"rank":116,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.32044456570819446,"rank":125,"remainingConfigurations":444},{"removed":"Datacurve","score":0.19029535706839343,"rank":133,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.23095023146615998,"rank":131,"remainingConfigurations":444},{"removed":"Scale","score":0.25184328307597004,"rank":131,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.22589209892956627,"rank":132,"remainingConfigurations":444},{"removed":"Cognition","score":0.18693889985816792,"rank":138,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2396813591798189,"rank":129,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.22998388866577105,"rank":132,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.23804411325538244,"rank":129,"remainingConfigurations":431},{"removed":"Vals AI","score":0.22275948901629486,"rank":132,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.23077753652275854,"rank":132,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.22687481446936486,"rank":131,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2305327081020845,"rank":132,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.23085843215777854,"rank":132,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2507043481102882,"rank":125,"remainingConfigurations":444},{"removed":"All provider reports","score":0.24612420041766056,"rank":126,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.23180531429103493,"rank":132,"remainingConfigurations":444},{"removed":"briefcase","score":0.23404968086456182,"rank":130,"remainingConfigurations":444},{"removed":"aime","score":0.2288972152160705,"rank":133,"remainingConfigurations":444},{"removed":"apex-agents","score":0.2325057794661657,"rank":131,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.23003782764538036,"rank":131,"remainingConfigurations":444},{"removed":"automationbench","score":0.22717159878084456,"rank":131,"remainingConfigurations":444},{"removed":"critpt","score":0.23030880764178252,"rank":132,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2312412631412599,"rank":132,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.225702986773794,"rank":134,"remainingConfigurations":444},{"removed":"gdpval","score":0.23171164533054725,"rank":131,"remainingConfigurations":444},{"removed":"gmmlu","score":0.23122615147080183,"rank":132,"remainingConfigurations":444},{"removed":"gpqa","score":0.22932420332272688,"rank":131,"remainingConfigurations":444},{"removed":"harvey","score":0.2289132702463946,"rank":132,"remainingConfigurations":444},{"removed":"hle","score":0.24437235225466317,"rank":131,"remainingConfigurations":444},{"removed":"ifbench","score":0.22972011217310853,"rank":131,"remainingConfigurations":444},{"removed":"itbench","score":0.23045944692363898,"rank":132,"remainingConfigurations":444},{"removed":"livecodebench","score":0.23101272953825316,"rank":132,"remainingConfigurations":444},{"removed":"math500","score":0.23084639400148296,"rank":132,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.23559000470748928,"rank":130,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2409836218573588,"rank":132,"remainingConfigurations":444},{"removed":"omniscience","score":0.22770003205886022,"rank":132,"remainingConfigurations":444},{"removed":"tau-bench","score":0.23171787857143622,"rank":132,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2326526060214864,"rank":132,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.22795886258579845,"rank":131,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2862409806378379,"rank":127,"remainingConfigurations":444},{"removed":"deepswe","score":0.19017608893975355,"rank":133,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.23087926458763597,"rank":132,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.23578942773775366,"rank":130,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18693889985816792,"rank":138,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.22877910303401572,"rank":132,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.22840032522760886,"rank":132,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.23073413169547094,"rank":132,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.23023171355549502,"rank":132,"remainingConfigurations":444},{"removed":"livebench-math","score":0.23108658020326958,"rank":132,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2289555922288581,"rank":132,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2331283721861814,"rank":131,"remainingConfigurations":444},{"removed":"livebench-data","score":0.2305435513063101,"rank":132,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.22755233796604588,"rank":132,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.22981819853898267,"rank":132,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.23498036782929754,"rank":131,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.22998388866577105,"rank":132,"remainingConfigurations":444},{"removed":"frontiermath","score":0.229329000334052,"rank":132,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2267937647777385,"rank":132,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2387536401015501,"rank":130,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.2305002444187065,"rank":132,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.23001529012651112,"rank":132,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.23055927375192395,"rank":132,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.23020202442096058,"rank":132,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2294623733618799,"rank":132,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.23057885590515959,"rank":132,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.2--effort-medium":{"score":0.22531502441808815,"rank":133,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2186091139332941,"rank":113,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.32321126512784143,"rank":123,"remainingConfigurations":444},{"removed":"Datacurve","score":0.18620230393407122,"rank":134,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.22551440854597912,"rank":133,"remainingConfigurations":444},{"removed":"Scale","score":0.2473852384529408,"rank":132,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2233008358406118,"rank":133,"remainingConfigurations":444},{"removed":"Cognition","score":0.2163078751114835,"rank":133,"remainingConfigurations":444},{"removed":"LiveBench","score":0.21973215568024887,"rank":135,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1549388998978923,"rank":161,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.22952511197921546,"rank":133,"remainingConfigurations":431},{"removed":"Vals AI","score":0.21588724930568592,"rank":133,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.22525780829906794,"rank":133,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.22102851364452433,"rank":132,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.22502891567042352,"rank":133,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.22531502441808815,"rank":133,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2267261740557912,"rank":133,"remainingConfigurations":444},{"removed":"All provider reports","score":0.22213165961871714,"rank":132,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.22612192870988554,"rank":133,"remainingConfigurations":444},{"removed":"briefcase","score":0.22542734738551293,"rank":132,"remainingConfigurations":444},{"removed":"aime","score":0.22207629617266003,"rank":135,"remainingConfigurations":444},{"removed":"apex-agents","score":0.22694346710536598,"rank":132,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2245435891454122,"rank":133,"remainingConfigurations":444},{"removed":"automationbench","score":0.2240832393999476,"rank":134,"remainingConfigurations":444},{"removed":"critpt","score":0.2239604164625131,"rank":134,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.22514235755283288,"rank":133,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.22678611736473417,"rank":132,"remainingConfigurations":444},{"removed":"gdpval","score":0.22488438516457973,"rank":133,"remainingConfigurations":444},{"removed":"gmmlu","score":0.22499760291918935,"rank":134,"remainingConfigurations":444},{"removed":"gpqa","score":0.2217053126707822,"rank":134,"remainingConfigurations":444},{"removed":"harvey","score":0.2232468618948181,"rank":133,"remainingConfigurations":444},{"removed":"hle","score":0.23814883773480877,"rank":132,"remainingConfigurations":444},{"removed":"ifbench","score":0.22498639087940617,"rank":133,"remainingConfigurations":444},{"removed":"itbench","score":0.224526925941526,"rank":134,"remainingConfigurations":444},{"removed":"livecodebench","score":0.22470743373610957,"rank":134,"remainingConfigurations":444},{"removed":"math500","score":0.22566196065054347,"rank":133,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.2307362096744082,"rank":133,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.23960190402083212,"rank":133,"remainingConfigurations":444},{"removed":"omniscience","score":0.21531314070657273,"rank":136,"remainingConfigurations":444},{"removed":"tau-bench","score":0.23175686401563736,"rank":131,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.22668399441576556,"rank":133,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.22261253068018613,"rank":133,"remainingConfigurations":444},{"removed":"arc-agi","score":0.314766547489039,"rank":122,"remainingConfigurations":444},{"removed":"deepswe","score":0.18625479134298162,"rank":134,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.22534279151798528,"rank":133,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2161991270256635,"rank":136,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2163078751114835,"rank":133,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.22368524442101304,"rank":134,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.22274872548383248,"rank":133,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.22518935949602212,"rank":133,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2245568495136477,"rank":133,"remainingConfigurations":444},{"removed":"livebench-math","score":0.2255412292273339,"rank":133,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.22354874661230825,"rank":133,"remainingConfigurations":444},{"removed":"livebench-language","score":0.22705715049036354,"rank":134,"remainingConfigurations":444},{"removed":"livebench-data","score":0.22535269481138145,"rank":134,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.22236471741540842,"rank":133,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.223842312700028,"rank":133,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.22949976605490527,"rank":133,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1549388998978923,"rank":161,"remainingConfigurations":444},{"removed":"frontiermath","score":0.22578487338261724,"rank":133,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.21965516568584229,"rank":134,"remainingConfigurations":444},{"removed":"simpleqa","score":0.23267697497827267,"rank":132,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.22468558184150064,"rank":133,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.22471818855957562,"rank":133,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.22478263926257427,"rank":133,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.22495736090273652,"rank":133,"remainingConfigurations":444},{"removed":"vibe-code","score":0.22421049875078147,"rank":133,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.22483093373549956,"rank":133,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5--effort-medium":{"score":0.22503557888922024,"rank":134,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2068654842486319,"rank":115,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23757068262636016,"rank":137,"remainingConfigurations":444},{"removed":"Datacurve","score":0.2159790670974964,"rank":122,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.22492603239262113,"rank":134,"remainingConfigurations":444},{"removed":"Scale","score":0.24545742390582528,"rank":133,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.21940936817030673,"rank":134,"remainingConfigurations":444},{"removed":"Cognition","score":0.16599510816265944,"rank":156,"remainingConfigurations":444},{"removed":"LiveBench","score":0.23128501126505582,"rank":131,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.22192134550949116,"rank":135,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.24869541485911584,"rank":125,"remainingConfigurations":431},{"removed":"Vals AI","score":0.21178154733793653,"rank":135,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.22502641910915222,"rank":134,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.2208678173782569,"rank":133,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.2249401497158632,"rank":134,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.22503557888922024,"rank":134,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.22564863545088107,"rank":134,"remainingConfigurations":444},{"removed":"All provider reports","score":0.22142745502020492,"rank":133,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.22552111933687813,"rank":134,"remainingConfigurations":444},{"removed":"briefcase","score":0.2224568525773449,"rank":134,"remainingConfigurations":444},{"removed":"aime","score":0.22184869439331367,"rank":136,"remainingConfigurations":444},{"removed":"apex-agents","score":0.22646680733736968,"rank":133,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.22666543594070668,"rank":132,"remainingConfigurations":444},{"removed":"automationbench","score":0.22520415974279617,"rank":133,"remainingConfigurations":444},{"removed":"critpt","score":0.2242065518543104,"rank":133,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.22510269103912983,"rank":134,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2261047876968859,"rank":133,"remainingConfigurations":444},{"removed":"gdpval","score":0.22375577683386352,"rank":134,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2253456046259558,"rank":133,"remainingConfigurations":444},{"removed":"gpqa","score":0.22631875990079164,"rank":132,"remainingConfigurations":444},{"removed":"harvey","score":0.22307871213718097,"rank":134,"remainingConfigurations":444},{"removed":"hle","score":0.23674444160946742,"rank":133,"remainingConfigurations":444},{"removed":"ifbench","score":0.22349068809271222,"rank":134,"remainingConfigurations":444},{"removed":"itbench","score":0.22459358726716613,"rank":133,"remainingConfigurations":444},{"removed":"livecodebench","score":0.22492548696950174,"rank":133,"remainingConfigurations":444},{"removed":"math500","score":0.22499443763041957,"rank":134,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.22909808948554322,"rank":134,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.23652965414657964,"rank":134,"remainingConfigurations":444},{"removed":"omniscience","score":0.22490444032803725,"rank":133,"remainingConfigurations":444},{"removed":"tau-bench","score":0.22419468185261274,"rank":134,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2240816222496945,"rank":134,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.22105289298995465,"rank":134,"remainingConfigurations":444},{"removed":"arc-agi","score":0.23574446122403284,"rank":135,"remainingConfigurations":444},{"removed":"deepswe","score":0.21614873751212269,"rank":122,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.22508278396460168,"rank":134,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.2233152258526073,"rank":133,"remainingConfigurations":444},{"removed":"frontiercode","score":0.16599510816265944,"rank":156,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.22388085845266706,"rank":133,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.22228070717869086,"rank":134,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.22493473828530475,"rank":134,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.22365658816101133,"rank":134,"remainingConfigurations":444},{"removed":"livebench-math","score":0.225035622785146,"rank":134,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.2219886941099866,"rank":134,"remainingConfigurations":444},{"removed":"livebench-language","score":0.22769180296803482,"rank":133,"remainingConfigurations":444},{"removed":"livebench-data","score":0.22559257435460064,"rank":133,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.2221729232227021,"rank":134,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.22343670982713867,"rank":134,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.2293757133503973,"rank":134,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.22192134550949116,"rank":135,"remainingConfigurations":444},{"removed":"frontiermath","score":0.22424499538063292,"rank":134,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.22942641074141465,"rank":130,"remainingConfigurations":444},{"removed":"simpleqa","score":0.23169336970332957,"rank":133,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.22439561888584555,"rank":134,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.22449930312756997,"rank":134,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.22433198201113433,"rank":134,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.22462723670472787,"rank":134,"remainingConfigurations":444},{"removed":"vibe-code","score":0.22410318439554136,"rank":134,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.22441045106394172,"rank":134,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-high":{"score":0.22113106689244924,"rank":135,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.18242338168647054,"rank":119,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.3392614101093551,"rank":117,"remainingConfigurations":444},{"removed":"Datacurve","score":0.18466792731041662,"rank":135,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.2212109764241812,"rank":135,"remainingConfigurations":444},{"removed":"Scale","score":0.2420363259153947,"rank":134,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.21751670893445138,"rank":136,"remainingConfigurations":444},{"removed":"Cognition","score":0.1657692362843986,"rank":157,"remainingConfigurations":444},{"removed":"LiveBench","score":0.22973705390198354,"rank":133,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2208838217114849,"rank":136,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.23007561502266152,"rank":132,"remainingConfigurations":431},{"removed":"Vals AI","score":0.21388638817869784,"rank":134,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.22104762102696962,"rank":135,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.21715278662804152,"rank":134,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.22082151920115292,"rank":135,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.22113106689244924,"rank":135,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2246978841583794,"rank":135,"remainingConfigurations":444},{"removed":"All provider reports","score":0.2203317786155448,"rank":134,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.22212655485799818,"rank":135,"remainingConfigurations":444},{"removed":"briefcase","score":0.2194134421033076,"rank":135,"remainingConfigurations":444},{"removed":"aime","score":0.21951209285550047,"rank":137,"remainingConfigurations":444},{"removed":"apex-agents","score":0.22280379196065536,"rank":135,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.21996622036704064,"rank":135,"remainingConfigurations":444},{"removed":"automationbench","score":0.21839010099773515,"rank":135,"remainingConfigurations":444},{"removed":"critpt","score":0.22012981600434142,"rank":136,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.22152978694388012,"rank":135,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2181652203389708,"rank":136,"remainingConfigurations":444},{"removed":"gdpval","score":0.2197159151118807,"rank":135,"remainingConfigurations":444},{"removed":"gmmlu","score":0.22158192292878784,"rank":135,"remainingConfigurations":444},{"removed":"gpqa","score":0.21972246270430654,"rank":135,"remainingConfigurations":444},{"removed":"harvey","score":0.21924445014097346,"rank":135,"remainingConfigurations":444},{"removed":"hle","score":0.23491679975559862,"rank":134,"remainingConfigurations":444},{"removed":"ifbench","score":0.22017717039825027,"rank":136,"remainingConfigurations":444},{"removed":"itbench","score":0.2207918052484952,"rank":135,"remainingConfigurations":444},{"removed":"livecodebench","score":0.2213539643686968,"rank":135,"remainingConfigurations":444},{"removed":"math500","score":0.22117351753052564,"rank":135,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.22577249372872218,"rank":135,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.2329868915213751,"rank":135,"remainingConfigurations":444},{"removed":"omniscience","score":0.21906117442698034,"rank":134,"remainingConfigurations":444},{"removed":"tau-bench","score":0.2220781235495418,"rank":135,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.2221120590572283,"rank":135,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.22075846698360432,"rank":135,"remainingConfigurations":444},{"removed":"arc-agi","score":0.25878233025907565,"rank":133,"remainingConfigurations":444},{"removed":"deepswe","score":0.18452953935010807,"rank":135,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.22115022308916799,"rank":135,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.24656785529559286,"rank":126,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1657692362843986,"rank":157,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.2191271408158356,"rank":135,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.21885162370347624,"rank":135,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.2210088933123763,"rank":135,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.22051522136822932,"rank":135,"remainingConfigurations":444},{"removed":"livebench-math","score":0.22135735417769986,"rank":135,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.21934913846847778,"rank":135,"remainingConfigurations":444},{"removed":"livebench-language","score":0.2233672030022867,"rank":135,"remainingConfigurations":444},{"removed":"livebench-data","score":0.22079692528910624,"rank":135,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.21791298754541752,"rank":135,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.22009617130003675,"rank":135,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.22508688445195738,"rank":135,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2208838217114849,"rank":136,"remainingConfigurations":444},{"removed":"frontiermath","score":0.22077069086989823,"rank":135,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.21743282584483622,"rank":135,"remainingConfigurations":444},{"removed":"simpleqa","score":0.22874603683949124,"rank":134,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.22072936946364052,"rank":136,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.22031407607962425,"rank":135,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.22081000281317917,"rank":136,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.22056135558593745,"rank":136,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2198048466470411,"rank":135,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.22084573839772828,"rank":135,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-flash--effort-high":{"score":0.21941248809962402,"rank":136,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.22070143798760045,"rank":112,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.17782831974910726,"rank":164,"remainingConfigurations":444},{"removed":"Datacurve","score":0.17060366618890088,"rank":136,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.22026827195439191,"rank":136,"remainingConfigurations":444},{"removed":"Scale","score":0.23979224354041392,"rank":136,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.2178398139244667,"rank":135,"remainingConfigurations":444},{"removed":"Cognition","score":0.3535647312124876,"rank":100,"remainingConfigurations":444},{"removed":"LiveBench","score":0.2305518193431696,"rank":132,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2161803463389068,"rank":137,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.231360624150625,"rank":130,"remainingConfigurations":431},{"removed":"Vals AI","score":0.15829361831673314,"rank":157,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.21934077831388485,"rank":136,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.21526473036016802,"rank":135,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.21909287488805176,"rank":136,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.21941248809962402,"rank":136,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.22010914017348945,"rank":136,"remainingConfigurations":444},{"removed":"All provider reports","score":0.21561603449190125,"rank":135,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.21972858951973132,"rank":136,"remainingConfigurations":444},{"removed":"briefcase","score":0.21871839799825368,"rank":136,"remainingConfigurations":444},{"removed":"aime","score":0.21680668061889194,"rank":138,"remainingConfigurations":444},{"removed":"apex-agents","score":0.22028305766824374,"rank":136,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.21909848620130853,"rank":136,"remainingConfigurations":444},{"removed":"automationbench","score":0.21810742597263,"rank":136,"remainingConfigurations":444},{"removed":"critpt","score":0.2203348047448542,"rank":135,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.21931392472266112,"rank":136,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.22010199264822464,"rank":135,"remainingConfigurations":444},{"removed":"gdpval","score":0.21917869036958978,"rank":136,"remainingConfigurations":444},{"removed":"gmmlu","score":0.21939155105319505,"rank":136,"remainingConfigurations":444},{"removed":"gpqa","score":0.21645678099279805,"rank":136,"remainingConfigurations":444},{"removed":"harvey","score":0.20685712112295088,"rank":136,"remainingConfigurations":444},{"removed":"hle","score":0.23010908470339797,"rank":136,"remainingConfigurations":444},{"removed":"ifbench","score":0.217943504289886,"rank":137,"remainingConfigurations":444},{"removed":"itbench","score":0.21877151205549641,"rank":136,"remainingConfigurations":444},{"removed":"livecodebench","score":0.22018217305141818,"rank":136,"remainingConfigurations":444},{"removed":"math500","score":0.21941841893094438,"rank":136,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.23112237198142474,"rank":132,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.23023398231928502,"rank":136,"remainingConfigurations":444},{"removed":"omniscience","score":0.21848091281997928,"rank":135,"remainingConfigurations":444},{"removed":"tau-bench","score":0.21901892764663503,"rank":136,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.21986332760118898,"rank":136,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.22325204219543007,"rank":132,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15911005766349745,"rank":170,"remainingConfigurations":444},{"removed":"deepswe","score":0.17072431325499957,"rank":136,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.21946754819578573,"rank":136,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.21622688629501505,"rank":135,"remainingConfigurations":444},{"removed":"frontiercode","score":0.3535647312124876,"rank":100,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.21799091878698196,"rank":136,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.21744203871584047,"rank":136,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.21933989155299324,"rank":136,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.21865396659907008,"rank":136,"remainingConfigurations":444},{"removed":"livebench-math","score":0.21986525764970855,"rank":136,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.21812803384414237,"rank":136,"remainingConfigurations":444},{"removed":"livebench-language","score":0.22114324892016266,"rank":136,"remainingConfigurations":444},{"removed":"livebench-data","score":0.22020162993311795,"rank":136,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.21620130557772566,"rank":136,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.21850501991967053,"rank":136,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.22187458212199693,"rank":136,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2161803463389068,"rank":137,"remainingConfigurations":444},{"removed":"frontiermath","score":0.22006858146161146,"rank":136,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.21635400267561564,"rank":136,"remainingConfigurations":444},{"removed":"simpleqa","score":0.22518819250122793,"rank":135,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.22200563722381042,"rank":135,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.21553908880751094,"rank":136,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.22293505006030448,"rank":135,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.22073265713204873,"rank":135,"remainingConfigurations":444},{"removed":"vibe-code","score":0.2155109167123824,"rank":136,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.21457572887238918,"rank":136,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5-5--effort-low":{"score":0.20124048734416985,"rank":137,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.11903749491197002,"rank":139,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.21593135778937386,"rank":151,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1652386127827694,"rank":137,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.20105953660302356,"rank":137,"remainingConfigurations":444},{"removed":"Scale","score":0.2213238117635744,"rank":137,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.19599706937454284,"rank":137,"remainingConfigurations":444},{"removed":"Cognition","score":0.33810710245270137,"rank":108,"remainingConfigurations":444},{"removed":"LiveBench","score":0.20341235113880618,"rank":136,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.19637777770234033,"rank":139,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.22907893674570565,"rank":134,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1882661432745468,"rank":136,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.20118203564268633,"rank":137,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.19708760916146428,"rank":137,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.200964272300341,"rank":137,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.20124048734416985,"rank":137,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.2021178840294057,"rank":137,"remainingConfigurations":444},{"removed":"All provider reports","score":0.197676204412385,"rank":137,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.20255287941303438,"rank":137,"remainingConfigurations":444},{"removed":"briefcase","score":0.1961601332331735,"rank":139,"remainingConfigurations":444},{"removed":"aime","score":0.198590276885196,"rank":139,"remainingConfigurations":444},{"removed":"apex-agents","score":0.20316391943659717,"rank":137,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.2045344610908363,"rank":138,"remainingConfigurations":444},{"removed":"automationbench","score":0.19856877147554688,"rank":138,"remainingConfigurations":444},{"removed":"critpt","score":0.2019467737698815,"rank":137,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.2021151018612424,"rank":137,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.2009654028705973,"rank":137,"remainingConfigurations":444},{"removed":"gdpval","score":0.20239699603468397,"rank":137,"remainingConfigurations":444},{"removed":"gmmlu","score":0.2018651195021625,"rank":137,"remainingConfigurations":444},{"removed":"gpqa","score":0.2044502154535636,"rank":137,"remainingConfigurations":444},{"removed":"harvey","score":0.19992922477139005,"rank":137,"remainingConfigurations":444},{"removed":"hle","score":0.21332659958301625,"rank":138,"remainingConfigurations":444},{"removed":"ifbench","score":0.20035365880755798,"rank":140,"remainingConfigurations":444},{"removed":"itbench","score":0.20133341601330548,"rank":137,"remainingConfigurations":444},{"removed":"livecodebench","score":0.20131903437537055,"rank":137,"remainingConfigurations":444},{"removed":"math500","score":0.2012795248861737,"rank":137,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.20543722844727685,"rank":137,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.21457110998130427,"rank":138,"remainingConfigurations":444},{"removed":"omniscience","score":0.1997884739582659,"rank":138,"remainingConfigurations":444},{"removed":"tau-bench","score":0.20207215134408016,"rank":137,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1914174267963793,"rank":141,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.19678509595432891,"rank":138,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2094066636073129,"rank":151,"remainingConfigurations":444},{"removed":"deepswe","score":0.1653697048849695,"rank":137,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.20127510474808583,"rank":137,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1993823849174675,"rank":138,"remainingConfigurations":444},{"removed":"frontiercode","score":0.33810710245270137,"rank":108,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.19985486714287048,"rank":137,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.19878557463257163,"rank":137,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.20115527071193504,"rank":137,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.2002409652323087,"rank":137,"remainingConfigurations":444},{"removed":"livebench-math","score":0.20123757611921642,"rank":137,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.19820471811477883,"rank":137,"remainingConfigurations":444},{"removed":"livebench-language","score":0.20396146981487864,"rank":137,"remainingConfigurations":444},{"removed":"livebench-data","score":0.20170987913773353,"rank":137,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.19837864975964073,"rank":137,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.19960606508282575,"rank":137,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.20563569808711754,"rank":137,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.19637777770234033,"rank":139,"remainingConfigurations":444},{"removed":"frontiermath","score":0.20051114477335116,"rank":137,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.2076025798996021,"rank":137,"remainingConfigurations":444},{"removed":"simpleqa","score":0.2057297901415909,"rank":136,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.20076426393789226,"rank":137,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.2006182359294789,"rank":137,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.20057166019143713,"rank":137,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.20081389463211274,"rank":137,"remainingConfigurations":444},{"removed":"vibe-code","score":0.20028775600107493,"rank":137,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.2006320491162873,"rank":137,"remainingConfigurations":444}],"sharedOrderConflicts":0},"hy3--effort-reasoning":{"score":0.19305312861799595,"rank":138,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23494591538056428,"rank":140,"remainingConfigurations":444},{"removed":"Datacurve","score":0.15882858741072423,"rank":138,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.19201973796271968,"rank":139,"remainingConfigurations":444},{"removed":"Scale","score":0.213933781379522,"rank":138,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.19181211214646035,"rank":138,"remainingConfigurations":444},{"removed":"Cognition","score":0.18375624093068024,"rank":141,"remainingConfigurations":444},{"removed":"LiveBench","score":0.19843611848292234,"rank":138,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.19668833749488193,"rank":138,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.19618619439558516,"rank":137,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1856306169095673,"rank":137,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.19297917891051786,"rank":138,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.18834063211726748,"rank":139,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.19272603308544453,"rank":138,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.19305312861799595,"rank":138,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1943389442186275,"rank":139,"remainingConfigurations":444},{"removed":"All provider reports","score":0.18927226319032162,"rank":139,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1945921219516984,"rank":138,"remainingConfigurations":444},{"removed":"briefcase","score":0.19091155555623548,"rank":142,"remainingConfigurations":444},{"removed":"aime","score":0.19270747432480903,"rank":140,"remainingConfigurations":444},{"removed":"apex-agents","score":0.19572864544630394,"rank":138,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18298235000288074,"rank":143,"remainingConfigurations":444},{"removed":"automationbench","score":0.2002837329314603,"rank":137,"remainingConfigurations":444},{"removed":"critpt","score":0.19451548099013946,"rank":138,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.19297839445615353,"rank":139,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.19593300102226588,"rank":139,"remainingConfigurations":444},{"removed":"gdpval","score":0.1945840554108893,"rank":139,"remainingConfigurations":444},{"removed":"gmmlu","score":0.19410330508646378,"rank":138,"remainingConfigurations":444},{"removed":"gpqa","score":0.18222466075655022,"rank":143,"remainingConfigurations":444},{"removed":"harvey","score":0.19074132123611778,"rank":139,"remainingConfigurations":444},{"removed":"hle","score":0.20127683679196248,"rank":140,"remainingConfigurations":444},{"removed":"ifbench","score":0.18871653649219558,"rank":144,"remainingConfigurations":444},{"removed":"itbench","score":0.1920202935952148,"rank":140,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1928842437603094,"rank":139,"remainingConfigurations":444},{"removed":"math500","score":0.19335597858514872,"rank":138,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.19747120734359933,"rank":138,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.20459928758680665,"rank":139,"remainingConfigurations":444},{"removed":"omniscience","score":0.19668635395318693,"rank":140,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18947294618209723,"rank":143,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.19494914009293382,"rank":137,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.19717126652301678,"rank":137,"remainingConfigurations":444},{"removed":"arc-agi","score":0.22877333278289905,"rank":139,"remainingConfigurations":444},{"removed":"deepswe","score":0.15893091443840715,"rank":138,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1930977689612703,"rank":138,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.19092611383593383,"rank":139,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18375624093068024,"rank":141,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.19129430342987552,"rank":139,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.19118353815983227,"rank":138,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.19291708878389757,"rank":138,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.19227661967043405,"rank":138,"remainingConfigurations":444},{"removed":"livebench-math","score":0.19319154534626634,"rank":138,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1914378640587863,"rank":138,"remainingConfigurations":444},{"removed":"livebench-language","score":0.19543231622707605,"rank":138,"remainingConfigurations":444},{"removed":"livebench-data","score":0.1930458115142726,"rank":138,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1899682078225636,"rank":138,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.19206881612811103,"rank":138,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.19625137642862175,"rank":139,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.19668833749488193,"rank":138,"remainingConfigurations":444},{"removed":"frontiermath","score":0.19321549591763676,"rank":138,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.18568943022411047,"rank":139,"remainingConfigurations":444},{"removed":"simpleqa","score":0.20019766977143427,"rank":137,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1924977096786803,"rank":138,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.19252298021338424,"rank":138,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1924884439409497,"rank":138,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1928221062173279,"rank":138,"remainingConfigurations":444},{"removed":"vibe-code","score":0.19206904263282665,"rank":139,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.19262856613065224,"rank":138,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-high":{"score":0.19282331690254007,"rank":139,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15199950960817177,"rank":125,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2676845880929239,"rank":134,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14800033335172463,"rank":148,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.19282836621538157,"rank":138,"remainingConfigurations":444},{"removed":"Scale","score":0.21283104939642486,"rank":139,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1895468358213712,"rank":140,"remainingConfigurations":444},{"removed":"Cognition","score":0.17561001437386026,"rank":148,"remainingConfigurations":444},{"removed":"LiveBench","score":0.20025506979094923,"rank":137,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18906516127662534,"rank":144,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.20274112112021103,"rank":136,"remainingConfigurations":431},{"removed":"Vals AI","score":0.18514787333961805,"rank":138,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.19279805536443562,"rank":139,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1891356729407485,"rank":138,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.19270461081260684,"rank":139,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.19282331690254007,"rank":139,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1950311168793407,"rank":138,"remainingConfigurations":444},{"removed":"All provider reports","score":0.19121859426658214,"rank":138,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.19375526334423668,"rank":139,"remainingConfigurations":444},{"removed":"briefcase","score":0.19142639059994707,"rank":141,"remainingConfigurations":444},{"removed":"aime","score":0.19101638339557112,"rank":142,"remainingConfigurations":444},{"removed":"apex-agents","score":0.19438675276758346,"rank":139,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.19212704747408063,"rank":139,"remainingConfigurations":444},{"removed":"automationbench","score":0.19152657302159062,"rank":139,"remainingConfigurations":444},{"removed":"critpt","score":0.1920429060917357,"rank":140,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.19317606102102738,"rank":138,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18909140948079836,"rank":143,"remainingConfigurations":444},{"removed":"gdpval","score":0.1916630202959202,"rank":142,"remainingConfigurations":444},{"removed":"gmmlu","score":0.19325540630843532,"rank":139,"remainingConfigurations":444},{"removed":"gpqa","score":0.19129962281986843,"rank":139,"remainingConfigurations":444},{"removed":"harvey","score":0.19098492487813193,"rank":138,"remainingConfigurations":444},{"removed":"hle","score":0.20515196753359524,"rank":139,"remainingConfigurations":444},{"removed":"ifbench","score":0.1920531025610452,"rank":141,"remainingConfigurations":444},{"removed":"itbench","score":0.19246001151677747,"rank":139,"remainingConfigurations":444},{"removed":"livecodebench","score":0.19306523790505956,"rank":138,"remainingConfigurations":444},{"removed":"math500","score":0.19292816113521125,"rank":139,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1970938397578256,"rank":139,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.20355826665123722,"rank":141,"remainingConfigurations":444},{"removed":"omniscience","score":0.19114752824353212,"rank":143,"remainingConfigurations":444},{"removed":"tau-bench","score":0.19354664053970302,"rank":140,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.19380054933211474,"rank":139,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.19157261726601774,"rank":141,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21586479852929571,"rank":145,"remainingConfigurations":444},{"removed":"deepswe","score":0.14792094742073636,"rank":148,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1928538828866949,"rank":139,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.21145906240845092,"rank":137,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17561001437386026,"rank":148,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.19134870591943454,"rank":138,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.19070322362729333,"rank":139,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.19278534801395664,"rank":139,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1920213652128213,"rank":139,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1930726238215753,"rank":139,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.19116161786796373,"rank":139,"remainingConfigurations":444},{"removed":"livebench-language","score":0.19486432533193307,"rank":139,"remainingConfigurations":444},{"removed":"livebench-data","score":0.19267254282319643,"rank":139,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18979649419222674,"rank":139,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.19185395851915285,"rank":139,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1963988178198727,"rank":138,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18906516127662534,"rank":144,"remainingConfigurations":444},{"removed":"frontiermath","score":0.19259788167257366,"rank":139,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.18939358519336155,"rank":138,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19993382226176745,"rank":138,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.19234744895514436,"rank":139,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.19219322543980574,"rank":139,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.19245696539721044,"rank":139,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.19235826465286932,"rank":139,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1916920453398239,"rank":140,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1925400440762183,"rank":139,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-flash-0424--effort-max":{"score":0.19163073542965728,"rank":140,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23263600208901616,"rank":142,"remainingConfigurations":444},{"removed":"Datacurve","score":0.15717236062433262,"rank":140,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.19061852727962936,"rank":140,"remainingConfigurations":444},{"removed":"Scale","score":0.21230878668854145,"rank":140,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1904350731498143,"rank":139,"remainingConfigurations":444},{"removed":"Cognition","score":0.18230510867358155,"rank":143,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1970455271870365,"rank":139,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.19497411150702967,"rank":140,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.19504043062848622,"rank":138,"remainingConfigurations":431},{"removed":"Vals AI","score":0.18418641790223247,"rank":140,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.19155856421812248,"rank":140,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1867541974667305,"rank":140,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1913576027462315,"rank":140,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.19163073542965728,"rank":140,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1928949123879531,"rank":140,"remainingConfigurations":444},{"removed":"All provider reports","score":0.187721627479833,"rank":140,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.18483538624452567,"rank":145,"remainingConfigurations":444},{"removed":"briefcase","score":0.1995164076735253,"rank":137,"remainingConfigurations":444},{"removed":"aime","score":0.19125692527997437,"rank":141,"remainingConfigurations":444},{"removed":"apex-agents","score":0.19431137174731472,"rank":140,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.188486225952477,"rank":140,"remainingConfigurations":444},{"removed":"automationbench","score":0.18893762509374823,"rank":141,"remainingConfigurations":444},{"removed":"critpt","score":0.19098674455603473,"rank":142,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.19121661560654027,"rank":141,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1971574891623429,"rank":138,"remainingConfigurations":444},{"removed":"gdpval","score":0.195360451448401,"rank":138,"remainingConfigurations":444},{"removed":"gmmlu","score":0.19282417408860142,"rank":140,"remainingConfigurations":444},{"removed":"gpqa","score":0.18417914683118478,"rank":141,"remainingConfigurations":444},{"removed":"harvey","score":0.18978996653585867,"rank":140,"remainingConfigurations":444},{"removed":"hle","score":0.19972989384910278,"rank":141,"remainingConfigurations":444},{"removed":"ifbench","score":0.1815794254946668,"rank":149,"remainingConfigurations":444},{"removed":"itbench","score":0.2007591724614635,"rank":138,"remainingConfigurations":444},{"removed":"livecodebench","score":0.19153559166609613,"rank":140,"remainingConfigurations":444},{"removed":"math500","score":0.19186226236761061,"rank":140,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.19607682884162267,"rank":140,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.20363718225226954,"rank":140,"remainingConfigurations":444},{"removed":"omniscience","score":0.19236865250834823,"rank":142,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18495154699198046,"rank":146,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.19399474819819473,"rank":138,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1918383765162862,"rank":140,"remainingConfigurations":444},{"removed":"arc-agi","score":0.22727884670192455,"rank":140,"remainingConfigurations":444},{"removed":"deepswe","score":0.1572813942833212,"rank":140,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.19166884523253738,"rank":140,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.18966239116852668,"rank":140,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18230510867358155,"rank":143,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1898749986057846,"rank":140,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18980695123768213,"rank":140,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.19149193338195525,"rank":140,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.19084492618995988,"rank":140,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1917582220527394,"rank":140,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1900547243937324,"rank":140,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1939993021354899,"rank":140,"remainingConfigurations":444},{"removed":"livebench-data","score":0.19159611205939675,"rank":140,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18856561089322943,"rank":140,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1906676434189,"rank":140,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.19479804606920573,"rank":140,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.19497411150702967,"rank":140,"remainingConfigurations":444},{"removed":"frontiermath","score":0.19184148652472766,"rank":140,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1846647854928228,"rank":140,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19877554647389298,"rank":139,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1911134202309501,"rank":140,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.19107965789529238,"rank":140,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1910518119436534,"rank":140,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.19139509249048423,"rank":140,"remainingConfigurations":444},{"removed":"vibe-code","score":0.19066212479871802,"rank":141,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.19120312462407998,"rank":140,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-sol--effort-non-reasoning":{"score":0.19045343692709873,"rank":141,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23267141496281196,"rank":141,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1574320870192879,"rank":139,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18948450605427714,"rank":142,"remainingConfigurations":444},{"removed":"Scale","score":0.21048796711371542,"rank":142,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18929641875732695,"rank":143,"remainingConfigurations":444},{"removed":"Cognition","score":0.17706194524558772,"rank":147,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1966109544387302,"rank":140,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.19316767290243866,"rank":142,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.19325468275457977,"rank":141,"remainingConfigurations":431},{"removed":"Vals AI","score":0.18431632894119654,"rank":139,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.19037060033016232,"rank":141,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.18583242598041474,"rank":141,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1901272437269376,"rank":141,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.19045343692709873,"rank":141,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1916245773317553,"rank":141,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1866411322967809,"rank":141,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.19293699008278653,"rank":140,"remainingConfigurations":444},{"removed":"briefcase","score":0.1818407731765674,"rank":146,"remainingConfigurations":444},{"removed":"aime","score":0.18898132007692403,"rank":144,"remainingConfigurations":444},{"removed":"apex-agents","score":0.19298423132145773,"rank":141,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.21383126033384967,"rank":137,"remainingConfigurations":444},{"removed":"automationbench","score":0.1865535988851269,"rank":143,"remainingConfigurations":444},{"removed":"critpt","score":0.19401849618422826,"rank":139,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1916880841456338,"rank":140,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1805667385211156,"rank":150,"remainingConfigurations":444},{"removed":"gdpval","score":0.18204860192073022,"rank":148,"remainingConfigurations":444},{"removed":"gmmlu","score":0.19021137005548527,"rank":142,"remainingConfigurations":444},{"removed":"gpqa","score":0.1863948507297596,"rank":140,"remainingConfigurations":444},{"removed":"harvey","score":0.18853339812365874,"rank":141,"remainingConfigurations":444},{"removed":"hle","score":0.22126666372366396,"rank":137,"remainingConfigurations":444},{"removed":"ifbench","score":0.18426897648269358,"rank":146,"remainingConfigurations":444},{"removed":"itbench","score":0.19003312553070306,"rank":141,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18919454816640505,"rank":143,"remainingConfigurations":444},{"removed":"math500","score":0.1903409756928834,"rank":142,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.19348209330605015,"rank":143,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.22806957346676496,"rank":137,"remainingConfigurations":444},{"removed":"omniscience","score":0.17622074474627314,"rank":151,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18649513217997557,"rank":145,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.17964396855682507,"rank":152,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.183251312895051,"rank":145,"remainingConfigurations":444},{"removed":"arc-agi","score":0.22589248226585099,"rank":141,"remainingConfigurations":444},{"removed":"deepswe","score":0.157514168962144,"rank":139,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.19049378979219353,"rank":141,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1883373137899215,"rank":141,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17706194524558772,"rank":147,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.18868331951354692,"rank":141,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18859065936924638,"rank":141,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.19030243879661005,"rank":141,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18980754463948937,"rank":141,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1905650206057455,"rank":141,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18877224986242824,"rank":142,"remainingConfigurations":444},{"removed":"livebench-language","score":0.19282271752760902,"rank":141,"remainingConfigurations":444},{"removed":"livebench-data","score":0.19046166320320926,"rank":141,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18740504773480984,"rank":141,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.18946116822162615,"rank":141,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.19371334731490275,"rank":141,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.19316767290243866,"rank":142,"remainingConfigurations":444},{"removed":"frontiermath","score":0.19050889967035886,"rank":142,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.18327220140320685,"rank":142,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19754693316859892,"rank":142,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18993267408619696,"rank":142,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.18990442224120008,"rank":141,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1898973929562314,"rank":141,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.19019441594130304,"rank":141,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1894598068244289,"rank":142,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.19002560890325826,"rank":141,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k2.7-code--effort-reasoning":{"score":0.19034087219007367,"rank":142,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23162071424799124,"rank":143,"remainingConfigurations":444},{"removed":"Datacurve","score":0.15684971118076163,"rank":141,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18914873410351632,"rank":143,"remainingConfigurations":444},{"removed":"Scale","score":0.21097488980791013,"rank":141,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18947322454675763,"rank":141,"remainingConfigurations":444},{"removed":"Cognition","score":0.18233433152310832,"rank":142,"remainingConfigurations":444},{"removed":"LiveBench","score":0.19564201567802134,"rank":142,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1936233504827242,"rank":141,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.19368549189056705,"rank":140,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1835055376921575,"rank":141,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1902798072046492,"rank":142,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.18560617210725172,"rank":143,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.19006348736134662,"rank":142,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.19034087219007367,"rank":142,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.19157700926448737,"rank":142,"remainingConfigurations":444},{"removed":"All provider reports","score":0.18655182718047233,"rank":143,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.19207431060999702,"rank":141,"remainingConfigurations":444},{"removed":"briefcase","score":0.19788691335354833,"rank":138,"remainingConfigurations":444},{"removed":"aime","score":0.18979039842898274,"rank":143,"remainingConfigurations":444},{"removed":"apex-agents","score":0.19264543808050583,"rank":142,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1804065770696005,"rank":148,"remainingConfigurations":444},{"removed":"automationbench","score":0.188764983698856,"rank":142,"remainingConfigurations":444},{"removed":"critpt","score":0.18584863189786419,"rank":145,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.18720883158037074,"rank":143,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1931167043734249,"rank":140,"remainingConfigurations":444},{"removed":"gdpval","score":0.19358809055015738,"rank":141,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1910895631806955,"rank":141,"remainingConfigurations":444},{"removed":"gpqa","score":0.18133157628751195,"rank":145,"remainingConfigurations":444},{"removed":"harvey","score":0.18830714137381402,"rank":142,"remainingConfigurations":444},{"removed":"hle","score":0.1974322831541404,"rank":144,"remainingConfigurations":444},{"removed":"ifbench","score":0.2020882245352821,"rank":138,"remainingConfigurations":444},{"removed":"itbench","score":0.18934586642674214,"rank":142,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18977171930182904,"rank":142,"remainingConfigurations":444},{"removed":"math500","score":0.19074350876061885,"rank":141,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.19450084221862615,"rank":142,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.20123946867012854,"rank":143,"remainingConfigurations":444},{"removed":"omniscience","score":0.1847306176531314,"rank":146,"remainingConfigurations":444},{"removed":"tau-bench","score":0.19177886819360312,"rank":141,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1924701111345383,"rank":140,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.18770402175974518,"rank":142,"remainingConfigurations":444},{"removed":"arc-agi","score":0.22510491225644458,"rank":142,"remainingConfigurations":444},{"removed":"deepswe","score":0.15696001997507356,"rank":141,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.19038311950337938,"rank":142,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.18824598035034665,"rank":142,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18233433152310832,"rank":142,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.18857749530255585,"rank":142,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1884955096436628,"rank":142,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.19021094959733606,"rank":142,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18958712381166629,"rank":142,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1904856676934226,"rank":142,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18877403008329183,"rank":141,"remainingConfigurations":444},{"removed":"livebench-language","score":0.19270146946721134,"rank":142,"remainingConfigurations":444},{"removed":"livebench-data","score":0.19030644172091984,"rank":142,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18728632556746794,"rank":142,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.18937256748135722,"rank":142,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1934828520816081,"rank":142,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1936233504827242,"rank":141,"remainingConfigurations":444},{"removed":"frontiermath","score":0.19052996447901838,"rank":141,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.18292792179745265,"rank":143,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19743580910642447,"rank":143,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18978913135586647,"rank":143,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1898100976457098,"rank":142,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18976861123965696,"rank":142,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.19011988752506434,"rank":142,"remainingConfigurations":444},{"removed":"vibe-code","score":0.18937161833182314,"rank":143,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.18992436824912493,"rank":142,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-4-6--effort-max":{"score":0.18970871566299438,"rank":143,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.17331624373938723,"rank":121,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.17277612666575606,"rank":165,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1565409808996925,"rank":142,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18970952160863355,"rank":141,"remainingConfigurations":444},{"removed":"Scale","score":0.20895758304170306,"rank":143,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18936502659616705,"rank":142,"remainingConfigurations":444},{"removed":"Cognition","score":0.2279409910368966,"rank":129,"remainingConfigurations":444},{"removed":"LiveBench","score":0.19592690204360141,"rank":141,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18797324718331732,"rank":145,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.24620306540216838,"rank":127,"remainingConfigurations":431},{"removed":"Vals AI","score":0.14890760935614875,"rank":160,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18966716701412756,"rank":143,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.185801676475661,"rank":142,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1897116066070843,"rank":143,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18970871566299438,"rank":143,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1905422197809632,"rank":143,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1866406305744036,"rank":142,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.19047276279760053,"rank":142,"remainingConfigurations":444},{"removed":"briefcase","score":0.1881552252944719,"rank":143,"remainingConfigurations":444},{"removed":"aime","score":0.18715526829384913,"rank":145,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1901873691870878,"rank":143,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18658912122791763,"rank":142,"remainingConfigurations":444},{"removed":"automationbench","score":0.19011539843672365,"rank":140,"remainingConfigurations":444},{"removed":"critpt","score":0.1910143671905242,"rank":141,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.18970810579672462,"rank":142,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18936401015627455,"rank":142,"remainingConfigurations":444},{"removed":"gdpval","score":0.1887833137235907,"rank":143,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18985806966273613,"rank":143,"remainingConfigurations":444},{"removed":"gpqa","score":0.19542089856749298,"rank":138,"remainingConfigurations":444},{"removed":"harvey","score":0.1869761925359915,"rank":143,"remainingConfigurations":444},{"removed":"hle","score":0.19949629787981907,"rank":142,"remainingConfigurations":444},{"removed":"ifbench","score":0.19140992350467392,"rank":142,"remainingConfigurations":444},{"removed":"itbench","score":0.18782601345026975,"rank":143,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18979715934574468,"rank":141,"remainingConfigurations":444},{"removed":"math500","score":0.18979821966894983,"rank":143,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1947076426145066,"rank":141,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.20200103317909135,"rank":142,"remainingConfigurations":444},{"removed":"omniscience","score":0.1884963330154904,"rank":144,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18944484225283312,"rank":144,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.19012197153419205,"rank":142,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.19470363433945928,"rank":139,"remainingConfigurations":444},{"removed":"arc-agi","score":0.16726851456086034,"rank":164,"remainingConfigurations":444},{"removed":"deepswe","score":0.15670185513136686,"rank":142,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.18975332561721228,"rank":143,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1879376827170691,"rank":143,"remainingConfigurations":444},{"removed":"frontiercode","score":0.2279409910368966,"rank":129,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.18836510820256938,"rank":143,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18774499196049166,"rank":143,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.18960781059149015,"rank":143,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18882509381757806,"rank":143,"remainingConfigurations":444},{"removed":"livebench-math","score":0.18991709949976443,"rank":143,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1876935183118453,"rank":143,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1919616626227232,"rank":143,"remainingConfigurations":444},{"removed":"livebench-data","score":0.19006962614743875,"rank":143,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18670204816011735,"rank":143,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.18869712535734337,"rank":143,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1929473191237481,"rank":143,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18797324718331732,"rank":145,"remainingConfigurations":444},{"removed":"frontiermath","score":0.18730350169729035,"rank":143,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.18450002469622065,"rank":141,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1987518291183309,"rank":140,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.190208086836924,"rank":141,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.186741395158583,"rank":143,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18755193668007616,"rank":143,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1894221519880012,"rank":143,"remainingConfigurations":444},{"removed":"vibe-code","score":0.19231260030522448,"rank":138,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1842560609558386,"rank":145,"remainingConfigurations":444}],"sharedOrderConflicts":1},"glm-5.2--effort-low":{"score":0.18703333522095078,"rank":144,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1782229185682176,"rank":120,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.22655154233447586,"rank":144,"remainingConfigurations":444},{"removed":"Datacurve","score":0.15299898213701776,"rank":145,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18664952057889142,"rank":144,"remainingConfigurations":444},{"removed":"Scale","score":0.2057230249116678,"rank":144,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18716537668512712,"rank":144,"remainingConfigurations":444},{"removed":"Cognition","score":0.18974615079709845,"rank":136,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18739384676039017,"rank":145,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18963209521918564,"rank":143,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.17884567751501165,"rank":142,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18700128174042066,"rank":144,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1829887512737789,"rank":144,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.18695330348579967,"rank":144,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18703333522095078,"rank":144,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.18805190320594958,"rank":144,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1839346178386437,"rank":144,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.18780136379550483,"rank":143,"remainingConfigurations":444},{"removed":"briefcase","score":0.18640305380037567,"rank":144,"remainingConfigurations":444},{"removed":"aime","score":0.2608739930579734,"rank":122,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18854101688651878,"rank":144,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18726338173236048,"rank":141,"remainingConfigurations":444},{"removed":"automationbench","score":0.18641352504188644,"rank":144,"remainingConfigurations":444},{"removed":"critpt","score":0.1865735614052564,"rank":143,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.18720405273853702,"rank":144,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18842984320553857,"rank":144,"remainingConfigurations":444},{"removed":"gdpval","score":0.18572683571684498,"rank":145,"remainingConfigurations":444},{"removed":"gmmlu","score":0.187676260691911,"rank":144,"remainingConfigurations":444},{"removed":"gpqa","score":0.15188023532380246,"rank":162,"remainingConfigurations":444},{"removed":"harvey","score":0.18518163203656524,"rank":144,"remainingConfigurations":444},{"removed":"hle","score":0.19628028242308312,"rank":145,"remainingConfigurations":444},{"removed":"ifbench","score":0.1887158376869732,"rank":145,"remainingConfigurations":444},{"removed":"itbench","score":0.18626356569849614,"rank":144,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18712636327864088,"rank":144,"remainingConfigurations":444},{"removed":"math500","score":0.18730829256250736,"rank":144,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1918007165063459,"rank":144,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19751807920307662,"rank":144,"remainingConfigurations":444},{"removed":"omniscience","score":0.18460165390697572,"rank":147,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1818314359371196,"rank":150,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.18818569568917073,"rank":143,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.18674880604362856,"rank":144,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21973279636145868,"rank":143,"remainingConfigurations":444},{"removed":"deepswe","score":0.15311115231775516,"rank":145,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.18706213521537718,"rank":144,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.18529549174202956,"rank":144,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18974615079709845,"rank":136,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.18596392969152717,"rank":144,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18472898315742728,"rank":144,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.18696138002712734,"rank":144,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1864422769412016,"rank":144,"remainingConfigurations":444},{"removed":"livebench-math","score":0.18755469211937414,"rank":144,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18486793666205595,"rank":144,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1890983620481743,"rank":144,"remainingConfigurations":444},{"removed":"livebench-data","score":0.18719382339388355,"rank":144,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18439473284023977,"rank":144,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.18600147186589744,"rank":144,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.19012702962823855,"rank":144,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18963209521918564,"rank":143,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1740430757933719,"rank":154,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.15925231914115293,"rank":158,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1933756988106177,"rank":144,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1864336782593543,"rank":144,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.18661034789415734,"rank":144,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18639152387223046,"rank":144,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.18682603028494757,"rank":144,"remainingConfigurations":444},{"removed":"vibe-code","score":0.18621448063357474,"rank":144,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.18658599002833473,"rank":143,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4--effort-low":{"score":0.1848501773371577,"rank":145,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.18426909938789673,"rank":118,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23652020875562474,"rank":138,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1485592449038102,"rank":147,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1861309258812707,"rank":145,"remainingConfigurations":444},{"removed":"Scale","score":0.2053807936402178,"rank":145,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18287855191871727,"rank":145,"remainingConfigurations":444},{"removed":"Cognition","score":0.17377411759528383,"rank":149,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18949060530255965,"rank":144,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1862765008813605,"rank":146,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.18320478055231518,"rank":146,"remainingConfigurations":431},{"removed":"Vals AI","score":0.17573072629691164,"rank":144,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18479343900099118,"rank":145,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.18067439921579928,"rank":145,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1846062255129061,"rank":145,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1848501773371577,"rank":145,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.18620616317001726,"rank":145,"remainingConfigurations":444},{"removed":"All provider reports","score":0.18176253606234505,"rank":145,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.18575761142692515,"rank":144,"remainingConfigurations":444},{"removed":"briefcase","score":0.18362515072994587,"rank":145,"remainingConfigurations":444},{"removed":"aime","score":0.18377920211379437,"rank":146,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18637835900176358,"rank":145,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18181856730583024,"rank":147,"remainingConfigurations":444},{"removed":"automationbench","score":0.18359644599209368,"rank":146,"remainingConfigurations":444},{"removed":"critpt","score":0.18372156965426925,"rank":147,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.18462445190101837,"rank":145,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18654143791020664,"rank":145,"remainingConfigurations":444},{"removed":"gdpval","score":0.184685409732239,"rank":146,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18535231600176547,"rank":145,"remainingConfigurations":444},{"removed":"gpqa","score":0.18144254022926778,"rank":144,"remainingConfigurations":444},{"removed":"harvey","score":0.18295124087512973,"rank":145,"remainingConfigurations":444},{"removed":"hle","score":0.1957286014143915,"rank":146,"remainingConfigurations":444},{"removed":"ifbench","score":0.18961015691816152,"rank":143,"remainingConfigurations":444},{"removed":"itbench","score":0.18404725505507158,"rank":145,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18628519730965884,"rank":145,"remainingConfigurations":444},{"removed":"math500","score":0.18494754493109197,"rank":145,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18900867014739134,"rank":145,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19247917296579464,"rank":148,"remainingConfigurations":444},{"removed":"omniscience","score":0.17235231937757756,"rank":152,"remainingConfigurations":444},{"removed":"tau-bench","score":0.19664229896010502,"rank":139,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1862768986570956,"rank":144,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1824558055859483,"rank":146,"remainingConfigurations":444},{"removed":"arc-agi","score":0.22941912894846136,"rank":138,"remainingConfigurations":444},{"removed":"deepswe","score":0.14861134001148965,"rank":147,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1848819719186032,"rank":145,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17571381049267587,"rank":151,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17377411759528383,"rank":149,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1829812944287391,"rank":145,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18302873447304988,"rank":145,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.18470458225756334,"rank":145,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18412233551680704,"rank":145,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1850128903997468,"rank":145,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18335714174637766,"rank":145,"remainingConfigurations":444},{"removed":"livebench-language","score":0.18693326485214157,"rank":145,"remainingConfigurations":444},{"removed":"livebench-data","score":0.18467165194270438,"rank":145,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1819351379632901,"rank":145,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1839577713775725,"rank":145,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18810797901007595,"rank":145,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1862765008813605,"rank":146,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1857561652651604,"rank":144,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1762998153581754,"rank":146,"remainingConfigurations":444},{"removed":"simpleqa","score":0.19156557961877443,"rank":145,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18430344243632632,"rank":145,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.18428036484406282,"rank":145,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18440769448060135,"rank":145,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.18451999073032643,"rank":145,"remainingConfigurations":444},{"removed":"vibe-code","score":0.18383471336149962,"rank":145,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.18442214801401868,"rank":144,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.6--effort-low":{"score":0.18367367027956036,"rank":146,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14377123106583636,"rank":128,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.20404682566794138,"rank":157,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14605470995956413,"rank":153,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18384375240548764,"rank":146,"remainingConfigurations":444},{"removed":"Scale","score":0.20335074715688436,"rank":147,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17900704752870636,"rank":150,"remainingConfigurations":444},{"removed":"Cognition","score":0.19616360702917393,"rank":135,"remainingConfigurations":444},{"removed":"LiveBench","score":0.19063412743734928,"rank":143,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1790877019550726,"rank":153,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.18848342428925793,"rank":142,"remainingConfigurations":431},{"removed":"Vals AI","score":0.17233058031750637,"rank":147,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18364919747175626,"rank":146,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1798134494332191,"rank":146,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.18356752735058898,"rank":146,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18367367027956036,"rank":146,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1846828412535719,"rank":146,"remainingConfigurations":444},{"removed":"All provider reports","score":0.18072703672898682,"rank":146,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.18425598332993212,"rank":146,"remainingConfigurations":444},{"removed":"briefcase","score":0.18018485442762164,"rank":148,"remainingConfigurations":444},{"removed":"aime","score":0.18188058444700592,"rank":147,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1852377960855748,"rank":146,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18239206066634708,"rank":145,"remainingConfigurations":444},{"removed":"automationbench","score":0.17982335718507034,"rank":149,"remainingConfigurations":444},{"removed":"critpt","score":0.1860382945858966,"rank":144,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1840784835174596,"rank":146,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18299599205194847,"rank":147,"remainingConfigurations":444},{"removed":"gdpval","score":0.18125983799826353,"rank":149,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18398251812805988,"rank":146,"remainingConfigurations":444},{"removed":"gpqa","score":0.18280461300840814,"rank":142,"remainingConfigurations":444},{"removed":"harvey","score":0.18120825706807286,"rank":146,"remainingConfigurations":444},{"removed":"hle","score":0.1978535695292735,"rank":143,"remainingConfigurations":444},{"removed":"ifbench","score":0.18227931372257153,"rank":148,"remainingConfigurations":444},{"removed":"itbench","score":0.18347066143689436,"rank":146,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18401422952413385,"rank":146,"remainingConfigurations":444},{"removed":"math500","score":0.1837567645236914,"rank":146,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18797333068187216,"rank":146,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19482253446492495,"rank":146,"remainingConfigurations":444},{"removed":"omniscience","score":0.1823807091946139,"rank":148,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1823399094667614,"rank":148,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.18485461902195346,"rank":145,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.18103811011213508,"rank":148,"remainingConfigurations":444},{"removed":"arc-agi","score":0.23344444252278876,"rank":136,"remainingConfigurations":444},{"removed":"deepswe","score":0.14609043049227857,"rank":153,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.18371292178637946,"rank":146,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.18142817604538097,"rank":145,"remainingConfigurations":444},{"removed":"frontiercode","score":0.19616360702917393,"rank":135,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.18229857162677765,"rank":146,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1817392757857421,"rank":146,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.18361989700836523,"rank":146,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18280834554714423,"rank":146,"remainingConfigurations":444},{"removed":"livebench-math","score":0.18370783335262142,"rank":146,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18221552087900397,"rank":146,"remainingConfigurations":444},{"removed":"livebench-language","score":0.185821751697805,"rank":146,"remainingConfigurations":444},{"removed":"livebench-data","score":0.183850351989568,"rank":146,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1806517891909376,"rank":146,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1828769793615637,"rank":146,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18664377482252079,"rank":146,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1790877019550726,"rank":153,"remainingConfigurations":444},{"removed":"frontiermath","score":0.18406468372713383,"rank":145,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17872352275378167,"rank":144,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1905345999419752,"rank":146,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18343681861400554,"rank":146,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.18319728312506264,"rank":146,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18303718518715406,"rank":146,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.18361769570045286,"rank":146,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1826971403916421,"rank":146,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1830830319400876,"rank":146,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.3-codex--effort-xhigh":{"score":0.18274994289090749,"rank":147,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01903234644690052,"rank":181,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.18080276409980342,"rank":162,"remainingConfigurations":444},{"removed":"Datacurve","score":0.15365129312803347,"rank":144,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.18204044695805913,"rank":147,"remainingConfigurations":444},{"removed":"Scale","score":0.20407919171954145,"rank":146,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.181587895573585,"rank":146,"remainingConfigurations":444},{"removed":"Cognition","score":0.1807353475075252,"rank":145,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18172599453609162,"rank":151,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.30220053274518116,"rank":111,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.18840790239018415,"rank":143,"remainingConfigurations":431},{"removed":"Vals AI","score":0.17700541201167055,"rank":143,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18269586133658008,"rank":147,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17888491322519082,"rank":147,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.18246529579593415,"rank":147,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18274994289090749,"rank":147,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.18385940793321412,"rank":147,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17968908261836394,"rank":147,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.18414708492331053,"rank":147,"remainingConfigurations":444},{"removed":"briefcase","score":0.1950762143813067,"rank":140,"remainingConfigurations":444},{"removed":"aime","score":0.18187557705294152,"rank":148,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18490882296558364,"rank":147,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1708314243151788,"rank":152,"remainingConfigurations":444},{"removed":"automationbench","score":0.18239502065822266,"rank":147,"remainingConfigurations":444},{"removed":"critpt","score":0.17811456844192133,"rank":150,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1829614009135708,"rank":147,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18609282435173458,"rank":146,"remainingConfigurations":444},{"removed":"gdpval","score":0.18330940960074674,"rank":147,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18345798235174002,"rank":147,"remainingConfigurations":444},{"removed":"gpqa","score":0.17686607708329483,"rank":146,"remainingConfigurations":444},{"removed":"harvey","score":0.18109377699776774,"rank":147,"remainingConfigurations":444},{"removed":"hle","score":0.18809519199303346,"rank":151,"remainingConfigurations":444},{"removed":"ifbench","score":0.18288294467498378,"rank":147,"remainingConfigurations":444},{"removed":"itbench","score":0.1820582310947958,"rank":147,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18244480611808864,"rank":147,"remainingConfigurations":444},{"removed":"math500","score":0.1831392845163602,"rank":147,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18680997841968583,"rank":147,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19344608617656425,"rank":147,"remainingConfigurations":444},{"removed":"omniscience","score":0.1688838999808806,"rank":154,"remainingConfigurations":444},{"removed":"tau-bench","score":0.197547675247727,"rank":138,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.18458794761821865,"rank":146,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.18151650423916488,"rank":147,"remainingConfigurations":444},{"removed":"arc-agi","score":0.17552970309816332,"rank":161,"remainingConfigurations":444},{"removed":"deepswe","score":0.15371009983298392,"rank":144,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1827749339202883,"rank":147,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.18018291691347654,"rank":146,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1807353475075252,"rank":145,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1815326787161585,"rank":147,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.18028319313246086,"rank":147,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1826919958096186,"rank":147,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1823434741081711,"rank":147,"remainingConfigurations":444},{"removed":"livebench-math","score":0.18293160914899428,"rank":147,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.18111980880704656,"rank":147,"remainingConfigurations":444},{"removed":"livebench-language","score":0.18444587739530297,"rank":147,"remainingConfigurations":444},{"removed":"livebench-data","score":0.1828334149646682,"rank":147,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.18005465289029157,"rank":147,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1814388325888815,"rank":147,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18645655276522152,"rank":147,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.30220053274518116,"rank":111,"remainingConfigurations":444},{"removed":"frontiermath","score":0.18291184284725479,"rank":147,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17617508328570866,"rank":147,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18964180951253837,"rank":147,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18218371140805142,"rank":147,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.182228163228048,"rank":147,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18222577616115787,"rank":147,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.18246133322905858,"rank":147,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1818082488428385,"rank":147,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.18233611962785656,"rank":147,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.7-plus--effort-reasoning":{"score":0.18096191744762746,"rank":148,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.22026552515334544,"rank":148,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14865295834416756,"rank":146,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17981994539341117,"rank":148,"remainingConfigurations":444},{"removed":"Scale","score":0.20116640958531073,"rank":148,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.18015196320306018,"rank":147,"remainingConfigurations":444},{"removed":"Cognition","score":0.1734213900138936,"rank":150,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1853777786320644,"rank":147,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18476774038790858,"rank":147,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1844662446522646,"rank":144,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1743216754281626,"rank":145,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.180903409342511,"rank":148,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17628779512517226,"rank":148,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.18069152972298322,"rank":148,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18096191744762746,"rank":148,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.18214311590113927,"rank":148,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17718722598460848,"rank":148,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.182322595104746,"rank":148,"remainingConfigurations":444},{"removed":"briefcase","score":0.1817520522235693,"rank":147,"remainingConfigurations":444},{"removed":"aime","score":0.1803099850252067,"rank":150,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18234529038333203,"rank":149,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.18241463194405638,"rank":144,"remainingConfigurations":444},{"removed":"automationbench","score":0.1850467046594845,"rank":145,"remainingConfigurations":444},{"removed":"critpt","score":0.1779336391449948,"rank":151,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.17419278650368844,"rank":155,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1810240469800641,"rank":148,"remainingConfigurations":444},{"removed":"gdpval","score":0.19444708931090868,"rank":140,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18134389195471534,"rank":148,"remainingConfigurations":444},{"removed":"gpqa","score":0.17150386881364477,"rank":150,"remainingConfigurations":444},{"removed":"harvey","score":0.17904525232099633,"rank":148,"remainingConfigurations":444},{"removed":"hle","score":0.18687509001971928,"rank":152,"remainingConfigurations":444},{"removed":"ifbench","score":0.16997398015034215,"rank":155,"remainingConfigurations":444},{"removed":"itbench","score":0.17979690856556876,"rank":148,"remainingConfigurations":444},{"removed":"livecodebench","score":0.18035680670359067,"rank":148,"remainingConfigurations":444},{"removed":"math500","score":0.18136462736959538,"rank":148,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1849345469791588,"rank":148,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.18029240813099098,"rank":154,"remainingConfigurations":444},{"removed":"omniscience","score":0.19882931641437632,"rank":139,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18052965359738093,"rank":151,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.18320947423598066,"rank":147,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1800458459664972,"rank":149,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21367101942590563,"rank":149,"remainingConfigurations":444},{"removed":"deepswe","score":0.1487617709834462,"rank":146,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.18100023902215803,"rank":148,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17894286202141363,"rank":148,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1734213900138936,"rank":150,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1792471552819824,"rank":148,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.17919631838483363,"rank":148,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1808359089223481,"rank":148,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.18025088559858735,"rank":148,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1811086000610295,"rank":148,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.17947478041968004,"rank":148,"remainingConfigurations":444},{"removed":"livebench-language","score":0.18324713252116853,"rank":148,"remainingConfigurations":444},{"removed":"livebench-data","score":0.18089080944998195,"rank":148,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.17801689557036035,"rank":148,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.18003211400355532,"rank":148,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18399021976705002,"rank":148,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18476774038790858,"rank":147,"remainingConfigurations":444},{"removed":"frontiermath","score":0.18112897198171693,"rank":148,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17389576097938483,"rank":148,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18785112411749846,"rank":148,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.18042668297882095,"rank":148,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.180440138789747,"rank":148,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.18040949527497405,"rank":148,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.180740366531006,"rank":148,"remainingConfigurations":444},{"removed":"vibe-code","score":0.18003596053157267,"rank":148,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.18055650717312058,"rank":148,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5.1--effort-reasoning":{"score":0.18023251462486842,"rank":149,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.22046867247674465,"rank":147,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14766395970878723,"rank":149,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17916582338592071,"rank":149,"remainingConfigurations":444},{"removed":"Scale","score":0.20067339109164073,"rank":149,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17926381062017413,"rank":148,"remainingConfigurations":444},{"removed":"Cognition","score":0.17230312183680016,"rank":151,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18541321258942567,"rank":146,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18405478945641363,"rank":148,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1835611081712624,"rank":145,"remainingConfigurations":431},{"removed":"Vals AI","score":0.17346945244611423,"rank":146,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.18015837417154068,"rank":149,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17561125828623703,"rank":149,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.17993875063732082,"rank":149,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.18023251462486842,"rank":149,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.18145517388389987,"rank":149,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17651116677279025,"rank":149,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1820717852758298,"rank":149,"remainingConfigurations":444},{"removed":"briefcase","score":0.17507402364035893,"rank":153,"remainingConfigurations":444},{"removed":"aime","score":0.17953756018149472,"rank":151,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18325861101329535,"rank":148,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1786499021169173,"rank":150,"remainingConfigurations":444},{"removed":"automationbench","score":0.182192360062121,"rank":148,"remainingConfigurations":444},{"removed":"critpt","score":0.18111764840995745,"rank":148,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1805880579104651,"rank":148,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.19272161789751777,"rank":141,"remainingConfigurations":444},{"removed":"gdpval","score":0.17672374635832577,"rank":154,"remainingConfigurations":444},{"removed":"gmmlu","score":0.18120898862434995,"rank":149,"remainingConfigurations":444},{"removed":"gpqa","score":0.174878965512737,"rank":147,"remainingConfigurations":444},{"removed":"harvey","score":0.1782196363417865,"rank":149,"remainingConfigurations":444},{"removed":"hle","score":0.18958726873579082,"rank":148,"remainingConfigurations":444},{"removed":"ifbench","score":0.1706032579063553,"rank":153,"remainingConfigurations":444},{"removed":"itbench","score":0.16313512640101674,"rank":158,"remainingConfigurations":444},{"removed":"livecodebench","score":0.17966722935192944,"rank":149,"remainingConfigurations":444},{"removed":"math500","score":0.18038655371167336,"rank":149,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18411023435603693,"rank":149,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19145377145302497,"rank":149,"remainingConfigurations":444},{"removed":"omniscience","score":0.19611855089085894,"rank":141,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18046803055661853,"rank":152,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1820972881665599,"rank":148,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1777937579074553,"rank":151,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21456856358190746,"rank":147,"remainingConfigurations":444},{"removed":"deepswe","score":0.1477629346913474,"rank":149,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.18027278654603685,"rank":149,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17822849695987245,"rank":149,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17230312183680016,"rank":151,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.17855931786331092,"rank":149,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.17848821139618645,"rank":149,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1801077157454111,"rank":149,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.17949945074272844,"rank":149,"remainingConfigurations":444},{"removed":"livebench-math","score":0.18036969516524073,"rank":149,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.17871316346647362,"rank":149,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1825094441213612,"rank":149,"remainingConfigurations":444},{"removed":"livebench-data","score":0.18018841123649873,"rank":149,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.17729374577343252,"rank":149,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.17929754325032687,"rank":149,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18328421011432364,"rank":149,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18405478945641363,"rank":148,"remainingConfigurations":444},{"removed":"frontiermath","score":0.18037818428376848,"rank":149,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17330930237631925,"rank":149,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18712676909191492,"rank":149,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.17970786708374073,"rank":149,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.17970963425702471,"rank":149,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.17969235696639776,"rank":149,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.18000409039133278,"rank":149,"remainingConfigurations":444},{"removed":"vibe-code","score":0.17930403896552619,"rank":149,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.17982330926062273,"rank":149,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-sol--effort-none":{"score":0.17904309140775784,"rank":150,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15646720561386668,"rank":122,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.20993595427196463,"rank":154,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14748389322388814,"rank":150,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17863578046233175,"rank":150,"remainingConfigurations":444},{"removed":"Scale","score":0.19920358275556557,"rank":150,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17906044352362435,"rank":149,"remainingConfigurations":444},{"removed":"Cognition","score":0.179628948861534,"rank":146,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17692532885031573,"rank":153,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18318831355340326,"rank":149,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.16985233784268172,"rank":151,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.17901405939899465,"rank":150,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17518715377727148,"rank":150,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1789391285451624,"rank":150,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.17904309140775784,"rank":150,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1800371576431957,"rank":150,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17608812423763323,"rank":150,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1797978579153624,"rank":150,"remainingConfigurations":444},{"removed":"briefcase","score":0.17845265758503326,"rank":149,"remainingConfigurations":444},{"removed":"aime","score":0.27162105123611147,"rank":120,"remainingConfigurations":444},{"removed":"apex-agents","score":0.18052397456907052,"rank":150,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.17924764661370904,"rank":149,"remainingConfigurations":444},{"removed":"automationbench","score":0.17847355908202542,"rank":150,"remainingConfigurations":444},{"removed":"critpt","score":0.177539157125675,"rank":153,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.17920541704684126,"rank":149,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1803947627406599,"rank":151,"remainingConfigurations":444},{"removed":"gdpval","score":0.17759523451643397,"rank":152,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1796776442631005,"rank":150,"remainingConfigurations":444},{"removed":"gpqa","score":0.17304981060472016,"rank":149,"remainingConfigurations":444},{"removed":"harvey","score":0.17724029871921174,"rank":150,"remainingConfigurations":444},{"removed":"hle","score":0.1889797144257929,"rank":149,"remainingConfigurations":444},{"removed":"ifbench","score":0.18061808741704158,"rank":150,"remainingConfigurations":444},{"removed":"itbench","score":0.17829514712909564,"rank":149,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1791076894332301,"rank":150,"remainingConfigurations":444},{"removed":"math500","score":0.17932326347687688,"rank":150,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18374393101776368,"rank":150,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.18920080081131865,"rank":150,"remainingConfigurations":444},{"removed":"omniscience","score":0.1768180202747152,"rank":150,"remainingConfigurations":444},{"removed":"tau-bench","score":0.17411959339890515,"rank":153,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1801746530844911,"rank":149,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.17866952556285606,"rank":150,"remainingConfigurations":444},{"removed":"arc-agi","score":0.20247089558289533,"rank":155,"remainingConfigurations":444},{"removed":"deepswe","score":0.14760800330044818,"rank":150,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.17907095270052295,"rank":150,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17762159530403213,"rank":150,"remainingConfigurations":444},{"removed":"frontiercode","score":0.179628948861534,"rank":146,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1780265722915155,"rank":150,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.17671536652694905,"rank":150,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.17899128461258196,"rank":150,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.17848810141580673,"rank":150,"remainingConfigurations":444},{"removed":"livebench-math","score":0.17954348383954524,"rank":150,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1769443338699733,"rank":150,"remainingConfigurations":444},{"removed":"livebench-language","score":0.18104261451525783,"rank":150,"remainingConfigurations":444},{"removed":"livebench-data","score":0.17918740139729214,"rank":150,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.17647907107448893,"rank":150,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.17802764336735022,"rank":150,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18208652948670723,"rank":150,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18318831355340326,"rank":149,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1835116697770057,"rank":146,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05969852782357945,"rank":229,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1821399747026928,"rank":153,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1784706633163574,"rank":150,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1786075487439808,"rank":150,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.17842804481206498,"rank":150,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.17883851575190576,"rank":150,"remainingConfigurations":444},{"removed":"vibe-code","score":0.17825633498507998,"rank":150,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.17861394712169462,"rank":150,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.6-plus--effort-reasoning":{"score":0.17780832314089043,"rank":151,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.21945411285996405,"rank":149,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14613626883330763,"rank":152,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1766713396631935,"rank":151,"remainingConfigurations":444},{"removed":"Scale","score":0.19843526376518508,"rank":152,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17699384240570668,"rank":152,"remainingConfigurations":444},{"removed":"Cognition","score":0.17093639023490706,"rank":153,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18247056284158814,"rank":149,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18140183235079277,"rank":150,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1797588588293363,"rank":147,"remainingConfigurations":431},{"removed":"Vals AI","score":0.171292104781848,"rank":149,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.17774748893275605,"rank":151,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17337304625653818,"rank":151,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.17752295204371352,"rank":151,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.17780832314089043,"rank":151,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17902280013290062,"rank":151,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1742834544546907,"rank":152,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.17877819339975123,"rank":152,"remainingConfigurations":444},{"removed":"briefcase","score":0.17575038470202506,"rank":152,"remainingConfigurations":444},{"removed":"aime","score":0.1778478623469492,"rank":152,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17998718090276963,"rank":151,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.16798820073608423,"rank":155,"remainingConfigurations":444},{"removed":"automationbench","score":0.17559095879200434,"rank":152,"remainingConfigurations":444},{"removed":"critpt","score":0.18421695920563197,"rank":146,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1774440000011469,"rank":150,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18022669627374552,"rank":152,"remainingConfigurations":444},{"removed":"gdpval","score":0.1886938369315986,"rank":144,"remainingConfigurations":444},{"removed":"gmmlu","score":0.17908486698310513,"rank":151,"remainingConfigurations":444},{"removed":"gpqa","score":0.17001359832770138,"rank":151,"remainingConfigurations":444},{"removed":"harvey","score":0.17593058248444593,"rank":152,"remainingConfigurations":444},{"removed":"hle","score":0.1931226211180622,"rank":147,"remainingConfigurations":444},{"removed":"ifbench","score":0.1708410484524222,"rank":152,"remainingConfigurations":444},{"removed":"itbench","score":0.17654360861298343,"rank":150,"remainingConfigurations":444},{"removed":"livecodebench","score":0.17745951819715478,"rank":151,"remainingConfigurations":444},{"removed":"math500","score":0.1781363029135837,"rank":151,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18176604543524774,"rank":151,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.18202704132049521,"rank":153,"remainingConfigurations":444},{"removed":"omniscience","score":0.18780072477975218,"rank":145,"remainingConfigurations":444},{"removed":"tau-bench","score":0.16964569891930892,"rank":156,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1797763351218211,"rank":151,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.17544422250013567,"rank":152,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21295379792652958,"rank":150,"remainingConfigurations":444},{"removed":"deepswe","score":0.14622719515784557,"rank":152,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1778459382048093,"rank":151,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17551613193874593,"rank":152,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17093639023490706,"rank":153,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.17611508080291463,"rank":151,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1760917331062911,"rank":151,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1776843417928857,"rank":151,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1770979986143657,"rank":151,"remainingConfigurations":444},{"removed":"livebench-math","score":0.17796814844423103,"rank":151,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.17628636327457883,"rank":151,"remainingConfigurations":444},{"removed":"livebench-language","score":0.18002405167867175,"rank":151,"remainingConfigurations":444},{"removed":"livebench-data","score":0.17775011785947123,"rank":151,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1749279725479921,"rank":151,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.17687924663545962,"rank":151,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18084802659624133,"rank":151,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18140183235079277,"rank":150,"remainingConfigurations":444},{"removed":"frontiermath","score":0.17811949943232072,"rank":151,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17008988121164093,"rank":150,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18465586231994566,"rank":150,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.17727791210796948,"rank":151,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1772903833413755,"rank":151,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.17728477904097018,"rank":151,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.177566776056886,"rank":151,"remainingConfigurations":444},{"removed":"vibe-code","score":0.17688924134399261,"rank":151,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.17740128174129818,"rank":151,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-5-20251101--effort-reasoning":{"score":0.17772498909943243,"rank":152,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.22155224045993308,"rank":146,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14617666271307952,"rank":151,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17636931359352823,"rank":152,"remainingConfigurations":444},{"removed":"Scale","score":0.19882991892908908,"rank":151,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17703845880779034,"rank":151,"remainingConfigurations":444},{"removed":"Cognition","score":0.1711042771825594,"rank":152,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1825534829765174,"rank":148,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1813107127569635,"rank":151,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17935485468079645,"rank":148,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1718958747420003,"rank":148,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.17766546201623848,"rank":152,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17332692503809244,"rank":152,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.17745520431425402,"rank":152,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.17772498909943243,"rank":152,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17898545967796797,"rank":152,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17429817655395996,"rank":151,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.17887910919242703,"rank":151,"remainingConfigurations":444},{"removed":"briefcase","score":0.17656697267183186,"rank":150,"remainingConfigurations":444},{"removed":"aime","score":0.1806484013341129,"rank":149,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1795485080523088,"rank":152,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.17076338096560198,"rank":153,"remainingConfigurations":444},{"removed":"automationbench","score":0.17620820439559992,"rank":151,"remainingConfigurations":444},{"removed":"critpt","score":0.1781474691391189,"rank":149,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1773560799468471,"rank":151,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18066059453445982,"rank":149,"remainingConfigurations":444},{"removed":"gdpval","score":0.17773607060153304,"rank":151,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1720615328266457,"rank":154,"remainingConfigurations":444},{"removed":"gpqa","score":0.1742299615681967,"rank":148,"remainingConfigurations":444},{"removed":"harvey","score":0.17601955281939163,"rank":151,"remainingConfigurations":444},{"removed":"hle","score":0.1881335070961951,"rank":150,"remainingConfigurations":444},{"removed":"ifbench","score":0.20089394759822662,"rank":139,"remainingConfigurations":444},{"removed":"itbench","score":0.17640853677061685,"rank":151,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1768427458306833,"rank":152,"remainingConfigurations":444},{"removed":"math500","score":0.17790788979156916,"rank":152,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17801956037439534,"rank":154,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.19657189660530316,"rank":145,"remainingConfigurations":444},{"removed":"omniscience","score":0.15501498858386561,"rank":159,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18271441193576154,"rank":147,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.17992242380390655,"rank":150,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.17278542905615824,"rank":154,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2147819922578816,"rank":146,"remainingConfigurations":444},{"removed":"deepswe","score":0.14626086334429717,"rank":151,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1777603101549237,"rank":152,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1752131143944257,"rank":153,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1711042771825594,"rank":152,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.17596260700603084,"rank":152,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1759757193077327,"rank":152,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.17759635308533406,"rank":152,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1770331127892016,"rank":152,"remainingConfigurations":444},{"removed":"livebench-math","score":0.17789111094424168,"rank":152,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.17619681036887758,"rank":152,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17992232655436288,"rank":152,"remainingConfigurations":444},{"removed":"livebench-data","score":0.17763890011829128,"rank":152,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1748694501142919,"rank":152,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1767999589308894,"rank":152,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18077747328311702,"rank":152,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1813107127569635,"rank":151,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1781723178946624,"rank":150,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16965133241381977,"rank":151,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1846403640069378,"rank":151,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1772027831376225,"rank":152,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.17719569409263988,"rank":152,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.17721036047825256,"rank":152,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.17747053528516407,"rank":152,"remainingConfigurations":444},{"removed":"vibe-code","score":0.17680842792665327,"rank":152,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1773158416449078,"rank":152,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.3--effort-medium":{"score":0.17718383287117856,"rank":153,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.21889630049556033,"rank":150,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1456099488430034,"rank":154,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1759816367757553,"rank":153,"remainingConfigurations":444},{"removed":"Scale","score":0.19824527468854328,"rank":153,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1763706183716054,"rank":153,"remainingConfigurations":444},{"removed":"Cognition","score":0.16790697106203978,"rank":155,"remainingConfigurations":444},{"removed":"LiveBench","score":0.18188394590848056,"rank":150,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.18100183468685058,"rank":152,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17922907923028242,"rank":149,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1710057837386083,"rank":150,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.17712363324898606,"rank":153,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17278349501824444,"rank":153,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.17690867602456126,"rank":153,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.17718383287117856,"rank":153,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17846417009638157,"rank":153,"remainingConfigurations":444},{"removed":"All provider reports","score":0.173768068853093,"rank":153,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.17846484352766082,"rank":154,"remainingConfigurations":444},{"removed":"briefcase","score":0.175776737346785,"rank":151,"remainingConfigurations":444},{"removed":"aime","score":0.17747578345270887,"rank":153,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17945775597519173,"rank":153,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1726305232236615,"rank":151,"remainingConfigurations":444},{"removed":"automationbench","score":0.17549664514227714,"rank":153,"remainingConfigurations":444},{"removed":"critpt","score":0.17479652509276578,"rank":154,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.17694244885470356,"rank":152,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.18012093442583088,"rank":153,"remainingConfigurations":444},{"removed":"gdpval","score":0.17706909421189196,"rank":153,"remainingConfigurations":444},{"removed":"gmmlu","score":0.178620121976259,"rank":152,"remainingConfigurations":444},{"removed":"gpqa","score":0.1655753916922634,"rank":154,"remainingConfigurations":444},{"removed":"harvey","score":0.17527028937542957,"rank":153,"remainingConfigurations":444},{"removed":"hle","score":0.18662003483384693,"rank":153,"remainingConfigurations":444},{"removed":"ifbench","score":0.15805895667406067,"rank":158,"remainingConfigurations":444},{"removed":"itbench","score":0.176238759135479,"rank":152,"remainingConfigurations":444},{"removed":"livecodebench","score":0.17678570089389614,"rank":153,"remainingConfigurations":444},{"removed":"math500","score":0.1772144361345407,"rank":153,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.18076055240947345,"rank":152,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.186603716902039,"rank":151,"remainingConfigurations":444},{"removed":"omniscience","score":0.18059888438589342,"rank":149,"remainingConfigurations":444},{"removed":"tau-bench","score":0.18193723696538652,"rank":149,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.17895508087214454,"rank":153,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.19810420211159271,"rank":136,"remainingConfigurations":444},{"removed":"arc-agi","score":0.21393558905757296,"rank":148,"remainingConfigurations":444},{"removed":"deepswe","score":0.14569198247658313,"rank":154,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.17721909712817016,"rank":153,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1747921611399085,"rank":154,"remainingConfigurations":444},{"removed":"frontiercode","score":0.16790697106203978,"rank":155,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.17547766845380733,"rank":153,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1754656643039855,"rank":153,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.17705672986600793,"rank":153,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.17648878357782605,"rank":153,"remainingConfigurations":444},{"removed":"livebench-math","score":0.17734349645356495,"rank":153,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.17565125145012564,"rank":153,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17938292620653837,"rank":153,"remainingConfigurations":444},{"removed":"livebench-data","score":0.1771108669142738,"rank":153,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.17432856103442293,"rank":153,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.176255239996981,"rank":153,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.18023823006098919,"rank":153,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.18100183468685058,"rank":152,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1772312139813995,"rank":152,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16946516641382578,"rank":152,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18402712266055213,"rank":152,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.17666182441123315,"rank":153,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.17665680288501537,"rank":153,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1766721672398037,"rank":153,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.17692586650890577,"rank":153,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1762624594693787,"rank":153,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.17677755347823895,"rank":153,"remainingConfigurations":444}],"sharedOrderConflicts":1},"deepseek-v4-flash-0424--effort-high":{"score":0.17476604599910753,"rank":154,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.21311040550324986,"rank":152,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14227036213225486,"rank":156,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17376674653056348,"rank":154,"remainingConfigurations":444},{"removed":"Scale","score":0.19507613726585518,"rank":154,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.17356519870362622,"rank":154,"remainingConfigurations":444},{"removed":"Cognition","score":0.16488772242407637,"rank":158,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17978063335921204,"rank":152,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.17848115249945784,"rank":154,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17886081127053968,"rank":150,"remainingConfigurations":431},{"removed":"Vals AI","score":0.16814700762014653,"rank":152,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1746997131052355,"rank":154,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.17036865991207004,"rank":154,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1744857149743475,"rank":154,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.17476604599910753,"rank":154,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17603123451436986,"rank":154,"remainingConfigurations":444},{"removed":"All provider reports","score":0.17132728988713208,"rank":154,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1761412967735904,"rank":155,"remainingConfigurations":444},{"removed":"briefcase","score":0.16873942010016585,"rank":155,"remainingConfigurations":444},{"removed":"aime","score":0.17446534007734202,"rank":155,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17722598514592483,"rank":154,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1821937697221789,"rank":146,"remainingConfigurations":444},{"removed":"automationbench","score":0.17058687045369844,"rank":154,"remainingConfigurations":444},{"removed":"critpt","score":0.17756920830432635,"rank":152,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1748356445328114,"rank":154,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.17919025450053028,"rank":154,"remainingConfigurations":444},{"removed":"gdpval","score":0.181067245628326,"rank":150,"remainingConfigurations":444},{"removed":"gmmlu","score":0.17620572899643727,"rank":153,"remainingConfigurations":444},{"removed":"gpqa","score":0.16999992099911632,"rank":152,"remainingConfigurations":444},{"removed":"harvey","score":0.17254285548044648,"rank":154,"remainingConfigurations":444},{"removed":"hle","score":0.1834104944257834,"rank":154,"remainingConfigurations":444},{"removed":"ifbench","score":0.17024435521075545,"rank":154,"remainingConfigurations":444},{"removed":"itbench","score":0.17384742389965724,"rank":153,"remainingConfigurations":444},{"removed":"livecodebench","score":0.17452526343238461,"rank":154,"remainingConfigurations":444},{"removed":"math500","score":0.17493183315018146,"rank":154,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17873925391732917,"rank":153,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1856293678545983,"rank":152,"remainingConfigurations":444},{"removed":"omniscience","score":0.17232604953795608,"rank":153,"remainingConfigurations":444},{"removed":"tau-bench","score":0.16530850563964974,"rank":158,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.17612298586484332,"rank":154,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.17436478812953274,"rank":153,"remainingConfigurations":444},{"removed":"arc-agi","score":0.20851079144141016,"rank":152,"remainingConfigurations":444},{"removed":"deepswe","score":0.1423542152507131,"rank":156,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.17480486580472054,"rank":154,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17275111185317105,"rank":155,"remainingConfigurations":444},{"removed":"frontiercode","score":0.16488772242407637,"rank":158,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.17309469503572494,"rank":154,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.17304618217227152,"rank":154,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1746422935388652,"rank":154,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.17405978115993972,"rank":154,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1749002055054548,"rank":154,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1732246035310424,"rank":154,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17699255500156774,"rank":154,"remainingConfigurations":444},{"removed":"livebench-data","score":0.17474459470329204,"rank":154,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.17188312507744619,"rank":154,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.17383346169996672,"rank":154,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.17781639255092793,"rank":154,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.17848115249945784,"rank":154,"remainingConfigurations":444},{"removed":"frontiermath","score":0.17515834579441883,"rank":153,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16818673600807246,"rank":153,"remainingConfigurations":444},{"removed":"simpleqa","score":0.18152551212230697,"rank":154,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.17425177276547477,"rank":154,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1742509786843377,"rank":154,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.17424342491071806,"rank":154,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.17452610979417024,"rank":154,"remainingConfigurations":444},{"removed":"vibe-code","score":0.17383934301571705,"rank":154,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.174367805420126,"rank":154,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5--effort-low":{"score":0.1701918236342067,"rank":155,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14686697997963793,"rank":127,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1925779669615343,"rank":158,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1547304212809111,"rank":143,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.17018593325499753,"rank":155,"remainingConfigurations":444},{"removed":"Scale","score":0.1890217592345286,"rank":156,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.16841548788272778,"rank":155,"remainingConfigurations":444},{"removed":"Cognition","score":0.18438203853339022,"rank":140,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17500169056436063,"rank":155,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.16897595171521895,"rank":157,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.15661114198419154,"rank":160,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1616770263417019,"rank":155,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1701723162071144,"rank":155,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1665455404961877,"rank":155,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.17011782346727955,"rank":155,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1701918236342067,"rank":155,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17168624325198945,"rank":155,"remainingConfigurations":444},{"removed":"All provider reports","score":0.16797177911012753,"rank":155,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.17094195101396173,"rank":156,"remainingConfigurations":444},{"removed":"briefcase","score":0.1697079907782879,"rank":154,"remainingConfigurations":444},{"removed":"aime","score":0.1758655983086197,"rank":154,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17153084217682912,"rank":155,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1687746352752024,"rank":154,"remainingConfigurations":444},{"removed":"automationbench","score":0.16929049810406963,"rank":155,"remainingConfigurations":444},{"removed":"critpt","score":0.16989894935727864,"rank":156,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.17032105048853796,"rank":156,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.17080088747197833,"rank":157,"remainingConfigurations":444},{"removed":"gdpval","score":0.1708209171348307,"rank":155,"remainingConfigurations":444},{"removed":"gmmlu","score":0.17060195315212623,"rank":155,"remainingConfigurations":444},{"removed":"gpqa","score":0.1685849725610772,"rank":153,"remainingConfigurations":444},{"removed":"harvey","score":0.16847124546689998,"rank":156,"remainingConfigurations":444},{"removed":"hle","score":0.1808438197094779,"rank":155,"remainingConfigurations":444},{"removed":"ifbench","score":0.17265004581749444,"rank":151,"remainingConfigurations":444},{"removed":"itbench","score":0.16963764442856843,"rank":154,"remainingConfigurations":444},{"removed":"livecodebench","score":0.17046804087503445,"rank":155,"remainingConfigurations":444},{"removed":"math500","score":0.17033600726585132,"rank":155,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17461436278721662,"rank":155,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.17852756399842065,"rank":155,"remainingConfigurations":444},{"removed":"omniscience","score":0.16478209157355989,"rank":155,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1710272469966534,"rank":155,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1711489773635481,"rank":157,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.16865000594535504,"rank":155,"remainingConfigurations":444},{"removed":"arc-agi","score":0.18466818098297685,"rank":158,"remainingConfigurations":444},{"removed":"deepswe","score":0.15474351856179067,"rank":143,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1702281819394118,"rank":155,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1695629830439714,"rank":156,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18438203853339022,"rank":140,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.16868552986003812,"rank":155,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1682329333147363,"rank":155,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.17017196791679137,"rank":155,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.16942184819890013,"rank":155,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1705098757382879,"rank":155,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.16856828206771077,"rank":155,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17211329041290327,"rank":155,"remainingConfigurations":444},{"removed":"livebench-data","score":0.169996913050642,"rank":155,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1674599092673086,"rank":155,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1693230550769811,"rank":155,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1734175155838362,"rank":155,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.16897595171521895,"rank":157,"remainingConfigurations":444},{"removed":"frontiermath","score":0.17115133835048987,"rank":155,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.15577854954508386,"rank":159,"remainingConfigurations":444},{"removed":"simpleqa","score":0.17620004585456786,"rank":155,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1696469301424456,"rank":155,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.16963424825277404,"rank":155,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.16981855994380557,"rank":155,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.16978596637819962,"rank":155,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1692009324063871,"rank":155,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.16990111688626788,"rank":155,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m3--effort-reasoning":{"score":0.16934596133409674,"rank":156,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.20834838800148694,"rank":155,"remainingConfigurations":444},{"removed":"Datacurve","score":0.13861307359767985,"rank":158,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1682919101707251,"rank":156,"remainingConfigurations":444},{"removed":"Scale","score":0.1890895865742742,"rank":155,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.16821981092715846,"rank":156,"remainingConfigurations":444},{"removed":"Cognition","score":0.16157140017627666,"rank":160,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17502358414921448,"rank":154,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.17274321290169167,"rank":155,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1738530658341969,"rank":155,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1633816777419758,"rank":154,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.16926844158991336,"rank":156,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1649299629921865,"rank":156,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1690731016525334,"rank":156,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.16934596133409674,"rank":156,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.17049468692277114,"rank":156,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1657706546580869,"rank":156,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.17854535481413492,"rank":153,"remainingConfigurations":444},{"removed":"briefcase","score":0.16221489520435306,"rank":158,"remainingConfigurations":444},{"removed":"aime","score":0.16858578822653647,"rank":156,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17135640717353326,"rank":156,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.15585944439547442,"rank":159,"remainingConfigurations":444},{"removed":"automationbench","score":0.16833050160412355,"rank":157,"remainingConfigurations":444},{"removed":"critpt","score":0.17174526730245399,"rank":155,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.17519944444576496,"rank":153,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1745302054276573,"rank":155,"remainingConfigurations":444},{"removed":"gdpval","score":0.1628004905279327,"rank":158,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1697011830715062,"rank":156,"remainingConfigurations":444},{"removed":"gpqa","score":0.15586159887404866,"rank":158,"remainingConfigurations":444},{"removed":"harvey","score":0.17018699036887855,"rank":155,"remainingConfigurations":444},{"removed":"hle","score":0.17312772141944432,"rank":158,"remainingConfigurations":444},{"removed":"ifbench","score":0.15637424393766486,"rank":159,"remainingConfigurations":444},{"removed":"itbench","score":0.16842828721806144,"rank":155,"remainingConfigurations":444},{"removed":"livecodebench","score":0.16878196483351834,"rank":156,"remainingConfigurations":444},{"removed":"math500","score":0.1697041681313686,"rank":156,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17318277640267074,"rank":156,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1735046498549888,"rank":158,"remainingConfigurations":444},{"removed":"omniscience","score":0.2033533069157286,"rank":137,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1711703239812572,"rank":154,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.17558971378008834,"rank":155,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.16570726793443638,"rank":157,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2022486213275624,"rank":156,"remainingConfigurations":444},{"removed":"deepswe","score":0.1387128222495129,"rank":158,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.16938358409020152,"rank":156,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.16761136232393628,"rank":157,"remainingConfigurations":444},{"removed":"frontiercode","score":0.16157140017627666,"rank":160,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.16771454770792374,"rank":156,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1676560859245292,"rank":156,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.16922878938071273,"rank":156,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.16873672558366012,"rank":156,"remainingConfigurations":444},{"removed":"livebench-math","score":0.16945257457435595,"rank":156,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1678565750462696,"rank":156,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17155883405484204,"rank":156,"remainingConfigurations":444},{"removed":"livebench-data","score":0.16933083727898804,"rank":156,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.16648064940630447,"rank":156,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.16844713012408588,"rank":156,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.17233231895363,"rank":156,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.17274321290169167,"rank":155,"remainingConfigurations":444},{"removed":"frontiermath","score":0.16943156771086887,"rank":156,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16274894351215888,"rank":156,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1760132617615553,"rank":156,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.16886832118154338,"rank":156,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.16882570686479817,"rank":156,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.16881450944790044,"rank":156,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.16911811636401045,"rank":156,"remainingConfigurations":444},{"removed":"vibe-code","score":0.16841786855046434,"rank":156,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.16895546764389766,"rank":156,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-7--effort-non-reasoning":{"score":0.16874012226909194,"rank":157,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.21158167010029863,"rank":153,"remainingConfigurations":444},{"removed":"Datacurve","score":0.13874153568967698,"rank":157,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.16756163272636548,"rank":157,"remainingConfigurations":444},{"removed":"Scale","score":0.1888089991380407,"rank":157,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.16801607584379966,"rank":157,"remainingConfigurations":444},{"removed":"Cognition","score":0.16210980795538477,"rank":159,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17397169590547676,"rank":156,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.17262195064076516,"rank":156,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.16957686534298885,"rank":156,"remainingConfigurations":431},{"removed":"Vals AI","score":0.16358566627964974,"rank":153,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.16868011867238006,"rank":157,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1644724899638965,"rank":157,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.16848240271381523,"rank":157,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.16874012226909194,"rank":157,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1699718026773587,"rank":157,"remainingConfigurations":444},{"removed":"All provider reports","score":0.16542452930001908,"rank":157,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1707186064578721,"rank":157,"remainingConfigurations":444},{"removed":"briefcase","score":0.1629779243145514,"rank":157,"remainingConfigurations":444},{"removed":"aime","score":0.16771491331493205,"rank":157,"remainingConfigurations":444},{"removed":"apex-agents","score":0.17132990867195064,"rank":157,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.14541345460041913,"rank":163,"remainingConfigurations":444},{"removed":"automationbench","score":0.16872954569009643,"rank":156,"remainingConfigurations":444},{"removed":"critpt","score":0.16548522383234102,"rank":158,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.16936578904506838,"rank":157,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.17342175745450797,"rank":156,"remainingConfigurations":444},{"removed":"gdpval","score":0.1694054246598705,"rank":156,"remainingConfigurations":444},{"removed":"gmmlu","score":0.16927607384877885,"rank":157,"remainingConfigurations":444},{"removed":"gpqa","score":0.1584260690756595,"rank":157,"remainingConfigurations":444},{"removed":"harvey","score":0.16710980484439583,"rank":157,"remainingConfigurations":444},{"removed":"hle","score":0.17416376746922946,"rank":157,"remainingConfigurations":444},{"removed":"ifbench","score":0.22207423560776954,"rank":135,"remainingConfigurations":444},{"removed":"itbench","score":0.16835125214545302,"rank":156,"remainingConfigurations":444},{"removed":"livecodebench","score":0.16731909745498208,"rank":157,"remainingConfigurations":444},{"removed":"math500","score":0.16871367813211444,"rank":157,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17135785435143633,"rank":157,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.17465380627136376,"rank":157,"remainingConfigurations":444},{"removed":"omniscience","score":0.14924684955024012,"rank":160,"remainingConfigurations":444},{"removed":"tau-bench","score":0.19128933783923333,"rank":142,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1712102203558767,"rank":156,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.15887542266468233,"rank":159,"remainingConfigurations":444},{"removed":"arc-agi","score":0.20444084803376403,"rank":154,"remainingConfigurations":444},{"removed":"deepswe","score":0.13882279629268576,"rank":157,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.16877484357526332,"rank":157,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1666501407468524,"rank":158,"remainingConfigurations":444},{"removed":"frontiercode","score":0.16210980795538477,"rank":159,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1671330246705293,"rank":157,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1671027176849915,"rank":157,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.16862166890982466,"rank":157,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.16811068205283652,"rank":157,"remainingConfigurations":444},{"removed":"livebench-math","score":0.16888690346361124,"rank":157,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1672481090874792,"rank":157,"remainingConfigurations":444},{"removed":"livebench-language","score":0.17088767642620264,"rank":157,"remainingConfigurations":444},{"removed":"livebench-data","score":0.16868264313115602,"rank":157,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.16595327885454358,"rank":157,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.16783724161478353,"rank":157,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1717157266848044,"rank":157,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.17262195064076516,"rank":156,"remainingConfigurations":444},{"removed":"frontiermath","score":0.16888451724183984,"rank":157,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16120911426506854,"rank":157,"remainingConfigurations":444},{"removed":"simpleqa","score":0.17539510192283245,"rank":157,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.16823732697695937,"rank":157,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1682278723687851,"rank":157,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.16823627649182962,"rank":157,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.16849139644749536,"rank":157,"remainingConfigurations":444},{"removed":"vibe-code","score":0.16783778048606768,"rank":157,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.16835194119181263,"rank":157,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-medium":{"score":0.16616131615628765,"rank":158,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12512810758976284,"rank":135,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2446121439376807,"rank":136,"remainingConfigurations":444},{"removed":"Datacurve","score":0.13286836438253327,"rank":159,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.16624047644214204,"rank":158,"remainingConfigurations":444},{"removed":"Scale","score":0.18507223320292823,"rank":158,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.16350087245782657,"rank":158,"remainingConfigurations":444},{"removed":"Cognition","score":0.13799560445665557,"rank":164,"remainingConfigurations":444},{"removed":"LiveBench","score":0.17343622554432972,"rank":157,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.16587616982009523,"rank":158,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17562266161924991,"rank":153,"remainingConfigurations":431},{"removed":"Vals AI","score":0.16065845524512543,"rank":156,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.16609740492095823,"rank":158,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1626918152553504,"rank":158,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.16592018148880547,"rank":158,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.16616131615628765,"rank":158,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.16885823432747993,"rank":158,"remainingConfigurations":444},{"removed":"All provider reports","score":0.16508324575280597,"rank":158,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.16706981564755527,"rank":158,"remainingConfigurations":444},{"removed":"briefcase","score":0.16432306582328968,"rank":156,"remainingConfigurations":444},{"removed":"aime","score":0.1650399512188462,"rank":158,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1676935921275202,"rank":158,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.16478953296667354,"rank":156,"remainingConfigurations":444},{"removed":"automationbench","score":0.16345708303747974,"rank":158,"remainingConfigurations":444},{"removed":"critpt","score":0.16563661167695073,"rank":157,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.16655068977901288,"rank":158,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.16486754765296258,"rank":158,"remainingConfigurations":444},{"removed":"gdpval","score":0.16464006577069626,"rank":157,"remainingConfigurations":444},{"removed":"gmmlu","score":0.16667903253151214,"rank":158,"remainingConfigurations":444},{"removed":"gpqa","score":0.16530986933344702,"rank":155,"remainingConfigurations":444},{"removed":"harvey","score":0.16454416699912244,"rank":158,"remainingConfigurations":444},{"removed":"hle","score":0.17887805707013307,"rank":156,"remainingConfigurations":444},{"removed":"ifbench","score":0.16552340507990035,"rank":156,"remainingConfigurations":444},{"removed":"itbench","score":0.1658852390611489,"rank":157,"remainingConfigurations":444},{"removed":"livecodebench","score":0.16653643499019352,"rank":158,"remainingConfigurations":444},{"removed":"math500","score":0.1662766991995172,"rank":158,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.17039389230061106,"rank":158,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.17525988400841183,"rank":156,"remainingConfigurations":444},{"removed":"omniscience","score":0.1626974819672273,"rank":156,"remainingConfigurations":444},{"removed":"tau-bench","score":0.16721168803512645,"rank":157,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.16708353992588143,"rank":158,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.16661387135410718,"rank":156,"remainingConfigurations":444},{"removed":"arc-agi","score":0.20695227001400474,"rank":153,"remainingConfigurations":444},{"removed":"deepswe","score":0.1327953094843606,"rank":159,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.16618065734081136,"rank":158,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.17943330092806967,"rank":147,"remainingConfigurations":444},{"removed":"frontiercode","score":0.13799560445665557,"rank":164,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1644789614996797,"rank":158,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.16436250341384737,"rank":158,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.16607447805536393,"rank":158,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.16563295672512035,"rank":158,"remainingConfigurations":444},{"removed":"livebench-math","score":0.16636558385669162,"rank":158,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1646448279778552,"rank":158,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1680975916657204,"rank":158,"remainingConfigurations":444},{"removed":"livebench-data","score":0.16587482088671132,"rank":158,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.16341037575749565,"rank":158,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.16529677263732748,"rank":158,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.16950334351114593,"rank":158,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.16587616982009523,"rank":158,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1660474522928019,"rank":158,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1632939905070063,"rank":155,"remainingConfigurations":444},{"removed":"simpleqa","score":0.17261491542374685,"rank":158,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1657691628913592,"rank":158,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.16550537588385858,"rank":158,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.16587082461275782,"rank":158,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.16570667240755912,"rank":158,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1650726314055682,"rank":158,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.16589645888397012,"rank":158,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.6-flash--effort-low":{"score":0.16203270712133336,"rank":159,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1521083107380853,"rank":124,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.18701346270002042,"rank":159,"remainingConfigurations":444},{"removed":"Datacurve","score":0.12442485238321123,"rank":161,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.16291081583173397,"rank":159,"remainingConfigurations":444},{"removed":"Scale","score":0.1802727132314611,"rank":159,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.15992869677572888,"rank":159,"remainingConfigurations":444},{"removed":"Cognition","score":0.17059393344079143,"rank":154,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1664688267023616,"rank":158,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.16041837222095942,"rank":159,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17424064139557696,"rank":154,"remainingConfigurations":431},{"removed":"Vals AI","score":0.15768276128821848,"rank":158,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.16197559543660042,"rank":159,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.15845141226918197,"rank":159,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.16187652088748192,"rank":159,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.16203270712133336,"rank":159,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1628933402871214,"rank":159,"remainingConfigurations":444},{"removed":"All provider reports","score":0.15913130019307095,"rank":159,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.16253273742863336,"rank":159,"remainingConfigurations":444},{"removed":"briefcase","score":0.1611761706792492,"rank":159,"remainingConfigurations":444},{"removed":"aime","score":0.15922925223813303,"rank":159,"remainingConfigurations":444},{"removed":"apex-agents","score":0.16309641024312738,"rank":159,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1616111026686889,"rank":157,"remainingConfigurations":444},{"removed":"automationbench","score":0.16101935065594977,"rank":159,"remainingConfigurations":444},{"removed":"critpt","score":0.1626012810186198,"rank":159,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.16193260609386417,"rank":159,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1626927905442327,"rank":159,"remainingConfigurations":444},{"removed":"gdpval","score":0.16158361887259498,"rank":159,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1621496254416723,"rank":159,"remainingConfigurations":444},{"removed":"gpqa","score":0.1548589411523972,"rank":159,"remainingConfigurations":444},{"removed":"harvey","score":0.15989505452437106,"rank":159,"remainingConfigurations":444},{"removed":"hle","score":0.1723174492092834,"rank":159,"remainingConfigurations":444},{"removed":"ifbench","score":0.160966237205085,"rank":157,"remainingConfigurations":444},{"removed":"itbench","score":0.16148701705274682,"rank":159,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1629335787635341,"rank":159,"remainingConfigurations":444},{"removed":"math500","score":0.1620991569741456,"rank":159,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1663122213983789,"rank":159,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1716853548861006,"rank":159,"remainingConfigurations":444},{"removed":"omniscience","score":0.15993192789350716,"rank":157,"remainingConfigurations":444},{"removed":"tau-bench","score":0.16104657723134638,"rank":159,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.16261765573430095,"rank":159,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.16093381836518866,"rank":158,"remainingConfigurations":444},{"removed":"arc-agi","score":0.17257946558437762,"rank":163,"remainingConfigurations":444},{"removed":"deepswe","score":0.12449034457217541,"rank":161,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1620608078812614,"rank":159,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.15484708691885507,"rank":159,"remainingConfigurations":444},{"removed":"frontiercode","score":0.17059393344079143,"rank":154,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.16057789712219075,"rank":159,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1603390370114356,"rank":159,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1619409707811091,"rank":159,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.16136947677170008,"rank":159,"remainingConfigurations":444},{"removed":"livebench-math","score":0.16229347849421463,"rank":159,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.16055168073201617,"rank":159,"remainingConfigurations":444},{"removed":"livebench-language","score":0.16379162063991262,"rank":159,"remainingConfigurations":444},{"removed":"livebench-data","score":0.16226474818151984,"rank":159,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.15939594556443304,"rank":159,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.16113691075512726,"rank":159,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1648396419665131,"rank":159,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.16041837222095942,"rank":159,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1630185671143274,"rank":159,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.16366239100689206,"rank":154,"remainingConfigurations":444},{"removed":"simpleqa","score":0.16673490774770142,"rank":159,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.16137434844573317,"rank":159,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1616238413678652,"rank":159,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.16159378473243946,"rank":159,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.16189129182938067,"rank":159,"remainingConfigurations":444},{"removed":"vibe-code","score":0.16124306138097388,"rank":159,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.16137110794430007,"rank":159,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.1--effort-high":{"score":0.15524596374396363,"rank":160,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.135291516363465,"rank":131,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.2067906465658728,"rank":156,"remainingConfigurations":444},{"removed":"Datacurve","score":0.12397366198984872,"rank":162,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.15608850962324214,"rank":160,"remainingConfigurations":444},{"removed":"Scale","score":0.1742700055335217,"rank":160,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1536488925312458,"rank":160,"remainingConfigurations":444},{"removed":"Cognition","score":0.146910471196515,"rank":161,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1589841052287195,"rank":159,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.15654138756291014,"rank":160,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.15523432710931628,"rank":161,"remainingConfigurations":431},{"removed":"Vals AI","score":0.14754489646756702,"rank":161,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1551958964449129,"rank":160,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.15148300925578445,"rank":160,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.15503355757942386,"rank":160,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.15524596374396363,"rank":160,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.15637474344463356,"rank":160,"remainingConfigurations":444},{"removed":"All provider reports","score":0.15237921917953615,"rank":160,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.15608564983670273,"rank":160,"remainingConfigurations":444},{"removed":"briefcase","score":0.1543424248232532,"rank":160,"remainingConfigurations":444},{"removed":"aime","score":0.1545899126320599,"rank":160,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1566726944290923,"rank":160,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.14872766903202353,"rank":160,"remainingConfigurations":444},{"removed":"automationbench","score":0.15423093541308655,"rank":160,"remainingConfigurations":444},{"removed":"critpt","score":0.15528785542719323,"rank":160,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.15507745587711033,"rank":160,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.15696360526502814,"rank":160,"remainingConfigurations":444},{"removed":"gdpval","score":0.1613968273920314,"rank":160,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1533341980572578,"rank":160,"remainingConfigurations":444},{"removed":"gpqa","score":0.1519494522030488,"rank":161,"remainingConfigurations":444},{"removed":"harvey","score":0.15354054880193674,"rank":160,"remainingConfigurations":444},{"removed":"hle","score":0.16676512133499807,"rank":161,"remainingConfigurations":444},{"removed":"ifbench","score":0.15219633038402916,"rank":160,"remainingConfigurations":444},{"removed":"itbench","score":0.1544554046221111,"rank":160,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1564312483591155,"rank":160,"remainingConfigurations":444},{"removed":"math500","score":0.15554255125659966,"rank":160,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.15940023552559293,"rank":160,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.16529305292185695,"rank":160,"remainingConfigurations":444},{"removed":"omniscience","score":0.14832726625836365,"rank":161,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1591241808918942,"rank":160,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.15657258091721346,"rank":160,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.15549469911839697,"rank":160,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2005367257999486,"rank":157,"remainingConfigurations":444},{"removed":"deepswe","score":0.12402945499920841,"rank":162,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.15527537394760335,"rank":160,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.14800628900506993,"rank":160,"remainingConfigurations":444},{"removed":"frontiercode","score":0.146910471196515,"rank":161,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1535850749877325,"rank":160,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1536453304889738,"rank":160,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.15513537640630964,"rank":160,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.15461203912414648,"rank":160,"remainingConfigurations":444},{"removed":"livebench-math","score":0.15540357955406855,"rank":160,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.15390025950690175,"rank":160,"remainingConfigurations":444},{"removed":"livebench-language","score":0.15715586912168775,"rank":160,"remainingConfigurations":444},{"removed":"livebench-data","score":0.15510266608420123,"rank":160,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.15262426117303718,"rank":160,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.15443008237589365,"rank":160,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.15814144973551636,"rank":160,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.15654138756291014,"rank":160,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1559321964825211,"rank":160,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1475156867230011,"rank":161,"remainingConfigurations":444},{"removed":"simpleqa","score":0.16135495569265704,"rank":160,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.15474495312464798,"rank":160,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1547383269767968,"rank":160,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.15483291787154163,"rank":160,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1549620703675886,"rank":160,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1543543329424222,"rank":160,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.15486572183610556,"rank":160,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-4-6--effort-high":{"score":0.14681669541375963,"rank":161,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.13435065861977358,"rank":132,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.08160484478802692,"rank":225,"remainingConfigurations":444},{"removed":"Datacurve","score":0.14429405607081688,"rank":155,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1470919966283035,"rank":161,"remainingConfigurations":444},{"removed":"Scale","score":0.16352673530640352,"rank":162,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.14549871208222293,"rank":161,"remainingConfigurations":444},{"removed":"Cognition","score":0.187630643097504,"rank":137,"remainingConfigurations":444},{"removed":"LiveBench","score":0.15045515015468805,"rank":162,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1426781065038729,"rank":163,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17816684873513036,"rank":151,"remainingConfigurations":431},{"removed":"Vals AI","score":0.13762534531724974,"rank":164,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1468478908967675,"rank":161,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.14374005449915597,"rank":161,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1469758744077778,"rank":161,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.14681669541375963,"rank":161,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.14734763750442534,"rank":162,"remainingConfigurations":444},{"removed":"All provider reports","score":0.14449216068827214,"rank":161,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.14709800623972924,"rank":162,"remainingConfigurations":444},{"removed":"briefcase","score":0.1458176628299989,"rank":161,"remainingConfigurations":444},{"removed":"aime","score":0.14945476723111778,"rank":161,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1476646074707074,"rank":164,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.14693132881406742,"rank":162,"remainingConfigurations":444},{"removed":"automationbench","score":0.14620481753611766,"rank":161,"remainingConfigurations":444},{"removed":"critpt","score":0.14698700173059218,"rank":164,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.14679697976516043,"rank":161,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1473377003097772,"rank":161,"remainingConfigurations":444},{"removed":"gdpval","score":0.146363855132126,"rank":161,"remainingConfigurations":444},{"removed":"gmmlu","score":0.14693278526861445,"rank":161,"remainingConfigurations":444},{"removed":"gpqa","score":0.14712561779186129,"rank":163,"remainingConfigurations":444},{"removed":"harvey","score":0.14528683069017567,"rank":161,"remainingConfigurations":444},{"removed":"hle","score":0.15559837918786415,"rank":163,"remainingConfigurations":444},{"removed":"ifbench","score":0.1462276472560278,"rank":161,"remainingConfigurations":444},{"removed":"itbench","score":0.14639398558395975,"rank":161,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1471114111726756,"rank":161,"remainingConfigurations":444},{"removed":"math500","score":0.14684325835570516,"rank":161,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.15039260967087845,"rank":161,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.15555343915723865,"rank":162,"remainingConfigurations":444},{"removed":"omniscience","score":0.14577842400855315,"rank":162,"remainingConfigurations":444},{"removed":"tau-bench","score":0.146217319896114,"rank":162,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.14681695037365147,"rank":162,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.14646353396568149,"rank":161,"remainingConfigurations":444},{"removed":"arc-agi","score":0.07978481367692507,"rank":226,"remainingConfigurations":444},{"removed":"deepswe","score":0.14437276624537052,"rank":155,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.14686229634098283,"rank":161,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.14608533782019234,"rank":161,"remainingConfigurations":444},{"removed":"frontiercode","score":0.187630643097504,"rank":137,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.14561023151093863,"rank":161,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1451943710768159,"rank":161,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.14684215775306547,"rank":161,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.14559795482590768,"rank":162,"remainingConfigurations":444},{"removed":"livebench-math","score":0.14700929006176308,"rank":162,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.14508249257788183,"rank":161,"remainingConfigurations":444},{"removed":"livebench-language","score":0.14862507952480564,"rank":161,"remainingConfigurations":444},{"removed":"livebench-data","score":0.14720099448689097,"rank":161,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.14434133263425564,"rank":162,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.14581709862978529,"rank":161,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.14968924109857132,"rank":162,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1426781065038729,"rank":163,"remainingConfigurations":444},{"removed":"frontiermath","score":0.14524217008483134,"rank":162,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.14333112021845565,"rank":162,"remainingConfigurations":444},{"removed":"simpleqa","score":0.15314006586061685,"rank":161,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.14608639393801745,"rank":161,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.14654109637408697,"rank":161,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.146305407031061,"rank":161,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1465821167319419,"rank":161,"remainingConfigurations":444},{"removed":"vibe-code","score":0.14614712849289277,"rank":161,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.14646577351059192,"rank":161,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.6-sol--effort-non-reasoning":{"score":0.1462783904156948,"rank":162,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.17843242077971014,"rank":163,"remainingConfigurations":444},{"removed":"Datacurve","score":0.11876346768836392,"rank":164,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.145372899785561,"rank":162,"remainingConfigurations":444},{"removed":"Scale","score":0.16431735185739682,"rank":161,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.14521678801566779,"rank":162,"remainingConfigurations":444},{"removed":"Cognition","score":0.13739779018448703,"rank":165,"remainingConfigurations":444},{"removed":"LiveBench","score":0.15117404722163819,"rank":160,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1491984015235512,"rank":162,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1485423925111282,"rank":162,"remainingConfigurations":431},{"removed":"Vals AI","score":0.14117334839817575,"rank":162,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.14622069817356878,"rank":162,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.14238460234769124,"rank":162,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.14603170619350267,"rank":162,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1462783904156948,"rank":162,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1473986370825255,"rank":161,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1432333339761804,"rank":162,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.14803746551664052,"rank":161,"remainingConfigurations":444},{"removed":"briefcase","score":0.1410005551521379,"rank":165,"remainingConfigurations":444},{"removed":"aime","score":0.14576647812441512,"rank":162,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1485038197884175,"rank":163,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.16137558029806306,"rank":158,"remainingConfigurations":444},{"removed":"automationbench","score":0.14566069430586923,"rank":162,"remainingConfigurations":444},{"removed":"critpt","score":0.14082267519644417,"rank":168,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1466883335151993,"rank":162,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13929559335827355,"rank":165,"remainingConfigurations":444},{"removed":"gdpval","score":0.13813049855089563,"rank":165,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1465677670865599,"rank":162,"remainingConfigurations":444},{"removed":"gpqa","score":0.1598525941248264,"rank":156,"remainingConfigurations":444},{"removed":"harvey","score":0.14460716950250094,"rank":162,"remainingConfigurations":444},{"removed":"hle","score":0.16824167483822106,"rank":160,"remainingConfigurations":444},{"removed":"ifbench","score":0.14190781143739895,"rank":164,"remainingConfigurations":444},{"removed":"itbench","score":0.14563908429457675,"rank":162,"remainingConfigurations":444},{"removed":"livecodebench","score":0.14577380140331206,"rank":162,"remainingConfigurations":444},{"removed":"math500","score":0.14628889750196686,"rank":162,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.14943732629667242,"rank":162,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.16354651071840112,"rank":161,"remainingConfigurations":444},{"removed":"omniscience","score":0.12787560437707943,"rank":176,"remainingConfigurations":444},{"removed":"tau-bench","score":0.14392876053491346,"rank":164,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1476245714153285,"rank":161,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.14134579513660175,"rank":164,"remainingConfigurations":444},{"removed":"arc-agi","score":0.17400719401627152,"rank":162,"remainingConfigurations":444},{"removed":"deepswe","score":0.11883363017745059,"rank":164,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.14631144602453489,"rank":162,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.14451931942672322,"rank":162,"remainingConfigurations":444},{"removed":"frontiercode","score":0.13739779018448703,"rank":165,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.14474948811032293,"rank":162,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1447583722777633,"rank":162,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.14617677699800094,"rank":162,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1457410862089347,"rank":161,"remainingConfigurations":444},{"removed":"livebench-math","score":0.14640345649242448,"rank":163,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1448934776316225,"rank":162,"remainingConfigurations":444},{"removed":"livebench-language","score":0.14825124603736275,"rank":162,"remainingConfigurations":444},{"removed":"livebench-data","score":0.14625501437112112,"rank":162,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.14372529848901758,"rank":163,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.14544350248026372,"rank":162,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.14902110399544588,"rank":163,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1491984015235512,"rank":162,"remainingConfigurations":444},{"removed":"frontiermath","score":0.14623302879649952,"rank":161,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.13978267170227918,"rank":164,"remainingConfigurations":444},{"removed":"simpleqa","score":0.15234534760519933,"rank":162,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.14581859042386827,"rank":162,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.14581519533690324,"rank":162,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.14582109147105618,"rank":162,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.14605181996023864,"rank":162,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1454551909416813,"rank":162,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.14592276534299,"rank":162,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5--effort-low":{"score":0.14479115931733572,"rank":163,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12170670338847615,"rank":137,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15539874436068965,"rank":177,"remainingConfigurations":444},{"removed":"Datacurve","score":0.12979853692625648,"rank":160,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.14466481026793052,"rank":163,"remainingConfigurations":444},{"removed":"Scale","score":0.1621647450081113,"rank":163,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.14159227640578775,"rank":164,"remainingConfigurations":444},{"removed":"Cognition","score":0.11644543764014405,"rank":180,"remainingConfigurations":444},{"removed":"LiveBench","score":0.15064733814455228,"rank":161,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1402776559590093,"rank":165,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1677511702611442,"rank":158,"remainingConfigurations":431},{"removed":"Vals AI","score":0.13638085565746746,"rank":165,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.14477379300590237,"rank":163,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1415601795515011,"rank":163,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.14469737143899833,"rank":163,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.14479115931733572,"rank":163,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.14534466625311754,"rank":163,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1420391924896444,"rank":163,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.14532475673208028,"rank":163,"remainingConfigurations":444},{"removed":"briefcase","score":0.1424722060521889,"rank":163,"remainingConfigurations":444},{"removed":"aime","score":0.14252211116965252,"rank":163,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1460700460986735,"rank":165,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.14774250939160977,"rank":161,"remainingConfigurations":444},{"removed":"automationbench","score":0.14474700696017972,"rank":163,"remainingConfigurations":444},{"removed":"critpt","score":0.14385382187325554,"rank":166,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.14491752198739138,"rank":163,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.14593966651835916,"rank":162,"remainingConfigurations":444},{"removed":"gdpval","score":0.14355848938747137,"rank":162,"remainingConfigurations":444},{"removed":"gmmlu","score":0.14508898262081935,"rank":163,"remainingConfigurations":444},{"removed":"gpqa","score":0.14525254366512355,"rank":164,"remainingConfigurations":444},{"removed":"harvey","score":0.14324949145470264,"rank":163,"remainingConfigurations":444},{"removed":"hle","score":0.15589350803768134,"rank":162,"remainingConfigurations":444},{"removed":"ifbench","score":0.14339679850317874,"rank":162,"remainingConfigurations":444},{"removed":"itbench","score":0.14438823879415524,"rank":163,"remainingConfigurations":444},{"removed":"livecodebench","score":0.14476483695216424,"rank":163,"remainingConfigurations":444},{"removed":"math500","score":0.14483192123302704,"rank":163,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.14811497150656897,"rank":163,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.15418242380387942,"rank":163,"remainingConfigurations":444},{"removed":"omniscience","score":0.14201035692216993,"rank":166,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1440054292516498,"rank":163,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.14434066369173915,"rank":163,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.14181054938772214,"rank":163,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15331005515654825,"rank":176,"remainingConfigurations":444},{"removed":"deepswe","score":0.1299045455819852,"rank":160,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1448255121285279,"rank":163,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.14384008137438606,"rank":163,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11644543764014405,"rank":180,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.14355492970093922,"rank":163,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.14286399305277123,"rank":163,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.14473756306533284,"rank":163,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.14391614869542854,"rank":163,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1448785048564097,"rank":164,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.14252111951105992,"rank":163,"remainingConfigurations":444},{"removed":"livebench-language","score":0.14679558398881318,"rank":163,"remainingConfigurations":444},{"removed":"livebench-data","score":0.14510945175754414,"rank":163,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.14259780805839703,"rank":164,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1435780979783317,"rank":163,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1481230865894912,"rank":164,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1402776559590093,"rank":165,"remainingConfigurations":444},{"removed":"frontiermath","score":0.14423718073507624,"rank":163,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1497079138871891,"rank":160,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1501139971871345,"rank":163,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.14430039811607517,"rank":163,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.14434780788530324,"rank":163,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.14427673452056522,"rank":163,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1444798700722906,"rank":163,"remainingConfigurations":444},{"removed":"vibe-code","score":0.14407126432782674,"rank":163,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.14432439334455324,"rank":163,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-4-6--effort-medium":{"score":0.1432365900388354,"rank":164,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.13796256981084684,"rank":130,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.16143172019165083,"rank":173,"remainingConfigurations":444},{"removed":"Datacurve","score":0.12004330351825872,"rank":163,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1432589706357037,"rank":164,"remainingConfigurations":444},{"removed":"Scale","score":0.16012184552284286,"rank":164,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.14261744068417825,"rank":163,"remainingConfigurations":444},{"removed":"Cognition","score":0.25646890806007694,"rank":123,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07970517160579492,"rank":217,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1403252811765354,"rank":164,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.16189163883902444,"rank":159,"remainingConfigurations":431},{"removed":"Vals AI","score":0.13904654292652477,"rank":163,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1432157476274117,"rank":164,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.14037308827595865,"rank":164,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.14292357168721861,"rank":164,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1432365900388354,"rank":164,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1437183341346467,"rank":164,"remainingConfigurations":444},{"removed":"All provider reports","score":0.14055155804087338,"rank":164,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.14338699120888956,"rank":164,"remainingConfigurations":444},{"removed":"briefcase","score":0.14218087199224888,"rank":164,"remainingConfigurations":444},{"removed":"aime","score":0.13706705109124784,"rank":164,"remainingConfigurations":444},{"removed":"apex-agents","score":0.14396745148564902,"rank":166,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.14373745885960815,"rank":164,"remainingConfigurations":444},{"removed":"automationbench","score":0.1429990198470292,"rank":164,"remainingConfigurations":444},{"removed":"critpt","score":0.14287922126299898,"rank":167,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1432979721707228,"rank":164,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.14389113415835467,"rank":164,"remainingConfigurations":444},{"removed":"gdpval","score":0.14276918402524522,"rank":163,"remainingConfigurations":444},{"removed":"gmmlu","score":0.14344880364425658,"rank":164,"remainingConfigurations":444},{"removed":"gpqa","score":0.15428961947081368,"rank":160,"remainingConfigurations":444},{"removed":"harvey","score":0.14185954272484028,"rank":164,"remainingConfigurations":444},{"removed":"hle","score":0.15182212276220322,"rank":164,"remainingConfigurations":444},{"removed":"ifbench","score":0.14268606580784596,"rank":163,"remainingConfigurations":444},{"removed":"itbench","score":0.14296646962625784,"rank":164,"remainingConfigurations":444},{"removed":"livecodebench","score":0.14331717224376092,"rank":164,"remainingConfigurations":444},{"removed":"math500","score":0.14327298358683407,"rank":164,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.14665689576667848,"rank":164,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.15231161302897028,"rank":164,"remainingConfigurations":444},{"removed":"omniscience","score":0.14296714067219451,"rank":164,"remainingConfigurations":444},{"removed":"tau-bench","score":0.14202721199965113,"rank":165,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1428104078900647,"rank":164,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.14341025330651289,"rank":162,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15548811965064227,"rank":174,"remainingConfigurations":444},{"removed":"deepswe","score":0.12014911734279243,"rank":163,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1432862713284428,"rank":164,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.14274223822319518,"rank":165,"remainingConfigurations":444},{"removed":"frontiercode","score":0.25646890806007694,"rank":123,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.14226878646257643,"rank":164,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.141517069338203,"rank":164,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1431246022897907,"rank":164,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.14279440012994607,"rank":164,"remainingConfigurations":444},{"removed":"livebench-math","score":0.14870023334622576,"rank":161,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13294089852380214,"rank":166,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1439873850326601,"rank":164,"remainingConfigurations":444},{"removed":"livebench-data","score":0.14031853795098698,"rank":164,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.14877182742066497,"rank":161,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13832646619163017,"rank":164,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.14989505262532335,"rank":161,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1403252811765354,"rank":164,"remainingConfigurations":444},{"removed":"frontiermath","score":0.14244138707538836,"rank":164,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.14181809490379804,"rank":163,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1473612307263087,"rank":164,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.14255019688914078,"rank":164,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.14299043428583674,"rank":164,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.14288771177126122,"rank":164,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.14288867806374728,"rank":164,"remainingConfigurations":444},{"removed":"vibe-code","score":0.14233729434603742,"rank":164,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.14294393711567466,"rank":164,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-397b-a17b--effort-reasoning":{"score":0.1356912052453863,"rank":165,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.16817056865229954,"rank":168,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10977191171273502,"rank":165,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13483383960539708,"rank":165,"remainingConfigurations":444},{"removed":"Scale","score":0.1530478473224912,"rank":165,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1347272921009384,"rank":165,"remainingConfigurations":444},{"removed":"Cognition","score":0.12994633305903908,"rank":167,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13906668601224664,"rank":164,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13882131335125095,"rank":166,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13877613648040546,"rank":165,"remainingConfigurations":431},{"removed":"Vals AI","score":0.13002460914244127,"rank":167,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1356390886363698,"rank":165,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.13182512344627043,"rank":165,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13548072251892615,"rank":165,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1356912052453863,"rank":165,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13664604600756075,"rank":165,"remainingConfigurations":444},{"removed":"All provider reports","score":0.13255304307856067,"rank":165,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1367422431006954,"rank":165,"remainingConfigurations":444},{"removed":"briefcase","score":0.1433235376311609,"rank":162,"remainingConfigurations":444},{"removed":"aime","score":0.13557760851789233,"rank":165,"remainingConfigurations":444},{"removed":"apex-agents","score":0.13634691532279253,"rank":167,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.13001811797958,"rank":169,"remainingConfigurations":444},{"removed":"automationbench","score":0.1394112677758597,"rank":165,"remainingConfigurations":444},{"removed":"critpt","score":0.13776328663778498,"rank":169,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.14019234769674474,"rank":165,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13261822001604334,"rank":171,"remainingConfigurations":444},{"removed":"gdpval","score":0.1417912523267853,"rank":164,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13398756418746066,"rank":167,"remainingConfigurations":444},{"removed":"gpqa","score":0.12842153391926203,"rank":170,"remainingConfigurations":444},{"removed":"harvey","score":0.1342934136620291,"rank":165,"remainingConfigurations":444},{"removed":"hle","score":0.1430400975250762,"rank":168,"remainingConfigurations":444},{"removed":"ifbench","score":0.1258552439045625,"rank":174,"remainingConfigurations":444},{"removed":"itbench","score":0.13198414794185762,"rank":167,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1357586481288807,"rank":165,"remainingConfigurations":444},{"removed":"math500","score":0.13610021571973183,"rank":165,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13946024496584863,"rank":165,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1406942150584902,"rank":168,"remainingConfigurations":444},{"removed":"omniscience","score":0.1343603764190456,"rank":172,"remainingConfigurations":444},{"removed":"tau-bench","score":0.13381043084567162,"rank":168,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.13751460671349844,"rank":165,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.14125553772227295,"rank":165,"remainingConfigurations":444},{"removed":"arc-agi","score":0.16294075191607357,"rank":167,"remainingConfigurations":444},{"removed":"deepswe","score":0.10985411082982245,"rank":165,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13572123749156198,"rank":165,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.13403083232597002,"rank":166,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12994633305903908,"rank":167,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1342304311245535,"rank":165,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13429877734337226,"rank":165,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1355985199003984,"rank":165,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13509844614830632,"rank":165,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1358118055050602,"rank":165,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.134452200469559,"rank":164,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1375815695859612,"rank":165,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13561791449121594,"rank":165,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.13326987656890218,"rank":165,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13491909480601819,"rank":165,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1382306485382351,"rank":165,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13882131335125095,"rank":166,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13578252654397038,"rank":167,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.12993414046399457,"rank":168,"remainingConfigurations":444},{"removed":"simpleqa","score":0.14146056232773108,"rank":166,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1352544959804463,"rank":165,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13524671432244253,"rank":165,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13524239003941538,"rank":165,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13549151304237803,"rank":165,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1349322231303328,"rank":165,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13535300458200292,"rank":165,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5--effort-reasoning":{"score":0.13514703041033652,"rank":166,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.16836712685077546,"rank":167,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10951750758195904,"rank":166,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.134185998439988,"rank":167,"remainingConfigurations":444},{"removed":"Scale","score":0.15255772347375748,"rank":166,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.13431644870603046,"rank":166,"remainingConfigurations":444},{"removed":"Cognition","score":0.12938352345751097,"rank":168,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13835367617505978,"rank":165,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13870308091706204,"rank":167,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1385398913984664,"rank":166,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12946879943237857,"rank":168,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.13509751758828722,"rank":166,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1313843297740515,"rank":166,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13493559411947864,"rank":166,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13514703041033652,"rank":166,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13612988038144508,"rank":166,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1321393461860318,"rank":166,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13608425766050133,"rank":166,"remainingConfigurations":444},{"removed":"briefcase","score":0.13437018365239728,"rank":166,"remainingConfigurations":444},{"removed":"aime","score":0.13538324220621567,"rank":166,"remainingConfigurations":444},{"removed":"apex-agents","score":0.15195263881083643,"rank":161,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12756649720369026,"rank":170,"remainingConfigurations":444},{"removed":"automationbench","score":0.13385804381616376,"rank":168,"remainingConfigurations":444},{"removed":"critpt","score":0.13711054042841633,"rank":170,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1343437772058238,"rank":167,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13737398641026474,"rank":167,"remainingConfigurations":444},{"removed":"gdpval","score":0.13475091242221462,"rank":166,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13627250029502497,"rank":165,"remainingConfigurations":444},{"removed":"gpqa","score":0.14295712570870997,"rank":165,"remainingConfigurations":444},{"removed":"harvey","score":0.13363406152283142,"rank":166,"remainingConfigurations":444},{"removed":"hle","score":0.13965144495049808,"rank":170,"remainingConfigurations":444},{"removed":"ifbench","score":0.13038299025368127,"rank":166,"remainingConfigurations":444},{"removed":"itbench","score":0.13371261628833608,"rank":166,"remainingConfigurations":444},{"removed":"livecodebench","score":0.13504888629232883,"rank":166,"remainingConfigurations":444},{"removed":"math500","score":0.13544839368876269,"rank":166,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13854490371017286,"rank":166,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14349189616858435,"rank":165,"remainingConfigurations":444},{"removed":"omniscience","score":0.13791440311020473,"rank":171,"remainingConfigurations":444},{"removed":"tau-bench","score":0.12381583739977499,"rank":176,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1366759573832339,"rank":166,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1287206063080317,"rank":172,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1633984604110231,"rank":166,"remainingConfigurations":444},{"removed":"deepswe","score":0.10959218785786502,"rank":166,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13517421351317327,"rank":166,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.13325714438935352,"rank":167,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12938352345751097,"rank":168,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.13367917568566892,"rank":166,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13376857132087344,"rank":166,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.13504930090720846,"rank":166,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13459681994374637,"rank":166,"remainingConfigurations":444},{"removed":"livebench-math","score":0.13527941137052965,"rank":166,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13389026873281634,"rank":165,"remainingConfigurations":444},{"removed":"livebench-language","score":0.13700003119755952,"rank":166,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13506079777468982,"rank":166,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.13276734565478038,"rank":166,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13437485936630666,"rank":166,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13769861678590486,"rank":166,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13870308091706204,"rank":167,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13566057931256256,"rank":168,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.12948597378888985,"rank":169,"remainingConfigurations":444},{"removed":"simpleqa","score":0.14092195516385567,"rank":167,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13471306227178137,"rank":166,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13469664114221477,"rank":166,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13471156626323563,"rank":166,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13492961343301216,"rank":166,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13439661939024822,"rank":166,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13480555568921238,"rank":166,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.5--effort-low":{"score":0.13407642140670828,"rank":167,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.11559510854972983,"rank":140,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05030389303977708,"rank":267,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09859312562743427,"rank":176,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.134519422903011,"rank":166,"remainingConfigurations":444},{"removed":"Scale","score":0.15058992770595106,"rank":167,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1306342074415223,"rank":169,"remainingConfigurations":444},{"removed":"Cognition","score":0.18156866224038345,"rank":144,"remainingConfigurations":444},{"removed":"LiveBench","score":0.140612786936126,"rank":163,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13275317854773985,"rank":171,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13995977929234868,"rank":164,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1261572322425659,"rank":171,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1340310572203541,"rank":167,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.13096342731043062,"rank":167,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13389402943330495,"rank":167,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13407642140670828,"rank":167,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13519559128130015,"rank":167,"remainingConfigurations":444},{"removed":"All provider reports","score":0.13187147206298436,"rank":167,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13421843223664265,"rank":168,"remainingConfigurations":444},{"removed":"briefcase","score":0.13263844319878734,"rank":167,"remainingConfigurations":444},{"removed":"aime","score":0.13252876422220677,"rank":167,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1350564109674781,"rank":168,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.13401074790186326,"rank":165,"remainingConfigurations":444},{"removed":"automationbench","score":0.13232886833493385,"rank":170,"remainingConfigurations":444},{"removed":"critpt","score":0.13511673624895376,"rank":172,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1340800481681003,"rank":168,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13401004578045303,"rank":169,"remainingConfigurations":444},{"removed":"gdpval","score":0.13318238302774696,"rank":167,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13412187121793936,"rank":166,"remainingConfigurations":444},{"removed":"gpqa","score":0.13282362012512358,"rank":166,"remainingConfigurations":444},{"removed":"harvey","score":0.1321624556581519,"rank":167,"remainingConfigurations":444},{"removed":"hle","score":0.14406540050338934,"rank":167,"remainingConfigurations":444},{"removed":"ifbench","score":0.13295007535178935,"rank":165,"remainingConfigurations":444},{"removed":"itbench","score":0.13378044811466053,"rank":165,"remainingConfigurations":444},{"removed":"livecodebench","score":0.13446660715593473,"rank":167,"remainingConfigurations":444},{"removed":"math500","score":0.13408486105448683,"rank":167,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13770342937131805,"rank":167,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14288458901381437,"rank":166,"remainingConfigurations":444},{"removed":"omniscience","score":0.13273897326257172,"rank":173,"remainingConfigurations":444},{"removed":"tau-bench","score":0.13402683569972879,"rank":167,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.13482090816597161,"rank":167,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.13180147380339788,"rank":170,"remainingConfigurations":444},{"removed":"arc-agi","score":0.16080424321218242,"rank":168,"remainingConfigurations":444},{"removed":"deepswe","score":0.09859622624407277,"rank":176,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13409820263194563,"rank":167,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1429514530408977,"rank":164,"remainingConfigurations":444},{"removed":"frontiercode","score":0.18156866224038345,"rank":144,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.13259220951713033,"rank":167,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13262077876737366,"rank":167,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.13400732706844035,"rank":167,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13351950785622346,"rank":167,"remainingConfigurations":444},{"removed":"livebench-math","score":0.13407132326708163,"rank":167,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13288328674572725,"rank":167,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1358204812192663,"rank":167,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13411549223759964,"rank":167,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.13161554534397238,"rank":167,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13346818173981626,"rank":167,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13663166939732224,"rank":167,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13275317854773985,"rank":171,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1342493664886862,"rank":169,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.13072975143349816,"rank":167,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13969530968055874,"rank":168,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13395440717401438,"rank":167,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13360176240836882,"rank":167,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13358825051403064,"rank":167,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13392632295089224,"rank":167,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1331937468898597,"rank":167,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13362403663606467,"rank":167,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.8-27b--effort-low":{"score":0.13232120280947038,"rank":168,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15167812073627887,"rank":126,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.13280788811198138,"rank":191,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10474145025146624,"rank":169,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13367427546790234,"rank":168,"remainingConfigurations":444},{"removed":"Scale","score":0.14966722354043724,"rank":168,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1306218626104657,"rank":170,"remainingConfigurations":444},{"removed":"Cognition","score":0.12599841938009634,"rank":171,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1365984449197752,"rank":166,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13344887124075505,"rank":170,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13263307155192958,"rank":171,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12575963210312519,"rank":172,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.13227211434961014,"rank":168,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12899960936082763,"rank":168,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1321268921323597,"rank":168,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13232120280947038,"rank":168,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13337292575890322,"rank":168,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12983093058650566,"rank":168,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13320441268070748,"rank":169,"remainingConfigurations":444},{"removed":"briefcase","score":0.1251132758016629,"rank":172,"remainingConfigurations":444},{"removed":"aime","score":0.13076118172866455,"rank":169,"remainingConfigurations":444},{"removed":"apex-agents","score":0.13368394043138765,"rank":169,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12722268191507557,"rank":172,"remainingConfigurations":444},{"removed":"automationbench","score":0.1285860765686739,"rank":172,"remainingConfigurations":444},{"removed":"critpt","score":0.15006821995902608,"rank":161,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1324827859731497,"rank":169,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13266402605135247,"rank":170,"remainingConfigurations":444},{"removed":"gdpval","score":0.12621472134608866,"rank":171,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13219494434704418,"rank":168,"remainingConfigurations":444},{"removed":"gpqa","score":0.12973283392248208,"rank":167,"remainingConfigurations":444},{"removed":"harvey","score":0.13072553835572887,"rank":168,"remainingConfigurations":444},{"removed":"hle","score":0.14647717937764623,"rank":165,"remainingConfigurations":444},{"removed":"ifbench","score":0.12909328190323432,"rank":167,"remainingConfigurations":444},{"removed":"itbench","score":0.1318720726260642,"rank":168,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1331936060022053,"rank":168,"remainingConfigurations":444},{"removed":"math500","score":0.13212555575121496,"rank":168,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13525400106729873,"rank":169,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14116677128732372,"rank":167,"remainingConfigurations":444},{"removed":"omniscience","score":0.14225170208305635,"rank":165,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1271649803608029,"rank":171,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1341261486928349,"rank":168,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12834723304781612,"rank":174,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12784418708090975,"rank":191,"remainingConfigurations":444},{"removed":"deepswe","score":0.10478233483255599,"rank":169,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13234636237035194,"rank":168,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12768331646530676,"rank":173,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12599841938009634,"rank":171,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.13083536176033206,"rank":168,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1309095924328433,"rank":168,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1322267856532794,"rank":168,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13179023814899823,"rank":168,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1324510915888308,"rank":168,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13108554091388028,"rank":169,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1340331010613689,"rank":168,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13220451155790552,"rank":168,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12996538357589985,"rank":168,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13158651216549766,"rank":169,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13496874012310453,"rank":168,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13344887124075505,"rank":170,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13295263718690697,"rank":170,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1254108969307931,"rank":173,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1377610209611452,"rank":169,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13188029045957358,"rank":169,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13185117506804525,"rank":168,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13197132423081182,"rank":168,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13204234313267324,"rank":169,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13149917355088095,"rank":169,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1319880253467868,"rank":168,"remainingConfigurations":444}],"sharedOrderConflicts":1},"grok-4.3--effort-high":{"score":0.13182479689142326,"rank":169,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15369387489530723,"rank":123,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15123610441463922,"rank":180,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10402960014615277,"rank":171,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13153853410464372,"rank":170,"remainingConfigurations":444},{"removed":"Scale","score":0.14718139726273213,"rank":172,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.13114911094600495,"rank":167,"remainingConfigurations":444},{"removed":"Cognition","score":0.13045166610153502,"rank":166,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13358257192736428,"rank":170,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1317496360115259,"rank":173,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10075258556883336,"rank":195,"remainingConfigurations":431},{"removed":"Vals AI","score":0.15088892218315306,"rank":159,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1317845375330669,"rank":169,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12870509393362878,"rank":169,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13180323477641773,"rank":169,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13182479689142326,"rank":169,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13250397638134517,"rank":170,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1293595507294399,"rank":169,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13448565210820237,"rank":167,"remainingConfigurations":444},{"removed":"briefcase","score":0.13200122466499611,"rank":168,"remainingConfigurations":444},{"removed":"aime","score":0.1245566670653523,"rank":175,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1322981550076159,"rank":172,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.13043401063663276,"rank":167,"remainingConfigurations":444},{"removed":"automationbench","score":0.13611434911421452,"rank":166,"remainingConfigurations":444},{"removed":"critpt","score":0.12991468885466542,"rank":175,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.13622024012567632,"rank":166,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13505944254960472,"rank":168,"remainingConfigurations":444},{"removed":"gdpval","score":0.1320298613935608,"rank":168,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13205226725950317,"rank":171,"remainingConfigurations":444},{"removed":"gpqa","score":0.12080585268620497,"rank":173,"remainingConfigurations":444},{"removed":"harvey","score":0.12641557902002867,"rank":173,"remainingConfigurations":444},{"removed":"hle","score":0.1372349814536473,"rank":172,"remainingConfigurations":444},{"removed":"ifbench","score":0.127054143037342,"rank":171,"remainingConfigurations":444},{"removed":"itbench","score":0.1308130484548888,"rank":170,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1318413013445909,"rank":170,"remainingConfigurations":444},{"removed":"math500","score":0.13201977876249027,"rank":169,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13446837023379365,"rank":172,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.13789446311521555,"rank":173,"remainingConfigurations":444},{"removed":"omniscience","score":0.1296841224300128,"rank":174,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1294778847840442,"rank":170,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.13280084270620837,"rank":172,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.13604913453694192,"rank":167,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1466551322586688,"rank":180,"remainingConfigurations":444},{"removed":"deepswe","score":0.10416787041018798,"rank":171,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13186223077438908,"rank":169,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.130380904909211,"rank":168,"remainingConfigurations":444},{"removed":"frontiercode","score":0.13045166610153502,"rank":166,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.13043704603848502,"rank":169,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13048128164500414,"rank":169,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.13175528206513995,"rank":169,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13102931256136344,"rank":170,"remainingConfigurations":444},{"removed":"livebench-math","score":0.13219088732508932,"rank":170,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13042993804173222,"rank":170,"remainingConfigurations":444},{"removed":"livebench-language","score":0.13359371595297317,"rank":169,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13193368856050877,"rank":169,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12946090366244256,"rank":169,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13119335020686446,"rank":170,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13399957307713795,"rank":171,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1317496360115259,"rank":173,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13587111869922816,"rank":166,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.12517283613690286,"rank":174,"remainingConfigurations":444},{"removed":"simpleqa","score":0.14604475258418398,"rank":165,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13275350113317194,"rank":168,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13120265722607694,"rank":169,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13019601794601748,"rank":173,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1329066528759076,"rank":168,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13270147115342903,"rank":168,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13152480435670186,"rank":169,"remainingConfigurations":444}],"sharedOrderConflicts":1},"mimo-v2.5-pro--effort-reasoning":{"score":0.13163187623569342,"rank":170,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1636379671963002,"rank":170,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10632261528870413,"rank":167,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13077806135944012,"rank":171,"remainingConfigurations":444},{"removed":"Scale","score":0.14879508780618542,"rank":169,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.13065997146590272,"rank":168,"remainingConfigurations":444},{"removed":"Cognition","score":0.1261941640346409,"rank":170,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13564241621586723,"rank":168,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13444360815311876,"rank":169,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13447881934396677,"rank":169,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1262546093617347,"rank":170,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.13157636645465948,"rank":170,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12787602189447464,"rank":171,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13141701340685516,"rank":170,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13163187623569342,"rank":170,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13255707857789728,"rank":169,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12856547133641197,"rank":171,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1279286932145525,"rank":174,"remainingConfigurations":444},{"removed":"briefcase","score":0.12947606647394963,"rank":170,"remainingConfigurations":444},{"removed":"aime","score":0.13093160179748128,"rank":168,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1486810167497937,"rank":162,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12521276765353664,"rank":176,"remainingConfigurations":444},{"removed":"automationbench","score":0.13266293882622038,"rank":169,"remainingConfigurations":444},{"removed":"critpt","score":0.13064920352282886,"rank":173,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.13162685321031412,"rank":170,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.14529696422126784,"rank":163,"remainingConfigurations":444},{"removed":"gdpval","score":0.12593650760189357,"rank":172,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13212502890938987,"rank":170,"remainingConfigurations":444},{"removed":"gpqa","score":0.12633775832324337,"rank":171,"remainingConfigurations":444},{"removed":"harvey","score":0.13014798924146245,"rank":169,"remainingConfigurations":444},{"removed":"hle","score":0.1348206757198712,"rank":176,"remainingConfigurations":444},{"removed":"ifbench","score":0.12035245991938576,"rank":176,"remainingConfigurations":444},{"removed":"itbench","score":0.12216005254477176,"rank":175,"remainingConfigurations":444},{"removed":"livecodebench","score":0.13120369054627098,"rank":171,"remainingConfigurations":444},{"removed":"math500","score":0.13186634036842132,"rank":170,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13489227839473053,"rank":170,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14066848292195552,"rank":169,"remainingConfigurations":444},{"removed":"omniscience","score":0.13991588809535035,"rank":168,"remainingConfigurations":444},{"removed":"tau-bench","score":0.13463665142077938,"rank":166,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.13328277303599834,"rank":169,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.13343310733300245,"rank":169,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15875361980091127,"rank":171,"remainingConfigurations":444},{"removed":"deepswe","score":0.10640211358126099,"rank":167,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1316615253575174,"rank":170,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.13010192378557192,"rank":169,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1261941640346409,"rank":170,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.130221349005924,"rank":170,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13027132712519945,"rank":170,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1315435699745776,"rank":170,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13110515026359482,"rank":169,"remainingConfigurations":444},{"removed":"livebench-math","score":0.13174485376844086,"rank":171,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13040534801951661,"rank":171,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1334787784096954,"rank":170,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13157445253614153,"rank":170,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.129256776534496,"rank":170,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1308767419427874,"rank":171,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13413344561230323,"rank":170,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13444360815311876,"rank":169,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13171915845688467,"rank":172,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1256940035736865,"rank":171,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13729337736847602,"rank":170,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13121324765057776,"rank":170,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13119257656982072,"rank":170,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1311949845303166,"rank":169,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1314293927988159,"rank":170,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13088739089179294,"rank":170,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13129758260585472,"rank":170,"remainingConfigurations":444}],"sharedOrderConflicts":0},"solar-pro4-260806--effort-reasoning":{"score":0.13145425738800717,"rank":171,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.16398936757136262,"rank":169,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10600332792689764,"rank":168,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13056591347143956,"rank":172,"remainingConfigurations":444},{"removed":"Scale","score":0.14858690851019737,"rank":171,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1303362069878461,"rank":171,"remainingConfigurations":444},{"removed":"Cognition","score":0.12546056026994482,"rank":172,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13571984615024058,"rank":167,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1344879894000538,"rank":168,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13455927926834416,"rank":168,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12625556921643252,"rank":169,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.13140075772214302,"rank":171,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12783300968229325,"rank":172,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1312281497925777,"rank":171,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13145425738800717,"rank":171,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1324105974428387,"rank":171,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1285417757659443,"rank":172,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13266926217721206,"rank":170,"remainingConfigurations":444},{"removed":"briefcase","score":0.11952226534994463,"rank":178,"remainingConfigurations":444},{"removed":"aime","score":0.13073233060026293,"rank":170,"remainingConfigurations":444},{"removed":"apex-agents","score":0.13351228283290395,"rank":170,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.13332668765328973,"rank":166,"remainingConfigurations":444},{"removed":"automationbench","score":0.13424497836443572,"rank":167,"remainingConfigurations":444},{"removed":"critpt","score":0.12496786926846455,"rank":179,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.13149701355606602,"rank":172,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13872277906338212,"rank":166,"remainingConfigurations":444},{"removed":"gdpval","score":0.125557947981529,"rank":174,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13213367115539176,"rank":169,"remainingConfigurations":444},{"removed":"gpqa","score":0.12094826063871422,"rank":172,"remainingConfigurations":444},{"removed":"harvey","score":0.12988246169061077,"rank":170,"remainingConfigurations":444},{"removed":"hle","score":0.13538578691252193,"rank":173,"remainingConfigurations":444},{"removed":"ifbench","score":0.12742837305021007,"rank":170,"remainingConfigurations":444},{"removed":"itbench","score":0.13065619639180134,"rank":171,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1308656263003366,"rank":172,"remainingConfigurations":444},{"removed":"math500","score":0.1315459517169649,"rank":171,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13453576699634123,"rank":171,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14040989521706224,"rank":170,"remainingConfigurations":444},{"removed":"omniscience","score":0.15695046037339333,"rank":158,"remainingConfigurations":444},{"removed":"tau-bench","score":0.12418247880819809,"rank":173,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.13300463035713492,"rank":170,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.13898219341226342,"rank":166,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15914570624106736,"rank":169,"remainingConfigurations":444},{"removed":"deepswe","score":0.10607448964577375,"rank":168,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13148652250925807,"rank":171,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12984974545370706,"rank":170,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12546056026994482,"rank":172,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.130022140449102,"rank":171,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.13006076018071486,"rank":171,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.13136819689655152,"rank":171,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13090240068164247,"rank":171,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1315684965358826,"rank":172,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13017756031669112,"rank":172,"remainingConfigurations":444},{"removed":"livebench-language","score":0.13329692494899895,"rank":171,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13144010476601428,"rank":171,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12907125972291053,"rank":171,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13068060775660584,"rank":172,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13399443589616572,"rank":172,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1344879894000538,"rank":168,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13156195647844718,"rank":173,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1256140715194535,"rank":172,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13708256348908784,"rank":171,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1310234450899526,"rank":171,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13102694408815058,"rank":171,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13102488476145854,"rank":170,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13125102126749028,"rank":171,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13069124514867658,"rank":171,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13112524101646453,"rank":171,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.8-27b--effort-medium":{"score":0.13124370428032436,"rank":172,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12748283901947227,"rank":134,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15991448486195048,"rank":174,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10423499484651443,"rank":170,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13259742260401697,"rank":169,"remainingConfigurations":444},{"removed":"Scale","score":0.1486279292535426,"rank":170,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12970218091176008,"rank":172,"remainingConfigurations":444},{"removed":"Cognition","score":0.12464795457313882,"rank":173,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13542709855052268,"rank":169,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.13246816536604525,"rank":172,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13077412090782928,"rank":172,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12473642278790116,"rank":173,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1311949506980404,"rank":172,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1279417308391605,"rank":170,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13105076296884166,"rank":172,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.13124370428032436,"rank":172,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1322879975462977,"rank":172,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12876714425992913,"rank":170,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.13226186406679896,"rank":171,"remainingConfigurations":444},{"removed":"briefcase","score":0.12395112123936863,"rank":175,"remainingConfigurations":444},{"removed":"aime","score":0.12977032409688924,"rank":172,"remainingConfigurations":444},{"removed":"apex-agents","score":0.13266941111482863,"rank":171,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12527620852501795,"rank":175,"remainingConfigurations":444},{"removed":"automationbench","score":0.12699406661618712,"rank":173,"remainingConfigurations":444},{"removed":"critpt","score":0.14987075899529462,"rank":162,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.13162434007209292,"rank":171,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.13011996257229855,"rank":172,"remainingConfigurations":444},{"removed":"gdpval","score":0.12577888853804364,"rank":173,"remainingConfigurations":444},{"removed":"gmmlu","score":0.13118253594637666,"rank":172,"remainingConfigurations":444},{"removed":"gpqa","score":0.1294596100261614,"rank":168,"remainingConfigurations":444},{"removed":"harvey","score":0.12974193910649565,"rank":171,"remainingConfigurations":444},{"removed":"hle","score":0.1462411230039792,"rank":166,"remainingConfigurations":444},{"removed":"ifbench","score":0.12834205984465277,"rank":169,"remainingConfigurations":444},{"removed":"itbench","score":0.130898389342055,"rank":169,"remainingConfigurations":444},{"removed":"livecodebench","score":0.13219631244152627,"rank":169,"remainingConfigurations":444},{"removed":"math500","score":0.1310711456769272,"rank":172,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1342541659544784,"rank":173,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.14025187407631604,"rank":171,"remainingConfigurations":444},{"removed":"omniscience","score":0.14043844538080152,"rank":167,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1245131906775556,"rank":172,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.132894124999785,"rank":171,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12813705848849977,"rank":175,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1530794132479322,"rank":177,"remainingConfigurations":444},{"removed":"deepswe","score":0.10427574968294544,"rank":170,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.131268718542629,"rank":172,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12351515191874764,"rank":177,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12464795457313882,"rank":173,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.12978435254118625,"rank":172,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1298472534985252,"rank":172,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.13115026484426312,"rank":172,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.13073712031670412,"rank":172,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1313730060699864,"rank":173,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13001484429711388,"rank":173,"remainingConfigurations":444},{"removed":"livebench-language","score":0.13294615904566465,"rank":172,"remainingConfigurations":444},{"removed":"livebench-data","score":0.13112780051668085,"rank":172,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12890171653429025,"rank":172,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13051318489586153,"rank":173,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1338758821186205,"rank":173,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.13246816536604525,"rank":172,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1318967149066073,"rank":171,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1243814618510154,"rank":175,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13668225453242924,"rank":172,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.13080527424293667,"rank":172,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.13077616065501088,"rank":172,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1308961422845708,"rank":172,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.13096618225181225,"rank":172,"remainingConfigurations":444},{"removed":"vibe-code","score":0.13042655151315657,"rank":172,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13091271589299205,"rank":172,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-5.4-mini--effort-xhigh":{"score":0.1302404901976077,"rank":173,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.11355688402851298,"rank":141,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15246903850166302,"rank":179,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10390426262530687,"rank":172,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.13027646913239424,"rank":173,"remainingConfigurations":444},{"removed":"Scale","score":0.1455933675380109,"rank":173,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12928365608737719,"rank":173,"remainingConfigurations":444},{"removed":"Cognition","score":0.14478835386142067,"rank":162,"remainingConfigurations":444},{"removed":"LiveBench","score":0.12646890715460504,"rank":174,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.12939587181121923,"rank":174,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13475044999598498,"rank":167,"remainingConfigurations":431},{"removed":"Vals AI","score":0.13362625875691772,"rank":166,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.13022971590192112,"rank":173,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12743549254743372,"rank":173,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.13013586888361126,"rank":173,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1302404901976077,"rank":173,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.13130112142469294,"rank":173,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12839992969168787,"rank":173,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1313470948602,"rank":172,"remainingConfigurations":444},{"removed":"briefcase","score":0.13106903713358778,"rank":169,"remainingConfigurations":444},{"removed":"aime","score":0.1289760644928595,"rank":173,"remainingConfigurations":444},{"removed":"apex-agents","score":0.12948715817090176,"rank":173,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.13039934561794186,"rank":168,"remainingConfigurations":444},{"removed":"automationbench","score":0.12917243402784231,"rank":171,"remainingConfigurations":444},{"removed":"critpt","score":0.12988947742566648,"rank":176,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.13059267078633702,"rank":173,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1297219658412965,"rank":173,"remainingConfigurations":444},{"removed":"gdpval","score":0.13038961751258185,"rank":169,"remainingConfigurations":444},{"removed":"gmmlu","score":0.130486060583242,"rank":173,"remainingConfigurations":444},{"removed":"gpqa","score":0.12846213605380255,"rank":169,"remainingConfigurations":444},{"removed":"harvey","score":0.12933968558106737,"rank":172,"remainingConfigurations":444},{"removed":"hle","score":0.13872819316473517,"rank":171,"remainingConfigurations":444},{"removed":"ifbench","score":0.12863332397338292,"rank":168,"remainingConfigurations":444},{"removed":"itbench","score":0.1296131675915303,"rank":172,"remainingConfigurations":444},{"removed":"livecodebench","score":0.13036422248219914,"rank":173,"remainingConfigurations":444},{"removed":"math500","score":0.13034026759810988,"rank":173,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13549286571387284,"rank":168,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1393787565595065,"rank":172,"remainingConfigurations":444},{"removed":"omniscience","score":0.12863928670340322,"rank":175,"remainingConfigurations":444},{"removed":"tau-bench","score":0.13019644770961053,"rank":169,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1308842147403004,"rank":173,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12983414773939697,"rank":171,"remainingConfigurations":444},{"removed":"arc-agi","score":0.14493023567930374,"rank":181,"remainingConfigurations":444},{"removed":"deepswe","score":0.10394770806781335,"rank":172,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.13028624783694773,"rank":173,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12984153931441486,"rank":171,"remainingConfigurations":444},{"removed":"frontiercode","score":0.14478835386142067,"rank":162,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1289566354873192,"rank":173,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.12889309098336266,"rank":173,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1301855533880362,"rank":173,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.12963299213886084,"rank":173,"remainingConfigurations":444},{"removed":"livebench-math","score":0.13243683928218142,"rank":169,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.13223841074702317,"rank":168,"remainingConfigurations":444},{"removed":"livebench-language","score":0.13131739499602968,"rank":173,"remainingConfigurations":444},{"removed":"livebench-data","score":0.12146674297700104,"rank":176,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12714862712716912,"rank":173,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.13250904425874402,"rank":168,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13474944967141073,"rank":169,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.12939587181121923,"rank":174,"remainingConfigurations":444},{"removed":"frontiermath","score":0.13012536098284197,"rank":174,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.12694569970401873,"rank":170,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1349292088140093,"rank":173,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1289464021826512,"rank":173,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1298130872146154,"rank":173,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.13101870849043032,"rank":171,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.12903456057181703,"rank":173,"remainingConfigurations":444},{"removed":"vibe-code","score":0.12779615111852613,"rank":173,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.13028907815244736,"rank":173,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k3--effort-low":{"score":0.1276040501244639,"rank":174,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0723684410753036,"rank":153,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1690669595656058,"rank":166,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1016681069283722,"rank":173,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1275805352311794,"rank":174,"remainingConfigurations":444},{"removed":"Scale","score":0.14417797566247922,"rank":174,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12644366755884243,"rank":174,"remainingConfigurations":444},{"removed":"Cognition","score":0.12396716377514343,"rank":174,"remainingConfigurations":444},{"removed":"LiveBench","score":0.13083416517528257,"rank":171,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1288564731746692,"rank":176,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.17652034811628314,"rank":152,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12159185575681121,"rank":174,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1275655411377045,"rank":174,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12445294255050206,"rank":174,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.12743996531535837,"rank":174,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1276040501244639,"rank":174,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1285316187265708,"rank":174,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12520348336483167,"rank":174,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.12851983491430216,"rank":173,"remainingConfigurations":444},{"removed":"briefcase","score":0.12690930613283527,"rank":171,"remainingConfigurations":444},{"removed":"aime","score":0.1299380223716923,"rank":171,"remainingConfigurations":444},{"removed":"apex-agents","score":0.12909704877864783,"rank":174,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12631330429518473,"rank":173,"remainingConfigurations":444},{"removed":"automationbench","score":0.12471857747196176,"rank":175,"remainingConfigurations":444},{"removed":"critpt","score":0.13062683656390076,"rank":174,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1278705402219382,"rank":174,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.12506312308644937,"rank":176,"remainingConfigurations":444},{"removed":"gdpval","score":0.12748405219361103,"rank":170,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1280100571663901,"rank":174,"remainingConfigurations":444},{"removed":"gpqa","score":0.11390713387851532,"rank":181,"remainingConfigurations":444},{"removed":"harvey","score":0.12619248873859953,"rank":174,"remainingConfigurations":444},{"removed":"hle","score":0.14020049071040944,"rank":169,"remainingConfigurations":444},{"removed":"ifbench","score":0.12628551625783757,"rank":172,"remainingConfigurations":444},{"removed":"itbench","score":0.12715984221421428,"rank":173,"remainingConfigurations":444},{"removed":"livecodebench","score":0.12795297328724453,"rank":174,"remainingConfigurations":444},{"removed":"math500","score":0.12782724931178527,"rank":174,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13125815745330763,"rank":174,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.13571025055502542,"rank":174,"remainingConfigurations":444},{"removed":"omniscience","score":0.12426161184569412,"rank":177,"remainingConfigurations":444},{"removed":"tau-bench","score":0.12391046704707713,"rank":175,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1287032208143268,"rank":174,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12516215538310618,"rank":176,"remainingConfigurations":444},{"removed":"arc-agi","score":0.16386512934792977,"rank":165,"remainingConfigurations":444},{"removed":"deepswe","score":0.10172331476438641,"rank":174,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.12762925072534365,"rank":174,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12377725984342779,"rank":176,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12396716377514343,"rank":174,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.12633822400023628,"rank":174,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.12616238253544443,"rank":174,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1275301507182994,"rank":174,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.12717232397720635,"rank":174,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1278105348892908,"rank":174,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1262867735032348,"rank":174,"remainingConfigurations":444},{"removed":"livebench-language","score":0.12927489275328327,"rank":174,"remainingConfigurations":444},{"removed":"livebench-data","score":0.1275666331988674,"rank":173,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1253623337618078,"rank":174,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.12687112425043476,"rank":174,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.13009886173804155,"rank":174,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1288564731746692,"rank":176,"remainingConfigurations":444},{"removed":"frontiermath","score":0.12678818916931653,"rank":175,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.13769968058348242,"rank":165,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1323521116588019,"rank":174,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.12715512843473392,"rank":174,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1271810297685984,"rank":174,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.12721065534058326,"rank":174,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.12737598335789838,"rank":174,"remainingConfigurations":444},{"removed":"vibe-code","score":0.12686252881736712,"rank":174,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1272701153728034,"rank":174,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.7--effort-reasoning":{"score":0.12598297354621527,"rank":175,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15870090645057403,"rank":175,"remainingConfigurations":444},{"removed":"Datacurve","score":0.10165899717724602,"rank":174,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.12499889022082224,"rank":175,"remainingConfigurations":444},{"removed":"Scale","score":0.1431426263472545,"rank":175,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12513102369013326,"rank":175,"remainingConfigurations":444},{"removed":"Cognition","score":0.12099980390724978,"rank":175,"remainingConfigurations":444},{"removed":"LiveBench","score":0.12979220634991892,"rank":172,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.12901808328215522,"rank":175,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.12867218065399502,"rank":173,"remainingConfigurations":431},{"removed":"Vals AI","score":0.12105999085382928,"rank":175,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.12593572453263707,"rank":175,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12251073685312243,"rank":175,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.12578236152268982,"rank":175,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.12598297354621527,"rank":175,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.12690661947461004,"rank":175,"remainingConfigurations":444},{"removed":"All provider reports","score":0.12321628879840489,"rank":175,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.12683526104551193,"rank":175,"remainingConfigurations":444},{"removed":"briefcase","score":0.12509967464522376,"rank":173,"remainingConfigurations":444},{"removed":"aime","score":0.12305698433776828,"rank":176,"remainingConfigurations":444},{"removed":"apex-agents","score":0.12765524833363143,"rank":175,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.12595230564268045,"rank":174,"remainingConfigurations":444},{"removed":"automationbench","score":0.12500140913360458,"rank":174,"remainingConfigurations":444},{"removed":"critpt","score":0.12665192778450782,"rank":177,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.12578064686353713,"rank":175,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.12838457782108986,"rank":174,"remainingConfigurations":444},{"removed":"gdpval","score":0.1241439423295822,"rank":176,"remainingConfigurations":444},{"removed":"gmmlu","score":0.12721980314670175,"rank":176,"remainingConfigurations":444},{"removed":"gpqa","score":0.1204527935812051,"rank":174,"remainingConfigurations":444},{"removed":"harvey","score":0.1245833853484725,"rank":175,"remainingConfigurations":444},{"removed":"hle","score":0.13500625218909412,"rank":175,"remainingConfigurations":444},{"removed":"ifbench","score":0.1250439400463401,"rank":175,"remainingConfigurations":444},{"removed":"itbench","score":0.12488663942168952,"rank":174,"remainingConfigurations":444},{"removed":"livecodebench","score":0.12202835740032932,"rank":176,"remainingConfigurations":444},{"removed":"math500","score":0.12638420110988044,"rank":175,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.13027799355377925,"rank":175,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1353368284959495,"rank":175,"remainingConfigurations":444},{"removed":"omniscience","score":0.1207543384213499,"rank":178,"remainingConfigurations":444},{"removed":"tau-bench","score":0.12394292802458545,"rank":174,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.12752198666633782,"rank":175,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.13395517049917047,"rank":168,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15380785705008085,"rank":175,"remainingConfigurations":444},{"removed":"deepswe","score":0.10172485737290062,"rank":173,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.12601188791838847,"rank":175,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12414380418435951,"rank":175,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12099980390724978,"rank":175,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.12457454993859574,"rank":175,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.12464418986237343,"rank":175,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.12590124584496978,"rank":175,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.12544437120337465,"rank":175,"remainingConfigurations":444},{"removed":"livebench-math","score":0.12611116971260586,"rank":175,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.12475093091382894,"rank":176,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1277389805029885,"rank":175,"remainingConfigurations":444},{"removed":"livebench-data","score":0.12594330953570151,"rank":174,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12370603491575372,"rank":175,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.12523744211023205,"rank":175,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.12843923395584975,"rank":175,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.12901808328215522,"rank":175,"remainingConfigurations":444},{"removed":"frontiermath","score":0.12624214239839307,"rank":176,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11991700850264275,"rank":176,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13147786696407163,"rank":175,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1255627165778962,"rank":175,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1255638217627029,"rank":175,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.12557325713088577,"rank":175,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.12577758798179758,"rank":175,"remainingConfigurations":444},{"removed":"vibe-code","score":0.12525258268512576,"rank":175,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.12566175373843055,"rank":175,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-27b--effort-reasoning":{"score":0.1248540683454374,"rank":176,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15703306550883253,"rank":176,"remainingConfigurations":444},{"removed":"Datacurve","score":0.1007955233552233,"rank":175,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1239001232482423,"rank":176,"remainingConfigurations":444},{"removed":"Scale","score":0.14169326489010967,"rank":176,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12401000529802099,"rank":176,"remainingConfigurations":444},{"removed":"Cognition","score":0.12006706177241672,"rank":176,"remainingConfigurations":444},{"removed":"LiveBench","score":0.12886343114372853,"rank":173,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1278025774835154,"rank":177,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1270441537848368,"rank":174,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1201788141829991,"rank":176,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.12480224232409616,"rank":176,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.12134762009051869,"rank":176,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.12465127599976293,"rank":176,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1248540683454374,"rank":176,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1257928092275121,"rank":176,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1220612435587886,"rank":176,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.12576411329283274,"rank":176,"remainingConfigurations":444},{"removed":"briefcase","score":0.12432431963751518,"rank":174,"remainingConfigurations":444},{"removed":"aime","score":0.12478760486164188,"rank":174,"remainingConfigurations":444},{"removed":"apex-agents","score":0.12664280726779034,"rank":176,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11494144740682753,"rank":179,"remainingConfigurations":444},{"removed":"automationbench","score":0.12386756954267265,"rank":176,"remainingConfigurations":444},{"removed":"critpt","score":0.1356632354572794,"rank":171,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.12493310792704387,"rank":176,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.12720224732838945,"rank":175,"remainingConfigurations":444},{"removed":"gdpval","score":0.1249154355709669,"rank":175,"remainingConfigurations":444},{"removed":"gmmlu","score":0.12735426027290334,"rank":175,"remainingConfigurations":444},{"removed":"gpqa","score":0.11916772594908287,"rank":176,"remainingConfigurations":444},{"removed":"harvey","score":0.12365826818434517,"rank":176,"remainingConfigurations":444},{"removed":"hle","score":0.13531517958254072,"rank":174,"remainingConfigurations":444},{"removed":"ifbench","score":0.11434144632229337,"rank":179,"remainingConfigurations":444},{"removed":"itbench","score":0.11550826791066597,"rank":180,"remainingConfigurations":444},{"removed":"livecodebench","score":0.12433850107150966,"rank":175,"remainingConfigurations":444},{"removed":"math500","score":0.12496352329580407,"rank":176,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.12753336507468263,"rank":176,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.13114673926899686,"rank":176,"remainingConfigurations":444},{"removed":"omniscience","score":0.1387733928278781,"rank":169,"remainingConfigurations":444},{"removed":"tau-bench","score":0.12020501221935394,"rank":177,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.12662822267382448,"rank":176,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12865595166888513,"rank":173,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15221503098209502,"rank":178,"remainingConfigurations":444},{"removed":"deepswe","score":0.10086073643499403,"rank":175,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.12488063085367916,"rank":176,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12309317235719792,"rank":178,"remainingConfigurations":444},{"removed":"frontiercode","score":0.12006706177241672,"rank":176,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.12344657145065265,"rank":176,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1235511683224891,"rank":176,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.12476795454278239,"rank":176,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.12435195419295764,"rank":176,"remainingConfigurations":444},{"removed":"livebench-math","score":0.12497621552725842,"rank":176,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.12364678276196323,"rank":177,"remainingConfigurations":444},{"removed":"livebench-language","score":0.12659831633154175,"rank":177,"remainingConfigurations":444},{"removed":"livebench-data","score":0.12479060320809977,"rank":175,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.12260472351549688,"rank":176,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.12412221323184242,"rank":176,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.12728555150012996,"rank":176,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1278025774835154,"rank":177,"remainingConfigurations":444},{"removed":"frontiermath","score":0.12490781128190315,"rank":177,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11887782454057018,"rank":177,"remainingConfigurations":444},{"removed":"simpleqa","score":0.13031679291281226,"rank":176,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1244495531640019,"rank":176,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1244265365030997,"rank":176,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.12444941223774715,"rank":176,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.12464298348811477,"rank":176,"remainingConfigurations":444},{"removed":"vibe-code","score":0.12413629236555405,"rank":176,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.12453189688778994,"rank":176,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5-turbo--effort-reasoning":{"score":0.12129528868696231,"rank":177,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1531063715614079,"rank":178,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09799848974272506,"rank":177,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.12031819205770912,"rank":177,"remainingConfigurations":444},{"removed":"Scale","score":0.1381134852228732,"rank":177,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.12053128808505507,"rank":177,"remainingConfigurations":444},{"removed":"Cognition","score":0.11687949333848224,"rank":179,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1250173445350979,"rank":175,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.12436901494504378,"rank":179,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1231340687599493,"rank":177,"remainingConfigurations":431},{"removed":"Vals AI","score":0.11662185756505805,"rank":177,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.12125020103210112,"rank":177,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11793184140053974,"rank":177,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1211008712434188,"rank":177,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.12129528868696231,"rank":177,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.12219739364963927,"rank":177,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11862273201690669,"rank":177,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.12209441518167137,"rank":177,"remainingConfigurations":444},{"removed":"briefcase","score":0.12032928070858384,"rank":176,"remainingConfigurations":444},{"removed":"aime","score":0.1216333945316035,"rank":177,"remainingConfigurations":444},{"removed":"apex-agents","score":0.12285971901662977,"rank":177,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1208526995322897,"rank":177,"remainingConfigurations":444},{"removed":"automationbench","score":0.12017282532285621,"rank":177,"remainingConfigurations":444},{"removed":"critpt","score":0.1478530653022906,"rank":163,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.12112610115068521,"rank":177,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.12352186792803199,"rank":177,"remainingConfigurations":444},{"removed":"gdpval","score":0.12119796393686287,"rank":177,"remainingConfigurations":444},{"removed":"gmmlu","score":0.12245340450054615,"rank":178,"remainingConfigurations":444},{"removed":"gpqa","score":0.1172996762619352,"rank":178,"remainingConfigurations":444},{"removed":"harvey","score":0.11999729223241168,"rank":177,"remainingConfigurations":444},{"removed":"hle","score":0.12772710764697,"rank":177,"remainingConfigurations":444},{"removed":"ifbench","score":0.11210150530131206,"rank":182,"remainingConfigurations":444},{"removed":"itbench","score":0.12026326435116012,"rank":177,"remainingConfigurations":444},{"removed":"livecodebench","score":0.12119694482649807,"rank":177,"remainingConfigurations":444},{"removed":"math500","score":0.12161940459987203,"rank":177,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.12448030512123147,"rank":177,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1299009013346332,"rank":178,"remainingConfigurations":444},{"removed":"omniscience","score":0.11517344212317675,"rank":180,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10604938376485958,"rank":191,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.12283881496893884,"rank":177,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12461216513680973,"rank":177,"remainingConfigurations":444},{"removed":"arc-agi","score":0.14814582890513542,"rank":179,"remainingConfigurations":444},{"removed":"deepswe","score":0.09806112021823155,"rank":177,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.12132231692195167,"rank":177,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11949452568976981,"rank":179,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11687949333848224,"rank":179,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11992947772488267,"rank":177,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.12002988040797873,"rank":177,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.12121271688707118,"rank":177,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1207888424606357,"rank":177,"remainingConfigurations":444},{"removed":"livebench-math","score":0.12141857277771,"rank":177,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.12008936858148002,"rank":178,"remainingConfigurations":444},{"removed":"livebench-language","score":0.12299969652137305,"rank":178,"remainingConfigurations":444},{"removed":"livebench-data","score":0.12125465682318193,"rank":177,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1190884973045878,"rank":177,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1205697394403736,"rank":177,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.12369353056755698,"rank":177,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.12436901494504378,"rank":179,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1215503927268189,"rank":178,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11524471898246948,"rank":178,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1266365275623307,"rank":177,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.12089134583056048,"rank":177,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.12088297014364006,"rank":177,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.12089925179899448,"rank":177,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1210897983151402,"rank":177,"remainingConfigurations":444},{"removed":"vibe-code","score":0.12058640889571025,"rank":177,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1209824524196218,"rank":177,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-nano--effort-xhigh":{"score":0.1189699128050661,"rank":178,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12005385202886916,"rank":138,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.18381560194864047,"rank":161,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09610067466734624,"rank":178,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11874683228910533,"rank":178,"remainingConfigurations":444},{"removed":"Scale","score":0.13457109107777707,"rank":178,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11878110572690535,"rank":178,"remainingConfigurations":444},{"removed":"Cognition","score":0.11871848870151173,"rank":178,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09056108483526175,"rank":209,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11928950481250822,"rank":181,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.12321873447389912,"rank":176,"remainingConfigurations":431},{"removed":"Vals AI","score":0.11502538581344485,"rank":178,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11894639773101157,"rank":178,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11610346793057262,"rank":178,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11875095546232567,"rank":178,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1189699128050661,"rank":178,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11972756251197207,"rank":178,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11664291736001653,"rank":178,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1194536820609325,"rank":178,"remainingConfigurations":444},{"removed":"briefcase","score":0.11988216922011075,"rank":177,"remainingConfigurations":444},{"removed":"aime","score":0.11787805663271202,"rank":179,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1169147269786967,"rank":180,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11763460887574838,"rank":178,"remainingConfigurations":444},{"removed":"automationbench","score":0.11982828208224011,"rank":178,"remainingConfigurations":444},{"removed":"critpt","score":0.11694721638969281,"rank":180,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11956788064312722,"rank":178,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.12039344368877584,"rank":179,"remainingConfigurations":444},{"removed":"gdpval","score":0.11904611063292982,"rank":179,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11904322793481653,"rank":180,"remainingConfigurations":444},{"removed":"gpqa","score":0.11840616219509703,"rank":177,"remainingConfigurations":444},{"removed":"harvey","score":0.11753249287019413,"rank":178,"remainingConfigurations":444},{"removed":"hle","score":0.12602174727828397,"rank":180,"remainingConfigurations":444},{"removed":"ifbench","score":0.1139463214825956,"rank":181,"remainingConfigurations":444},{"removed":"itbench","score":0.12103838741829508,"rank":176,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11887841682986881,"rank":179,"remainingConfigurations":444},{"removed":"math500","score":0.11911512232658067,"rank":178,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.12215575933225344,"rank":178,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.13075799931302926,"rank":177,"remainingConfigurations":444},{"removed":"omniscience","score":0.1183587466158778,"rank":179,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11756286650448279,"rank":178,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11976529259417894,"rank":178,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11859253026487965,"rank":180,"remainingConfigurations":444},{"removed":"arc-agi","score":0.17661324362006192,"rank":160,"remainingConfigurations":444},{"removed":"deepswe","score":0.09615931274786631,"rank":178,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11900922717035416,"rank":178,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11494083994652936,"rank":181,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11871848870151173,"rank":178,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11781692934268372,"rank":178,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11773912769052292,"rank":178,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11888363494736183,"rank":178,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11847440285023025,"rank":178,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11662382366354372,"rank":180,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.12520747855256906,"rank":175,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1268384213090756,"rank":176,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11379079894897365,"rank":183,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11569080177886748,"rank":179,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11853247802667204,"rank":178,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1163792506675228,"rank":183,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11928950481250822,"rank":181,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11930325325362319,"rank":179,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11442065792743611,"rank":179,"remainingConfigurations":444},{"removed":"simpleqa","score":0.12366064197321312,"rank":178,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11838517722144017,"rank":178,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11869891260732306,"rank":178,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11869591561799904,"rank":178,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11872986959584157,"rank":178,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11818181159597145,"rank":178,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11871638753689139,"rank":178,"remainingConfigurations":444}],"sharedOrderConflicts":0},"hy3-preview--effort-reasoning":{"score":0.1179965091808408,"rank":179,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.14854798783634235,"rank":182,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09498193635599646,"rank":180,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11703385044704158,"rank":180,"remainingConfigurations":444},{"removed":"Scale","score":0.13456265783694635,"rank":179,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11716305915730661,"rank":179,"remainingConfigurations":444},{"removed":"Cognition","score":0.1126997756817441,"rank":181,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1216622360253849,"rank":176,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.12053428318828151,"rank":180,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1209819034397412,"rank":178,"remainingConfigurations":431},{"removed":"Vals AI","score":0.11338536833328156,"rank":179,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11795209001899769,"rank":179,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11471031321091023,"rank":179,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11780687020288676,"rank":179,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1179965091808408,"rank":179,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11889047134698323,"rank":179,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11539723655307034,"rank":179,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11877263956192506,"rank":179,"remainingConfigurations":444},{"removed":"briefcase","score":0.11668852168599375,"rank":181,"remainingConfigurations":444},{"removed":"aime","score":0.11844333325085306,"rank":178,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11950231341144833,"rank":178,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1273697168754863,"rank":171,"remainingConfigurations":444},{"removed":"automationbench","score":0.1165496016595969,"rank":180,"remainingConfigurations":444},{"removed":"critpt","score":0.11071948649385406,"rank":190,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11768812948584051,"rank":179,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11992007168825142,"rank":180,"remainingConfigurations":444},{"removed":"gdpval","score":0.11749783355444728,"rank":180,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11940302948669289,"rank":179,"remainingConfigurations":444},{"removed":"gpqa","score":0.1082158535625962,"rank":189,"remainingConfigurations":444},{"removed":"harvey","score":0.1167065992979573,"rank":179,"remainingConfigurations":444},{"removed":"hle","score":0.12395990229759124,"rank":181,"remainingConfigurations":444},{"removed":"ifbench","score":0.12628160518053574,"rank":173,"remainingConfigurations":444},{"removed":"itbench","score":0.11688001995508719,"rank":178,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11787897026479176,"rank":181,"remainingConfigurations":444},{"removed":"math500","score":0.11820753914591255,"rank":179,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.12101851408704556,"rank":179,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12662927322455328,"rank":179,"remainingConfigurations":444},{"removed":"omniscience","score":0.11364292240608494,"rank":181,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11322119456048045,"rank":185,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11947323264079152,"rank":179,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11987212857145961,"rank":179,"remainingConfigurations":444},{"removed":"arc-agi","score":0.14400608378423163,"rank":182,"remainingConfigurations":444},{"removed":"deepswe","score":0.09504155096604815,"rank":180,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11802282323208806,"rank":179,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11624644298624309,"rank":180,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1126997756817441,"rank":181,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11663262438534137,"rank":179,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1167325348404491,"rank":179,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11791719032331992,"rank":179,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11750497986827191,"rank":179,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11811677409283011,"rank":178,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11680984947841638,"rank":179,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11966572132564753,"rank":179,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11795844081166122,"rank":178,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11583580745579708,"rank":178,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1172838686553549,"rank":179,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.12035318241104953,"rank":178,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.12053428318828151,"rank":180,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1180142171486041,"rank":180,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11219593727548578,"rank":181,"remainingConfigurations":444},{"removed":"simpleqa","score":0.12323467440749901,"rank":179,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11760166205102619,"rank":179,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11759161651957724,"rank":179,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1176095708190481,"rank":179,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11779274065319985,"rank":179,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11730074834317498,"rank":179,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11769015443971714,"rank":179,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5--effort-high":{"score":0.11726197144176782,"rank":180,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08125866522210867,"rank":149,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1630606817920748,"rank":171,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09266928298430137,"rank":181,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11765205273356265,"rank":179,"remainingConfigurations":444},{"removed":"Scale","score":0.13344957691215725,"rank":180,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11584308979026121,"rank":180,"remainingConfigurations":444},{"removed":"Cognition","score":0.11218277972228298,"rank":182,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11945188822377885,"rank":177,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1276808603782515,"rank":178,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11752088950157956,"rank":181,"remainingConfigurations":431},{"removed":"Vals AI","score":0.11101098625587275,"rank":180,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11722251891130225,"rank":180,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1142243997724894,"rank":180,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1170978674973016,"rank":180,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11726197144176782,"rank":180,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1181671557764501,"rank":180,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11494767126270677,"rank":180,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1179309247870638,"rank":180,"remainingConfigurations":444},{"removed":"briefcase","score":0.11669322509113238,"rank":180,"remainingConfigurations":444},{"removed":"aime","score":0.11644753308701054,"rank":180,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11846180944487052,"rank":179,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11400084020075858,"rank":181,"remainingConfigurations":444},{"removed":"automationbench","score":0.11660866680405944,"rank":179,"remainingConfigurations":444},{"removed":"critpt","score":0.11647770802953156,"rank":181,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1172230753103272,"rank":180,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11862969564308246,"rank":181,"remainingConfigurations":444},{"removed":"gdpval","score":0.11914863867076318,"rank":178,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11506233934298071,"rank":182,"remainingConfigurations":444},{"removed":"gpqa","score":0.11584095531072057,"rank":179,"remainingConfigurations":444},{"removed":"harvey","score":0.1158866202089112,"rank":180,"remainingConfigurations":444},{"removed":"hle","score":0.12672304445243524,"rank":178,"remainingConfigurations":444},{"removed":"ifbench","score":0.11427353445321904,"rank":180,"remainingConfigurations":444},{"removed":"itbench","score":0.11666327727646049,"rank":179,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11876397705380577,"rank":180,"remainingConfigurations":444},{"removed":"math500","score":0.11769815209507788,"rank":180,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.120820101843528,"rank":180,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12635223477486449,"rank":180,"remainingConfigurations":444},{"removed":"omniscience","score":0.11047434834025394,"rank":185,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11719937412215038,"rank":179,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11829021650948586,"rank":181,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.12041381301980658,"rank":178,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1578605792977105,"rank":172,"remainingConfigurations":444},{"removed":"deepswe","score":0.09271055129410344,"rank":181,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1172852480563838,"rank":180,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11191815687237339,"rank":183,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11218277972228298,"rank":182,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11590010382747022,"rank":180,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11598561801202145,"rank":180,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1171852262302981,"rank":180,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.1167671125544056,"rank":180,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11739751043697472,"rank":179,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11613635194348822,"rank":180,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11882127859143449,"rank":180,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11716139568431057,"rank":179,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11512766663012665,"rank":180,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11657149833913262,"rank":180,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.1196640806279875,"rank":179,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1276808603782515,"rank":178,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11778970337012908,"rank":181,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11175811998438027,"rank":182,"remainingConfigurations":444},{"removed":"simpleqa","score":0.12225145055260694,"rank":180,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11684999285770377,"rank":180,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11684220327235795,"rank":180,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11693337169135982,"rank":180,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11701843014147793,"rank":180,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11652792274233835,"rank":180,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11695137211674002,"rank":180,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash-lite--effort-reasoning":{"score":0.11471989529234455,"rank":181,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.14470566091882814,"rank":183,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09208514693265642,"rank":182,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11395586711410838,"rank":182,"remainingConfigurations":444},{"removed":"Scale","score":0.13039200299107626,"rank":182,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11378046920984984,"rank":181,"remainingConfigurations":444},{"removed":"Cognition","score":0.10933584917926342,"rank":185,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11899987403168417,"rank":178,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11744184699903798,"rank":182,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11829013470435072,"rank":180,"remainingConfigurations":431},{"removed":"Vals AI","score":0.11037524143205475,"rank":181,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11466472920686328,"rank":181,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11140675442600152,"rank":182,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11452273631131211,"rank":181,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11471989529234455,"rank":181,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11557259008122883,"rank":182,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11203550151510978,"rank":182,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11625430821383742,"rank":181,"remainingConfigurations":444},{"removed":"briefcase","score":0.1189098327468971,"rank":179,"remainingConfigurations":444},{"removed":"aime","score":0.11421662629188783,"rank":183,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11678752084624465,"rank":181,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11156763077481807,"rank":185,"remainingConfigurations":444},{"removed":"automationbench","score":0.10804612251429763,"rank":190,"remainingConfigurations":444},{"removed":"critpt","score":0.14512939198418787,"rank":165,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10312265570471209,"rank":199,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10767040773070109,"rank":193,"remainingConfigurations":444},{"removed":"gdpval","score":0.114861756475559,"rank":182,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11534033874146132,"rank":181,"remainingConfigurations":444},{"removed":"gpqa","score":0.11299731886137855,"rank":185,"remainingConfigurations":444},{"removed":"harvey","score":0.11262549784617949,"rank":183,"remainingConfigurations":444},{"removed":"hle","score":0.12656691440061732,"rank":179,"remainingConfigurations":444},{"removed":"ifbench","score":0.11112941630678265,"rank":185,"remainingConfigurations":444},{"removed":"itbench","score":0.11448909554680135,"rank":181,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11450339000184584,"rank":182,"remainingConfigurations":444},{"removed":"math500","score":0.1150402095627695,"rank":181,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11784798922336426,"rank":181,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11268253242374653,"rank":195,"remainingConfigurations":444},{"removed":"omniscience","score":0.11330299301854435,"rank":182,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11206972544881982,"rank":187,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11911135962872953,"rank":180,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11329727519649864,"rank":183,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1400124403939885,"rank":183,"remainingConfigurations":444},{"removed":"deepswe","score":0.09215139318379255,"rank":182,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11474772043945662,"rank":181,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11338415558833241,"rank":182,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10933584917926342,"rank":185,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11340622571511248,"rank":181,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11347818779367376,"rank":181,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11464554693251677,"rank":181,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11420290486577257,"rank":181,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11480840298030848,"rank":182,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11356605194386309,"rank":181,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11640227199428878,"rank":181,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11470400508028249,"rank":180,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11255464234133938,"rank":182,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11402384512867438,"rank":181,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11703390591106226,"rank":181,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11744184699903798,"rank":182,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11476443068378589,"rank":184,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10962417824381758,"rank":183,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11981888105914595,"rank":181,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1143461992365334,"rank":181,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11432102143470557,"rank":181,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11432765173106642,"rank":182,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11453033887959267,"rank":181,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11401548502698224,"rank":181,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11442648844287666,"rank":181,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5--effort-medium":{"score":0.11467870166925721,"rank":182,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10301086432474209,"rank":143,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.18533948424651295,"rank":160,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09048234401264306,"rank":183,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11509578184166475,"rank":181,"remainingConfigurations":444},{"removed":"Scale","score":0.13062565755243272,"rank":181,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11326232839306795,"rank":182,"remainingConfigurations":444},{"removed":"Cognition","score":0.1097392733519627,"rank":184,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11682618270585395,"rank":181,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10081829723080259,"rank":203,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11366078068460338,"rank":183,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10853407658506325,"rank":182,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1146392865770492,"rank":182,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11170642072934202,"rank":181,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11451313399790276,"rank":182,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11467870166925721,"rank":182,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11557554237733442,"rank":181,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1124189333147121,"rank":181,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11530595743060756,"rank":182,"remainingConfigurations":444},{"removed":"briefcase","score":0.11393366968296338,"rank":182,"remainingConfigurations":444},{"removed":"aime","score":0.11298708619073079,"rank":184,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11581992073887352,"rank":182,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11084640908290448,"rank":186,"remainingConfigurations":444},{"removed":"automationbench","score":0.1138224637275499,"rank":181,"remainingConfigurations":444},{"removed":"critpt","score":0.12647255881601305,"rank":178,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11459985896174078,"rank":181,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11578550951137344,"rank":182,"remainingConfigurations":444},{"removed":"gdpval","score":0.11454588239851467,"rank":183,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11203602592793376,"rank":187,"remainingConfigurations":444},{"removed":"gpqa","score":0.11299768000025467,"rank":184,"remainingConfigurations":444},{"removed":"harvey","score":0.11332770109695985,"rank":181,"remainingConfigurations":444},{"removed":"hle","score":0.1235689440667278,"rank":182,"remainingConfigurations":444},{"removed":"ifbench","score":0.1117245176764,"rank":183,"remainingConfigurations":444},{"removed":"itbench","score":0.11408470259775176,"rank":182,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11941089179923754,"rank":178,"remainingConfigurations":444},{"removed":"math500","score":0.11465060505156133,"rank":182,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11704183242067584,"rank":182,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12262143760064409,"rank":183,"remainingConfigurations":444},{"removed":"omniscience","score":0.10607498054546677,"rank":192,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1147671491803038,"rank":181,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1156820930081029,"rank":182,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11287340117099598,"rank":184,"remainingConfigurations":444},{"removed":"arc-agi","score":0.17960689126919957,"rank":159,"remainingConfigurations":444},{"removed":"deepswe","score":0.09052083673554136,"rank":183,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11470063205277219,"rank":182,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10932349780124777,"rank":186,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1097392733519627,"rank":184,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11333284002995596,"rank":182,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11342077438591891,"rank":182,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11460226048016096,"rank":182,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11419559617602885,"rank":182,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11481156423223027,"rank":181,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11356329297225654,"rank":182,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11620427032199192,"rank":182,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11457946660897356,"rank":181,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11258506818766206,"rank":181,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11399930976368505,"rank":182,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11705432098746259,"rank":180,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10081829723080259,"rank":203,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11523162948552175,"rank":182,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10920200961004461,"rank":184,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11958470846167961,"rank":182,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11427716578753673,"rank":182,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11426168033128194,"rank":182,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11436042844965795,"rank":181,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11443218842881137,"rank":182,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11395281467543618,"rank":182,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11437377924355284,"rank":182,"remainingConfigurations":444}],"sharedOrderConflicts":0},"o4-mini--effort-high":{"score":0.1141101535499744,"rank":183,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1232871383814549,"rank":136,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07824889780378327,"rank":227,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09010893760984094,"rank":185,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06599657718797196,"rank":226,"remainingConfigurations":444},{"removed":"Scale","score":0.130070841370763,"rank":183,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11273568997691809,"rank":183,"remainingConfigurations":444},{"removed":"Cognition","score":0.11054961122880382,"rank":183,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11690402920226584,"rank":180,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11441299845895385,"rank":184,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11338483429949094,"rank":184,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10787469073188054,"rank":183,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11407339393210392,"rank":183,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11117818750702142,"rank":183,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11395296721380314,"rank":183,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1141101535499744,"rank":183,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1150147939890549,"rank":183,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11190880028158345,"rank":183,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11472636893203046,"rank":183,"remainingConfigurations":444},{"removed":"briefcase","score":0.11337489893958029,"rank":183,"remainingConfigurations":444},{"removed":"aime","score":0.11112133028292616,"rank":188,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11521030278724782,"rank":183,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.114572794357591,"rank":180,"remainingConfigurations":444},{"removed":"automationbench","score":0.1132889467945033,"rank":182,"remainingConfigurations":444},{"removed":"critpt","score":0.11527148786173354,"rank":183,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11402161223637157,"rank":182,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11508997544524424,"rank":183,"remainingConfigurations":444},{"removed":"gdpval","score":0.11402754195969834,"rank":184,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11428027302173166,"rank":183,"remainingConfigurations":444},{"removed":"gpqa","score":0.11366166983729036,"rank":182,"remainingConfigurations":444},{"removed":"harvey","score":0.1127456359299297,"rank":182,"remainingConfigurations":444},{"removed":"hle","score":0.12339142048293918,"rank":184,"remainingConfigurations":444},{"removed":"ifbench","score":0.11007085579032554,"rank":186,"remainingConfigurations":444},{"removed":"itbench","score":0.1135493028276401,"rank":183,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06405570032070194,"rank":228,"remainingConfigurations":444},{"removed":"math500","score":0.11206759820968822,"rank":185,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11697736737745033,"rank":183,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12295960510429155,"rank":182,"remainingConfigurations":444},{"removed":"omniscience","score":0.10932770905545387,"rank":187,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11693021854226661,"rank":180,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11503283180765235,"rank":183,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1179455212670479,"rank":181,"remainingConfigurations":444},{"removed":"arc-agi","score":0.07543660883859425,"rank":229,"remainingConfigurations":444},{"removed":"deepswe","score":0.0901465512447087,"rank":185,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1141322911318739,"rank":183,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10880867699333217,"rank":187,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11054961122880382,"rank":183,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11275662515844896,"rank":183,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11287497351860316,"rank":183,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1140367834717872,"rank":183,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11361369182687475,"rank":183,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11425280168088642,"rank":183,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1130102160853252,"rank":183,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11564641217905713,"rank":183,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11399163604930711,"rank":182,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1120124233825238,"rank":183,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11346389330460632,"rank":183,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11643720261612629,"rank":182,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11441299845895385,"rank":184,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11477612775005282,"rank":183,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10744872846086147,"rank":186,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11898675261236173,"rank":183,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11370062841917063,"rank":183,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11368718890630562,"rank":183,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11380592715552451,"rank":183,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11385485642991015,"rank":183,"remainingConfigurations":444},{"removed":"vibe-code","score":0.113380516100531,"rank":183,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11381194896986106,"rank":183,"remainingConfigurations":444}],"sharedOrderConflicts":2},"gpt-5.6-terra--effort-low":{"score":0.11339897694701019,"rank":184,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.09057039096876461,"rank":147,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.15033121273460434,"rank":181,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09509279526432908,"rank":179,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11328642441679133,"rank":184,"remainingConfigurations":444},{"removed":"Scale","score":0.1283705054235861,"rank":184,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1123860291527836,"rank":184,"remainingConfigurations":444},{"removed":"Cognition","score":0.1266498266247245,"rank":169,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11695709117939523,"rank":179,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11208388072243693,"rank":187,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09435386568572916,"rank":200,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10736493997702083,"rank":185,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11337645879396001,"rank":184,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.11071290724788015,"rank":184,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11330995478218775,"rank":184,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11339897694701019,"rank":184,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11454355027606146,"rank":184,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11176069726607046,"rank":184,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11406110676231664,"rank":184,"remainingConfigurations":444},{"removed":"briefcase","score":0.11214671904118194,"rank":184,"remainingConfigurations":444},{"removed":"aime","score":0.11123877230501268,"rank":187,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11458755298507683,"rank":184,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11391396783807432,"rank":182,"remainingConfigurations":444},{"removed":"automationbench","score":0.11191515348789388,"rank":184,"remainingConfigurations":444},{"removed":"critpt","score":0.11240360593821581,"rank":186,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11366758121366434,"rank":183,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11157586491328013,"rank":186,"remainingConfigurations":444},{"removed":"gdpval","score":0.11252655811831608,"rank":185,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1138245990838223,"rank":184,"remainingConfigurations":444},{"removed":"gpqa","score":0.11197909393977663,"rank":186,"remainingConfigurations":444},{"removed":"harvey","score":0.11210732324261219,"rank":184,"remainingConfigurations":444},{"removed":"hle","score":0.12147722730361989,"rank":186,"remainingConfigurations":444},{"removed":"ifbench","score":0.11486503478741382,"rank":178,"remainingConfigurations":444},{"removed":"itbench","score":0.11304914703216029,"rank":184,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11365701627764253,"rank":183,"remainingConfigurations":444},{"removed":"math500","score":0.11358850888961503,"rank":183,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11680575771654739,"rank":184,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1204507046668334,"rank":185,"remainingConfigurations":444},{"removed":"omniscience","score":0.11001043436223162,"rank":186,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11455550422545065,"rank":182,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11419176310088201,"rank":184,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11267418912202216,"rank":185,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12144560868545236,"rank":196,"remainingConfigurations":444},{"removed":"deepswe","score":0.09510023182227245,"rank":179,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11342123067584094,"rank":184,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.12779180047346098,"rank":172,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1266498266247245,"rank":169,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1122215179776473,"rank":184,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11201270270448442,"rank":184,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1133722181893589,"rank":184,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11290895845370912,"rank":184,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11362430620980023,"rank":184,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11212653890850029,"rank":184,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11489222065432715,"rank":184,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11330069798986565,"rank":184,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11132607114850072,"rank":184,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1127398832041565,"rank":184,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11584059380817396,"rank":184,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11208388072243693,"rank":187,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1144704669509019,"rank":185,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1079931555291852,"rank":185,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11800815229560162,"rank":185,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11302345472435267,"rank":184,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11299440633917884,"rank":184,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11311152527558128,"rank":184,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11311949057532733,"rank":184,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11267813524346537,"rank":184,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11317300571478779,"rank":184,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-haiku-5-5--effort-low":{"score":0.11269543114836837,"rank":185,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.07390518363109654,"rank":152,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.23593753025894423,"rank":139,"remainingConfigurations":444},{"removed":"Datacurve","score":0.09044324393152588,"rank":184,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11271507012029151,"rank":185,"remainingConfigurations":444},{"removed":"Scale","score":0.12747536486243752,"rank":185,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11012115097638418,"rank":187,"remainingConfigurations":444},{"removed":"Cognition","score":0.06277782224425392,"rank":229,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11637549681686242,"rank":182,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11284826865464205,"rank":186,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1259264439097119,"rank":175,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10597246183785737,"rank":188,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11265447981964248,"rank":185,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10987865880055553,"rank":185,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11253546746108382,"rank":185,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11269543114836837,"rank":185,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.1134178041796552,"rank":185,"remainingConfigurations":444},{"removed":"All provider reports","score":0.11042355813103588,"rank":185,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11345499832384347,"rank":185,"remainingConfigurations":444},{"removed":"briefcase","score":0.10964616796009145,"rank":187,"remainingConfigurations":444},{"removed":"aime","score":0.1112897464656566,"rank":186,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1138624366974379,"rank":185,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1132459366801023,"rank":183,"remainingConfigurations":444},{"removed":"automationbench","score":0.11202214202353256,"rank":183,"remainingConfigurations":444},{"removed":"critpt","score":0.11201138557495567,"rank":188,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1130368297870536,"rank":184,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11291924555194884,"rank":185,"remainingConfigurations":444},{"removed":"gdpval","score":0.11154104680882504,"rank":186,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1130236975978306,"rank":185,"remainingConfigurations":444},{"removed":"gpqa","score":0.1133244253201765,"rank":183,"remainingConfigurations":444},{"removed":"harvey","score":0.1097471175024851,"rank":187,"remainingConfigurations":444},{"removed":"hle","score":0.12164663518786613,"rank":185,"remainingConfigurations":444},{"removed":"ifbench","score":0.11166051795541033,"rank":184,"remainingConfigurations":444},{"removed":"itbench","score":0.11254527382622614,"rank":185,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11290092073811155,"rank":185,"remainingConfigurations":444},{"removed":"math500","score":0.11279638526886193,"rank":184,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11590257749811049,"rank":185,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12128733565407197,"rank":184,"remainingConfigurations":444},{"removed":"omniscience","score":0.11116450573825387,"rank":184,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11313597138851494,"rank":186,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1127553298776391,"rank":186,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11038156757390098,"rank":190,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2316393045425359,"rank":137,"remainingConfigurations":444},{"removed":"deepswe","score":0.09049715374112642,"rank":184,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1127171743603414,"rank":185,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10756700714752009,"rank":188,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06277782224425392,"rank":229,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11149546694307666,"rank":185,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11130251702182686,"rank":185,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11262280550930366,"rank":185,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11213963824634905,"rank":185,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11281210266133866,"rank":185,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11108231018378657,"rank":185,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11429462165725925,"rank":185,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11277996817537501,"rank":185,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.11078647961711664,"rank":185,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11179972527082112,"rank":185,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11536629121636766,"rank":185,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11284826865464205,"rank":186,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11277494538423712,"rank":186,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.11407860630954429,"rank":180,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1173029178811041,"rank":186,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11233122702728193,"rank":185,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11226433968312245,"rank":185,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.1123332420158833,"rank":185,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11241451579955146,"rank":185,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11200674024048347,"rank":185,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11233272193635531,"rank":185,"remainingConfigurations":444}],"sharedOrderConflicts":0},"solar-mini4-260922--effort-reasoning":{"score":0.1116682402600682,"rank":186,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.14071549346011158,"rank":184,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08958719338340813,"rank":187,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11088770173804056,"rank":186,"remainingConfigurations":444},{"removed":"Scale","score":0.12728909547308034,"rank":186,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11073597827490693,"rank":185,"remainingConfigurations":444},{"removed":"Cognition","score":0.1062852034464115,"rank":191,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11592007398941649,"rank":183,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11460529968618895,"rank":183,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11462035310542662,"rank":182,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10751778738294683,"rank":184,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11162068383853847,"rank":186,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10848259272875167,"rank":186,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11147245167794362,"rank":186,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.1116682402600682,"rank":186,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11253870293789443,"rank":186,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10913543600213732,"rank":186,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1127363606564985,"rank":186,"remainingConfigurations":444},{"removed":"briefcase","score":0.1092887602216107,"rank":189,"remainingConfigurations":444},{"removed":"aime","score":0.11096623821211561,"rank":189,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11356534701251624,"rank":186,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08930132235084635,"rank":208,"remainingConfigurations":444},{"removed":"automationbench","score":0.10570814865213783,"rank":193,"remainingConfigurations":444},{"removed":"critpt","score":0.11290780645798183,"rank":185,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1118829578564731,"rank":185,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1226322606290189,"rank":178,"remainingConfigurations":444},{"removed":"gdpval","score":0.10380347083753577,"rank":197,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1123892240941497,"rank":186,"remainingConfigurations":444},{"removed":"gpqa","score":0.1096892872521656,"rank":188,"remainingConfigurations":444},{"removed":"harvey","score":0.11033460809019931,"rank":185,"remainingConfigurations":444},{"removed":"hle","score":0.11753402190349714,"rank":192,"remainingConfigurations":444},{"removed":"ifbench","score":0.10831715834160653,"rank":189,"remainingConfigurations":444},{"removed":"itbench","score":0.11099834460333662,"rank":186,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11117936660884993,"rank":186,"remainingConfigurations":444},{"removed":"math500","score":0.11174373697887478,"rank":186,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11440973487686223,"rank":186,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12036347008630555,"rank":186,"remainingConfigurations":444},{"removed":"omniscience","score":0.14407959318941801,"rank":163,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11002931319247615,"rank":189,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11300597385409461,"rank":185,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11137913408997567,"rank":186,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1363137666294721,"rank":184,"remainingConfigurations":444},{"removed":"deepswe","score":0.08964399210425102,"rank":187,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11169559951656145,"rank":186,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.11032273304400668,"rank":184,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1062852034464115,"rank":191,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11038218594373507,"rank":186,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11046242254756679,"rank":186,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11159354539028114,"rank":186,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11123019741571284,"rank":186,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11176378080634519,"rank":186,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1105159406384023,"rank":186,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11330437446237708,"rank":186,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11166033761695517,"rank":186,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10955865417410666,"rank":186,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11097643395541852,"rank":186,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11395227673200657,"rank":186,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11460529968618895,"rank":183,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11179635719716836,"rank":187,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10646749384010279,"rank":187,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1166794477409569,"rank":187,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.1112939160833102,"rank":186,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11128185200323092,"rank":186,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11129318478740542,"rank":186,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11147611380122335,"rank":186,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11098945271567996,"rank":186,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11137760211934074,"rank":186,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m2.5--effort-reasoning":{"score":0.11130839411104665,"rank":187,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1403452714304251,"rank":185,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08964339854327341,"rank":186,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11044911391757066,"rank":187,"remainingConfigurations":444},{"removed":"Scale","score":0.12717073144186908,"rank":187,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.11055601871534115,"rank":186,"remainingConfigurations":444},{"removed":"Cognition","score":0.10740135882417089,"rank":187,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11481175007877202,"rank":184,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11369406077618666,"rank":185,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.11296748843251055,"rank":185,"remainingConfigurations":431},{"removed":"Vals AI","score":0.1069559585890197,"rank":186,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11126628313837206,"rank":187,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10817143371147052,"rank":188,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11112865631977752,"rank":187,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11130839411104665,"rank":187,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11214208462390533,"rank":187,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10880926626444498,"rank":188,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11204014310063797,"rank":187,"remainingConfigurations":444},{"removed":"briefcase","score":0.11051812015981288,"rank":185,"remainingConfigurations":444},{"removed":"aime","score":0.11149387306285187,"rank":185,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1127377470307412,"rank":187,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1062718883573175,"rank":189,"remainingConfigurations":444},{"removed":"automationbench","score":0.1103506931781938,"rank":186,"remainingConfigurations":444},{"removed":"critpt","score":0.11560357346097354,"rank":182,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11116854511947939,"rank":186,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11335919659591463,"rank":184,"remainingConfigurations":444},{"removed":"gdpval","score":0.11130292137325846,"rank":187,"remainingConfigurations":444},{"removed":"gmmlu","score":0.12408530057949772,"rank":177,"remainingConfigurations":444},{"removed":"gpqa","score":0.10636600061175062,"rank":191,"remainingConfigurations":444},{"removed":"harvey","score":0.11009666759351698,"rank":186,"remainingConfigurations":444},{"removed":"hle","score":0.12355716389049289,"rank":183,"remainingConfigurations":444},{"removed":"ifbench","score":0.1050089950085281,"rank":194,"remainingConfigurations":444},{"removed":"itbench","score":0.11031156957097915,"rank":188,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11112815624745,"rank":187,"remainingConfigurations":444},{"removed":"math500","score":0.11154134391085557,"rank":187,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11416899803457524,"rank":188,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11912973283678248,"rank":187,"remainingConfigurations":444},{"removed":"omniscience","score":0.10805566305678636,"rank":190,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10192593446760485,"rank":198,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11271545866494935,"rank":187,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11089980099899345,"rank":188,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1356718559605655,"rank":185,"remainingConfigurations":444},{"removed":"deepswe","score":0.08970170080468208,"rank":186,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1113336102850795,"rank":187,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10961190968448618,"rank":185,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10740135882417089,"rank":187,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.11000231941245087,"rank":187,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.11012855856772917,"rank":187,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11123241628612386,"rank":187,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11084132093280306,"rank":187,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11142540297013348,"rank":187,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.11017532416582361,"rank":187,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11290439065133355,"rank":187,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11126779124823329,"rank":187,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10924261924365401,"rank":187,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11062924086575641,"rank":187,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11356263294396544,"rank":187,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11369406077618666,"rank":185,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11157258309900742,"rank":188,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10547673110103384,"rank":188,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11632458789315513,"rank":188,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11092925793605957,"rank":187,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11092046013582058,"rank":187,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11093816073461282,"rank":187,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11111324519574821,"rank":187,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1106441292636292,"rank":187,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11101402952376917,"rank":187,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-sonnet-4-5-20250929--effort-thinking-32k":{"score":0.11102746648740552,"rank":188,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10069575315902744,"rank":144,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05514979701673268,"rank":258,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08617578485254475,"rank":191,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11329172857346988,"rank":183,"remainingConfigurations":444},{"removed":"Scale","score":0.1263877687644177,"rank":188,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10949156142180215,"rank":188,"remainingConfigurations":444},{"removed":"Cognition","score":0.10731474190907737,"rank":188,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11378650222752386,"rank":185,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11147513161221308,"rank":189,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.13386769439089655,"rank":170,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10359732082428501,"rank":191,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11099163058594617,"rank":188,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10833091392590967,"rank":187,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11095248055276002,"rank":188,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11102746648740552,"rank":188,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11182424589270645,"rank":188,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10903759859714406,"rank":187,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11149689919938525,"rank":188,"remainingConfigurations":444},{"removed":"briefcase","score":0.11022887288622425,"rank":186,"remainingConfigurations":444},{"removed":"aime","score":0.11422783239928526,"rank":182,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1118845608601756,"rank":188,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11044666427847016,"rank":187,"remainingConfigurations":444},{"removed":"automationbench","score":0.11033087268732888,"rank":187,"remainingConfigurations":444},{"removed":"critpt","score":0.11227360444271452,"rank":187,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.11098621895110494,"rank":187,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.1115749843291161,"rank":187,"remainingConfigurations":444},{"removed":"gdpval","score":0.1105598733964026,"rank":188,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11103962714991163,"rank":189,"remainingConfigurations":444},{"removed":"gpqa","score":0.08942912010599108,"rank":207,"remainingConfigurations":444},{"removed":"harvey","score":0.10956332862733853,"rank":188,"remainingConfigurations":444},{"removed":"hle","score":0.11973461721927015,"rank":189,"remainingConfigurations":444},{"removed":"ifbench","score":0.11001400813417084,"rank":187,"remainingConfigurations":444},{"removed":"itbench","score":0.11059256475979544,"rank":187,"remainingConfigurations":444},{"removed":"livecodebench","score":0.1132190128247307,"rank":184,"remainingConfigurations":444},{"removed":"math500","score":0.11108958296122624,"rank":188,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11436102756412699,"rank":187,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11898906096670038,"rank":188,"remainingConfigurations":444},{"removed":"omniscience","score":0.10879830161295338,"rank":189,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11036856507688064,"rank":188,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11163310797267656,"rank":188,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11036706849577732,"rank":191,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05368590957860428,"rank":258,"remainingConfigurations":444},{"removed":"deepswe","score":0.08623041968337501,"rank":191,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11104524558950059,"rank":188,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10369400389423135,"rank":194,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10731474190907737,"rank":188,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10970621090524696,"rank":188,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10979828365650211,"rank":188,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11094998867259544,"rank":188,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.11056767674235006,"rank":188,"remainingConfigurations":444},{"removed":"livebench-math","score":0.11121211641573525,"rank":188,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10986593591723559,"rank":188,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11248771604155332,"rank":188,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11097248264473897,"rank":188,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10900023034559302,"rank":188,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.11042017879935102,"rank":188,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11327612954807716,"rank":188,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11147513161221308,"rank":189,"remainingConfigurations":444},{"removed":"frontiermath","score":0.14007629690345139,"rank":165,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10102773525171756,"rank":193,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1186093497376175,"rank":184,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.11060019157314531,"rank":188,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.11062780390715382,"rank":188,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.11071732141897445,"rank":188,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.11078324801199806,"rank":188,"remainingConfigurations":444},{"removed":"vibe-code","score":0.11032285029967288,"rank":188,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.11075283605900094,"rank":188,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash--effort-minimal":{"score":0.11017765363338244,"rank":189,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10563281699634149,"rank":142,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.16213898076570418,"rank":172,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08737686716401609,"rank":190,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.11019924914353002,"rank":188,"remainingConfigurations":444},{"removed":"Scale","score":0.12527332920455633,"rank":189,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10923347590759219,"rank":189,"remainingConfigurations":444},{"removed":"Cognition","score":0.10876672286780227,"rank":186,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11292976352705936,"rank":186,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.11090016544826349,"rank":190,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0952791370646119,"rank":199,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10479529773962175,"rank":190,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.11014561021093544,"rank":189,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10733617163812266,"rank":189,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.11004183376433835,"rank":189,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.11017765363338244,"rank":189,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11099293749533783,"rank":189,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1080050534763129,"rank":189,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11080938632061493,"rank":190,"remainingConfigurations":444},{"removed":"briefcase","score":0.10949608551031398,"rank":188,"remainingConfigurations":444},{"removed":"aime","score":0.11624787349087913,"rank":181,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11129458976492601,"rank":189,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.11286986542217003,"rank":184,"remainingConfigurations":444},{"removed":"automationbench","score":0.10949460652233341,"rank":188,"remainingConfigurations":444},{"removed":"critpt","score":0.1100730938209883,"rank":191,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1101787516019606,"rank":188,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11125969948245934,"rank":188,"remainingConfigurations":444},{"removed":"gdpval","score":0.10980887144104261,"rank":189,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11051318246730842,"rank":190,"remainingConfigurations":444},{"removed":"gpqa","score":0.10233476585775562,"rank":194,"remainingConfigurations":444},{"removed":"harvey","score":0.10890170932524028,"rank":189,"remainingConfigurations":444},{"removed":"hle","score":0.1179876107082994,"rank":191,"remainingConfigurations":444},{"removed":"ifbench","score":0.11578419409326512,"rank":177,"remainingConfigurations":444},{"removed":"itbench","score":0.1096219657546199,"rank":189,"remainingConfigurations":444},{"removed":"livecodebench","score":0.11043116518821779,"rank":188,"remainingConfigurations":444},{"removed":"math500","score":0.11034969377323321,"rank":189,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11331874828226451,"rank":189,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11162929707153983,"rank":199,"remainingConfigurations":444},{"removed":"omniscience","score":0.10198752522979367,"rank":196,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11369563096536511,"rank":184,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11114153243064033,"rank":189,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.1066885424825953,"rank":194,"remainingConfigurations":444},{"removed":"arc-agi","score":0.15716132927086643,"rank":173,"remainingConfigurations":444},{"removed":"deepswe","score":0.0874258251129964,"rank":190,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.11019852156077603,"rank":189,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1074108228839783,"rank":190,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10876672286780227,"rank":186,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10902105332425661,"rank":189,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1089431142192298,"rank":189,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.11010804132758856,"rank":189,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10970159635810998,"rank":189,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1103873389410296,"rank":189,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10896299171975622,"rank":189,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11167327314617748,"rank":189,"remainingConfigurations":444},{"removed":"livebench-data","score":0.11012827722017328,"rank":189,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10818275816697241,"rank":189,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10951229472913865,"rank":189,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.11244059209630049,"rank":189,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.11090016544826349,"rank":190,"remainingConfigurations":444},{"removed":"frontiermath","score":0.11137308819893847,"rank":189,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10185164339689756,"rank":190,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11512437774852169,"rank":189,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10978897773876917,"rank":189,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10979497384688179,"rank":189,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10982525653724884,"rank":189,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10996337302739323,"rank":189,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10951402346240612,"rank":189,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10985954956557491,"rank":189,"remainingConfigurations":444}],"sharedOrderConflicts":0},"o3--effort-reasoning":{"score":0.10922822945509685,"rank":190,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1384427161543832,"rank":186,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08789493494875332,"rank":189,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10816015412900841,"rank":189,"remainingConfigurations":444},{"removed":"Scale","score":0.1248797298732316,"rank":190,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.1084823884854431,"rank":190,"remainingConfigurations":444},{"removed":"Cognition","score":0.10550857496879895,"rank":192,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11269497486408492,"rank":187,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1116075422355015,"rank":188,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1101955532405073,"rank":186,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10503196928936888,"rank":189,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10918702410596563,"rank":190,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10614163295367368,"rank":190,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.1090479829284785,"rank":190,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10922822945509685,"rank":190,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.11004739401808962,"rank":190,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10676485493581726,"rank":190,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.11001213193269188,"rank":191,"remainingConfigurations":444},{"removed":"briefcase","score":0.1085065151211198,"rank":190,"remainingConfigurations":444},{"removed":"aime","score":0.11006726522798627,"rank":190,"remainingConfigurations":444},{"removed":"apex-agents","score":0.11059555707593671,"rank":190,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10303988697019555,"rank":195,"remainingConfigurations":444},{"removed":"automationbench","score":0.10835184793152286,"rank":189,"remainingConfigurations":444},{"removed":"critpt","score":0.11173762973617356,"rank":189,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10906065735217328,"rank":190,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11123713015884235,"rank":189,"remainingConfigurations":444},{"removed":"gdpval","score":0.10932998011824495,"rank":191,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10989222080316711,"rank":191,"remainingConfigurations":444},{"removed":"gpqa","score":0.10991937468644312,"rank":187,"remainingConfigurations":444},{"removed":"harvey","score":0.10801659715264274,"rank":190,"remainingConfigurations":444},{"removed":"hle","score":0.12125358219842065,"rank":187,"remainingConfigurations":444},{"removed":"ifbench","score":0.10425832424359795,"rank":195,"remainingConfigurations":444},{"removed":"itbench","score":0.10830538870235229,"rank":190,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10942221484088936,"rank":189,"remainingConfigurations":444},{"removed":"math500","score":0.108439292086787,"rank":190,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11303095321686951,"rank":190,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.12364178074688831,"rank":181,"remainingConfigurations":444},{"removed":"omniscience","score":0.09349722859574434,"rank":202,"remainingConfigurations":444},{"removed":"tau-bench","score":0.11403899536279437,"rank":183,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.11067091690915642,"rank":190,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10675915148612525,"rank":193,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1337396336587949,"rank":186,"remainingConfigurations":444},{"removed":"deepswe","score":0.0879522005312478,"rank":189,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10925294066003884,"rank":190,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10751683983856242,"rank":189,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10550857496879895,"rank":192,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10792382577912225,"rank":190,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1080343303803834,"rank":190,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10915698655632679,"rank":190,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10877166266730814,"rank":190,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10934442547087346,"rank":190,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10811757829892815,"rank":190,"remainingConfigurations":444},{"removed":"livebench-language","score":0.11079944292551151,"rank":190,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10918513041295831,"rank":190,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.1071928330396869,"rank":190,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10855909172362971,"rank":190,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.111447562645564,"rank":190,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1116075422355015,"rank":188,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10947439556960885,"rank":190,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10324543483955717,"rank":189,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11419390643802203,"rank":190,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10885384623911071,"rank":190,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1088457074894837,"rank":190,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10886562369007151,"rank":190,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10903432335164998,"rank":190,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1085725657099416,"rank":190,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10893972818945874,"rank":190,"remainingConfigurations":444}],"sharedOrderConflicts":0},"solar-open2-250b--effort-reasoning":{"score":0.10705954953420134,"rank":191,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.13485825372634916,"rank":187,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08549330425237883,"rank":193,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1062373744866919,"rank":191,"remainingConfigurations":444},{"removed":"Scale","score":0.12227268083726966,"rank":192,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10615486867437395,"rank":191,"remainingConfigurations":444},{"removed":"Cognition","score":0.10231672921905643,"rank":194,"remainingConfigurations":444},{"removed":"LiveBench","score":0.1106045450419081,"rank":189,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10942800140970184,"rank":191,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10934178700319012,"rank":187,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10266362530821442,"rank":192,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1070165773476283,"rank":191,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10399876032508448,"rank":192,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10688016249741063,"rank":191,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10705954953420134,"rank":191,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10786448209277094,"rank":192,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10460663592983686,"rank":192,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10783757299663715,"rank":192,"remainingConfigurations":444},{"removed":"briefcase","score":0.10576280832495359,"rank":193,"remainingConfigurations":444},{"removed":"aime","score":0.1067253607272856,"rank":192,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10864222266533023,"rank":192,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.1050580109673812,"rank":191,"remainingConfigurations":444},{"removed":"automationbench","score":0.10584704507468844,"rank":192,"remainingConfigurations":444},{"removed":"critpt","score":0.0952868152277816,"rank":203,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10702226943627491,"rank":192,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10890946082482951,"rank":191,"remainingConfigurations":444},{"removed":"gdpval","score":0.10939625080635489,"rank":190,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10795177943609806,"rank":193,"remainingConfigurations":444},{"removed":"gpqa","score":0.09918276199138625,"rank":200,"remainingConfigurations":444},{"removed":"harvey","score":0.10581008503626509,"rank":191,"remainingConfigurations":444},{"removed":"hle","score":0.1073707452251879,"rank":201,"remainingConfigurations":444},{"removed":"ifbench","score":0.1040991802576533,"rank":197,"remainingConfigurations":444},{"removed":"itbench","score":0.10621473331629096,"rank":192,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10657962831606314,"rank":191,"remainingConfigurations":444},{"removed":"math500","score":0.10721211358152305,"rank":192,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10966464761400085,"rank":192,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11523025853936665,"rank":191,"remainingConfigurations":444},{"removed":"omniscience","score":0.1382700003513499,"rank":170,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0995606183805447,"rank":199,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1083495710370227,"rank":191,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11054412426198033,"rank":189,"remainingConfigurations":444},{"removed":"arc-agi","score":0.13089133069711203,"rank":187,"remainingConfigurations":444},{"removed":"deepswe","score":0.08554922820546079,"rank":193,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1070852693038017,"rank":191,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10553500674857484,"rank":191,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10231672921905643,"rank":194,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1057942594529011,"rank":191,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10588515537748185,"rank":191,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10699047976732089,"rank":191,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10658730532476579,"rank":191,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10716823331370705,"rank":192,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.1059546418871633,"rank":191,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10861915486125702,"rank":191,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10703980077737124,"rank":191,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10503978051161704,"rank":191,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10639472695561326,"rank":192,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10925244560713122,"rank":191,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10942800140970184,"rank":191,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10713799030143915,"rank":192,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.10147011889852381,"rank":192,"remainingConfigurations":444},{"removed":"simpleqa","score":0.111916127472163,"rank":191,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10668872618266513,"rank":191,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.1066886732596826,"rank":191,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10669754692083538,"rank":191,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10687431826251033,"rank":191,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10640990188224712,"rank":191,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10677615738139322,"rank":191,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v3.2--effort-reasoning":{"score":0.10692655501130399,"rank":192,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.13415432587990814,"rank":188,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0857644096712511,"rank":192,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10607305740489664,"rank":192,"remainingConfigurations":444},{"removed":"Scale","score":0.12209623438342461,"rank":193,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10612631627260372,"rank":192,"remainingConfigurations":444},{"removed":"Cognition","score":0.10281454955035661,"rank":193,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10988094007002637,"rank":190,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.109407327895583,"rank":192,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10897424747510588,"rank":188,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10238167713278246,"rank":193,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10688519123497393,"rank":192,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10381955250022235,"rank":193,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10675279555443529,"rank":192,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10692655501130399,"rank":192,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10772200910334075,"rank":193,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10442599574253275,"rank":193,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10767938586571325,"rank":193,"remainingConfigurations":444},{"removed":"briefcase","score":0.10639159762800615,"rank":191,"remainingConfigurations":444},{"removed":"aime","score":0.10495069005153174,"rank":195,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10914978662527891,"rank":191,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10273638229933602,"rank":196,"remainingConfigurations":444},{"removed":"automationbench","score":0.10606577158498685,"rank":191,"remainingConfigurations":444},{"removed":"critpt","score":0.10486962072565353,"rank":196,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10657401604583616,"rank":193,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10886965929007214,"rank":192,"remainingConfigurations":444},{"removed":"gdpval","score":0.11673135473148094,"rank":181,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10808152650934337,"rank":192,"remainingConfigurations":444},{"removed":"gpqa","score":0.10541660352306058,"rank":192,"remainingConfigurations":444},{"removed":"harvey","score":0.10571951181173704,"rank":192,"remainingConfigurations":444},{"removed":"hle","score":0.11481577407800488,"rank":193,"remainingConfigurations":444},{"removed":"ifbench","score":0.1093342731925524,"rank":188,"remainingConfigurations":444},{"removed":"itbench","score":0.10593979994993312,"rank":193,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10482126743179034,"rank":195,"remainingConfigurations":444},{"removed":"math500","score":0.10741537611361392,"rank":191,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10866948619398126,"rank":195,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11468449154744355,"rank":192,"remainingConfigurations":444},{"removed":"omniscience","score":0.09760368090003857,"rank":199,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10463677270640641,"rank":193,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1083142603993877,"rank":192,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10792932518377701,"rank":192,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12981447123082904,"rank":188,"remainingConfigurations":444},{"removed":"deepswe","score":0.08582382970326541,"rank":192,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10695023778017905,"rank":192,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10532404902719916,"rank":192,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10281454955035661,"rank":193,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10565245953073632,"rank":193,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10576864116339968,"rank":192,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10685446121961673,"rank":192,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10647348680781588,"rank":192,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10703839486329869,"rank":193,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10585244475250893,"rank":192,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1084826059270999,"rank":192,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10686937482900309,"rank":192,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10492347053190676,"rank":192,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1062728149172145,"rank":193,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10909549237606002,"rank":193,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.109407327895583,"rank":192,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10711544339858814,"rank":193,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.1015485735562789,"rank":191,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11180384395405359,"rank":192,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10655931875398661,"rank":192,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10654853992534023,"rank":192,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10656444187979981,"rank":192,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10673925224795093,"rank":192,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10628944456138202,"rank":192,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10664074955311863,"rank":192,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-medium":{"score":0.10677516122948026,"rank":193,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06918663879505076,"rank":154,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1290556810013661,"rank":196,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08512378738028888,"rank":194,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10668283757382185,"rank":190,"remainingConfigurations":444},{"removed":"Scale","score":0.12133580546855899,"rank":194,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10557374729780904,"rank":193,"remainingConfigurations":444},{"removed":"Cognition","score":0.09508787977758333,"rank":203,"remainingConfigurations":444},{"removed":"LiveBench","score":0.11185885400288002,"rank":188,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10658668107495367,"rank":197,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.14438820642131708,"rank":163,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10234118615537548,"rank":194,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10675316372120376,"rank":193,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1042043754743952,"rank":191,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10668525946793157,"rank":193,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10677516122948026,"rank":193,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10789981728148684,"rank":191,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10522949473497405,"rank":191,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1075068470256787,"rank":194,"remainingConfigurations":444},{"removed":"briefcase","score":0.10589621764262734,"rank":192,"remainingConfigurations":444},{"removed":"aime","score":0.10616732177745736,"rank":193,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1080203159773548,"rank":193,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10668744387732916,"rank":188,"remainingConfigurations":444},{"removed":"automationbench","score":0.10557871677213743,"rank":194,"remainingConfigurations":444},{"removed":"critpt","score":0.10532556259977675,"rank":192,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10714923219717183,"rank":191,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10532990895083305,"rank":198,"remainingConfigurations":444},{"removed":"gdpval","score":0.1054425516371514,"rank":192,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10721204346054468,"rank":194,"remainingConfigurations":444},{"removed":"gpqa","score":0.10389107631358369,"rank":193,"remainingConfigurations":444},{"removed":"harvey","score":0.10558618899019079,"rank":193,"remainingConfigurations":444},{"removed":"hle","score":0.11469016202490023,"rank":194,"remainingConfigurations":444},{"removed":"ifbench","score":0.10831348436662915,"rank":190,"remainingConfigurations":444},{"removed":"itbench","score":0.10655413210914,"rank":191,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10707594732694753,"rank":190,"remainingConfigurations":444},{"removed":"math500","score":0.10697685924709566,"rank":193,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.11010531794746407,"rank":191,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11346201807249356,"rank":193,"remainingConfigurations":444},{"removed":"omniscience","score":0.10365584130802084,"rank":195,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1074847162585526,"rank":190,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1075739433208394,"rank":193,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10652937787230542,"rank":195,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11140095552554304,"rank":205,"remainingConfigurations":444},{"removed":"deepswe","score":0.08512252213152456,"rank":194,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.1067961324428815,"rank":193,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1268913854676559,"rank":174,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09508787977758333,"rank":203,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10566876580069705,"rank":192,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10542022162392327,"rank":193,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10675837436530977,"rank":193,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10633018349971242,"rank":193,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10696529632778179,"rank":194,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10559933847834678,"rank":193,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10819677015416262,"rank":193,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10665968440116531,"rank":193,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10478379577563189,"rank":193,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10615481390577224,"rank":194,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10912677855611107,"rank":192,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10658668107495367,"rank":197,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10275816414424517,"rank":200,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.13530416500026324,"rank":166,"remainingConfigurations":444},{"removed":"simpleqa","score":0.11139509616795402,"rank":193,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10641374580705831,"rank":193,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10638139805854546,"rank":193,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10651968154934692,"rank":193,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10649013591312284,"rank":193,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10606604679334053,"rank":193,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10657576138701068,"rank":193,"remainingConfigurations":444}],"sharedOrderConflicts":1},"qwen3.7-plus--effort-non-reasoning":{"score":0.10570278471746135,"rank":194,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.09652107395864719,"rank":146,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.12917355010565879,"rank":194,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08366336151089691,"rank":197,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10540892909055068,"rank":193,"remainingConfigurations":444},{"removed":"Scale","score":0.11923776053240787,"rank":197,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10538935279103095,"rank":194,"remainingConfigurations":444},{"removed":"Cognition","score":0.10661389922498049,"rank":189,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10740848568175237,"rank":194,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10724847276916803,"rank":194,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10054660392268076,"rank":196,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10567879337738151,"rank":194,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.103052493872124,"rank":194,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10564254762896617,"rank":194,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10570278471746135,"rank":194,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10635281583843974,"rank":194,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10364368888491193,"rank":194,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1062334688582713,"rank":195,"remainingConfigurations":444},{"removed":"briefcase","score":0.10526856929660171,"rank":194,"remainingConfigurations":444},{"removed":"aime","score":0.10251575685243602,"rank":198,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10672578609074553,"rank":194,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10593274114554403,"rank":190,"remainingConfigurations":444},{"removed":"automationbench","score":0.10529102508178,"rank":195,"remainingConfigurations":444},{"removed":"critpt","score":0.10513474811965072,"rank":193,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10580686838597643,"rank":194,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10662830546163786,"rank":194,"remainingConfigurations":444},{"removed":"gdpval","score":0.10459542567809849,"rank":195,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10612916006620265,"rank":195,"remainingConfigurations":444},{"removed":"gpqa","score":0.1149320080327735,"rank":180,"remainingConfigurations":444},{"removed":"harvey","score":0.10442229536898134,"rank":194,"remainingConfigurations":444},{"removed":"hle","score":0.11249309953795233,"rank":197,"remainingConfigurations":444},{"removed":"ifbench","score":0.10706812654284159,"rank":192,"remainingConfigurations":444},{"removed":"itbench","score":0.10514931262576525,"rank":194,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10580264721754967,"rank":192,"remainingConfigurations":444},{"removed":"math500","score":0.10589044136944566,"rank":194,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.1089438540412511,"rank":193,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11300741543669086,"rank":194,"remainingConfigurations":444},{"removed":"omniscience","score":0.10427077013181162,"rank":193,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1020683941660881,"rank":197,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10649267693442584,"rank":194,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10515300429540302,"rank":198,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12589363391698744,"rank":193,"remainingConfigurations":444},{"removed":"deepswe","score":0.08374371556950255,"rank":197,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10572228089818181,"rank":194,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10457244045934416,"rank":193,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10661389922498049,"rank":189,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1046767950388122,"rank":194,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10432793854701354,"rank":194,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10565982785548855,"rank":194,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10530872509353595,"rank":194,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10602659847842717,"rank":195,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10428425926620359,"rank":194,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10713016914378216,"rank":194,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10582488457912038,"rank":194,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10386317803891765,"rank":194,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10503391986488371,"rank":195,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10779365251058004,"rank":194,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10724847276916803,"rank":194,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09495534266567995,"rank":206,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09526410948820374,"rank":200,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10881645722340567,"rank":197,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10530075624552908,"rank":194,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10539161158646508,"rank":195,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10528124709148425,"rank":194,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10555514363521579,"rank":194,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10514963032846514,"rank":194,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10540383584636785,"rank":194,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash-lite--effort-high":{"score":0.10476973642853114,"rank":195,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.09980687629243466,"rank":145,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.12146965164930386,"rank":200,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0829008848662897,"rank":199,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10505513283670591,"rank":194,"remainingConfigurations":444},{"removed":"Scale","score":0.11808007454137599,"rank":199,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10449283426483769,"rank":195,"remainingConfigurations":444},{"removed":"Cognition","score":0.1063941722872966,"rank":190,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09401201803832233,"rank":203,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10351672629973489,"rank":200,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.120607092601421,"rank":179,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10622392772653355,"rank":187,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.1047610441745694,"rank":195,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1024506404855403,"rank":195,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10467276165255064,"rank":195,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10476973642853114,"rank":195,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10534769025828285,"rank":196,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10294491772401093,"rank":195,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10506334934467233,"rank":198,"remainingConfigurations":444},{"removed":"briefcase","score":0.10431265087779541,"rank":195,"remainingConfigurations":444},{"removed":"aime","score":0.10707615147362048,"rank":191,"remainingConfigurations":444},{"removed":"apex-agents","score":0.1053012258622751,"rank":198,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10463351370891964,"rank":192,"remainingConfigurations":444},{"removed":"automationbench","score":0.10435495196135164,"rank":196,"remainingConfigurations":444},{"removed":"critpt","score":0.1049594516763213,"rank":195,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10482732775183419,"rank":195,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10528512138519991,"rank":199,"remainingConfigurations":444},{"removed":"gdpval","score":0.1043783624321837,"rank":196,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1048700157697728,"rank":197,"remainingConfigurations":444},{"removed":"gpqa","score":0.09959721051673957,"rank":199,"remainingConfigurations":444},{"removed":"harvey","score":0.10363747234446867,"rank":195,"remainingConfigurations":444},{"removed":"hle","score":0.11163470492269527,"rank":198,"remainingConfigurations":444},{"removed":"ifbench","score":0.10419117943363616,"rank":196,"remainingConfigurations":444},{"removed":"itbench","score":0.10438976897226783,"rank":195,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10510155734186244,"rank":193,"remainingConfigurations":444},{"removed":"math500","score":0.10481813846608985,"rank":196,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.108407435112986,"rank":196,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11190616543117303,"rank":198,"remainingConfigurations":444},{"removed":"omniscience","score":0.10381437053868754,"rank":194,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10390526981355502,"rank":194,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10515688517749437,"rank":198,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10613406437526873,"rank":196,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11653572482428938,"rank":200,"remainingConfigurations":444},{"removed":"deepswe","score":0.08297539610776516,"rank":199,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10481291676760669,"rank":195,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10245528685169336,"rank":198,"remainingConfigurations":444},{"removed":"frontiercode","score":0.1063941722872966,"rank":190,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.1037265598931985,"rank":195,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10367425713399665,"rank":195,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10472060516237947,"rank":195,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10423113719572125,"rank":196,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10906865588863714,"rank":191,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10244018095728974,"rank":199,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10711350738732228,"rank":195,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10545263365148598,"rank":195,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10179014358216833,"rank":198,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10723356714915395,"rank":191,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10033459851570363,"rank":202,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10351672629973489,"rank":200,"remainingConfigurations":444},{"removed":"frontiermath","score":0.1086023634470104,"rank":191,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09799688245907617,"rank":198,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10797388741604376,"rank":199,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10259096079184549,"rank":199,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10615545223572675,"rank":194,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10474594906755715,"rank":195,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10470209595907197,"rank":195,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10279604313034367,"rank":199,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.1039231734893377,"rank":197,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.3--effort-low":{"score":0.10473166973732329,"rank":196,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.13288068686768403,"rank":190,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08400436795675008,"rank":195,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10390492889837492,"rank":195,"remainingConfigurations":444},{"removed":"Scale","score":0.12008734045584958,"rank":195,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10394126275249384,"rank":196,"remainingConfigurations":444},{"removed":"Cognition","score":0.09976546078100969,"rank":196,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10828381083754603,"rank":191,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1076242134957271,"rank":193,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10645816589261381,"rank":190,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10072866249614891,"rank":195,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10469103216278418,"rank":196,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10173697214109982,"rank":196,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10455753685003395,"rank":196,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10473166973732329,"rank":196,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10554522029526865,"rank":195,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1023594348925116,"rank":196,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10553987557351045,"rank":196,"remainingConfigurations":444},{"removed":"briefcase","score":0.10373078580525102,"rank":196,"remainingConfigurations":444},{"removed":"aime","score":0.10517751792224438,"rank":194,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10616826721993265,"rank":195,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09734519734833096,"rank":200,"remainingConfigurations":444},{"removed":"automationbench","score":0.10358606228160971,"rank":197,"remainingConfigurations":444},{"removed":"critpt","score":0.11459393261545198,"rank":184,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10455629422210899,"rank":196,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10652379690466031,"rank":195,"remainingConfigurations":444},{"removed":"gdpval","score":0.10471888271481174,"rank":193,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10548341853995996,"rank":196,"remainingConfigurations":444},{"removed":"gpqa","score":0.10160248175788811,"rank":195,"remainingConfigurations":444},{"removed":"harvey","score":0.1035293242003707,"rank":196,"remainingConfigurations":444},{"removed":"hle","score":0.1183719548837363,"rank":190,"remainingConfigurations":444},{"removed":"ifbench","score":0.08841110402235024,"rank":208,"remainingConfigurations":444},{"removed":"itbench","score":0.10377185104634605,"rank":196,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10487484102599981,"rank":194,"remainingConfigurations":444},{"removed":"math500","score":0.10505647569766897,"rank":195,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10765206605914363,"rank":197,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11213337488577407,"rank":197,"remainingConfigurations":444},{"removed":"omniscience","score":0.1008862833853215,"rank":198,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10297656707381216,"rank":195,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10595840077555634,"rank":195,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11364599770081855,"rank":182,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1291377693558237,"rank":189,"remainingConfigurations":444},{"removed":"deepswe","score":0.08405668562204836,"rank":195,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10475532771684994,"rank":196,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10316398984985814,"rank":195,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09976546078100969,"rank":196,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10349884890212639,"rank":196,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10360319820243523,"rank":196,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10466279354878076,"rank":196,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10429324425351243,"rank":195,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10484126369101654,"rank":196,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10364601622921284,"rank":195,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10625364275439693,"rank":196,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10469758974154907,"rank":196,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10276165059091184,"rank":195,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10408060131188367,"rank":196,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10689132085747181,"rank":195,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1076242134957271,"rank":193,"remainingConfigurations":444},{"removed":"frontiermath","score":0.104846483588129,"rank":195,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09908367805058971,"rank":195,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10951149226667295,"rank":194,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10436991770912646,"rank":195,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10436092748243168,"rank":196,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10438266357599918,"rank":196,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10453943164274405,"rank":196,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10409299092610381,"rank":195,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10445289377220913,"rank":195,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2-flash--effort-reasoning":{"score":0.10443680581397241,"rank":197,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1328979078963435,"rank":189,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08379075475882547,"rank":196,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10354536848312895,"rank":196,"remainingConfigurations":444},{"removed":"Scale","score":0.119653291386557,"rank":196,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10368816184727471,"rank":197,"remainingConfigurations":444},{"removed":"Cognition","score":0.10056752158990356,"rank":195,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10778669209633256,"rank":192,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10672761781273593,"rank":196,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10627903540327761,"rank":191,"remainingConfigurations":431},{"removed":"Vals AI","score":0.10037771006303498,"rank":197,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10439670899201038,"rank":197,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.1014598477264389,"rank":197,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10426791577656952,"rank":197,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10443680581397241,"rank":197,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10523352078517852,"rank":197,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10207154136272999,"rank":197,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.1052115718256243,"rank":197,"remainingConfigurations":444},{"removed":"briefcase","score":0.10363732628553163,"rank":197,"remainingConfigurations":444},{"removed":"aime","score":0.10042108640590904,"rank":200,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10576440502704491,"rank":196,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10328659413530779,"rank":193,"remainingConfigurations":444},{"removed":"automationbench","score":0.10349288718502403,"rank":198,"remainingConfigurations":444},{"removed":"critpt","score":0.09912612679076582,"rank":199,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.1043098735950645,"rank":197,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10631565442835304,"rank":196,"remainingConfigurations":444},{"removed":"gdpval","score":0.10466403101768706,"rank":194,"remainingConfigurations":444},{"removed":"gmmlu","score":0.11181469949300411,"rank":188,"remainingConfigurations":444},{"removed":"gpqa","score":0.10044246516125899,"rank":196,"remainingConfigurations":444},{"removed":"harvey","score":0.10326740087967849,"rank":197,"remainingConfigurations":444},{"removed":"hle","score":0.11358914328610326,"rank":195,"remainingConfigurations":444},{"removed":"ifbench","score":0.10595861828705679,"rank":193,"remainingConfigurations":444},{"removed":"itbench","score":0.10345863954103622,"rank":197,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10112131962435807,"rank":199,"remainingConfigurations":444},{"removed":"math500","score":0.10473435098732746,"rank":197,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10884601842431225,"rank":194,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1121729619816789,"rank":196,"remainingConfigurations":444},{"removed":"omniscience","score":0.10183990719672187,"rank":197,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09759329275304673,"rank":200,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10580837892571476,"rank":196,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.11097397295867227,"rank":187,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12847159602589028,"rank":190,"remainingConfigurations":444},{"removed":"deepswe","score":0.08384434804776449,"rank":196,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10446054899660774,"rank":197,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10277417683336328,"rank":196,"remainingConfigurations":444},{"removed":"frontiercode","score":0.10056752158990356,"rank":195,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10317541554626551,"rank":197,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.1032961183015698,"rank":197,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10436754643773899,"rank":197,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10400025703942174,"rank":197,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10454913381215435,"rank":197,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10335431242669134,"rank":196,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10595335834518797,"rank":197,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10439875316189395,"rank":197,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10247271159096943,"rank":196,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.1037888257877792,"rank":197,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10658980018575832,"rank":196,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10672761781273593,"rank":196,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10458145909573933,"rank":197,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09875274664777738,"rank":196,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10923254650116763,"rank":195,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10407597497211994,"rank":196,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10406640569373334,"rank":197,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10408665582940803,"rank":197,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10424787351720692,"rank":197,"remainingConfigurations":444},{"removed":"vibe-code","score":0.103802911128892,"rank":196,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10415735433240692,"rank":196,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nemotron-3-ultra--effort-reasoning":{"score":0.10405973318641598,"rank":198,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1307060827081018,"rank":192,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0832873312743262,"rank":198,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.1032820183440052,"rank":197,"remainingConfigurations":444},{"removed":"Scale","score":0.11896379685691653,"rank":198,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10317087880200702,"rank":198,"remainingConfigurations":444},{"removed":"Cognition","score":0.09972872122704808,"rank":197,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10754616039938047,"rank":193,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10682316336087853,"rank":195,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10690351860198867,"rank":189,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09995481686404724,"rank":198,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10401937322054737,"rank":198,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10101048896908009,"rank":198,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10389211138505704,"rank":198,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10405973318641598,"rank":198,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10482130335058713,"rank":198,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10159036340946963,"rank":198,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.111053266644546,"rank":189,"remainingConfigurations":444},{"removed":"briefcase","score":0.10129672573356562,"rank":200,"remainingConfigurations":444},{"removed":"aime","score":0.10354279173068147,"rank":197,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10550039081718186,"rank":197,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09641814136892113,"rank":201,"remainingConfigurations":444},{"removed":"automationbench","score":0.11183179414292266,"rank":185,"remainingConfigurations":444},{"removed":"critpt","score":0.10192404050565873,"rank":198,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10940503967760852,"rank":189,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.11108449824161228,"rank":190,"remainingConfigurations":444},{"removed":"gdpval","score":0.10183650253997924,"rank":199,"remainingConfigurations":444},{"removed":"gmmlu","score":0.1044257949522423,"rank":198,"remainingConfigurations":444},{"removed":"gpqa","score":0.0975585723167382,"rank":201,"remainingConfigurations":444},{"removed":"harvey","score":0.10272453893199968,"rank":198,"remainingConfigurations":444},{"removed":"hle","score":0.10862286374744114,"rank":200,"remainingConfigurations":444},{"removed":"ifbench","score":0.09104449407145514,"rank":206,"remainingConfigurations":444},{"removed":"itbench","score":0.10289334730186876,"rank":198,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10372696962559756,"rank":197,"remainingConfigurations":444},{"removed":"math500","score":0.10446740701326845,"rank":198,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10688234792284827,"rank":198,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1109870640967675,"rank":200,"remainingConfigurations":444},{"removed":"omniscience","score":0.10920313866892094,"rank":188,"remainingConfigurations":444},{"removed":"tau-bench","score":0.10477095931352987,"rank":192,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10532988714165363,"rank":197,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10266924965038289,"rank":199,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12655499504073386,"rank":192,"remainingConfigurations":444},{"removed":"deepswe","score":0.08334868553630025,"rank":198,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10408515491344228,"rank":198,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.10273794806783383,"rank":197,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09972872122704808,"rank":197,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10284575472968494,"rank":198,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10291736351814884,"rank":198,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.1039948593182,"rank":198,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10363959619821221,"rank":198,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10415722633288771,"rank":198,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10300154550059355,"rank":197,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10560576350752227,"rank":198,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10403170714393133,"rank":198,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10206577142574719,"rank":197,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10341549000132759,"rank":198,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10619284210036878,"rank":197,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10682316336087853,"rank":195,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10414718692741994,"rank":198,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09919149893167963,"rank":194,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10882650522855437,"rank":196,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10370313165012623,"rank":197,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10369372260356995,"rank":198,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10369662621549504,"rank":198,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.1038853200838375,"rank":198,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10342488783539754,"rank":197,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10378375080793469,"rank":198,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-5--effort-non-reasoning":{"score":0.10367309964846345,"rank":199,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1291574886502129,"rank":195,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08259767016156956,"rank":200,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10292933525593632,"rank":198,"remainingConfigurations":444},{"removed":"Scale","score":0.11796777747274816,"rank":200,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10280877594624638,"rank":199,"remainingConfigurations":444},{"removed":"Cognition","score":0.0987329783047523,"rank":198,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10716145424384915,"rank":195,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1058560628061343,"rank":198,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.1052828952396122,"rank":192,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0994972934952345,"rank":199,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10363177437067345,"rank":199,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.10068616690671593,"rank":199,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10349546440913591,"rank":199,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10367309964846345,"rank":199,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10447401361424502,"rank":199,"remainingConfigurations":444},{"removed":"All provider reports","score":0.10129197390696594,"rank":199,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10468346503052367,"rank":199,"remainingConfigurations":444},{"removed":"briefcase","score":0.10240605000699321,"rank":198,"remainingConfigurations":444},{"removed":"aime","score":0.10399624921324524,"rank":196,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10504756008512213,"rank":199,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.10306643087603486,"rank":194,"remainingConfigurations":444},{"removed":"automationbench","score":0.10261102245341717,"rank":200,"remainingConfigurations":444},{"removed":"critpt","score":0.10512783407182545,"rank":194,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10359882061211213,"rank":198,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10535556890219681,"rank":197,"remainingConfigurations":444},{"removed":"gdpval","score":0.09773212478351158,"rank":202,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10398658565411216,"rank":199,"remainingConfigurations":444},{"removed":"gpqa","score":0.1192017508658894,"rank":175,"remainingConfigurations":444},{"removed":"harvey","score":0.10243130521038253,"rank":199,"remainingConfigurations":444},{"removed":"hle","score":0.11326662083799155,"rank":196,"remainingConfigurations":444},{"removed":"ifbench","score":0.10060086090950433,"rank":198,"remainingConfigurations":444},{"removed":"itbench","score":0.10284563743524368,"rank":199,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10379264633060394,"rank":196,"remainingConfigurations":444},{"removed":"math500","score":0.10385444844435203,"rank":199,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10661374747856399,"rank":199,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.11582379275011367,"rank":190,"remainingConfigurations":444},{"removed":"omniscience","score":0.09672162148690423,"rank":201,"remainingConfigurations":444},{"removed":"tau-bench","score":0.1027023505347352,"rank":196,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.1048542606907133,"rank":199,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09310096431538485,"rank":204,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12586538625934063,"rank":194,"remainingConfigurations":444},{"removed":"deepswe","score":0.08264954821392946,"rank":200,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10369750971380905,"rank":199,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1021877695287819,"rank":199,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0987329783047523,"rank":198,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10243895686239184,"rank":199,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10253234243419607,"rank":199,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10360722538698092,"rank":199,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10322574731127859,"rank":199,"remainingConfigurations":444},{"removed":"livebench-math","score":0.1037828438462497,"rank":199,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10260479939325391,"rank":198,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10518387302710153,"rank":199,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10364260183003192,"rank":199,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10171353389404451,"rank":199,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10302962229505219,"rank":199,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10580621280295867,"rank":198,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1058560628061343,"rank":198,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10364491070638894,"rank":199,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0984237623452654,"rank":197,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10841183877055645,"rank":198,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10331161638392439,"rank":198,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10331095679971562,"rank":199,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10332513083540106,"rank":199,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10348837227200329,"rank":199,"remainingConfigurations":444},{"removed":"vibe-code","score":0.10303986080394871,"rank":198,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10339700078855128,"rank":199,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.6-27b--effort-reasoning":{"score":0.10241108131562011,"rank":200,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1295585890648911,"rank":193,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08184742036707032,"rank":201,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.10163955723041933,"rank":199,"remainingConfigurations":444},{"removed":"Scale","score":0.11726238244199876,"rank":201,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.10150436831371921,"rank":200,"remainingConfigurations":444},{"removed":"Cognition","score":0.09791960686647544,"rank":199,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10607614422773119,"rank":196,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.1049105346880722,"rank":199,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10518356385916726,"rank":193,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09838798091048319,"rank":200,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.10236908169902888,"rank":200,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09942563661944902,"rank":200,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.10223358040232806,"rank":200,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.10241108131562011,"rank":200,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.10319726344498013,"rank":200,"remainingConfigurations":444},{"removed":"All provider reports","score":0.1000166436241585,"rank":200,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.10333027348788987,"rank":200,"remainingConfigurations":444},{"removed":"briefcase","score":0.10179250064079974,"rank":199,"remainingConfigurations":444},{"removed":"aime","score":0.10217197931940654,"rank":199,"remainingConfigurations":444},{"removed":"apex-agents","score":0.10392441946913163,"rank":200,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09520944750574196,"rank":203,"remainingConfigurations":444},{"removed":"automationbench","score":0.10328975825595536,"rank":199,"remainingConfigurations":444},{"removed":"critpt","score":0.10433172952192395,"rank":197,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10238974376916608,"rank":200,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09810064001820795,"rank":202,"remainingConfigurations":444},{"removed":"gdpval","score":0.102226742475384,"rank":198,"remainingConfigurations":444},{"removed":"gmmlu","score":0.10314762934766708,"rank":200,"remainingConfigurations":444},{"removed":"gpqa","score":0.09964263498263093,"rank":198,"remainingConfigurations":444},{"removed":"harvey","score":0.10116206428636439,"rank":200,"remainingConfigurations":444},{"removed":"hle","score":0.11027751654210911,"rank":199,"remainingConfigurations":444},{"removed":"ifbench","score":0.09909627789584967,"rank":200,"remainingConfigurations":444},{"removed":"itbench","score":0.10158334027997275,"rank":200,"remainingConfigurations":444},{"removed":"livecodebench","score":0.10225917761689057,"rank":198,"remainingConfigurations":444},{"removed":"math500","score":0.10268717919521465,"rank":200,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10525724361260765,"rank":200,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10785511143045239,"rank":201,"remainingConfigurations":444},{"removed":"omniscience","score":0.11168605982469736,"rank":183,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09733894845246605,"rank":201,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.10371738925408307,"rank":200,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.10584748504589052,"rank":197,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12547624917191255,"rank":195,"remainingConfigurations":444},{"removed":"deepswe","score":0.08190165472150296,"rank":201,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.10243611249436498,"rank":200,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.1010503899179931,"rank":200,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09791960686647544,"rank":199,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.10119549949901842,"rank":200,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.10128768157288948,"rank":200,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.10234615331655288,"rank":200,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.10195437275015994,"rank":200,"remainingConfigurations":444},{"removed":"livebench-math","score":0.10250929695533806,"rank":200,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.10134985364803921,"rank":200,"remainingConfigurations":444},{"removed":"livebench-language","score":0.10392792369486616,"rank":200,"remainingConfigurations":444},{"removed":"livebench-data","score":0.10238889828312357,"rank":200,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.10045329469563691,"rank":200,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.10176973708231511,"rank":200,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10453137176803179,"rank":199,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.1049105346880722,"rank":199,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10257144771525378,"rank":201,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09755461864867476,"rank":199,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10710427657335075,"rank":200,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.10205666118536429,"rank":200,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.10205006267929324,"rank":200,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.10206141225385945,"rank":200,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.10223122425341435,"rank":200,"remainingConfigurations":444},{"removed":"vibe-code","score":0.1017818672890638,"rank":200,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.10213895273356392,"rank":200,"remainingConfigurations":444}],"sharedOrderConflicts":0},"step-3.7-flash--effort-reasoning":{"score":0.09864501225088051,"rank":201,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.12414712428697385,"rank":199,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07884696420743152,"rank":203,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0978959619506124,"rank":200,"remainingConfigurations":444},{"removed":"Scale","score":0.11285907784697698,"rank":203,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09784877034218387,"rank":201,"remainingConfigurations":444},{"removed":"Cognition","score":0.0948822680484122,"rank":204,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10148963645822635,"rank":198,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10118129408500048,"rank":201,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10041538994355508,"rank":196,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09439733910913804,"rank":202,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09860597773323244,"rank":201,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09568087504413719,"rank":201,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09848523320820284,"rank":201,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09864501225088051,"rank":201,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09937258291575861,"rank":201,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09623490966341597,"rank":201,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09923642955153618,"rank":201,"remainingConfigurations":444},{"removed":"briefcase","score":0.09815718711989063,"rank":201,"remainingConfigurations":444},{"removed":"aime","score":0.09842084326040278,"rank":202,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09847501166461849,"rank":202,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09364443068510593,"rank":206,"remainingConfigurations":444},{"removed":"automationbench","score":0.09768141552640153,"rank":202,"remainingConfigurations":444},{"removed":"critpt","score":0.09707801681882429,"rank":201,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.10201166141610742,"rank":201,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.100289881824887,"rank":201,"remainingConfigurations":444},{"removed":"gdpval","score":0.10105033845416521,"rank":200,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09908417511718964,"rank":201,"remainingConfigurations":444},{"removed":"gpqa","score":0.10032262363375921,"rank":197,"remainingConfigurations":444},{"removed":"harvey","score":0.09738285011955201,"rank":202,"remainingConfigurations":444},{"removed":"hle","score":0.10626809882366976,"rank":203,"remainingConfigurations":444},{"removed":"ifbench","score":0.09554210817701314,"rank":203,"remainingConfigurations":444},{"removed":"itbench","score":0.10043328625936006,"rank":201,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09847098388491422,"rank":200,"remainingConfigurations":444},{"removed":"math500","score":0.09903551516224475,"rank":201,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.10142407255604037,"rank":201,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10202935079815802,"rank":206,"remainingConfigurations":444},{"removed":"omniscience","score":0.0974671290295042,"rank":200,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09337494581169543,"rank":203,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09983408892895869,"rank":202,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0998586885198669,"rank":200,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1201564402949205,"rank":198,"remainingConfigurations":444},{"removed":"deepswe","score":0.07890566236955458,"rank":203,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09866723871876486,"rank":201,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0972726698189955,"rank":201,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0948822680484122,"rank":204,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09745629000507851,"rank":201,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0975600970631126,"rank":201,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09858091286672926,"rank":201,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09821794732368706,"rank":201,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09874451049490517,"rank":201,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.097652729210091,"rank":201,"remainingConfigurations":444},{"removed":"livebench-language","score":0.1001187795948474,"rank":201,"remainingConfigurations":444},{"removed":"livebench-data","score":0.098588650579438,"rank":201,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.09675659599539044,"rank":201,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09803285091977994,"rank":201,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10067089608181934,"rank":200,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10118129408500048,"rank":201,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09877530003696584,"rank":202,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09371017366725161,"rank":201,"remainingConfigurations":444},{"removed":"simpleqa","score":0.1032177352652709,"rank":201,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0983021984374479,"rank":201,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09829017666350522,"rank":201,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09830012563538948,"rank":201,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09847382986478277,"rank":201,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09804813945155992,"rank":201,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09837872701534511,"rank":201,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v3.2-speciale--effort-reasoning":{"score":0.09845190321497826,"rank":202,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1255515161722708,"rank":198,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0788901640634019,"rank":202,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09754053473023538,"rank":201,"remainingConfigurations":444},{"removed":"Scale","score":0.11292770165892692,"rank":202,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09773180678203021,"rank":202,"remainingConfigurations":444},{"removed":"Cognition","score":0.09509903547265708,"rank":202,"remainingConfigurations":444},{"removed":"LiveBench","score":0.10167845110395511,"rank":197,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.10085208302763578,"rank":202,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09955629176006586,"rank":197,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09460594261131001,"rank":201,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09841395257789953,"rank":202,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09561955352362178,"rank":202,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09829105865166225,"rank":202,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09845190321497826,"rank":202,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0991969421969584,"rank":202,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09618877239637792,"rank":202,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09920619643183255,"rank":202,"remainingConfigurations":444},{"removed":"briefcase","score":0.09783274731841497,"rank":202,"remainingConfigurations":444},{"removed":"aime","score":0.09351473037694528,"rank":205,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09978925753889217,"rank":201,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09801428508582731,"rank":199,"remainingConfigurations":444},{"removed":"automationbench","score":0.09768208655531685,"rank":201,"remainingConfigurations":444},{"removed":"critpt","score":0.0903668222211933,"rank":211,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09843104218499064,"rank":202,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.10032858005428846,"rank":200,"remainingConfigurations":444},{"removed":"gdpval","score":0.09866946031829804,"rank":201,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09614826653822561,"rank":203,"remainingConfigurations":444},{"removed":"gpqa","score":0.09090556140271584,"rank":206,"remainingConfigurations":444},{"removed":"harvey","score":0.0974126973891259,"rank":201,"remainingConfigurations":444},{"removed":"hle","score":0.10192559682493507,"rank":205,"remainingConfigurations":444},{"removed":"ifbench","score":0.09915855992855661,"rank":199,"remainingConfigurations":444},{"removed":"itbench","score":0.09762145913665021,"rank":202,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09289266829267114,"rank":205,"remainingConfigurations":444},{"removed":"math500","score":0.09852427676772946,"rank":202,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09828626354737645,"rank":204,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10549503997667607,"rank":202,"remainingConfigurations":444},{"removed":"omniscience","score":0.0832764289618463,"rank":208,"remainingConfigurations":444},{"removed":"tau-bench","score":0.15458295033181146,"rank":161,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0998409191664531,"rank":201,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0976013903254172,"rank":201,"remainingConfigurations":444},{"removed":"arc-agi","score":0.12130269895435476,"rank":197,"remainingConfigurations":444},{"removed":"deepswe","score":0.0789425066351431,"rank":202,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09847471360447553,"rank":202,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.09687119447136609,"rank":202,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09509903547265708,"rank":202,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09723269646651261,"rank":202,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.09736027992257446,"rank":202,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09838732267649376,"rank":202,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0980356376282579,"rank":202,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09855938451390232,"rank":202,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.09742051755848863,"rank":202,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09990072601810555,"rank":202,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09841489692513317,"rank":202,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.096576200321101,"rank":202,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09783364744305906,"rank":202,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.10050751489043115,"rank":201,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.10085208302763578,"rank":202,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09868502522065857,"rank":203,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09298456978968439,"rank":203,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10303688309044727,"rank":202,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0981064711572791,"rank":202,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09809815499522602,"rank":202,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0981171806084104,"rank":202,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09827187553417764,"rank":202,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09784744759896265,"rank":202,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09818484404550659,"rank":202,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-6--effort-non-reasoning":{"score":0.09618606768230231,"rank":203,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0801767632499897,"rank":151,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.10260526817668501,"rank":213,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07740380720975182,"rank":204,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0958067274369276,"rank":203,"remainingConfigurations":444},{"removed":"Scale","score":0.12329717544602271,"rank":191,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09447132527078468,"rank":203,"remainingConfigurations":444},{"removed":"Cognition","score":0.08986454663579092,"rank":206,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09970957736464038,"rank":199,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09766534862921793,"rank":204,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09559850482748118,"rank":198,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09140646355793448,"rank":203,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09613467212835736,"rank":203,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09371609359757137,"rank":204,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0960180117118763,"rank":204,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09618606768230231,"rank":203,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09681894758033711,"rank":203,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09415168035648847,"rank":204,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09681143825068002,"rank":203,"remainingConfigurations":444},{"removed":"briefcase","score":0.0957715341988914,"rank":204,"remainingConfigurations":444},{"removed":"aime","score":0.09650145763640293,"rank":203,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09713135277466069,"rank":204,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09805571747848617,"rank":198,"remainingConfigurations":444},{"removed":"automationbench","score":0.09590368945626426,"rank":204,"remainingConfigurations":444},{"removed":"critpt","score":0.0945697991234649,"rank":204,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09614703311033844,"rank":204,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09782190862969431,"rank":205,"remainingConfigurations":444},{"removed":"gdpval","score":0.09662896193829483,"rank":203,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09058092121584599,"rank":209,"remainingConfigurations":444},{"removed":"gpqa","score":0.09490735842224496,"rank":202,"remainingConfigurations":444},{"removed":"harvey","score":0.09524361151530751,"rank":203,"remainingConfigurations":444},{"removed":"hle","score":0.12059294518906537,"rank":188,"remainingConfigurations":444},{"removed":"ifbench","score":0.10783701857810472,"rank":191,"remainingConfigurations":444},{"removed":"itbench","score":0.09560353090581448,"rank":204,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09641632119864647,"rank":202,"remainingConfigurations":444},{"removed":"math500","score":0.0961995356295573,"rank":204,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09914244010389132,"rank":203,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10374138151062372,"rank":205,"remainingConfigurations":444},{"removed":"omniscience","score":0.08288088354979907,"rank":209,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09726993003687279,"rank":202,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09716837266405036,"rank":203,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09049552686823524,"rank":209,"remainingConfigurations":444},{"removed":"arc-agi","score":0.09933355946411247,"rank":214,"remainingConfigurations":444},{"removed":"deepswe","score":0.07745127608306875,"rank":204,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09620462790297137,"rank":203,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0945242369657151,"rank":204,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08986454663579092,"rank":206,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08973736323163307,"rank":208,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.09545672035857478,"rank":203,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09575622479721192,"rank":204,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09593113064002856,"rank":203,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0961364399273749,"rank":204,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.09485843616772897,"rank":204,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09747877500466716,"rank":203,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09625647076134503,"rank":204,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.09487872108738987,"rank":203,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09569343545991997,"rank":203,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09803905271113261,"rank":204,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09766534862921793,"rank":204,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09617941473971559,"rank":204,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09120989867678786,"rank":204,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10015815444592076,"rank":204,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.09588256680500327,"rank":203,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09587610214504204,"rank":203,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09589061169291145,"rank":203,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09600916111684198,"rank":203,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09562579729775746,"rank":203,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09595497183161948,"rank":203,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-pro-0424--effort-high":{"score":0.0961153034618835,"rank":204,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04114238479154921,"rank":166,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11084646619123512,"rank":210,"remainingConfigurations":444},{"removed":"Datacurve","score":0.08803817714398438,"rank":188,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09584181754169069,"rank":202,"remainingConfigurations":444},{"removed":"Scale","score":0.10983371513969196,"rank":204,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09422172407833596,"rank":204,"remainingConfigurations":444},{"removed":"Cognition","score":0.09647917142191127,"rank":200,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09899281279216765,"rank":200,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.2247324509153393,"rank":134,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.10218500488924935,"rank":194,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09111657693252012,"rank":204,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.096092123951371,"rank":204,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09436787751303592,"rank":203,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09603776282567754,"rank":203,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0961153034618835,"rank":204,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09652759044414429,"rank":204,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09469106422431971,"rank":203,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09673576834396364,"rank":204,"remainingConfigurations":444},{"removed":"briefcase","score":0.09658520325539915,"rank":203,"remainingConfigurations":444},{"removed":"aime","score":0.09555358488822367,"rank":204,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09736832937470936,"rank":203,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09899435575337161,"rank":197,"remainingConfigurations":444},{"removed":"automationbench","score":0.09655592004066792,"rank":203,"remainingConfigurations":444},{"removed":"critpt","score":0.09430789210654626,"rank":205,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09647035734785757,"rank":203,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09800541591822982,"rank":203,"remainingConfigurations":444},{"removed":"gdpval","score":0.09325049864767203,"rank":206,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09705790464138574,"rank":202,"remainingConfigurations":444},{"removed":"gpqa","score":0.0929702200488678,"rank":204,"remainingConfigurations":444},{"removed":"harvey","score":0.09501755919138886,"rank":204,"remainingConfigurations":444},{"removed":"hle","score":0.10185076271186795,"rank":206,"remainingConfigurations":444},{"removed":"ifbench","score":0.09604581049439066,"rank":202,"remainingConfigurations":444},{"removed":"itbench","score":0.09589432709630845,"rank":203,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09666203538953862,"rank":201,"remainingConfigurations":444},{"removed":"math500","score":0.09640810317467945,"rank":203,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09928286951533495,"rank":202,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10404320981918126,"rank":204,"remainingConfigurations":444},{"removed":"omniscience","score":0.09226392165186481,"rank":204,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09318231798759612,"rank":204,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09678553637124228,"rank":204,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09416239862260456,"rank":202,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1094487569377751,"rank":207,"remainingConfigurations":444},{"removed":"deepswe","score":0.08801496446487915,"rank":188,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09611509099590893,"rank":204,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.09517491755728424,"rank":203,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09647917142191127,"rank":200,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09591962326200239,"rank":203,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0936638607556075,"rank":204,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09624271193873583,"rank":203,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09588850036918828,"rank":204,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09622577312308568,"rank":203,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.094919416778858,"rank":203,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0972402502746448,"rank":204,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09632779918308336,"rank":203,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.094393985244395,"rank":204,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09530295770952141,"rank":204,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09847766712243526,"rank":203,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.2247324509153393,"rank":134,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09598218359639159,"rank":205,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.09298973604957739,"rank":202,"remainingConfigurations":444},{"removed":"simpleqa","score":0.10048962796564825,"rank":203,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0957921028444574,"rank":204,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09579947953812977,"rank":204,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0957639596466135,"rank":204,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09595328447538003,"rank":204,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09557175675827141,"rank":204,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09580952995427111,"rank":204,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-397b-a17b--effort-non-reasoning":{"score":0.0943903647858945,"rank":205,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1416792884903578,"rank":129,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11667762313482292,"rank":203,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07543432988477107,"rank":205,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09381320550865892,"rank":205,"remainingConfigurations":444},{"removed":"Scale","score":0.10745506076644867,"rank":205,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09413568976281972,"rank":205,"remainingConfigurations":444},{"removed":"Cognition","score":0.09346222422635342,"rank":205,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09701934237209488,"rank":201,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09583516955916793,"rank":205,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.062374051261404655,"rank":224,"remainingConfigurations":431},{"removed":"Vals AI","score":0.09017693615453666,"rank":205,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09436271667477288,"rank":205,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09180668825179374,"rank":206,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09428404493458592,"rank":205,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0943903647858945,"rank":205,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09504119152228252,"rank":205,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09234612168532437,"rank":206,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09488083450283386,"rank":205,"remainingConfigurations":444},{"removed":"briefcase","score":0.09352384110666428,"rank":206,"remainingConfigurations":444},{"removed":"aime","score":0.09253632183537135,"rank":206,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09537606763945546,"rank":206,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09414241921953831,"rank":205,"remainingConfigurations":444},{"removed":"automationbench","score":0.09347631647577148,"rank":207,"remainingConfigurations":444},{"removed":"critpt","score":0.09383335146068646,"rank":208,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09424239325984801,"rank":206,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09541207587147749,"rank":208,"remainingConfigurations":444},{"removed":"gdpval","score":0.09348872806693409,"rank":204,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09308454363923026,"rank":205,"remainingConfigurations":444},{"removed":"gpqa","score":0.08208840018823219,"rank":213,"remainingConfigurations":444},{"removed":"harvey","score":0.09324271171058772,"rank":205,"remainingConfigurations":444},{"removed":"hle","score":0.09980431144617553,"rank":208,"remainingConfigurations":444},{"removed":"ifbench","score":0.09743404489692087,"rank":201,"remainingConfigurations":444},{"removed":"itbench","score":0.09365874282318888,"rank":206,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09393544771872293,"rank":204,"remainingConfigurations":444},{"removed":"math500","score":0.09450846594395391,"rank":205,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09673262931557558,"rank":206,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1159521868112303,"rank":189,"remainingConfigurations":444},{"removed":"omniscience","score":0.09094858157053154,"rank":205,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09144763229763893,"rank":207,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09534426114727146,"rank":205,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0909268979569462,"rank":208,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11281283220915139,"rank":202,"remainingConfigurations":444},{"removed":"deepswe","score":0.07549610499523392,"rank":205,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09440997110736245,"rank":205,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.09314248890581002,"rank":205,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09346222422635342,"rank":205,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09330806212297355,"rank":205,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.09325877813955934,"rank":205,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09433750992966634,"rank":205,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09401072016303587,"rank":205,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09458609191719257,"rank":206,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.09324674058092114,"rank":205,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09573714156661593,"rank":205,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0944434665130906,"rank":205,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0926374086985497,"rank":206,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09378991483800268,"rank":205,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09633588901840151,"rank":205,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09583516955916793,"rank":205,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10467845377034246,"rank":196,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08361158883635865,"rank":210,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09784719980085627,"rank":205,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0940430923330605,"rank":205,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09407882283445673,"rank":205,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09402842658977044,"rank":205,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09424056957475602,"rank":205,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0938548202517168,"rank":205,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09412732171569495,"rank":205,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-flash-lite--effort-high":{"score":0.09430747410987834,"rank":206,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0901632655373079,"rank":148,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.12039186258442552,"rank":201,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07503613657414394,"rank":206,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09404138538538565,"rank":204,"remainingConfigurations":444},{"removed":"Scale","score":0.10702343800073065,"rank":206,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09394977354254548,"rank":206,"remainingConfigurations":444},{"removed":"Cognition","score":0.09546694312239329,"rank":201,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0935542525352855,"rank":206,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09550234715042562,"rank":206,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08975889769102029,"rank":206,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09428236878356444,"rank":206,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.09187892419948207,"rank":205,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09424468396730613,"rank":206,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09430747410987834,"rank":206,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0949005448893367,"rank":206,"remainingConfigurations":444},{"removed":"All provider reports","score":0.09240693959326235,"rank":205,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0948108040098934,"rank":206,"remainingConfigurations":444},{"removed":"briefcase","score":0.09391901957465214,"rank":205,"remainingConfigurations":444},{"removed":"aime","score":0.07910016275302954,"rank":216,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09527468835491333,"rank":207,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09472324566554922,"rank":204,"remainingConfigurations":444},{"removed":"automationbench","score":0.093997788000011,"rank":205,"remainingConfigurations":444},{"removed":"critpt","score":0.09390208214797931,"rank":207,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09439724921016851,"rank":205,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09522526813458303,"rank":209,"remainingConfigurations":444},{"removed":"gdpval","score":0.09331471228038334,"rank":205,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09485233246042546,"rank":204,"remainingConfigurations":444},{"removed":"gpqa","score":0.10801621410474839,"rank":190,"remainingConfigurations":444},{"removed":"harvey","score":0.09313019395995605,"rank":206,"remainingConfigurations":444},{"removed":"hle","score":0.100725919233788,"rank":207,"remainingConfigurations":444},{"removed":"ifbench","score":0.09512489507221496,"rank":204,"remainingConfigurations":444},{"removed":"itbench","score":0.09379210243223546,"rank":205,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09436212436284751,"rank":203,"remainingConfigurations":444},{"removed":"math500","score":0.09447012444192371,"rank":206,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09742314249310874,"rank":205,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.10092968419777508,"rank":207,"remainingConfigurations":444},{"removed":"omniscience","score":0.09281845392342568,"rank":203,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09068469609849668,"rank":209,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09503234412259863,"rank":206,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09381556714811938,"rank":203,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11723911213008847,"rank":199,"remainingConfigurations":444},{"removed":"deepswe","score":0.07510882359957964,"rank":206,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09432652663917968,"rank":206,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.09296863125544408,"rank":206,"remainingConfigurations":444},{"removed":"frontiercode","score":0.09546694312239329,"rank":201,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09333228880751145,"rank":204,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.09314724178340911,"rank":206,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09425826053149906,"rank":206,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09392249216729477,"rank":206,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09464228097039834,"rank":205,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.09294580344810315,"rank":206,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09562902467849237,"rank":206,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09437898892121051,"rank":206,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0926669886644705,"rank":205,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09365949365554725,"rank":206,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09626426250830643,"rank":206,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09550234715042562,"rank":206,"remainingConfigurations":444},{"removed":"frontiermath","score":0.10488937101886357,"rank":194,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06858011253468689,"rank":223,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09665037627926036,"rank":206,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.09395009346937966,"rank":206,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09402237395771242,"rank":206,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09392800568097108,"rank":206,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09417738668728325,"rank":206,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09379928895431518,"rank":206,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09401930823210031,"rank":206,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2.5--effort-reasoning":{"score":0.09132497515670569,"rank":207,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11615162433687963,"rank":204,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0727825482849132,"rank":207,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09057320591343049,"rank":206,"remainingConfigurations":444},{"removed":"Scale","score":0.10488904784842963,"rank":207,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.09050427688377694,"rank":207,"remainingConfigurations":444},{"removed":"Cognition","score":0.08767331541734719,"rank":207,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09457325785105715,"rank":202,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09363161600418925,"rank":207,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09343969519664165,"rank":201,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08758107691906476,"rank":207,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09128764172701986,"rank":207,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08861517324896025,"rank":207,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09116618314185072,"rank":207,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09132497515670569,"rank":207,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09202203628136839,"rank":207,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08913815909524996,"rank":207,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09198666346089608,"rank":208,"remainingConfigurations":444},{"removed":"briefcase","score":0.09084470010734619,"rank":209,"remainingConfigurations":444},{"removed":"aime","score":0.09101027927948191,"rank":208,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09270892231253226,"rank":208,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08710022612213142,"rank":211,"remainingConfigurations":444},{"removed":"automationbench","score":0.08784010384669894,"rank":210,"remainingConfigurations":444},{"removed":"critpt","score":0.08741915169726434,"rank":213,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09119763102348362,"rank":207,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09797636466543407,"rank":204,"remainingConfigurations":444},{"removed":"gdpval","score":0.08931223306722981,"rank":209,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09190051269154915,"rank":206,"remainingConfigurations":444},{"removed":"gpqa","score":0.08614673665520008,"rank":209,"remainingConfigurations":444},{"removed":"harvey","score":0.09022302536779814,"rank":207,"remainingConfigurations":444},{"removed":"hle","score":0.0960217068520139,"rank":211,"remainingConfigurations":444},{"removed":"ifbench","score":0.08804105646466177,"rank":209,"remainingConfigurations":444},{"removed":"itbench","score":0.09052580423112543,"rank":208,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0910717791025545,"rank":207,"remainingConfigurations":444},{"removed":"math500","score":0.09164861210780074,"rank":207,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09388969538570051,"rank":207,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09385533797015493,"rank":212,"remainingConfigurations":444},{"removed":"omniscience","score":0.10638822295813473,"rank":191,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09235590138354943,"rank":205,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09251384937728642,"rank":207,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09037384919630871,"rank":210,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11229617133258539,"rank":203,"remainingConfigurations":444},{"removed":"deepswe","score":0.0728327886187843,"rank":207,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09134764906798004,"rank":207,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.09006639805409729,"rank":207,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08767331541734719,"rank":207,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.09020078553432165,"rank":206,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.09030154590600083,"rank":207,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09126859136320058,"rank":207,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09091429703032892,"rank":207,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09141728606581234,"rank":207,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0903594653598775,"rank":207,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09270759109550518,"rank":207,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09130099264859308,"rank":207,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08954175764317863,"rank":207,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09074049040174675,"rank":207,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09325932177123773,"rank":207,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09363161600418925,"rank":207,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09143986079164988,"rank":207,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08661127475500573,"rank":205,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09561910886083246,"rank":207,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.09099990372601656,"rank":207,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09099486413770878,"rank":207,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0910061890634261,"rank":207,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09115992343271546,"rank":207,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09075313078158598,"rank":207,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09107622766890429,"rank":207,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5v-turbo--effort-reasoning":{"score":0.09088045925744366,"rank":208,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11565469805785483,"rank":205,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07250366293084344,"rank":208,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.09010621812191695,"rank":207,"remainingConfigurations":444},{"removed":"Scale","score":0.10455806705232605,"rank":208,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0901492220650737,"rank":208,"remainingConfigurations":444},{"removed":"Cognition","score":0.08751861845598967,"rank":208,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09396797098421232,"rank":204,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09309613823985141,"rank":208,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09213630723537242,"rank":203,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08723356062936967,"rank":208,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09084462595855529,"rank":208,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08821228266225094,"rank":208,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09072680858044996,"rank":208,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09088045925744366,"rank":208,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09158397843590109,"rank":208,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08874731481322173,"rank":208,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0915450920298329,"rank":209,"remainingConfigurations":444},{"removed":"briefcase","score":0.09009172470610399,"rank":210,"remainingConfigurations":444},{"removed":"aime","score":0.09125951411442546,"rank":207,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09204079652199999,"rank":209,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08935747808589213,"rank":207,"remainingConfigurations":444},{"removed":"automationbench","score":0.08998248623283413,"rank":208,"remainingConfigurations":444},{"removed":"critpt","score":0.09699884843712629,"rank":202,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0906588864874367,"rank":208,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0925290780801593,"rank":212,"remainingConfigurations":444},{"removed":"gdpval","score":0.09081436994326442,"rank":207,"remainingConfigurations":444},{"removed":"gmmlu","score":0.09178853551892609,"rank":207,"remainingConfigurations":444},{"removed":"gpqa","score":0.09375034962170292,"rank":203,"remainingConfigurations":444},{"removed":"harvey","score":0.08983745880612694,"rank":208,"remainingConfigurations":444},{"removed":"hle","score":0.10236646756308805,"rank":204,"remainingConfigurations":444},{"removed":"ifbench","score":0.09323681460488219,"rank":205,"remainingConfigurations":444},{"removed":"itbench","score":0.0900906666525522,"rank":209,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09103293237697706,"rank":208,"remainingConfigurations":444},{"removed":"math500","score":0.09123109361541303,"rank":208,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09362869303159706,"rank":208,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09653029432859522,"rank":211,"remainingConfigurations":444},{"removed":"omniscience","score":0.08154048795067877,"rank":211,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07813070462478942,"rank":216,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09207739536146359,"rank":208,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09120275565803086,"rank":206,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11185253687725381,"rank":204,"remainingConfigurations":444},{"removed":"deepswe","score":0.07255084300168717,"rank":208,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09090157282991873,"rank":208,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08948355605846185,"rank":209,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08751861845598967,"rank":208,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08975028872174451,"rank":207,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0898719619684506,"rank":208,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09082158693876219,"rank":208,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09049216194926042,"rank":208,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09097895836212733,"rank":208,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08990965705357758,"rank":208,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09224075658184949,"rank":208,"remainingConfigurations":444},{"removed":"livebench-data","score":0.09085166881363003,"rank":208,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0891213148847144,"rank":208,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0902988394759297,"rank":208,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09281271549666907,"rank":208,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09309613823985141,"rank":208,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09108264425918973,"rank":208,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08588328229371694,"rank":207,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09516623751428026,"rank":208,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.09055798107209839,"rank":208,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09054870603962313,"rank":208,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09056751917918561,"rank":208,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09070925438441502,"rank":208,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0903126371556885,"rank":208,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09063164512787247,"rank":208,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m2.7--effort-reasoning":{"score":0.09067310873728786,"rank":209,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11442192974662142,"rank":206,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07222947552273354,"rank":209,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.08999666091306859,"rank":208,"remainingConfigurations":444},{"removed":"Scale","score":0.10407757438881182,"rank":209,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08984587628052604,"rank":209,"remainingConfigurations":444},{"removed":"Cognition","score":0.08695685399756682,"rank":209,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09364018110213362,"rank":205,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09306576188410225,"rank":209,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09313606847921006,"rank":202,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08677253108601268,"rank":209,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.09063422540448479,"rank":209,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08791963572796362,"rank":209,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.09051942219993074,"rank":209,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.09067310873728786,"rank":209,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.09134688816083004,"rank":209,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08842421163748419,"rank":209,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.09214115768301935,"rank":207,"remainingConfigurations":444},{"removed":"briefcase","score":0.09127960642449932,"rank":208,"remainingConfigurations":444},{"removed":"aime","score":0.09023437998353766,"rank":209,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0968397255905342,"rank":205,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08751194935948836,"rank":210,"remainingConfigurations":444},{"removed":"automationbench","score":0.09382655715677841,"rank":206,"remainingConfigurations":444},{"removed":"critpt","score":0.09417929429051175,"rank":206,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.09041979730349292,"rank":209,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0940727713164401,"rank":210,"remainingConfigurations":444},{"removed":"gdpval","score":0.08836800153521156,"rank":211,"remainingConfigurations":444},{"removed":"gmmlu","score":0.090990197481566,"rank":208,"remainingConfigurations":444},{"removed":"gpqa","score":0.08361507099941612,"rank":211,"remainingConfigurations":444},{"removed":"harvey","score":0.08958294828627235,"rank":209,"remainingConfigurations":444},{"removed":"hle","score":0.09300626028727038,"rank":213,"remainingConfigurations":444},{"removed":"ifbench","score":0.08089864823524524,"rank":214,"remainingConfigurations":444},{"removed":"itbench","score":0.09360826546588852,"rank":207,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09047277174798901,"rank":209,"remainingConfigurations":444},{"removed":"math500","score":0.09104504739443409,"rank":209,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09330661972286523,"rank":209,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09698541572599206,"rank":210,"remainingConfigurations":444},{"removed":"omniscience","score":0.08825998705720384,"rank":207,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09225948266058387,"rank":206,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0919205005911334,"rank":209,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09114301797149055,"rank":207,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11071693781106327,"rank":206,"remainingConfigurations":444},{"removed":"deepswe","score":0.07228423381381376,"rank":209,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.09069499059774765,"rank":209,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08949931371851105,"rank":208,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08695685399756682,"rank":209,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08956287687803328,"rank":209,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.08966466306434617,"rank":209,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.09061608565860159,"rank":209,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.09027838892667926,"rank":209,"remainingConfigurations":444},{"removed":"livebench-math","score":0.09076043599101423,"rank":209,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0897385909827421,"rank":209,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09205818089364942,"rank":209,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0906303073322773,"rank":209,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08889678276227253,"rank":209,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.09010029155326436,"rank":209,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09257833736194587,"rank":209,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09306576188410225,"rank":209,"remainingConfigurations":444},{"removed":"frontiermath","score":0.09073729696055921,"rank":209,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08631606702738137,"rank":206,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09495392514013139,"rank":209,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.09035611793316757,"rank":209,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.09033995352742503,"rank":209,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.09035054976390063,"rank":209,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.09051209727436936,"rank":209,"remainingConfigurations":444},{"removed":"vibe-code","score":0.09011286661187863,"rank":209,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.09042297764724738,"rank":209,"remainingConfigurations":444}],"sharedOrderConflicts":1},"claude-sonnet-4-5-20250929--effort-reasoning":{"score":0.08886774659080754,"rank":210,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11289096353531808,"rank":207,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07072518615441319,"rank":210,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0880609432678604,"rank":209,"remainingConfigurations":444},{"removed":"Scale","score":0.10216160875089586,"rank":210,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08806225900087329,"rank":210,"remainingConfigurations":444},{"removed":"Cognition","score":0.08525394332546304,"rank":210,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09189813930183756,"rank":207,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09097151433487131,"rank":210,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.09027660766267027,"rank":205,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0851016050296442,"rank":210,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0888315857316865,"rank":210,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08621953383178349,"rank":210,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08871671667517306,"rank":210,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.08886774659080754,"rank":210,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08954870723449293,"rank":210,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08673459300422799,"rank":210,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08960127413676378,"rank":210,"remainingConfigurations":444},{"removed":"briefcase","score":0.08916779131293455,"rank":211,"remainingConfigurations":444},{"removed":"aime","score":0.08854240361514737,"rank":210,"remainingConfigurations":444},{"removed":"apex-agents","score":0.09011590360343895,"rank":210,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08538624405726952,"rank":212,"remainingConfigurations":444},{"removed":"automationbench","score":0.08646027241622224,"rank":211,"remainingConfigurations":444},{"removed":"critpt","score":0.08903754161967109,"rank":212,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08880556800861433,"rank":210,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09280509454355168,"rank":211,"remainingConfigurations":444},{"removed":"gdpval","score":0.08894400030955757,"rank":210,"remainingConfigurations":444},{"removed":"gmmlu","score":0.08544314928302506,"rank":211,"remainingConfigurations":444},{"removed":"gpqa","score":0.08656037359264725,"rank":208,"remainingConfigurations":444},{"removed":"harvey","score":0.08786852112333536,"rank":210,"remainingConfigurations":444},{"removed":"hle","score":0.09765802499515823,"rank":210,"remainingConfigurations":444},{"removed":"ifbench","score":0.08974043966420485,"rank":207,"remainingConfigurations":444},{"removed":"itbench","score":0.08811571364240867,"rank":210,"remainingConfigurations":444},{"removed":"livecodebench","score":0.09277981575243793,"rank":206,"remainingConfigurations":444},{"removed":"math500","score":0.08917993778631012,"rank":210,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.08922713263902014,"rank":211,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09929847486654926,"rank":208,"remainingConfigurations":444},{"removed":"omniscience","score":0.08167807777319935,"rank":210,"remainingConfigurations":444},{"removed":"tau-bench","score":0.08504618251313834,"rank":210,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.09008113883094875,"rank":210,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09018594946538183,"rank":211,"remainingConfigurations":444},{"removed":"arc-agi","score":0.10919030555505356,"rank":208,"remainingConfigurations":444},{"removed":"deepswe","score":0.07077370452472413,"rank":210,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.08888983831007911,"rank":210,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08756732793250827,"rank":210,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08525394332546304,"rank":210,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0877607729542574,"rank":210,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.08787199784545502,"rank":210,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08881245903411915,"rank":210,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08846982372002886,"rank":210,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0889609692524637,"rank":210,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08792329944842747,"rank":210,"remainingConfigurations":444},{"removed":"livebench-language","score":0.09021604187778158,"rank":210,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08883986869974557,"rank":210,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08712759429203408,"rank":210,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.08829746382037183,"rank":210,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09076008273432656,"rank":210,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09097151433487131,"rank":210,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08899436311727875,"rank":210,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08415836111434162,"rank":208,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09307718883291816,"rank":210,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08854869518529306,"rank":210,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.08854443885685893,"rank":210,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08855684591561312,"rank":210,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.08870561145740735,"rank":210,"remainingConfigurations":444},{"removed":"vibe-code","score":0.08830917040621576,"rank":210,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08862367294392366,"rank":210,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-122b-a10b--effort-reasoning":{"score":0.08822589639702975,"rank":211,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1121010294622413,"rank":208,"remainingConfigurations":444},{"removed":"Datacurve","score":0.07024934399235334,"rank":211,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.08754849868520699,"rank":210,"remainingConfigurations":444},{"removed":"Scale","score":0.10158499175092887,"rank":211,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08741088102206951,"rank":211,"remainingConfigurations":444},{"removed":"Cognition","score":0.08456658182315539,"rank":211,"remainingConfigurations":444},{"removed":"LiveBench","score":0.09121739058352472,"rank":208,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.09053056775075297,"rank":211,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.090500297239128,"rank":204,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0845764652052118,"rank":211,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0881892410889296,"rank":211,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08559023855379266,"rank":211,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08807246291349725,"rank":211,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.08822589639702975,"rank":211,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08891074322952619,"rank":211,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08610592251073451,"rank":211,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08872417235382286,"rank":211,"remainingConfigurations":444},{"removed":"briefcase","score":0.09261672520943086,"rank":207,"remainingConfigurations":444},{"removed":"aime","score":0.08835691269808721,"rank":211,"remainingConfigurations":444},{"removed":"apex-agents","score":0.08937330993061295,"rank":211,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08229151326486324,"rank":214,"remainingConfigurations":444},{"removed":"automationbench","score":0.08952470183344167,"rank":209,"remainingConfigurations":444},{"removed":"critpt","score":0.09183486509893544,"rank":209,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08793434001054638,"rank":211,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09661343222857673,"rank":206,"remainingConfigurations":444},{"removed":"gdpval","score":0.08937060121908681,"rank":208,"remainingConfigurations":444},{"removed":"gmmlu","score":0.08528520360605844,"rank":212,"remainingConfigurations":444},{"removed":"gpqa","score":0.08333617391557424,"rank":212,"remainingConfigurations":444},{"removed":"harvey","score":0.0870955948268217,"rank":211,"remainingConfigurations":444},{"removed":"hle","score":0.0939526481976564,"rank":212,"remainingConfigurations":444},{"removed":"ifbench","score":0.07976014969586537,"rank":217,"remainingConfigurations":444},{"removed":"itbench","score":0.08729890020195262,"rank":211,"remainingConfigurations":444},{"removed":"livecodebench","score":0.08844285687465847,"rank":210,"remainingConfigurations":444},{"removed":"math500","score":0.08861002753890079,"rank":211,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.09110026277755102,"rank":210,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09163118824010967,"rank":213,"remainingConfigurations":444},{"removed":"omniscience","score":0.0882867969544709,"rank":206,"remainingConfigurations":444},{"removed":"tau-bench","score":0.08410819655424367,"rank":211,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.08934479209020742,"rank":211,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.09255213468060414,"rank":205,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1084122099140552,"rank":209,"remainingConfigurations":444},{"removed":"deepswe","score":0.07029668670738448,"rank":211,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.08824774313939177,"rank":211,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08699354898175939,"rank":211,"remainingConfigurations":444},{"removed":"frontiercode","score":0.08456658182315539,"rank":211,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0871400787243054,"rank":211,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0872485416039127,"rank":211,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08817047028537851,"rank":211,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08783122028346964,"rank":211,"remainingConfigurations":444},{"removed":"livebench-math","score":0.08831511180611905,"rank":211,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08728129990690918,"rank":211,"remainingConfigurations":444},{"removed":"livebench-language","score":0.08956894232178479,"rank":211,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08820401034699288,"rank":211,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08649362605030753,"rank":211,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.08765684258086119,"rank":211,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.09011355273149524,"rank":211,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.09053056775075297,"rank":211,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08833568582635896,"rank":211,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08370821677039043,"rank":209,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09240296949007674,"rank":211,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08791110429016401,"rank":211,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0879039326964952,"rank":211,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08791699020950373,"rank":211,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0880632595546137,"rank":211,"remainingConfigurations":444},{"removed":"vibe-code","score":0.08766863362558214,"rank":211,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08798381847907177,"rank":211,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4.1-flash--effort-non-reasoning":{"score":0.08635675642801664,"rank":212,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11095866330974695,"rank":209,"remainingConfigurations":444},{"removed":"Datacurve","score":0.06919471258212452,"rank":212,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.08559238141002977,"rank":211,"remainingConfigurations":444},{"removed":"Scale","score":0.09905302705431997,"rank":212,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08554892539799817,"rank":212,"remainingConfigurations":444},{"removed":"Cognition","score":0.0825931867490142,"rank":212,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0899889538376518,"rank":210,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.08848403573748624,"rank":212,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.08717078627510573,"rank":206,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08317845789519719,"rank":212,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0863195920793256,"rank":212,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0837872137369919,"rank":212,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08620337710365827,"rank":212,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.08635675642801664,"rank":212,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08707738519494901,"rank":212,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08433577171242328,"rank":212,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08749891133783926,"rank":212,"remainingConfigurations":444},{"removed":"briefcase","score":0.07501513862426927,"rank":219,"remainingConfigurations":444},{"removed":"aime","score":0.08551536445442755,"rank":212,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0878792925055381,"rank":212,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.09523520627146391,"rank":202,"remainingConfigurations":444},{"removed":"automationbench","score":0.07493668498368924,"rank":219,"remainingConfigurations":444},{"removed":"critpt","score":0.09729873417377587,"rank":200,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08687011469571283,"rank":212,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.09616126452775238,"rank":207,"remainingConfigurations":444},{"removed":"gdpval","score":0.07345815236092067,"rank":221,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0862396530055121,"rank":210,"remainingConfigurations":444},{"removed":"gpqa","score":0.08430223109770645,"rank":210,"remainingConfigurations":444},{"removed":"harvey","score":0.08543428888595112,"rank":212,"remainingConfigurations":444},{"removed":"hle","score":0.10690484402540845,"rank":202,"remainingConfigurations":444},{"removed":"ifbench","score":0.08271405190906966,"rank":212,"remainingConfigurations":444},{"removed":"itbench","score":0.08597724445104249,"rank":212,"remainingConfigurations":444},{"removed":"livecodebench","score":0.08545874879596137,"rank":211,"remainingConfigurations":444},{"removed":"math500","score":0.08628184033024151,"rank":212,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.08814177577990821,"rank":212,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.1052956938647418,"rank":203,"remainingConfigurations":444},{"removed":"omniscience","score":0.08031254878158992,"rank":213,"remainingConfigurations":444},{"removed":"tau-bench","score":0.08403344179421733,"rank":212,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.08751781222634673,"rank":212,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.08124812067808128,"rank":214,"remainingConfigurations":444},{"removed":"arc-agi","score":0.10654167238954676,"rank":210,"remainingConfigurations":444},{"removed":"deepswe","score":0.06923657944872162,"rank":212,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.08637784954029581,"rank":212,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08526113267301257,"rank":212,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0825931867490142,"rank":212,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08530557794316852,"rank":212,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.08538254600655627,"rank":212,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08630174571112403,"rank":212,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08604207884025898,"rank":212,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0864394596267853,"rank":212,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08540996630924476,"rank":212,"remainingConfigurations":444},{"removed":"livebench-language","score":0.08767900543416625,"rank":212,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08634587126139293,"rank":212,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08465211289363488,"rank":212,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0857909329152934,"rank":212,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.08823380436566695,"rank":212,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.08848403573748624,"rank":212,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08649820519812922,"rank":212,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.08167877806445263,"rank":211,"remainingConfigurations":444},{"removed":"simpleqa","score":0.09047479714871447,"rank":212,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08605182896603802,"rank":212,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.08603788703755716,"rank":212,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08605610253678152,"rank":212,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.08619068945836317,"rank":212,"remainingConfigurations":444},{"removed":"vibe-code","score":0.08580412009836495,"rank":212,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08611995464548398,"rank":212,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-non-reasoning":{"score":0.0833751995838355,"rank":213,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.10428375300033989,"rank":212,"remainingConfigurations":444},{"removed":"Datacurve","score":0.06615773554904165,"rank":213,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.08265155757019936,"rank":213,"remainingConfigurations":444},{"removed":"Scale","score":0.09570813839346483,"rank":213,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08253613200215754,"rank":213,"remainingConfigurations":444},{"removed":"Cognition","score":0.07836761950916808,"rank":214,"remainingConfigurations":444},{"removed":"LiveBench","score":0.08662134100867107,"rank":211,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.08520245371300801,"rank":213,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.08438381220576825,"rank":207,"remainingConfigurations":431},{"removed":"Vals AI","score":0.08009958558577523,"rank":213,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.08333940751148396,"rank":213,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08087894169736261,"rank":213,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08322793668642203,"rank":213,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0833751995838355,"rank":213,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08405365278988654,"rank":213,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08139286001867983,"rank":213,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08440523796465878,"rank":213,"remainingConfigurations":444},{"removed":"briefcase","score":0.07758324642575908,"rank":215,"remainingConfigurations":444},{"removed":"aime","score":0.08314386118884375,"rank":213,"remainingConfigurations":444},{"removed":"apex-agents","score":0.08483835662090765,"rank":213,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08871945888342121,"rank":209,"remainingConfigurations":444},{"removed":"automationbench","score":0.08329497089498288,"rank":212,"remainingConfigurations":444},{"removed":"critpt","score":0.07964145799216427,"rank":215,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08369402034810214,"rank":213,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07989544323852422,"rank":215,"remainingConfigurations":444},{"removed":"gdpval","score":0.07771579215635498,"rank":215,"remainingConfigurations":444},{"removed":"gmmlu","score":0.08369810769598157,"rank":213,"remainingConfigurations":444},{"removed":"gpqa","score":0.09288229845524293,"rank":205,"remainingConfigurations":444},{"removed":"harvey","score":0.08234735733812427,"rank":213,"remainingConfigurations":444},{"removed":"hle","score":0.09835893172581527,"rank":209,"remainingConfigurations":444},{"removed":"ifbench","score":0.08037356623879187,"rank":215,"remainingConfigurations":444},{"removed":"itbench","score":0.08295138784985358,"rank":214,"remainingConfigurations":444},{"removed":"livecodebench","score":0.08303582886891636,"rank":212,"remainingConfigurations":444},{"removed":"math500","score":0.08345450334647948,"rank":213,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.08559197127207481,"rank":213,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.09748786717428776,"rank":209,"remainingConfigurations":444},{"removed":"omniscience","score":0.07298427429869493,"rank":218,"remainingConfigurations":444},{"removed":"tau-bench","score":0.08058008562046416,"rank":215,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0843114006071314,"rank":213,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.08206168405135643,"rank":213,"remainingConfigurations":444},{"removed":"arc-agi","score":0.1012310935998947,"rank":213,"remainingConfigurations":444},{"removed":"deepswe","score":0.06619975400116147,"rank":213,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.08339575947520272,"rank":213,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08220803724275377,"rank":213,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07836761950916808,"rank":214,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08233836941453411,"rank":213,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0824319076270854,"rank":213,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08332273603342537,"rank":213,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08302194375728546,"rank":213,"remainingConfigurations":444},{"removed":"livebench-math","score":0.08345793710673743,"rank":213,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0824583409863675,"rank":213,"remainingConfigurations":444},{"removed":"livebench-language","score":0.08465700979524303,"rank":213,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08336438870641356,"rank":213,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08172202711586789,"rank":213,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.08282674297211745,"rank":213,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.08519295565435116,"rank":213,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.08520245371300801,"rank":213,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08346031278617572,"rank":213,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0788236793311646,"rank":212,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08735820695322061,"rank":213,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08307684941008094,"rank":213,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0830676875218244,"rank":213,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08308233560790461,"rank":213,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0832159681224988,"rank":213,"remainingConfigurations":444},{"removed":"vibe-code","score":0.08284042231850319,"rank":213,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08314467888331505,"rank":213,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-mini--effort-high":{"score":0.08198730975204271,"rank":214,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06918179662331347,"rank":155,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0589481110603346,"rank":252,"remainingConfigurations":444},{"removed":"Datacurve","score":0.06184529291758409,"rank":215,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0828666346042438,"rank":212,"remainingConfigurations":444},{"removed":"Scale","score":0.0942583429686757,"rank":215,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08057994409372626,"rank":215,"remainingConfigurations":444},{"removed":"Cognition","score":0.11932886780440148,"rank":177,"remainingConfigurations":444},{"removed":"LiveBench","score":0.08562917830035406,"rank":212,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.08017281330360365,"rank":215,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.08313227279102926,"rank":209,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07715606614830184,"rank":215,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.08195777996477871,"rank":214,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.08002163212030938,"rank":214,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08186855829786953,"rank":214,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.08198730975204271,"rank":214,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08313514718779605,"rank":214,"remainingConfigurations":444},{"removed":"All provider reports","score":0.08102220959856465,"rank":214,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08234695172322347,"rank":214,"remainingConfigurations":444},{"removed":"briefcase","score":0.08153802774245594,"rank":212,"remainingConfigurations":444},{"removed":"aime","score":0.08119501092910818,"rank":215,"remainingConfigurations":444},{"removed":"apex-agents","score":0.08267907428109442,"rank":215,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08157806472149372,"rank":215,"remainingConfigurations":444},{"removed":"automationbench","score":0.08135517770799076,"rank":213,"remainingConfigurations":444},{"removed":"critpt","score":0.08237985431964887,"rank":214,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08201553959714135,"rank":214,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.08169105475416849,"rank":214,"remainingConfigurations":444},{"removed":"gdpval","score":0.08173821564141188,"rank":213,"remainingConfigurations":444},{"removed":"gmmlu","score":0.08204109857996832,"rank":214,"remainingConfigurations":444},{"removed":"gpqa","score":0.08115244119287456,"rank":214,"remainingConfigurations":444},{"removed":"harvey","score":0.0809892519935746,"rank":214,"remainingConfigurations":444},{"removed":"hle","score":0.0889788670800865,"rank":215,"remainingConfigurations":444},{"removed":"ifbench","score":0.08131815772644739,"rank":213,"remainingConfigurations":444},{"removed":"itbench","score":0.08170648656826772,"rank":215,"remainingConfigurations":444},{"removed":"livecodebench","score":0.08285145857963015,"rank":213,"remainingConfigurations":444},{"removed":"math500","score":0.08202708235598034,"rank":214,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.08514447495258537,"rank":214,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.08791092925186268,"rank":214,"remainingConfigurations":444},{"removed":"omniscience","score":0.08016788580365786,"rank":214,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0822076097450095,"rank":213,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.08239166223528539,"rank":215,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.08111724178303135,"rank":215,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05577327584135142,"rank":254,"remainingConfigurations":444},{"removed":"deepswe","score":0.06183840578071687,"rank":215,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0820013849103285,"rank":214,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08074471544536062,"rank":214,"remainingConfigurations":444},{"removed":"frontiercode","score":0.11932886780440148,"rank":177,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08103011270020812,"rank":214,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.08103300523778269,"rank":214,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08195572846094777,"rank":214,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08164000466132451,"rank":214,"remainingConfigurations":444},{"removed":"livebench-math","score":0.08212582482143495,"rank":214,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08103794776742683,"rank":214,"remainingConfigurations":444},{"removed":"livebench-language","score":0.08312548465186315,"rank":214,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08190059912799084,"rank":214,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.08039663360486042,"rank":214,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.08148110452700834,"rank":214,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.08390269440265098,"rank":214,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.08017281330360365,"rank":215,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08215422253697445,"rank":214,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07801307174172312,"rank":214,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08569251109751853,"rank":214,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08168359741259441,"rank":214,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.08203915590179371,"rank":214,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08219223318806838,"rank":214,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.082206614705105,"rank":214,"remainingConfigurations":444},{"removed":"vibe-code","score":0.08182061073104036,"rank":214,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08226374164618028,"rank":214,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3-flash-preview--effort-non-reasoning":{"score":0.08149576236635474,"rank":215,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.1060251745705773,"rank":211,"remainingConfigurations":444},{"removed":"Datacurve","score":0.06500203088209174,"rank":214,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0806210327823834,"rank":214,"remainingConfigurations":444},{"removed":"Scale","score":0.09429157183984904,"rank":214,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.08082263775430848,"rank":214,"remainingConfigurations":444},{"removed":"Cognition","score":0.0787571821604236,"rank":213,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0845184299613513,"rank":213,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.08383156856398888,"rank":214,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.08239332332088016,"rank":210,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0785424735581504,"rank":214,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.08146300450641375,"rank":215,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07907034647851356,"rank":215,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.08135948296158783,"rank":215,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.08149576236635474,"rank":215,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.08213423259705882,"rank":215,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07955840142690272,"rank":215,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0822628939315128,"rank":216,"remainingConfigurations":444},{"removed":"briefcase","score":0.08138172202596261,"rank":213,"remainingConfigurations":444},{"removed":"aime","score":0.09859411927384874,"rank":201,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0827879565565564,"rank":214,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.08298885946929638,"rank":213,"remainingConfigurations":444},{"removed":"automationbench","score":0.0812636985611819,"rank":214,"remainingConfigurations":444},{"removed":"critpt","score":0.07922592653737277,"rank":217,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.08156632120003365,"rank":215,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.08353897025468053,"rank":213,"remainingConfigurations":444},{"removed":"gdpval","score":0.08209950073705835,"rank":212,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07318073516283667,"rank":220,"remainingConfigurations":444},{"removed":"gpqa","score":0.08096287065401873,"rank":215,"remainingConfigurations":444},{"removed":"harvey","score":0.08067397849704293,"rank":215,"remainingConfigurations":444},{"removed":"hle","score":0.09177790669069785,"rank":214,"remainingConfigurations":444},{"removed":"ifbench","score":0.08414194494268827,"rank":211,"remainingConfigurations":444},{"removed":"itbench","score":0.08089092993569011,"rank":216,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07969097444203922,"rank":214,"remainingConfigurations":444},{"removed":"math500","score":0.08153736881091157,"rank":215,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0789287441031337,"rank":218,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07838164987683179,"rank":221,"remainingConfigurations":444},{"removed":"omniscience","score":0.0656174552718792,"rank":224,"remainingConfigurations":444},{"removed":"tau-bench","score":0.09128587067481912,"rank":208,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.08278071515696654,"rank":214,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.08212425591527368,"rank":212,"remainingConfigurations":444},{"removed":"arc-agi","score":0.10200867274795826,"rank":212,"remainingConfigurations":444},{"removed":"deepswe","score":0.06504453517317117,"rank":214,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.08151494965585139,"rank":215,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.08019627242638391,"rank":215,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0787571821604236,"rank":213,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.08044867311612683,"rank":215,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.08057304167837943,"rank":215,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.08144400697498475,"rank":215,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.08114726711915503,"rank":215,"remainingConfigurations":444},{"removed":"livebench-math","score":0.08158678202534377,"rank":215,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.08060507750753095,"rank":215,"remainingConfigurations":444},{"removed":"livebench-language","score":0.08273813961675307,"rank":215,"remainingConfigurations":444},{"removed":"livebench-data","score":0.08146844198380944,"rank":215,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07988868264190684,"rank":215,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.08096392492413766,"rank":215,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.08326895988688524,"rank":215,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.08383156856398888,"rank":214,"remainingConfigurations":444},{"removed":"frontiermath","score":0.08163915472912947,"rank":215,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07687689760204534,"rank":215,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08544305154838701,"rank":215,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.08120076984364977,"rank":215,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.08119095219462764,"rank":215,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.08121074905706928,"rank":215,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.08133689458835426,"rank":215,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0809753450676537,"rank":215,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.08126819567279665,"rank":215,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-35b-a3b--effort-reasoning":{"score":0.07753403475799447,"rank":216,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09959398298974237,"rank":214,"remainingConfigurations":444},{"removed":"Datacurve","score":0.061634319167942896,"rank":216,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07689597978559203,"rank":216,"remainingConfigurations":444},{"removed":"Scale","score":0.08976047617231912,"rank":216,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0768419436764347,"rank":216,"remainingConfigurations":444},{"removed":"Cognition","score":0.07473326078002082,"rank":216,"remainingConfigurations":444},{"removed":"LiveBench","score":0.08015846452434004,"rank":214,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07948992174098057,"rank":216,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07952044329766335,"rank":211,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07425517949326081,"rank":216,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07750062248974728,"rank":216,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07517064745590814,"rank":216,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07740142703424117,"rank":216,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07753403475799447,"rank":216,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.078146048938703,"rank":216,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07563475037641558,"rank":217,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07786764115255071,"rank":217,"remainingConfigurations":444},{"removed":"briefcase","score":0.07672417817274527,"rank":217,"remainingConfigurations":444},{"removed":"aime","score":0.07792102841953734,"rank":217,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0783671769583909,"rank":216,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07306589481840102,"rank":220,"remainingConfigurations":444},{"removed":"automationbench","score":0.07651938529678143,"rank":217,"remainingConfigurations":444},{"removed":"critpt","score":0.07884418868429803,"rank":218,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.077203089287034,"rank":217,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07877136684347123,"rank":217,"remainingConfigurations":444},{"removed":"gdpval","score":0.07721060098497616,"rank":216,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07779174096067788,"rank":216,"remainingConfigurations":444},{"removed":"gpqa","score":0.0729005194429207,"rank":218,"remainingConfigurations":444},{"removed":"harvey","score":0.07661443280081744,"rank":216,"remainingConfigurations":444},{"removed":"hle","score":0.08311070971281048,"rank":218,"remainingConfigurations":444},{"removed":"ifbench","score":0.06978953832090791,"rank":222,"remainingConfigurations":444},{"removed":"itbench","score":0.08518738877953304,"rank":213,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07776261876737255,"rank":215,"remainingConfigurations":444},{"removed":"math500","score":0.07790784391491427,"rank":216,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07995681511255308,"rank":215,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.08188026585257228,"rank":216,"remainingConfigurations":444},{"removed":"omniscience","score":0.08150354196672506,"rank":212,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0738905089138016,"rank":219,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07859734835420179,"rank":216,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.08085847776986722,"rank":216,"remainingConfigurations":444},{"removed":"arc-agi","score":0.09620324781678928,"rank":215,"remainingConfigurations":444},{"removed":"deepswe","score":0.06167585307553001,"rank":216,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07755212768520599,"rank":216,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07634100622312556,"rank":217,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07473326078002082,"rank":216,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07654518698888031,"rank":216,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07666834794963745,"rank":216,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.077484311075581,"rank":216,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07719985648185745,"rank":216,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07761758789696832,"rank":216,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07668944328676952,"rank":216,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07873120137392713,"rank":216,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07750164124015357,"rank":216,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07599270900793649,"rank":216,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07702606382878117,"rank":216,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07922882132034119,"rank":216,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07948992174098057,"rank":216,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07764394323743574,"rank":216,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07357620803411997,"rank":216,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08130494668790401,"rank":216,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07725440193852558,"rank":216,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07723951879157297,"rank":216,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07725937578608733,"rank":216,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07738225555341204,"rank":216,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07703880452221687,"rank":216,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07731462021132525,"rank":216,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5--effort-non-reasoning":{"score":0.07707646315235553,"rank":217,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09856820041083092,"rank":215,"remainingConfigurations":444},{"removed":"Datacurve","score":0.06130128131135116,"rank":217,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07641166762085595,"rank":217,"remainingConfigurations":444},{"removed":"Scale","score":0.08885800997164445,"rank":217,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07638056859552193,"rank":217,"remainingConfigurations":444},{"removed":"Cognition","score":0.07388775920027736,"rank":218,"remainingConfigurations":444},{"removed":"LiveBench","score":0.08007800955184748,"rank":215,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0790117349324617,"rank":217,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07820653894226053,"rank":213,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07407087494605034,"rank":217,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07704420825063688,"rank":217,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07474514647068738,"rank":218,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07694426423538431,"rank":217,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07707646315235553,"rank":217,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07768053778390903,"rank":218,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07520266676008414,"rank":218,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.08234206125832881,"rank":215,"remainingConfigurations":444},{"removed":"briefcase","score":0.07644029602734488,"rank":218,"remainingConfigurations":444},{"removed":"aime","score":0.07726922522848571,"rank":218,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0782523786587503,"rank":217,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07401931191260526,"rank":217,"remainingConfigurations":444},{"removed":"automationbench","score":0.07647683398630435,"rank":218,"remainingConfigurations":444},{"removed":"critpt","score":0.07448769827107236,"rank":222,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07702517034451366,"rank":219,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0787832674919245,"rank":216,"remainingConfigurations":444},{"removed":"gdpval","score":0.07671048361417655,"rank":217,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07754670217883773,"rank":217,"remainingConfigurations":444},{"removed":"gpqa","score":0.08008004873237688,"rank":216,"remainingConfigurations":444},{"removed":"harvey","score":0.07619166513612995,"rank":217,"remainingConfigurations":444},{"removed":"hle","score":0.08720269178582209,"rank":216,"remainingConfigurations":444},{"removed":"ifbench","score":0.08432246579779311,"rank":210,"remainingConfigurations":444},{"removed":"itbench","score":0.07629255024423752,"rank":218,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07718822567934665,"rank":217,"remainingConfigurations":444},{"removed":"math500","score":0.07741908512748015,"rank":217,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07949911175663539,"rank":217,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.08209387092431474,"rank":215,"remainingConfigurations":444},{"removed":"omniscience","score":0.06339517755858491,"rank":225,"remainingConfigurations":444},{"removed":"tau-bench","score":0.08072439415364062,"rank":214,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07813958333768943,"rank":217,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06826834406148878,"rank":225,"remainingConfigurations":444},{"removed":"arc-agi","score":0.09532645006694689,"rank":216,"remainingConfigurations":444},{"removed":"deepswe","score":0.06134273650976348,"rank":217,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0770950887187613,"rank":217,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07596179423969031,"rank":218,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07388775920027736,"rank":218,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07609043733460445,"rank":217,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07619896684996341,"rank":217,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07702897221560993,"rank":217,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07673999179316446,"rank":217,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07715847979300607,"rank":217,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07622353837017576,"rank":217,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07826799240316817,"rank":217,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07705907615178198,"rank":217,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07553333867766644,"rank":217,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07656859260811617,"rank":217,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0787748150805118,"rank":218,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0790117349324617,"rank":217,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0771019170898372,"rank":217,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07284723618730855,"rank":218,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08083962172105608,"rank":217,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07679937256828497,"rank":217,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07678510511349931,"rank":217,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07680108250329497,"rank":217,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07692556518596187,"rank":217,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07657915198029137,"rank":217,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07685779567900164,"rank":217,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-low":{"score":0.07695348597845032,"rank":218,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.050928133398214816,"rank":159,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.12841058210865183,"rank":197,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05900253711311457,"rank":220,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0770414671710934,"rank":215,"remainingConfigurations":444},{"removed":"Scale","score":0.08871878834814384,"rank":218,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07581358387818457,"rank":218,"remainingConfigurations":444},{"removed":"Cognition","score":0.06532616469308293,"rank":225,"remainingConfigurations":444},{"removed":"LiveBench","score":0.08000573079317397,"rank":216,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07670523457285852,"rank":220,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07876032849039356,"rank":212,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07385470869484612,"rank":218,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0769225605497449,"rank":218,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07493156239984118,"rank":217,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07683475423333859,"rank":218,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07695348597845032,"rank":218,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07809655914433747,"rank":217,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07592344196412365,"rank":216,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07746358346182874,"rank":218,"remainingConfigurations":444},{"removed":"briefcase","score":0.07698613654225255,"rank":216,"remainingConfigurations":444},{"removed":"aime","score":0.07671815762540705,"rank":220,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07783616253371793,"rank":218,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07538796116601497,"rank":216,"remainingConfigurations":444},{"removed":"automationbench","score":0.07668191849930446,"rank":216,"remainingConfigurations":444},{"removed":"critpt","score":0.07667101587026522,"rank":220,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07707541219853457,"rank":218,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07650134244293456,"rank":219,"remainingConfigurations":444},{"removed":"gdpval","score":0.07602944900273141,"rank":218,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0774072143481182,"rank":218,"remainingConfigurations":444},{"removed":"gpqa","score":0.07670450693006406,"rank":217,"remainingConfigurations":444},{"removed":"harvey","score":0.07601359962087462,"rank":218,"remainingConfigurations":444},{"removed":"hle","score":0.08409018729528143,"rank":217,"remainingConfigurations":444},{"removed":"ifbench","score":0.07640256973643682,"rank":218,"remainingConfigurations":444},{"removed":"itbench","score":0.0766976319409352,"rank":217,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0774854381392043,"rank":216,"remainingConfigurations":444},{"removed":"math500","score":0.0771472638016676,"rank":218,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07972707183532238,"rank":216,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.08075696442753373,"rank":217,"remainingConfigurations":444},{"removed":"omniscience","score":0.0724171949568141,"rank":219,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07747978168798197,"rank":217,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07753388385858812,"rank":218,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07933732698873187,"rank":217,"remainingConfigurations":444},{"removed":"arc-agi","score":0.10646087963559431,"rank":211,"remainingConfigurations":444},{"removed":"deepswe","score":0.05899334788322724,"rank":220,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07696705020811966,"rank":218,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07981756805464857,"rank":216,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06532616469308293,"rank":225,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07603140993052922,"rank":218,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07606870313945831,"rank":218,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0769184063027366,"rank":218,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07663726949265019,"rank":218,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07707370945434186,"rank":218,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07610542802575342,"rank":218,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07806940749179685,"rank":218,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07680203439342846,"rank":218,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07541015386850229,"rank":218,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07647952862976276,"rank":218,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07879037093853382,"rank":217,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07670523457285852,"rank":220,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07706621975922336,"rank":218,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07308872686483144,"rank":217,"remainingConfigurations":444},{"removed":"simpleqa","score":0.08058350593621412,"rank":218,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0766950760906661,"rank":218,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07661793349997902,"rank":218,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07677671027082923,"rank":218,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07672604790607178,"rank":218,"remainingConfigurations":444},{"removed":"vibe-code","score":0.076380140538876,"rank":218,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07678962927827676,"rank":218,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-31b-it--effort-reasoning":{"score":0.07561808394242077,"rank":219,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09616723317573683,"rank":216,"remainingConfigurations":444},{"removed":"Datacurve","score":0.059898043801324,"rank":218,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07505269919371363,"rank":218,"remainingConfigurations":444},{"removed":"Scale","score":0.08743684998428215,"rank":219,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07487857508424663,"rank":219,"remainingConfigurations":444},{"removed":"Cognition","score":0.07252509727864422,"rank":219,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07827747833236612,"rank":218,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07756656100796143,"rank":219,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07806279436384737,"rank":214,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07269054587449232,"rank":219,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07558596958653872,"rank":219,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07326204373385999,"rank":219,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07548964506102032,"rank":219,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07561808394242077,"rank":219,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07620488154198128,"rank":219,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07370695539745249,"rank":219,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07620412385562357,"rank":219,"remainingConfigurations":444},{"removed":"briefcase","score":0.08096524653095567,"rank":214,"remainingConfigurations":444},{"removed":"aime","score":0.0754030244313334,"rank":221,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07682609514512974,"rank":219,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07385318449951885,"rank":218,"remainingConfigurations":444},{"removed":"automationbench","score":0.07674958621565149,"rank":215,"remainingConfigurations":444},{"removed":"critpt","score":0.07435150610166064,"rank":223,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07889936290862684,"rank":216,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07698365974924357,"rank":218,"remainingConfigurations":444},{"removed":"gdpval","score":0.07796890240805726,"rank":214,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07613203900155523,"rank":219,"remainingConfigurations":444},{"removed":"gpqa","score":0.07066464833998902,"rank":220,"remainingConfigurations":444},{"removed":"harvey","score":0.07468548244850698,"rank":219,"remainingConfigurations":444},{"removed":"hle","score":0.08013830600426881,"rank":220,"remainingConfigurations":444},{"removed":"ifbench","score":0.06759654202887104,"rank":225,"remainingConfigurations":444},{"removed":"itbench","score":0.06769941890835722,"rank":225,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07564512339882329,"rank":218,"remainingConfigurations":444},{"removed":"math500","score":0.075987074410815,"rank":219,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07800785795266468,"rank":219,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07929736176517162,"rank":219,"remainingConfigurations":444},{"removed":"omniscience","score":0.07916373027924363,"rank":215,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07645105600480943,"rank":218,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07664870855297211,"rank":219,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07703267172792895,"rank":218,"remainingConfigurations":444},{"removed":"arc-agi","score":0.09300821490324236,"rank":217,"remainingConfigurations":444},{"removed":"deepswe","score":0.05994140070701371,"rank":218,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07563670474553995,"rank":219,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07457496226141665,"rank":219,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07252509727864422,"rank":219,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07466345368112809,"rank":219,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07476496065914758,"rank":219,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07557181539722198,"rank":219,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07527834376884802,"rank":219,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07569365015210515,"rank":219,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07479939217784314,"rank":219,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07680756694363801,"rank":219,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07559075114778983,"rank":219,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07409317668135885,"rank":219,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0751193252833617,"rank":219,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07727245582702646,"rank":219,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07756656100796143,"rank":219,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07569228453477116,"rank":219,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07185524068023012,"rank":219,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07930331127261443,"rank":219,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07534354260901589,"rank":219,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07533281573882994,"rank":219,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07534335989988378,"rank":219,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0754765080600034,"rank":219,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07513079466366021,"rank":219,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0754059934330519,"rank":219,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m2.1--effort-reasoning":{"score":0.07473159000144385,"rank":220,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09604341584975985,"rank":217,"remainingConfigurations":444},{"removed":"Datacurve","score":0.059451707814504186,"rank":219,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07392890210901686,"rank":219,"remainingConfigurations":444},{"removed":"Scale","score":0.08656502676528995,"rank":220,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0740930940860379,"rank":220,"remainingConfigurations":444},{"removed":"Cognition","score":0.07231516896888386,"rank":220,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07738355561538642,"rank":219,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07647638752378919,"rank":221,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07571808002400564,"rank":215,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07173903846775971,"rank":220,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07470143732189408,"rank":220,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07248411773809475,"rank":220,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07460567926464724,"rank":220,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07473159000144385,"rank":220,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07531372912492654,"rank":220,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07292751485002955,"rank":220,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07526397893248335,"rank":220,"remainingConfigurations":444},{"removed":"briefcase","score":0.07422635365596984,"rank":221,"remainingConfigurations":444},{"removed":"aime","score":0.07712009812404912,"rank":219,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07576470724346353,"rank":220,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07376103242200337,"rank":219,"remainingConfigurations":444},{"removed":"automationbench","score":0.07415255181287417,"rank":220,"remainingConfigurations":444},{"removed":"critpt","score":0.07942722961098277,"rank":216,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0746237572490309,"rank":220,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07619540547664555,"rank":220,"remainingConfigurations":444},{"removed":"gdpval","score":0.07496154030273218,"rank":219,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07876410035633447,"rank":215,"remainingConfigurations":444},{"removed":"gpqa","score":0.07192874178113445,"rank":219,"remainingConfigurations":444},{"removed":"harvey","score":0.07388476847466684,"rank":220,"remainingConfigurations":444},{"removed":"hle","score":0.07919698031546034,"rank":221,"remainingConfigurations":444},{"removed":"ifbench","score":0.0699689440060317,"rank":221,"remainingConfigurations":444},{"removed":"itbench","score":0.07405636102810506,"rank":219,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07219945510084437,"rank":222,"remainingConfigurations":444},{"removed":"math500","score":0.07492972804865954,"rank":221,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07225384590289063,"rank":222,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.08061473461838135,"rank":218,"remainingConfigurations":444},{"removed":"omniscience","score":0.07320486303358238,"rank":217,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07264280832413143,"rank":221,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07578707904323967,"rank":220,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07596998757669783,"rank":219,"remainingConfigurations":444},{"removed":"arc-agi","score":0.09262008425980717,"rank":218,"remainingConfigurations":444},{"removed":"deepswe","score":0.059491825415032416,"rank":219,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07474956517516021,"rank":220,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07349249093775172,"rank":220,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07231516896888386,"rank":220,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07376130406058222,"rank":220,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07388218771794329,"rank":220,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07468444916041247,"rank":220,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07440801171311891,"rank":220,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07481674451428431,"rank":220,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07390177704563122,"rank":220,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07588723359230672,"rank":220,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07470747167894227,"rank":220,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07323750072167512,"rank":220,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07423619725960416,"rank":220,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07638273752484724,"rank":220,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07647638752378919,"rank":221,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07490344397593839,"rank":220,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07030041315271339,"rank":220,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07840176502126313,"rank":220,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07445626153363341,"rank":220,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07444834193447299,"rank":220,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07446613876515625,"rank":220,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07458431342725905,"rank":220,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0742486688458311,"rank":220,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07451932676961641,"rank":220,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.6-flash--effort-minimal":{"score":0.07301812201611717,"rank":221,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06286860555427903,"rank":156,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.223459795503171,"rank":145,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05748845732264066,"rank":221,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07321433318781441,"rank":220,"remainingConfigurations":444},{"removed":"Scale","score":0.0838752037384168,"rank":222,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07217554947646575,"rank":221,"remainingConfigurations":444},{"removed":"Cognition","score":0.07449329986576428,"rank":217,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07420141730700122,"rank":221,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07147974220103925,"rank":225,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02953441200799191,"rank":275,"remainingConfigurations":431},{"removed":"Vals AI","score":0.07024615364802311,"rank":221,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07299364563084008,"rank":221,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07106794033439444,"rank":221,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07292936859490672,"rank":221,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07301812201611717,"rank":221,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0735724389955633,"rank":221,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07152231305840961,"rank":221,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07337043870200234,"rank":221,"remainingConfigurations":444},{"removed":"briefcase","score":0.07247192260840789,"rank":223,"remainingConfigurations":444},{"removed":"aime","score":0.07427808407266497,"rank":222,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07369789746745135,"rank":221,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07273063651978187,"rank":221,"remainingConfigurations":444},{"removed":"automationbench","score":0.07258460663003784,"rank":223,"remainingConfigurations":444},{"removed":"critpt","score":0.07324972158303752,"rank":225,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07300659607836642,"rank":221,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07345156270371812,"rank":221,"remainingConfigurations":444},{"removed":"gdpval","score":0.07268502074378606,"rank":223,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07315278204540669,"rank":221,"remainingConfigurations":444},{"removed":"gpqa","score":0.06946052472497671,"rank":222,"remainingConfigurations":444},{"removed":"harvey","score":0.07206991111638815,"rank":221,"remainingConfigurations":444},{"removed":"hle","score":0.07897880809483739,"rank":222,"remainingConfigurations":444},{"removed":"ifbench","score":0.07226152408654266,"rank":219,"remainingConfigurations":444},{"removed":"itbench","score":0.07270201842587708,"rank":220,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07322316080844692,"rank":219,"remainingConfigurations":444},{"removed":"math500","score":0.07308859903638466,"rank":222,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07541536854435732,"rank":220,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07863796303029719,"rank":220,"remainingConfigurations":444},{"removed":"omniscience","score":0.07129123477536697,"rank":220,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07218547233339537,"rank":223,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07344026766599286,"rank":222,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07222648280086903,"rank":222,"remainingConfigurations":444},{"removed":"arc-agi","score":0.2175247446548062,"rank":144,"remainingConfigurations":444},{"removed":"deepswe","score":0.05752036594910537,"rank":221,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07303290761881705,"rank":221,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0689765208672057,"rank":224,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07449329986576428,"rank":217,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07218210717679632,"rank":221,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0721510041099767,"rank":221,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07297680064292454,"rank":221,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0726755717671972,"rank":221,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0731650678084405,"rank":221,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07210347523771488,"rank":221,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07408835505455157,"rank":221,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07297749247209917,"rank":221,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07160405958343401,"rank":221,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07252647413349601,"rank":221,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07470233184763762,"rank":221,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07147974220103925,"rank":225,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07434068808700237,"rank":221,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05390347615804599,"rank":233,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07765591768487919,"rank":221,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07275034151769681,"rank":221,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07275027545517782,"rank":221,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07279213195485802,"rank":221,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07285672804884616,"rank":221,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07255324174304419,"rank":221,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07279300002290039,"rank":221,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.6-35b-a3b--effort-reasoning":{"score":0.0725456405214346,"rank":222,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09266863928110437,"rank":218,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05741268134449798,"rank":222,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07194503190524543,"rank":221,"remainingConfigurations":444},{"removed":"Scale","score":0.0841061326604381,"rank":221,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07182401727107345,"rank":222,"remainingConfigurations":444},{"removed":"Cognition","score":0.06951420934890386,"rank":221,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07523878119432317,"rank":220,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07438832583146478,"rank":222,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07471889669662486,"rank":217,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06956929531648841,"rank":222,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07251473283747427,"rank":222,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.07031774657711697,"rank":222,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07241738767147843,"rank":222,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0725456405214346,"rank":222,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07312123509236129,"rank":222,"remainingConfigurations":444},{"removed":"All provider reports","score":0.07075117961871816,"rank":222,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07314903549336275,"rank":222,"remainingConfigurations":444},{"removed":"briefcase","score":0.07199983100748786,"rank":224,"remainingConfigurations":444},{"removed":"aime","score":0.07239270190084622,"rank":223,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07362399166813163,"rank":222,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06907566502323408,"rank":223,"remainingConfigurations":444},{"removed":"automationbench","score":0.07323225723190144,"rank":221,"remainingConfigurations":444},{"removed":"critpt","score":0.07675343635953612,"rank":219,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07248618707003247,"rank":222,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0726665150906317,"rank":222,"remainingConfigurations":444},{"removed":"gdpval","score":0.07221299610007519,"rank":224,"remainingConfigurations":444},{"removed":"gmmlu","score":0.07307358019944316,"rank":222,"remainingConfigurations":444},{"removed":"gpqa","score":0.06905762252572142,"rank":223,"remainingConfigurations":444},{"removed":"harvey","score":0.07164374569439637,"rank":222,"remainingConfigurations":444},{"removed":"hle","score":0.07716295405095516,"rank":224,"remainingConfigurations":444},{"removed":"ifbench","score":0.06942248094831326,"rank":223,"remainingConfigurations":444},{"removed":"itbench","score":0.0718861143891028,"rank":221,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0725172221927194,"rank":221,"remainingConfigurations":444},{"removed":"math500","score":0.07283949070968278,"rank":223,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07480199825780583,"rank":221,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07406294202920977,"rank":223,"remainingConfigurations":444},{"removed":"omniscience","score":0.07752829834685993,"rank":216,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0691490755755078,"rank":224,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07352338978471573,"rank":221,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07407151598857613,"rank":220,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08957239331328863,"rank":219,"remainingConfigurations":444},{"removed":"deepswe","score":0.05745160528868606,"rank":222,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07256395477107545,"rank":222,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.07151367027207117,"rank":221,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06951420934890386,"rank":221,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07161500471321279,"rank":222,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.071717024898907,"rank":222,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07250171523385825,"rank":222,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07221803489058953,"rank":222,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07262084919556201,"rank":222,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07173868483186277,"rank":222,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07368630969525393,"rank":222,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07253028975192817,"rank":222,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.07107576719723295,"rank":222,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07206023339341718,"rank":222,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07415735320821855,"rank":222,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07438832583146478,"rank":222,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07259274898510369,"rank":222,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0688283577151297,"rank":222,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07610335714865246,"rank":222,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.07227866199308461,"rank":222,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07227108379497948,"rank":222,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.07228441838137711,"rank":222,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07240468190272899,"rank":222,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07207181573026633,"rank":222,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07234061462097872,"rank":222,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-5-20251101--effort-non-reasoning":{"score":0.07107014873383986,"rank":223,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.09228539606548791,"rank":219,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0563848344875835,"rank":224,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.07033353665589036,"rank":222,"remainingConfigurations":444},{"removed":"Scale","score":0.08224509419499752,"rank":223,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.07043513899265895,"rank":223,"remainingConfigurations":444},{"removed":"Cognition","score":0.06864604087763564,"rank":222,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07371105743359292,"rank":222,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07312757403259988,"rank":223,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0717872045538379,"rank":218,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06824988015282708,"rank":223,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0710410811997858,"rank":223,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06891296137420981,"rank":223,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07094893691972763,"rank":223,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07107014873383986,"rank":223,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07163438075487744,"rank":223,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06934305935552611,"rank":223,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.07166658023632806,"rank":223,"remainingConfigurations":444},{"removed":"briefcase","score":0.07068461467939581,"rank":225,"remainingConfigurations":444},{"removed":"aime","score":0.08236811947239679,"rank":214,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07209182094016191,"rank":223,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06799182397355834,"rank":226,"remainingConfigurations":444},{"removed":"automationbench","score":0.07058698190307469,"rank":224,"remainingConfigurations":444},{"removed":"critpt","score":0.07506976762791055,"rank":221,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07105418515373808,"rank":223,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07260153751231353,"rank":223,"remainingConfigurations":444},{"removed":"gdpval","score":0.07127902227425786,"rank":225,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06479036517096544,"rank":226,"remainingConfigurations":444},{"removed":"gpqa","score":0.070318632573814,"rank":221,"remainingConfigurations":444},{"removed":"harvey","score":0.07028012827798205,"rank":223,"remainingConfigurations":444},{"removed":"hle","score":0.08114960468964996,"rank":219,"remainingConfigurations":444},{"removed":"ifbench","score":0.08036271586054243,"rank":216,"remainingConfigurations":444},{"removed":"itbench","score":0.07046996937649193,"rank":222,"remainingConfigurations":444},{"removed":"livecodebench","score":0.07273441209550084,"rank":220,"remainingConfigurations":444},{"removed":"math500","score":0.07128246329059217,"rank":224,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0684514442608271,"rank":226,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07581020631333844,"rank":222,"remainingConfigurations":444},{"removed":"omniscience","score":0.058022851802800555,"rank":231,"remainingConfigurations":444},{"removed":"tau-bench","score":0.06849094139651056,"rank":225,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07210996923750251,"rank":223,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06646490308102022,"rank":226,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08908798495109353,"rank":220,"remainingConfigurations":444},{"removed":"deepswe","score":0.056421861968013215,"rank":224,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07108716766085928,"rank":223,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0699065882057689,"rank":222,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06864604087763564,"rank":222,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.07013768260536941,"rank":223,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.07025810522516138,"rank":223,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.07102559980052081,"rank":223,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.07076256535647553,"rank":223,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07115143794038652,"rank":223,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.07027245810620729,"rank":223,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07217651073676977,"rank":223,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07104863735076118,"rank":223,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0696396855711107,"rank":223,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.07059490715387837,"rank":223,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.07265549067302489,"rank":223,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07312757403259988,"rank":223,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07121656243183835,"rank":223,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06689289175350882,"rank":224,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07458491787240622,"rank":223,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0708070232539691,"rank":223,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.07079837916971164,"rank":223,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0708169669739276,"rank":223,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07092715280807145,"rank":223,"remainingConfigurations":444},{"removed":"vibe-code","score":0.07060651642295242,"rank":223,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.07086733760252432,"rank":223,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-2.5-pro--effort-reasoning":{"score":0.07016173073535538,"rank":224,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0897739450630937,"rank":220,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05558796483791343,"rank":225,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06937630944195262,"rank":223,"remainingConfigurations":444},{"removed":"Scale","score":0.08130810936688476,"rank":224,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.06948194157238724,"rank":224,"remainingConfigurations":444},{"removed":"Cognition","score":0.06760292596698693,"rank":223,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07268856843037073,"rank":223,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0719654160771892,"rank":224,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0716500408046369,"rank":219,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0672650482262115,"rank":224,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.07013272110944993,"rank":224,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0680115195250738,"rank":224,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.07003992836826416,"rank":224,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.07016173073535538,"rank":224,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.07070844986475959,"rank":224,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06842414237067895,"rank":224,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0707280810849087,"rank":224,"remainingConfigurations":444},{"removed":"briefcase","score":0.07434133675219032,"rank":220,"remainingConfigurations":444},{"removed":"aime","score":0.06918756903645926,"rank":224,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07122248063247434,"rank":224,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06854587266604668,"rank":224,"remainingConfigurations":444},{"removed":"automationbench","score":0.07274365809788795,"rank":222,"remainingConfigurations":444},{"removed":"critpt","score":0.06747721409735884,"rank":227,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07010797463904134,"rank":225,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.06852253536106137,"rank":225,"remainingConfigurations":444},{"removed":"gdpval","score":0.07451439723441526,"rank":220,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06607258779708998,"rank":225,"remainingConfigurations":444},{"removed":"gpqa","score":0.06673267663923076,"rank":224,"remainingConfigurations":444},{"removed":"harvey","score":0.06934049162288887,"rank":224,"remainingConfigurations":444},{"removed":"hle","score":0.07508446892278925,"rank":225,"remainingConfigurations":444},{"removed":"ifbench","score":0.07201596700361652,"rank":220,"remainingConfigurations":444},{"removed":"itbench","score":0.06954859104204898,"rank":223,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06876829468398225,"rank":223,"remainingConfigurations":444},{"removed":"math500","score":0.07503665111775472,"rank":220,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07020884090210792,"rank":224,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07312290118344096,"rank":224,"remainingConfigurations":444},{"removed":"omniscience","score":0.06093067441245384,"rank":228,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07245193448194585,"rank":222,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.07116344281950897,"rank":224,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.07355932235276114,"rank":221,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08664863817917386,"rank":221,"remainingConfigurations":444},{"removed":"deepswe","score":0.05562692828830562,"rank":225,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.07017950228429144,"rank":224,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0690722434893959,"rank":223,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06760292596698693,"rank":223,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06924293789031964,"rank":224,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.06935432383764893,"rank":224,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0701195474035038,"rank":224,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06984556287487217,"rank":224,"remainingConfigurations":444},{"removed":"livebench-math","score":0.07023911486368134,"rank":224,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.06938383199963948,"rank":224,"remainingConfigurations":444},{"removed":"livebench-language","score":0.07126665921830977,"rank":224,"remainingConfigurations":444},{"removed":"livebench-data","score":0.07013828405109258,"rank":224,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0687373006013335,"rank":224,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.06969280436845227,"rank":224,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0717220597565474,"rank":224,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0719654160771892,"rank":224,"remainingConfigurations":444},{"removed":"frontiermath","score":0.07026154739595665,"rank":224,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06619263995610854,"rank":225,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07363397924350097,"rank":224,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06989955591124651,"rank":224,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0698947615971602,"rank":224,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0699083524192865,"rank":224,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.07002526604782544,"rank":224,"remainingConfigurations":444},{"removed":"vibe-code","score":0.06970386630918869,"rank":224,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06996125231356205,"rank":224,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-medium":{"score":0.06811261613523233,"rank":225,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03751153746209944,"rank":173,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07907733674249597,"rank":226,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05693339270227979,"rank":223,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06805722902632803,"rank":224,"remainingConfigurations":444},{"removed":"Scale","score":0.07847770865238628,"rank":226,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.06717705126245307,"rank":226,"remainingConfigurations":444},{"removed":"Cognition","score":0.06276688340127756,"rank":230,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07123152035143442,"rank":224,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.07874117144186649,"rank":218,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.08434039549957796,"rank":208,"remainingConfigurations":431},{"removed":"Vals AI","score":0.064529992245917,"rank":226,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.06809425251133464,"rank":225,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06637295288431917,"rank":225,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.06805426568734207,"rank":225,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.06811261613523233,"rank":225,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06872089800365283,"rank":225,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06691403459185297,"rank":225,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06862280368469731,"rank":226,"remainingConfigurations":444},{"removed":"briefcase","score":0.06738709006633463,"rank":226,"remainingConfigurations":444},{"removed":"aime","score":0.06789849162378357,"rank":227,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06900606643736958,"rank":226,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06826137807941567,"rank":225,"remainingConfigurations":444},{"removed":"automationbench","score":0.06739201641169344,"rank":225,"remainingConfigurations":444},{"removed":"critpt","score":0.06767558596122646,"rank":226,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.06839580845799843,"rank":226,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0673126143688601,"rank":227,"remainingConfigurations":444},{"removed":"gdpval","score":0.06700918912281409,"rank":226,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06845859876620526,"rank":223,"remainingConfigurations":444},{"removed":"gpqa","score":0.06631844855657518,"rank":226,"remainingConfigurations":444},{"removed":"harvey","score":0.06722656787037998,"rank":225,"remainingConfigurations":444},{"removed":"hle","score":0.07392141656130653,"rank":226,"remainingConfigurations":444},{"removed":"ifbench","score":0.068012021315621,"rank":224,"remainingConfigurations":444},{"removed":"itbench","score":0.06798156525110848,"rank":224,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06837122300545014,"rank":224,"remainingConfigurations":444},{"removed":"math500","score":0.06828629693509021,"rank":226,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07043177827511242,"rank":223,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07276333000817349,"rank":225,"remainingConfigurations":444},{"removed":"omniscience","score":0.06578647201250688,"rank":223,"remainingConfigurations":444},{"removed":"tau-bench","score":0.06806313638885014,"rank":226,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06862566806999121,"rank":226,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06833425962529914,"rank":224,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0835529738302329,"rank":223,"remainingConfigurations":444},{"removed":"deepswe","score":0.0569390522560403,"rank":223,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06812604662483616,"rank":225,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.06821752387082267,"rank":225,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06276688340127756,"rank":230,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06741111059174969,"rank":225,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.067154329450324,"rank":226,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.06811840464402148,"rank":225,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06780627130764903,"rank":225,"remainingConfigurations":444},{"removed":"livebench-math","score":0.06822224163485403,"rank":225,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.06729878357548581,"rank":226,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06908707550833691,"rank":226,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0680913985727928,"rank":225,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.06674167996409561,"rank":225,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0676580891675502,"rank":225,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0697459798693814,"rank":225,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.07874117144186649,"rank":218,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06716363519768843,"rank":226,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.07849316063465694,"rank":213,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07133907795662972,"rank":226,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06790145298281715,"rank":225,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.06784589325476571,"rank":225,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.06791059560765338,"rank":225,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.06796353108257543,"rank":225,"remainingConfigurations":444},{"removed":"vibe-code","score":0.06765459914671026,"rank":225,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06792162873435745,"rank":225,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-flash-lite--effort-reasoning":{"score":0.06804571874556382,"rank":226,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.08674767462776396,"rank":221,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05382025918719569,"rank":226,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06751813833787006,"rank":225,"remainingConfigurations":444},{"removed":"Scale","score":0.078897132589759,"rank":225,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.06738229579285508,"rank":225,"remainingConfigurations":444},{"removed":"Cognition","score":0.0653952763211939,"rank":224,"remainingConfigurations":444},{"removed":"LiveBench","score":0.07040462797580159,"rank":225,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.06989076836602626,"rank":226,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.07014582448588484,"rank":220,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06523608716490384,"rank":225,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.06801764556333859,"rank":226,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06590301921144902,"rank":226,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.06793003988967443,"rank":226,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.06804571874556382,"rank":226,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06856808704213406,"rank":226,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06629875370419619,"rank":226,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06993783979888872,"rank":225,"remainingConfigurations":444},{"removed":"briefcase","score":0.07378278781557716,"rank":222,"remainingConfigurations":444},{"removed":"aime","score":0.0676323372080178,"rank":228,"remainingConfigurations":444},{"removed":"apex-agents","score":0.07000700856226864,"rank":225,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06481345788664933,"rank":229,"remainingConfigurations":444},{"removed":"automationbench","score":0.06721539254583868,"rank":226,"remainingConfigurations":444},{"removed":"critpt","score":0.06709957654783354,"rank":228,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.07100509597633993,"rank":224,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.06778962425410558,"rank":226,"remainingConfigurations":444},{"removed":"gdpval","score":0.07295182771018897,"rank":222,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06823795465285969,"rank":224,"remainingConfigurations":444},{"removed":"gpqa","score":0.06581122086451724,"rank":227,"remainingConfigurations":444},{"removed":"harvey","score":0.06718942985586325,"rank":226,"remainingConfigurations":444},{"removed":"hle","score":0.07371276781296064,"rank":227,"remainingConfigurations":444},{"removed":"ifbench","score":0.0588790590012877,"rank":231,"remainingConfigurations":444},{"removed":"itbench","score":0.06740880409067397,"rank":226,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06789175604686244,"rank":225,"remainingConfigurations":444},{"removed":"math500","score":0.06835525667354982,"rank":225,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.07009978259815798,"rank":225,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.06871423827957442,"rank":230,"remainingConfigurations":444},{"removed":"omniscience","score":0.06071899160281985,"rank":229,"remainingConfigurations":444},{"removed":"tau-bench","score":0.07388107642798979,"rank":220,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06901274363137114,"rank":225,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06886546983361887,"rank":223,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08379434700498994,"rank":222,"remainingConfigurations":444},{"removed":"deepswe","score":0.05386087398214217,"rank":226,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06806261254099703,"rank":226,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.06709817754558758,"rank":226,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0653952763211939,"rank":224,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06716567160126256,"rank":226,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0672635364429994,"rank":225,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.06800461093160991,"rank":226,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06773696812761644,"rank":226,"remainingConfigurations":444},{"removed":"livebench-math","score":0.06811591656257568,"rank":226,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.06730287230593864,"rank":225,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06913344280691464,"rank":225,"remainingConfigurations":444},{"removed":"livebench-data","score":0.06801493332171521,"rank":226,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.06665161262783506,"rank":226,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.06759209284821117,"rank":226,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06955642797809759,"rank":226,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.06989076836602626,"rank":226,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06810289562592105,"rank":225,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0645272455777617,"rank":226,"remainingConfigurations":444},{"removed":"simpleqa","score":0.07142433025600492,"rank":225,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06779446311712377,"rank":226,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.06778409153178015,"rank":226,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.06779380288578195,"rank":226,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0679157058590158,"rank":226,"remainingConfigurations":444},{"removed":"vibe-code","score":0.06760239389691655,"rank":226,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06785081072946451,"rank":226,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-122b-a10b--effort-non-reasoning":{"score":0.06532580541220011,"rank":227,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05892407541091247,"rank":157,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.08349896726231588,"rank":222,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05171462748320956,"rank":228,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06486767328180232,"rank":227,"remainingConfigurations":444},{"removed":"Scale","score":0.07550261113349149,"rank":227,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.06484653366217755,"rank":227,"remainingConfigurations":444},{"removed":"Cognition","score":0.06398633290924113,"rank":227,"remainingConfigurations":444},{"removed":"LiveBench","score":0.06760143958413664,"rank":226,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.06739666068254838,"rank":227,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.057881201731174954,"rank":226,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06267943211549346,"rank":227,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.06530333746094531,"rank":227,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06339378054372814,"rank":227,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.06523327898802751,"rank":227,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.06532580541220011,"rank":227,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06581634358564045,"rank":227,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06378420501893986,"rank":227,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06573996200783169,"rank":227,"remainingConfigurations":444},{"removed":"briefcase","score":0.06489876568173943,"rank":227,"remainingConfigurations":444},{"removed":"aime","score":0.06861199301824687,"rank":226,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06616288860723223,"rank":227,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06558019165334998,"rank":228,"remainingConfigurations":444},{"removed":"automationbench","score":0.06486060120888872,"rank":227,"remainingConfigurations":444},{"removed":"critpt","score":0.06425201380949012,"rank":230,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.06522966316852491,"rank":227,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0662596656489717,"rank":228,"remainingConfigurations":444},{"removed":"gdpval","score":0.06530984754176493,"rank":227,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06466480103061001,"rank":228,"remainingConfigurations":444},{"removed":"gpqa","score":0.06278931043656431,"rank":230,"remainingConfigurations":444},{"removed":"harvey","score":0.06453089219561407,"rank":227,"remainingConfigurations":444},{"removed":"hle","score":0.07028568441837775,"rank":228,"remainingConfigurations":444},{"removed":"ifbench","score":0.06705801219332938,"rank":226,"remainingConfigurations":444},{"removed":"itbench","score":0.0648079733547946,"rank":227,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06518716262903713,"rank":226,"remainingConfigurations":444},{"removed":"math500","score":0.06555057947142164,"rank":227,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06736274318261937,"rank":227,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.06989772971182415,"rank":227,"remainingConfigurations":444},{"removed":"omniscience","score":0.06579159071686244,"rank":222,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0631759064164644,"rank":228,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06609483610469147,"rank":227,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0639755483882294,"rank":228,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08049710961399337,"rank":225,"remainingConfigurations":444},{"removed":"deepswe","score":0.05175088872982869,"rank":228,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06534035762272834,"rank":227,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.06460634645006387,"rank":227,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06398633290924113,"rank":227,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06456101634424925,"rank":227,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.06444742963161136,"rank":227,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.06530263699754278,"rank":227,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06506572467947443,"rank":227,"remainingConfigurations":444},{"removed":"livebench-math","score":0.06543099231281187,"rank":227,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.06453258324097745,"rank":227,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06632085422134194,"rank":227,"remainingConfigurations":444},{"removed":"livebench-data","score":0.06534295460404636,"rank":227,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.06402555399712635,"rank":227,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.06488370957288216,"rank":227,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06678962909301688,"rank":227,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.06739666068254838,"rank":227,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0669632404595423,"rank":227,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05349608894570088,"rank":234,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0684054695699932,"rank":227,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06506877983520439,"rank":227,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.06508507516765041,"rank":227,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.06508133184420227,"rank":227,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.06519246475300486,"rank":227,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0649057778334208,"rank":227,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06514442031143802,"rank":227,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-low":{"score":0.06437908240754836,"rank":228,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04689355566081659,"rank":160,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07719376059892906,"rank":228,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0518192081598304,"rank":227,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06433515993617188,"rank":228,"remainingConfigurations":444},{"removed":"Scale","score":0.07420321537309271,"rank":228,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0637607329186947,"rank":228,"remainingConfigurations":444},{"removed":"Cognition","score":0.07664425668412657,"rank":215,"remainingConfigurations":444},{"removed":"LiveBench","score":0.06683696270880363,"rank":227,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0641316598799099,"rank":229,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05958681164859309,"rank":225,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06106051523458442,"rank":229,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.06436179374568445,"rank":228,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06265339178294653,"rank":228,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0643159333751978,"rank":228,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.06437908240754836,"rank":228,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06503961652825348,"rank":228,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06324150229186017,"rank":228,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06481310574645748,"rank":229,"remainingConfigurations":444},{"removed":"briefcase","score":0.06422958665082298,"rank":228,"remainingConfigurations":444},{"removed":"aime","score":0.06902070674698742,"rank":225,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06515410851448268,"rank":229,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06447550962631414,"rank":230,"remainingConfigurations":444},{"removed":"automationbench","score":0.06408241068461355,"rank":228,"remainingConfigurations":444},{"removed":"critpt","score":0.06388002994148105,"rank":231,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.06451558965186088,"rank":229,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.06303090322349174,"rank":229,"remainingConfigurations":444},{"removed":"gdpval","score":0.06381427350869769,"rank":228,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06471111287373353,"rank":227,"remainingConfigurations":444},{"removed":"gpqa","score":0.06317926760117824,"rank":228,"remainingConfigurations":444},{"removed":"harvey","score":0.06356292667306426,"rank":228,"remainingConfigurations":444},{"removed":"hle","score":0.06994103564642032,"rank":229,"remainingConfigurations":444},{"removed":"ifbench","score":0.06410083144321456,"rank":227,"remainingConfigurations":444},{"removed":"itbench","score":0.06412583201991,"rank":228,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06468646001699711,"rank":227,"remainingConfigurations":444},{"removed":"math500","score":0.06455773280052979,"rank":228,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06668155749833582,"rank":228,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.06880167325855553,"rank":229,"remainingConfigurations":444},{"removed":"omniscience","score":0.06139410593951516,"rank":227,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0642349496033198,"rank":227,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06492073980395466,"rank":228,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06533761333206216,"rank":227,"remainingConfigurations":444},{"removed":"arc-agi","score":0.08287470812101384,"rank":224,"remainingConfigurations":444},{"removed":"deepswe","score":0.05183161420336193,"rank":227,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06439310999025206,"rank":228,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.06219096146680265,"rank":229,"remainingConfigurations":444},{"removed":"frontiercode","score":0.07664425668412657,"rank":215,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06360661582776753,"rank":228,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0635598089825223,"rank":228,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.06436175503554213,"rank":228,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06408685873258968,"rank":228,"remainingConfigurations":444},{"removed":"livebench-math","score":0.064511097261787,"rank":228,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.06360136421804098,"rank":228,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06532768156014963,"rank":228,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0643263847074499,"rank":228,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.06307045052864077,"rank":228,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.06396049341045204,"rank":228,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06590376760648071,"rank":228,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0641316598799099,"rank":229,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06035841543982263,"rank":232,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05950687798517055,"rank":230,"remainingConfigurations":444},{"removed":"simpleqa","score":0.06738112187304664,"rank":228,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06413759921436314,"rank":228,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0641250893663202,"rank":228,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0641855154587129,"rank":228,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0642141461192774,"rank":228,"remainingConfigurations":444},{"removed":"vibe-code","score":0.063931012381611,"rank":228,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06422421093418827,"rank":228,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-pro--effort-non-reasoning":{"score":0.06389493893717302,"rank":229,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.08243147582090377,"rank":223,"remainingConfigurations":444},{"removed":"Datacurve","score":0.05056794553331556,"rank":229,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.06333402788573929,"rank":229,"remainingConfigurations":444},{"removed":"Scale","score":0.07402788394189531,"rank":229,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.06320762059299836,"rank":229,"remainingConfigurations":444},{"removed":"Cognition","score":0.0609190635854076,"rank":231,"remainingConfigurations":444},{"removed":"LiveBench","score":0.06672566273234502,"rank":228,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.06572771201190795,"rank":228,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.06486652309987365,"rank":222,"remainingConfigurations":431},{"removed":"Vals AI","score":0.06150633747283927,"rank":228,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.06386661621113744,"rank":229,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.06191664868091109,"rank":229,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.06378034927002796,"rank":229,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.06389493893717302,"rank":229,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06443248440210092,"rank":229,"remainingConfigurations":444},{"removed":"All provider reports","score":0.062325052392545176,"rank":229,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06484735538314929,"rank":228,"remainingConfigurations":444},{"removed":"briefcase","score":0.0571934172339531,"rank":232,"remainingConfigurations":444},{"removed":"aime","score":0.06287284877123321,"rank":230,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06527216999723302,"rank":228,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.07206339771442725,"rank":222,"remainingConfigurations":444},{"removed":"automationbench","score":0.05480760205463325,"rank":233,"remainingConfigurations":444},{"removed":"critpt","score":0.09167847054233731,"rank":210,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.06454114370752671,"rank":228,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.07045489330382035,"rank":224,"remainingConfigurations":444},{"removed":"gdpval","score":0.057561215938215664,"rank":232,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06403940249398701,"rank":229,"remainingConfigurations":444},{"removed":"gpqa","score":0.06252486809599732,"rank":231,"remainingConfigurations":444},{"removed":"harvey","score":0.06323036835133243,"rank":229,"remainingConfigurations":444},{"removed":"hle","score":0.07816177972027705,"rank":223,"remainingConfigurations":444},{"removed":"ifbench","score":0.06101497201776771,"rank":229,"remainingConfigurations":444},{"removed":"itbench","score":0.06374337715826385,"rank":229,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06303594612826989,"rank":229,"remainingConfigurations":444},{"removed":"math500","score":0.06372170968717082,"rank":229,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06508829477697096,"rank":229,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.06891292235749376,"rank":228,"remainingConfigurations":444},{"removed":"omniscience","score":0.04779161306919161,"rank":244,"remainingConfigurations":444},{"removed":"tau-bench","score":0.06190653613526564,"rank":230,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06485852522624069,"rank":229,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.06089187541648975,"rank":230,"remainingConfigurations":444},{"removed":"arc-agi","score":0.07954862997966745,"rank":227,"remainingConfigurations":444},{"removed":"deepswe","score":0.05060009682211588,"rank":229,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06391115594970571,"rank":229,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.06304833848422521,"rank":228,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0609190635854076,"rank":231,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06306445063473153,"rank":229,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.06315231470525864,"rank":229,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.06385595546370454,"rank":229,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06362596548078336,"rank":229,"remainingConfigurations":444},{"removed":"livebench-math","score":0.06395931399092507,"rank":229,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0631562584685089,"rank":229,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06491969047277824,"rank":229,"remainingConfigurations":444},{"removed":"livebench-data","score":0.06388949578171697,"rank":229,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0625761088620434,"rank":229,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.06345453907822222,"rank":229,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06535805722230863,"rank":229,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.06572771201190795,"rank":228,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06387446847920021,"rank":228,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06034584747320695,"rank":228,"remainingConfigurations":444},{"removed":"simpleqa","score":0.06708248522830225,"rank":229,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0636575909599816,"rank":229,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.06364775174530482,"rank":229,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.063663557411564,"rank":229,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.06376298983337426,"rank":229,"remainingConfigurations":444},{"removed":"vibe-code","score":0.06346903878263009,"rank":229,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06371079617179905,"rank":229,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-mini--effort-high":{"score":0.0621780261829154,"rank":230,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03868294960429871,"rank":170,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.08210915954964149,"rank":224,"remainingConfigurations":444},{"removed":"Datacurve","score":0.04851993103226474,"rank":230,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.062103280765114004,"rank":230,"remainingConfigurations":444},{"removed":"Scale","score":0.07229873628270213,"rank":230,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.061304877996630036,"rank":230,"remainingConfigurations":444},{"removed":"Cognition","score":0.060322744725278515,"rank":232,"remainingConfigurations":444},{"removed":"LiveBench","score":0.06324631430640348,"rank":229,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.06387555954272887,"rank":230,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0659705589901528,"rank":221,"remainingConfigurations":431},{"removed":"Vals AI","score":0.058835749040999884,"rank":230,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.062154866341287036,"rank":230,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.060378150544127186,"rank":230,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0620821139141153,"rank":230,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0621780261829154,"rank":230,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06267516925836931,"rank":230,"remainingConfigurations":444},{"removed":"All provider reports","score":0.06076819018532564,"rank":230,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0625802068761369,"rank":230,"remainingConfigurations":444},{"removed":"briefcase","score":0.06325204448586784,"rank":229,"remainingConfigurations":444},{"removed":"aime","score":0.06068801647772045,"rank":231,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06303656884558644,"rank":230,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06057692202709147,"rank":232,"remainingConfigurations":444},{"removed":"automationbench","score":0.06208264697515531,"rank":229,"remainingConfigurations":444},{"removed":"critpt","score":0.06579450298676132,"rank":229,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0623291046701242,"rank":230,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.06225766114967466,"rank":230,"remainingConfigurations":444},{"removed":"gdpval","score":0.06233943175534908,"rank":229,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06138469195978244,"rank":231,"remainingConfigurations":444},{"removed":"gpqa","score":0.06058740020648793,"rank":232,"remainingConfigurations":444},{"removed":"harvey","score":0.061387217220164984,"rank":230,"remainingConfigurations":444},{"removed":"hle","score":0.06726920553718287,"rank":231,"remainingConfigurations":444},{"removed":"ifbench","score":0.05862922454254502,"rank":232,"remainingConfigurations":444},{"removed":"itbench","score":0.062012553946810045,"rank":230,"remainingConfigurations":444},{"removed":"livecodebench","score":0.06115126680223803,"rank":230,"remainingConfigurations":444},{"removed":"math500","score":0.06233504100053599,"rank":230,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06444498191284537,"rank":230,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.067463187455481,"rank":231,"remainingConfigurations":444},{"removed":"omniscience","score":0.05907093505169154,"rank":230,"remainingConfigurations":444},{"removed":"tau-bench","score":0.061885083978070236,"rank":231,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0628107974421966,"rank":230,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0637063744371188,"rank":229,"remainingConfigurations":444},{"removed":"arc-agi","score":0.07930600902937303,"rank":228,"remainingConfigurations":444},{"removed":"deepswe","score":0.048545603388163654,"rank":230,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.06219216029029312,"rank":230,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05978669130667428,"rank":230,"remainingConfigurations":444},{"removed":"frontiercode","score":0.060322744725278515,"rank":232,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.06136434728868225,"rank":230,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.061427474157191984,"rank":230,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.062143510535122744,"rank":230,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.06189695669892953,"rank":230,"remainingConfigurations":444},{"removed":"livebench-math","score":0.06225759076475986,"rank":230,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.061483098523829334,"rank":230,"remainingConfigurations":444},{"removed":"livebench-language","score":0.06308142946721597,"rank":230,"remainingConfigurations":444},{"removed":"livebench-data","score":0.06214947869722284,"rank":230,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.060926577465715094,"rank":230,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.061725896059499206,"rank":230,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06366554946735072,"rank":230,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.06387555954272887,"rank":230,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06220333807587066,"rank":229,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06166174043914977,"rank":227,"remainingConfigurations":444},{"removed":"simpleqa","score":0.06519774552049605,"rank":230,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.06193255511596663,"rank":230,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.06192800243718186,"rank":230,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.06197834348728059,"rank":230,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.062029599749718216,"rank":230,"remainingConfigurations":444},{"removed":"vibe-code","score":0.06174620097932665,"rank":230,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.06199871800795314,"rank":230,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5.1--effort-non-reasoning":{"score":0.05955118311297708,"rank":231,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04484687206078661,"rank":163,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07621759909899271,"rank":229,"remainingConfigurations":444},{"removed":"Datacurve","score":0.04690924922818784,"rank":231,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05909804463061937,"rank":231,"remainingConfigurations":444},{"removed":"Scale","score":0.06909795929375817,"rank":231,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05906926481443923,"rank":231,"remainingConfigurations":444},{"removed":"Cognition","score":0.058103414064802184,"rank":233,"remainingConfigurations":444},{"removed":"LiveBench","score":0.06143568570412276,"rank":230,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.06129273354800504,"rank":231,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.06363291385223036,"rank":223,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05686842609939479,"rank":231,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.059528378708743744,"rank":231,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.057763226199794786,"rank":231,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05947313620833521,"rank":231,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05955118311297708,"rank":231,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.06000118100203996,"rank":231,"remainingConfigurations":444},{"removed":"All provider reports","score":0.058126328475174634,"rank":231,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.06002063720764303,"rank":231,"remainingConfigurations":444},{"removed":"briefcase","score":0.05926412715621198,"rank":230,"remainingConfigurations":444},{"removed":"aime","score":0.05954101541373691,"rank":232,"remainingConfigurations":444},{"removed":"apex-agents","score":0.06041424605207585,"rank":231,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06322054164966887,"rank":231,"remainingConfigurations":444},{"removed":"automationbench","score":0.05922668758736808,"rank":230,"remainingConfigurations":444},{"removed":"critpt","score":0.07432714988474311,"rank":224,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.059594643753487275,"rank":231,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.060685560797788946,"rank":231,"remainingConfigurations":444},{"removed":"gdpval","score":0.059341740552950044,"rank":230,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0601424065271165,"rank":232,"remainingConfigurations":444},{"removed":"gpqa","score":0.05600801798287841,"rank":236,"remainingConfigurations":444},{"removed":"harvey","score":0.058834127555433706,"rank":231,"remainingConfigurations":444},{"removed":"hle","score":0.059403570847429144,"rank":235,"remainingConfigurations":444},{"removed":"ifbench","score":0.06180286868488546,"rank":228,"remainingConfigurations":444},{"removed":"itbench","score":0.059113998229612004,"rank":231,"remainingConfigurations":444},{"removed":"livecodebench","score":0.05949649771372199,"rank":231,"remainingConfigurations":444},{"removed":"math500","score":0.0596842070578203,"rank":231,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06139989717914002,"rank":231,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.06449710088492284,"rank":232,"remainingConfigurations":444},{"removed":"omniscience","score":0.0550009181527917,"rank":233,"remainingConfigurations":444},{"removed":"tau-bench","score":0.051337457087905804,"rank":237,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.06031102221247434,"rank":231,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05577838993330711,"rank":233,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0737650949473324,"rank":230,"remainingConfigurations":444},{"removed":"deepswe","score":0.04694608857959379,"rank":231,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0595648843165913,"rank":231,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.058629117995903555,"rank":231,"remainingConfigurations":444},{"removed":"frontiercode","score":0.058103414064802184,"rank":233,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.05879143638709886,"rank":231,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.058825280301695766,"rank":231,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.05951859147774136,"rank":231,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05929703989285845,"rank":231,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05965201295977813,"rank":231,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.058814966623026384,"rank":231,"remainingConfigurations":444},{"removed":"livebench-language","score":0.060488093013005756,"rank":231,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05956616676580182,"rank":231,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.058342726087107555,"rank":231,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0591464320707332,"rank":231,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.06089065440197516,"rank":231,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.06129273354800504,"rank":231,"remainingConfigurations":444},{"removed":"frontiermath","score":0.06194692236223103,"rank":230,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04944631258440877,"rank":239,"remainingConfigurations":444},{"removed":"simpleqa","score":0.06131740049665305,"rank":231,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0593149758106305,"rank":231,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.059330264614247154,"rank":231,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.059322932408829604,"rank":231,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05943544908605519,"rank":231,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05916407959844989,"rank":231,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.059379275350945275,"rank":231,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-mini--effort-medium":{"score":0.05773029012157312,"rank":232,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03788101955982394,"rank":172,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0759689222713733,"rank":230,"remainingConfigurations":444},{"removed":"Datacurve","score":0.04446709987391203,"rank":233,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05774575896279819,"rank":232,"remainingConfigurations":444},{"removed":"Scale","score":0.0673102848239352,"rank":232,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05696536522496162,"rank":232,"remainingConfigurations":444},{"removed":"Cognition","score":0.06487525801648439,"rank":226,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05998885682486122,"rank":231,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05787746712120987,"rank":233,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.057675839172856486,"rank":227,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05475087493249881,"rank":232,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05770772796778792,"rank":232,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.05610768697552641,"rank":232,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05764056504224238,"rank":232,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05773029012157312,"rank":232,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05840871602238356,"rank":232,"remainingConfigurations":444},{"removed":"All provider reports","score":0.056677632415960404,"rank":232,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05812177511445079,"rank":232,"remainingConfigurations":444},{"removed":"briefcase","score":0.05743483892515131,"rank":231,"remainingConfigurations":444},{"removed":"aime","score":0.057574773414889896,"rank":234,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05841659544277123,"rank":232,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05742772450533271,"rank":233,"remainingConfigurations":444},{"removed":"automationbench","score":0.05734264025306319,"rank":231,"remainingConfigurations":444},{"removed":"critpt","score":0.05616642528880853,"rank":233,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.057763247702342486,"rank":232,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05818270089566594,"rank":232,"remainingConfigurations":444},{"removed":"gdpval","score":0.05778803328770441,"rank":231,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05807033999419744,"rank":233,"remainingConfigurations":444},{"removed":"gpqa","score":0.05690725094018076,"rank":234,"remainingConfigurations":444},{"removed":"harvey","score":0.057009120966327126,"rank":232,"remainingConfigurations":444},{"removed":"hle","score":0.06332590107083502,"rank":233,"remainingConfigurations":444},{"removed":"ifbench","score":0.0563286675846589,"rank":234,"remainingConfigurations":444},{"removed":"itbench","score":0.057416314519809185,"rank":232,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0581061757502912,"rank":232,"remainingConfigurations":444},{"removed":"math500","score":0.05792126609658841,"rank":232,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05981524927666499,"rank":233,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.062026522985660464,"rank":233,"remainingConfigurations":444},{"removed":"omniscience","score":0.05233926403680967,"rank":236,"remainingConfigurations":444},{"removed":"tau-bench","score":0.06199615706639381,"rank":229,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05828268606456968,"rank":232,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05689397781448207,"rank":232,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0737045159181131,"rank":231,"remainingConfigurations":444},{"removed":"deepswe","score":0.0444737341290724,"rank":233,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.057741615780104665,"rank":232,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.056302429775366675,"rank":232,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06487525801648439,"rank":226,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0569877659714948,"rank":232,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.057065326738849155,"rank":232,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.057702041798579684,"rank":232,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.057483258580047304,"rank":232,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05780950569205071,"rank":232,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.057047369114010565,"rank":232,"remainingConfigurations":444},{"removed":"livebench-language","score":0.058611061725388804,"rank":232,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05768110354170251,"rank":232,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.056546459909025105,"rank":232,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05734191170368557,"rank":232,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05912208379159939,"rank":232,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05787746712120987,"rank":233,"remainingConfigurations":444},{"removed":"frontiermath","score":0.057896443031655136,"rank":233,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05433729509035215,"rank":232,"remainingConfigurations":444},{"removed":"simpleqa","score":0.06058386116915323,"rank":232,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05752688919263645,"rank":232,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05746461230910744,"rank":232,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05757185647495647,"rank":232,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.057553529433620305,"rank":232,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05729699486658469,"rank":232,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.057584481345326656,"rank":232,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m2--effort-reasoning":{"score":0.05656517979819281,"rank":233,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07303154748638406,"rank":231,"remainingConfigurations":444},{"removed":"Datacurve","score":0.044738862247134026,"rank":232,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05590130828202151,"rank":233,"remainingConfigurations":444},{"removed":"Scale","score":0.06606145880605908,"rank":233,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.056034013396774086,"rank":233,"remainingConfigurations":444},{"removed":"Cognition","score":0.05480528004540954,"rank":234,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05870607751412557,"rank":232,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0579819158357591,"rank":232,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05746614510993764,"rank":228,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05428520603685565,"rank":233,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05654156336302605,"rank":233,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.05480650466188308,"rank":233,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05646754784395572,"rank":233,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05656517979819281,"rank":233,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.057015478790040826,"rank":233,"remainingConfigurations":444},{"removed":"All provider reports","score":0.055148560585531546,"rank":233,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05700065073660681,"rank":233,"remainingConfigurations":444},{"removed":"briefcase","score":0.056268392638549235,"rank":233,"remainingConfigurations":444},{"removed":"aime","score":0.059275200273157296,"rank":233,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05738438782894611,"rank":233,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.055641213647346977,"rank":234,"remainingConfigurations":444},{"removed":"automationbench","score":0.05621179753482422,"rank":232,"remainingConfigurations":444},{"removed":"critpt","score":0.05504138164920073,"rank":234,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.056480251132964315,"rank":233,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05780117585284933,"rank":233,"remainingConfigurations":444},{"removed":"gdpval","score":0.05675332713844042,"rank":233,"remainingConfigurations":444},{"removed":"gmmlu","score":0.06351385654901151,"rank":230,"remainingConfigurations":444},{"removed":"gpqa","score":0.05705277887932409,"rank":233,"remainingConfigurations":444},{"removed":"harvey","score":0.05591153481823096,"rank":233,"remainingConfigurations":444},{"removed":"hle","score":0.06351902157735126,"rank":232,"remainingConfigurations":444},{"removed":"ifbench","score":0.05003727133614937,"rank":243,"remainingConfigurations":444},{"removed":"itbench","score":0.05602860970471902,"rank":233,"remainingConfigurations":444},{"removed":"livecodebench","score":0.052765528365337676,"rank":236,"remainingConfigurations":444},{"removed":"math500","score":0.05671675974066315,"rank":233,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.06004445639293484,"rank":232,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.061145368136839594,"rank":234,"remainingConfigurations":444},{"removed":"omniscience","score":0.05164663254668602,"rank":237,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05291574065543473,"rank":235,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05739432943898223,"rank":233,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.057423365028888174,"rank":231,"remainingConfigurations":444},{"removed":"arc-agi","score":0.07035612219708738,"rank":232,"remainingConfigurations":444},{"removed":"deepswe","score":0.044769440859348274,"rank":232,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05657918308104129,"rank":233,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.055603181184114746,"rank":233,"remainingConfigurations":444},{"removed":"frontiercode","score":0.05480528004540954,"rank":234,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.05579834091066566,"rank":233,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.055909218509442894,"rank":233,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.056530698945063,"rank":233,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05631549068764156,"rank":233,"remainingConfigurations":444},{"removed":"livebench-math","score":0.056631793384373234,"rank":233,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.055908787030710984,"rank":233,"remainingConfigurations":444},{"removed":"livebench-language","score":0.057473213883117935,"rank":233,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05654970282002336,"rank":233,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.055392506713515054,"rank":233,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05617458861320723,"rank":233,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05786931604706877,"rank":233,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0579819158357591,"rank":232,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0566909119756891,"rank":234,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05302829191008875,"rank":235,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05945844630895424,"rank":233,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05634894294822488,"rank":233,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05634206203330346,"rank":233,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05635748339012559,"rank":233,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05644736031496894,"rank":233,"remainingConfigurations":444},{"removed":"vibe-code","score":0.056185277262061024,"rank":233,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05639882770591772,"rank":233,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-6-luna--effort-non-reasoning":{"score":0.05502854653428089,"rank":234,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07024592110668976,"rank":233,"remainingConfigurations":444},{"removed":"Datacurve","score":0.043186993869961166,"rank":234,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.054525019367995455,"rank":234,"remainingConfigurations":444},{"removed":"Scale","score":0.06399032387475172,"rank":234,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.054403574137031306,"rank":234,"remainingConfigurations":444},{"removed":"Cognition","score":0.052188276918937355,"rank":235,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0573712522566547,"rank":233,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.056491612726491586,"rank":235,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.055882302477703094,"rank":230,"remainingConfigurations":431},{"removed":"Vals AI","score":0.052874957810281224,"rank":234,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05500408005448278,"rank":234,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.05329454777432551,"rank":234,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05492874178326127,"rank":234,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05502854653428089,"rank":234,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05548590473698831,"rank":234,"remainingConfigurations":444},{"removed":"All provider reports","score":0.05363980313128292,"rank":234,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.055752322746602856,"rank":234,"remainingConfigurations":444},{"removed":"briefcase","score":0.05023332698085888,"rank":240,"remainingConfigurations":444},{"removed":"aime","score":0.05456176074270822,"rank":238,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0561135589392144,"rank":234,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.06560626687529957,"rank":227,"remainingConfigurations":444},{"removed":"automationbench","score":0.05395213908404566,"rank":234,"remainingConfigurations":444},{"removed":"critpt","score":0.05086819777965171,"rank":241,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.055363122890087955,"rank":234,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.055893129429687556,"rank":234,"remainingConfigurations":444},{"removed":"gdpval","score":0.04963460556645929,"rank":242,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0553315668164411,"rank":234,"remainingConfigurations":444},{"removed":"gpqa","score":0.05408801691387519,"rank":237,"remainingConfigurations":444},{"removed":"harvey","score":0.05436969646490567,"rank":234,"remainingConfigurations":444},{"removed":"hle","score":0.06903216897246678,"rank":230,"remainingConfigurations":444},{"removed":"ifbench","score":0.052619628177414585,"rank":241,"remainingConfigurations":444},{"removed":"itbench","score":0.05480713765723211,"rank":234,"remainingConfigurations":444},{"removed":"livecodebench","score":0.05471209081001575,"rank":234,"remainingConfigurations":444},{"removed":"math500","score":0.05517121363148947,"rank":234,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.056488511562793775,"rank":234,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.07078039732033699,"rank":226,"remainingConfigurations":444},{"removed":"omniscience","score":0.04478801790244815,"rank":248,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05320683088399514,"rank":233,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.055690390132172835,"rank":234,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.052411495101481055,"rank":237,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06792370021687463,"rank":234,"remainingConfigurations":444},{"removed":"deepswe","score":0.04321541619961785,"rank":234,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05504260076728628,"rank":234,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05417072933128159,"rank":234,"remainingConfigurations":444},{"removed":"frontiercode","score":0.052188276918937355,"rank":235,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.054294451109152854,"rank":234,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.05438304421156396,"rank":234,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.05499537525888648,"rank":234,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05479424425256135,"rank":234,"remainingConfigurations":444},{"removed":"livebench-math","score":0.055086061353261745,"rank":234,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.05438207381907153,"rank":234,"remainingConfigurations":444},{"removed":"livebench-language","score":0.055925375735433214,"rank":234,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05502433707169691,"rank":234,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.05387540151726885,"rank":234,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05464242616217387,"rank":234,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05630908846160118,"rank":234,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.056491612726491586,"rank":235,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05511089366154282,"rank":235,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0518792230909991,"rank":236,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05782980409007099,"rank":234,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.054819335577357124,"rank":234,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.054811674400939314,"rank":234,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.054823668382396884,"rank":234,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.054914362545643726,"rank":234,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05465560354389542,"rank":234,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05486643579222495,"rank":234,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.6--effort-reasoning":{"score":0.053494224809493986,"rank":235,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06886387543610349,"rank":235,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0421599367183191,"rank":235,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05291245900016251,"rank":235,"remainingConfigurations":444},{"removed":"Scale","score":0.06239154068104938,"rank":235,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0529509583877056,"rank":235,"remainingConfigurations":444},{"removed":"Cognition","score":0.05157528605154491,"rank":237,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05552182509441891,"rank":234,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05479364001473294,"rank":236,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05427019146630272,"rank":232,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05128410003800335,"rank":235,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05347156480411001,"rank":235,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.051814342431086576,"rank":235,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05340149686911455,"rank":235,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.053494224809493986,"rank":235,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05392173335245857,"rank":235,"remainingConfigurations":444},{"removed":"All provider reports","score":0.052138800282978646,"rank":235,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.053957056907456995,"rank":235,"remainingConfigurations":444},{"removed":"briefcase","score":0.053180215022188164,"rank":234,"remainingConfigurations":444},{"removed":"aime","score":0.051967890774747026,"rank":240,"remainingConfigurations":444},{"removed":"apex-agents","score":0.054313820064807776,"rank":235,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05459641341525628,"rank":235,"remainingConfigurations":444},{"removed":"automationbench","score":0.0531635474779465,"rank":235,"remainingConfigurations":444},{"removed":"critpt","score":0.05105939011290749,"rank":240,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05344751354709051,"rank":235,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05468397768999811,"rank":236,"remainingConfigurations":444},{"removed":"gdpval","score":0.05333749708536348,"rank":234,"remainingConfigurations":444},{"removed":"gmmlu","score":0.052056502652533254,"rank":239,"remainingConfigurations":444},{"removed":"gpqa","score":0.05323683970719357,"rank":240,"remainingConfigurations":444},{"removed":"harvey","score":0.05286469054924031,"rank":235,"remainingConfigurations":444},{"removed":"hle","score":0.058735164774580795,"rank":237,"remainingConfigurations":444},{"removed":"ifbench","score":0.05696249512878113,"rank":233,"remainingConfigurations":444},{"removed":"itbench","score":0.05302400154514972,"rank":235,"remainingConfigurations":444},{"removed":"livecodebench","score":0.055918389316022214,"rank":233,"remainingConfigurations":444},{"removed":"math500","score":0.05370417019894511,"rank":235,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05528347593894448,"rank":235,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.057812086186586197,"rank":237,"remainingConfigurations":444},{"removed":"omniscience","score":0.04717014108429507,"rank":246,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05156896395886454,"rank":236,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05426320321466699,"rank":235,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05265442396863828,"rank":235,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06644599585854148,"rank":236,"remainingConfigurations":444},{"removed":"deepswe","score":0.04218883096482038,"rank":235,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05350769230239799,"rank":235,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05260560182751431,"rank":235,"remainingConfigurations":444},{"removed":"frontiercode","score":0.05157528605154491,"rank":237,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.05276309953357869,"rank":235,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.05286455945038354,"rank":235,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.05346237312742108,"rank":235,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05325491329522353,"rank":235,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05355722872781523,"rank":235,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.052869645094054035,"rank":235,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05435975091185986,"rank":235,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05348109382680987,"rank":235,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.05237674804545345,"rank":235,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0531221521188942,"rank":235,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05473564617037912,"rank":235,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05479364001473294,"rank":236,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05358725252048823,"rank":237,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05014360729213337,"rank":237,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05624423685710845,"rank":235,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.053288041821912734,"rank":235,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.053282529241375505,"rank":235,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05329607745873796,"rank":235,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.053382640263914205,"rank":235,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05313250184937377,"rank":235,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05333603224843022,"rank":235,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.6-27b--effort-non-reasoning":{"score":0.05285839823790497,"rank":236,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0466709222365124,"rank":161,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06720109332576221,"rank":240,"remainingConfigurations":444},{"removed":"Datacurve","score":0.041668074590573846,"rank":236,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.052517276489237985,"rank":236,"remainingConfigurations":444},{"removed":"Scale","score":0.06129581282329823,"rank":238,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05252026720058487,"rank":236,"remainingConfigurations":444},{"removed":"Cognition","score":0.05218364663437253,"rank":236,"remainingConfigurations":444},{"removed":"LiveBench","score":0.054656035108816996,"rank":237,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.054112527466735255,"rank":238,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05665391723136279,"rank":229,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05054702061371458,"rank":237,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.052840043946463154,"rank":236,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.05127609140862715,"rank":236,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05278883690954259,"rank":236,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05285839823790497,"rank":236,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05325036639941904,"rank":236,"remainingConfigurations":444},{"removed":"All provider reports","score":0.05159267112713819,"rank":236,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05323078032158598,"rank":236,"remainingConfigurations":444},{"removed":"briefcase","score":0.05255794224582461,"rank":236,"remainingConfigurations":444},{"removed":"aime","score":0.05648673048386476,"rank":236,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05357725952861934,"rank":237,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.051796592464267356,"rank":240,"remainingConfigurations":444},{"removed":"automationbench","score":0.05256855546048469,"rank":236,"remainingConfigurations":444},{"removed":"critpt","score":0.05175581233413736,"rank":238,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05287205290946315,"rank":236,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05374572925898491,"rank":237,"remainingConfigurations":444},{"removed":"gdpval","score":0.05126384765923605,"rank":237,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05328787223904702,"rank":235,"remainingConfigurations":444},{"removed":"gpqa","score":0.042354907578295624,"rank":255,"remainingConfigurations":444},{"removed":"harvey","score":0.052186128068965464,"rank":236,"remainingConfigurations":444},{"removed":"hle","score":0.05707050639233513,"rank":241,"remainingConfigurations":444},{"removed":"ifbench","score":0.055304775690623864,"rank":236,"remainingConfigurations":444},{"removed":"itbench","score":0.052456886538990305,"rank":236,"remainingConfigurations":444},{"removed":"livecodebench","score":0.05289638623639246,"rank":235,"remainingConfigurations":444},{"removed":"math500","score":0.05304321054083108,"rank":236,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.054644643355667384,"rank":236,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05565976092229119,"rank":239,"remainingConfigurations":444},{"removed":"omniscience","score":0.05552968038914826,"rank":232,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04983035090669882,"rank":241,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.053472165179456695,"rank":237,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.052643388091037906,"rank":236,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06483630813376669,"rank":240,"remainingConfigurations":444},{"removed":"deepswe","score":0.04170175965685852,"rank":236,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.052870665957829514,"rank":236,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05210514763282086,"rank":236,"remainingConfigurations":444},{"removed":"frontiercode","score":0.05218364663437253,"rank":236,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.05218918258748586,"rank":236,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.05219750437593778,"rank":236,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0528316140218535,"rank":236,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.052629488545436205,"rank":236,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05296892855801688,"rank":236,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.052168876759892284,"rank":236,"remainingConfigurations":444},{"removed":"livebench-language","score":0.053690324535527946,"rank":236,"remainingConfigurations":444},{"removed":"livebench-data","score":0.052883014951536605,"rank":236,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.05178282969496365,"rank":236,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0524898716242569,"rank":236,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05406318239839165,"rank":236,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.054112527466735255,"rank":238,"remainingConfigurations":444},{"removed":"frontiermath","score":0.047126413786427394,"rank":248,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.05785672338378503,"rank":231,"remainingConfigurations":444},{"removed":"simpleqa","score":0.055378865120830324,"rank":238,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05264771140846847,"rank":236,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05266377335778203,"rank":236,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.052645721076204514,"rank":236,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05275974686975277,"rank":236,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05252266208934655,"rank":236,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05269846816579241,"rank":236,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-medium-3.5--effort-reasoning":{"score":0.05269633352845284,"rank":237,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06778139714134884,"rank":237,"remainingConfigurations":444},{"removed":"Datacurve","score":0.041476314286164655,"rank":238,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05216280191476814,"rank":237,"remainingConfigurations":444},{"removed":"Scale","score":0.0615040034164837,"rank":237,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05215488815488534,"rank":237,"remainingConfigurations":444},{"removed":"Cognition","score":0.050709631901782216,"rank":239,"remainingConfigurations":444},{"removed":"LiveBench","score":0.054785107240369474,"rank":235,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05413076886154377,"rank":237,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05439113966214637,"rank":231,"remainingConfigurations":431},{"removed":"Vals AI","score":0.050625980536239824,"rank":236,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0526739065107073,"rank":237,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.051012677459305746,"rank":238,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05260461118531464,"rank":237,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05269633352845284,"rank":237,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.053112650376362446,"rank":237,"remainingConfigurations":444},{"removed":"All provider reports","score":0.05132758959240532,"rank":238,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.051703453655869175,"rank":239,"remainingConfigurations":444},{"removed":"briefcase","score":0.052587058647335407,"rank":235,"remainingConfigurations":444},{"removed":"aime","score":0.05240443792960919,"rank":239,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05364778478341727,"rank":236,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05196489413835689,"rank":238,"remainingConfigurations":444},{"removed":"automationbench","score":0.05140654925632616,"rank":238,"remainingConfigurations":444},{"removed":"critpt","score":0.0619378773096757,"rank":232,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04955101308927077,"rank":244,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.055845778062869465,"rank":235,"remainingConfigurations":444},{"removed":"gdpval","score":0.052127862752511495,"rank":236,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05299496848359419,"rank":236,"remainingConfigurations":444},{"removed":"gpqa","score":0.05369307611620847,"rank":238,"remainingConfigurations":444},{"removed":"harvey","score":0.05214564723724722,"rank":237,"remainingConfigurations":444},{"removed":"hle","score":0.05793974724827031,"rank":240,"remainingConfigurations":444},{"removed":"ifbench","score":0.04745449213729,"rank":251,"remainingConfigurations":444},{"removed":"itbench","score":0.052294598364498075,"rank":237,"remainingConfigurations":444},{"removed":"livecodebench","score":0.05251566017330999,"rank":237,"remainingConfigurations":444},{"removed":"math500","score":0.05294177856619075,"rank":237,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.054398105817054565,"rank":237,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05929907007981552,"rank":236,"remainingConfigurations":444},{"removed":"omniscience","score":0.04961407713422861,"rank":239,"remainingConfigurations":444},{"removed":"tau-bench","score":0.047337434937701255,"rank":245,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05357676243087006,"rank":236,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.052014382122944604,"rank":238,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06539520057631291,"rank":238,"remainingConfigurations":444},{"removed":"deepswe","score":0.0415066782445225,"rank":238,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05270990382706103,"rank":237,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05192567662832315,"rank":237,"remainingConfigurations":444},{"removed":"frontiercode","score":0.050709631901782216,"rank":239,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.051983147310025964,"rank":237,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.052075566281469136,"rank":237,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.052665813563588716,"rank":237,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05245569606342962,"rank":237,"remainingConfigurations":444},{"removed":"livebench-math","score":0.052753304264480834,"rank":237,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.05209037244231235,"rank":237,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0535616192385327,"rank":237,"remainingConfigurations":444},{"removed":"livebench-data","score":0.052680357682543026,"rank":237,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.051584396221498914,"rank":237,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05233074578438388,"rank":237,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.053915927257143996,"rank":237,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05413076886154377,"rank":237,"remainingConfigurations":444},{"removed":"frontiermath","score":0.052746081119498,"rank":239,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.049763344988891796,"rank":238,"remainingConfigurations":444},{"removed":"simpleqa","score":0.055405051449451466,"rank":236,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.052495229485985256,"rank":237,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05248726639881716,"rank":237,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05249738979198542,"rank":237,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.052589360850981655,"rank":237,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05233937969543831,"rank":237,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.052541133962180825,"rank":237,"remainingConfigurations":444}],"sharedOrderConflicts":0},"ernie-5.0-thinking-preview--effort-reasoning":{"score":0.052664137922462655,"rank":238,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06826610777406152,"rank":236,"remainingConfigurations":444},{"removed":"Datacurve","score":0.04156422905823802,"rank":237,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.051994492335679626,"rank":238,"remainingConfigurations":444},{"removed":"Scale","score":0.06154091082150734,"rank":236,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.052140352583320816,"rank":238,"remainingConfigurations":444},{"removed":"Cognition","score":0.0509892067922745,"rank":238,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05466458635412386,"rank":236,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05395710936486956,"rank":239,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05334143033720475,"rank":233,"remainingConfigurations":431},{"removed":"Vals AI","score":0.05050071115245101,"rank":238,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.052642008572202165,"rank":238,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.05101331639661843,"rank":237,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.052572311100592774,"rank":238,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.052664137922462655,"rank":238,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05308620836481857,"rank":238,"remainingConfigurations":444},{"removed":"All provider reports","score":0.051333486783904085,"rank":237,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05306414338608928,"rank":237,"remainingConfigurations":444},{"removed":"briefcase","score":0.052314358442210794,"rank":237,"remainingConfigurations":444},{"removed":"aime","score":0.05097549204238668,"rank":242,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05339315047339166,"rank":238,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.051707455621587545,"rank":241,"remainingConfigurations":444},{"removed":"automationbench","score":0.052277209014798126,"rank":237,"remainingConfigurations":444},{"removed":"critpt","score":0.04903479103933567,"rank":245,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05253887000923235,"rank":237,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05374299103022665,"rank":238,"remainingConfigurations":444},{"removed":"gdpval","score":0.05290649696951081,"rank":235,"remainingConfigurations":444},{"removed":"gmmlu","score":0.050038780170080004,"rank":245,"remainingConfigurations":444},{"removed":"gpqa","score":0.05271716018463432,"rank":241,"remainingConfigurations":444},{"removed":"harvey","score":0.05205036043171441,"rank":238,"remainingConfigurations":444},{"removed":"hle","score":0.05899559641030818,"rank":236,"remainingConfigurations":444},{"removed":"ifbench","score":0.05910538941235932,"rank":230,"remainingConfigurations":444},{"removed":"itbench","score":0.052162378084461815,"rank":238,"remainingConfigurations":444},{"removed":"livecodebench","score":0.049259310168379776,"rank":246,"remainingConfigurations":444},{"removed":"math500","score":0.0528973122894242,"rank":238,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05387664499587005,"rank":238,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.060416948239998845,"rank":235,"remainingConfigurations":444},{"removed":"omniscience","score":0.04853428883869645,"rank":242,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05064584727591361,"rank":238,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.053438555901800515,"rank":238,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05345081007921971,"rank":234,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06575716790410173,"rank":237,"remainingConfigurations":444},{"removed":"deepswe","score":0.04159257935272656,"rank":237,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.052677179487185644,"rank":238,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.051765716352928204,"rank":239,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0509892067922745,"rank":238,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.051940554252101645,"rank":238,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.052043559718449324,"rank":238,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.05263230583789991,"rank":238,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05243124935359558,"rank":238,"remainingConfigurations":444},{"removed":"livebench-math","score":0.052726679667149445,"rank":238,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.05204835859707549,"rank":238,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05351589864027956,"rank":238,"remainingConfigurations":444},{"removed":"livebench-data","score":0.052649167315566396,"rank":238,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.051564404076727945,"rank":238,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05229777348759799,"rank":238,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05388868901761925,"rank":238,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05395710936486956,"rank":239,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05278597227728071,"rank":238,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04934257090984213,"rank":240,"remainingConfigurations":444},{"removed":"simpleqa","score":0.055380864394656754,"rank":237,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05246138674139516,"rank":238,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05245449117462497,"rank":238,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05246972764383545,"rank":238,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05255271399614062,"rank":238,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05230747945272244,"rank":238,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05250821374663541,"rank":238,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.8-27b--effort-non-reasoning":{"score":0.05205981193727822,"rank":239,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06745871216012617,"rank":238,"remainingConfigurations":444},{"removed":"Datacurve","score":0.040888074281327846,"rank":239,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05160424324548132,"rank":239,"remainingConfigurations":444},{"removed":"Scale","score":0.06070951082608019,"rank":239,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05146650554786721,"rank":239,"remainingConfigurations":444},{"removed":"Cognition","score":0.04930522097225067,"rank":243,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05430897327918235,"rank":238,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05345488091664541,"rank":240,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05298456805488322,"rank":234,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04998449082504125,"rank":239,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.052036058587517135,"rank":239,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.050414940188985895,"rank":239,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.051965087444664874,"rank":239,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05205981193727822,"rank":239,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.052502270493167386,"rank":239,"remainingConfigurations":444},{"removed":"All provider reports","score":0.050750050889622145,"rank":239,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05270873112836999,"rank":238,"remainingConfigurations":444},{"removed":"briefcase","score":0.048181069545729836,"rank":249,"remainingConfigurations":444},{"removed":"aime","score":0.051626987806766646,"rank":241,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05300218013633844,"rank":239,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.048773805788416724,"rank":247,"remainingConfigurations":444},{"removed":"automationbench","score":0.050365538239679965,"rank":239,"remainingConfigurations":444},{"removed":"critpt","score":0.05404779855755228,"rank":236,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05227676495093786,"rank":238,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.052844296467741074,"rank":239,"remainingConfigurations":444},{"removed":"gdpval","score":0.04715007892386399,"rank":248,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05228936611438425,"rank":238,"remainingConfigurations":444},{"removed":"gpqa","score":0.04876724572033355,"rank":245,"remainingConfigurations":444},{"removed":"harvey","score":0.051408909334986395,"rank":239,"remainingConfigurations":444},{"removed":"hle","score":0.05815537952499994,"rank":238,"remainingConfigurations":444},{"removed":"ifbench","score":0.04976347383979154,"rank":245,"remainingConfigurations":444},{"removed":"itbench","score":0.05173621875408869,"rank":239,"remainingConfigurations":444},{"removed":"livecodebench","score":0.051764711590375684,"rank":239,"remainingConfigurations":444},{"removed":"math500","score":0.0520370715023914,"rank":239,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05341744108180813,"rank":239,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0557387300853063,"rank":238,"remainingConfigurations":444},{"removed":"omniscience","score":0.06988846224178034,"rank":221,"remainingConfigurations":444},{"removed":"tau-bench","score":0.047849572710656596,"rank":244,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05294177817039103,"rank":239,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05172252020952,"rank":239,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06511293548438139,"rank":239,"remainingConfigurations":444},{"removed":"deepswe","score":0.04091486319688079,"rank":239,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05207312303116889,"rank":239,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05131821973492142,"rank":240,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04930522097225067,"rank":243,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.05135976014912232,"rank":239,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.051445608822599055,"rank":239,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.05202856608503025,"rank":239,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05183481385623481,"rank":239,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05211478554937598,"rank":239,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.05144122544798405,"rank":239,"remainingConfigurations":444},{"removed":"livebench-language","score":0.052912580154732346,"rank":239,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05205568247499468,"rank":239,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.050962823067188696,"rank":239,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05169257426866908,"rank":239,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.053282830617974265,"rank":239,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05345488091664541,"rank":240,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05206971086117324,"rank":240,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.048998408566286455,"rank":241,"remainingConfigurations":444},{"removed":"simpleqa","score":0.054728165843258986,"rank":239,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.051862415077417214,"rank":239,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05185207172523979,"rank":239,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05186589836020239,"rank":240,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05194937715289144,"rank":239,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0517024221338415,"rank":239,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05190658110234612,"rank":239,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4--effort-non-reasoning":{"score":0.05057009842585819,"rank":240,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06563577014388774,"rank":241,"remainingConfigurations":444},{"removed":"Datacurve","score":0.039817558540925856,"rank":241,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05004571475659237,"rank":243,"remainingConfigurations":444},{"removed":"Scale","score":0.058917918306012784,"rank":242,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05004701181193752,"rank":241,"remainingConfigurations":444},{"removed":"Cognition","score":0.048621362297504765,"rank":245,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05259262524320016,"rank":239,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05177016343423082,"rank":241,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05097646093806477,"rank":236,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04849249100577321,"rank":240,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05054852984863609,"rank":240,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.048974048301266164,"rank":241,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0504809426365333,"rank":241,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05057009842585819,"rank":240,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.050983012553680096,"rank":240,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04928759464087019,"rank":241,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.051037897106399444,"rank":240,"remainingConfigurations":444},{"removed":"briefcase","score":0.050256715469044304,"rank":238,"remainingConfigurations":444},{"removed":"aime","score":0.05069171789000367,"rank":244,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05132106407010991,"rank":240,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.051464656345944326,"rank":242,"remainingConfigurations":444},{"removed":"automationbench","score":0.0502816743200254,"rank":241,"remainingConfigurations":444},{"removed":"critpt","score":0.04956737311972013,"rank":244,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05055429170695191,"rank":240,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05178980918102161,"rank":240,"remainingConfigurations":444},{"removed":"gdpval","score":0.050457200716389254,"rank":239,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05082450241161462,"rank":240,"remainingConfigurations":444},{"removed":"gpqa","score":0.0534139148513095,"rank":239,"remainingConfigurations":444},{"removed":"harvey","score":0.05000785643607761,"rank":240,"remainingConfigurations":444},{"removed":"hle","score":0.058046176987589355,"rank":239,"remainingConfigurations":444},{"removed":"ifbench","score":0.052748659851659725,"rank":240,"remainingConfigurations":444},{"removed":"itbench","score":0.0501110101660295,"rank":242,"remainingConfigurations":444},{"removed":"livecodebench","score":0.050607618127987364,"rank":241,"remainingConfigurations":444},{"removed":"math500","score":0.050836328775319704,"rank":240,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05220941508663984,"rank":242,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05184981274263121,"rank":248,"remainingConfigurations":444},{"removed":"omniscience","score":0.03877196388471242,"rank":261,"remainingConfigurations":444},{"removed":"tau-bench","score":0.057817140108133935,"rank":232,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.051361633403773366,"rank":240,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0448596321174411,"rank":251,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0634054331024858,"rank":242,"remainingConfigurations":444},{"removed":"deepswe","score":0.03984416642613716,"rank":241,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0505827160899787,"rank":240,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04975545332210043,"rank":241,"remainingConfigurations":444},{"removed":"frontiercode","score":0.048621362297504765,"rank":245,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04987437362168631,"rank":241,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.049973109590447866,"rank":241,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.050539744710754925,"rank":241,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05034525957322852,"rank":240,"remainingConfigurations":444},{"removed":"livebench-math","score":0.050628997259929615,"rank":241,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04997276049009075,"rank":241,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05139280256854593,"rank":240,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0505598058428671,"rank":240,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04950874942492054,"rank":240,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05021531281701049,"rank":241,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05175394241655992,"rank":240,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05177016343423082,"rank":241,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05070662482545901,"rank":242,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04734127479258018,"rank":243,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05318243447976013,"rank":240,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05037538232152075,"rank":240,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.050368093176199114,"rank":240,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.050382626516505546,"rank":241,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05046234595721047,"rank":240,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05022556918219373,"rank":240,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05042027740972937,"rank":241,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-nano--effort-high":{"score":0.05056321435917205,"rank":241,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04386461811321512,"rank":164,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06731225706513272,"rank":239,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03891125557271748,"rank":246,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05109969832539602,"rank":240,"remainingConfigurations":444},{"removed":"Scale","score":0.05922274914870718,"rank":240,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.05009567111623877,"rank":240,"remainingConfigurations":444},{"removed":"Cognition","score":0.05027526269270413,"rank":240,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05225092273121119,"rank":240,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04901545422119247,"rank":248,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04962998345578957,"rank":239,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04227103815299535,"rank":253,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.05054771601905181,"rank":241,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04924926416988449,"rank":240,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0504888186228274,"rank":240,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.05056321435917205,"rank":241,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05093532957864186,"rank":241,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04954216742617301,"rank":240,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05079266844671081,"rank":241,"remainingConfigurations":444},{"removed":"briefcase","score":0.05020740065075258,"rank":241,"remainingConfigurations":444},{"removed":"aime","score":0.049936722434418046,"rank":245,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05094304750996121,"rank":242,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05027403185982424,"rank":243,"remainingConfigurations":444},{"removed":"automationbench","score":0.05028401422168254,"rank":240,"remainingConfigurations":444},{"removed":"critpt","score":0.051106330580343216,"rank":239,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05058332900374479,"rank":239,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.050809236439407296,"rank":243,"remainingConfigurations":444},{"removed":"gdpval","score":0.05044412082017824,"rank":240,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05055279226945086,"rank":241,"remainingConfigurations":444},{"removed":"gpqa","score":0.04994103629174577,"rank":243,"remainingConfigurations":444},{"removed":"harvey","score":0.04882920615464651,"rank":246,"remainingConfigurations":444},{"removed":"hle","score":0.055515803345588505,"rank":242,"remainingConfigurations":444},{"removed":"ifbench","score":0.04977052686014688,"rank":244,"remainingConfigurations":444},{"removed":"itbench","score":0.050321893905303915,"rank":240,"remainingConfigurations":444},{"removed":"livecodebench","score":0.051008549348342654,"rank":240,"remainingConfigurations":444},{"removed":"math500","score":0.05059195676221081,"rank":242,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.053262319996861866,"rank":240,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05458597563931732,"rank":241,"remainingConfigurations":444},{"removed":"omniscience","score":0.04938082840994037,"rank":240,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05051174138935421,"rank":240,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.050836073007797224,"rank":242,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05158011895005812,"rank":241,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06363891481882915,"rank":241,"remainingConfigurations":444},{"removed":"deepswe","score":0.03894362514588284,"rank":246,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0505787759944857,"rank":241,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.047275397112826946,"rank":248,"remainingConfigurations":444},{"removed":"frontiercode","score":0.05027526269270413,"rank":240,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.049923225749485885,"rank":240,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.049988046207922576,"rank":240,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.050545390614221745,"rank":240,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.050269169031074805,"rank":241,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05073794867820048,"rank":240,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04998224388121474,"rank":240,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05131187404739843,"rank":241,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05050680145568134,"rank":241,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.049479730653119704,"rank":241,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.050310793803619115,"rank":240,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.051638876517043214,"rank":241,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04901545422119247,"rank":248,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05100402388836722,"rank":241,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.047015359844590064,"rank":244,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05276951827928172,"rank":242,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05019040361469743,"rank":242,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.048619825635982265,"rank":247,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05188620914209798,"rank":239,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04895999481620001,"rank":246,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04946975937859688,"rank":244,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05189950771579269,"rank":240,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-mini--effort-medium":{"score":0.050401243584308364,"rank":242,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.030756204572288833,"rank":175,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.07171222802364328,"rank":232,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03918018211575804,"rank":243,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.05040873891324907,"rank":241,"remainingConfigurations":444},{"removed":"Scale","score":0.05895102135069739,"rank":241,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04967087337053113,"rank":243,"remainingConfigurations":444},{"removed":"Cognition","score":0.04898998308623396,"rank":244,"remainingConfigurations":444},{"removed":"LiveBench","score":0.051538719742192624,"rank":242,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.057868307776706734,"rank":234,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05128322407684715,"rank":235,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04766182450344719,"rank":242,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.050381470770946325,"rank":242,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04891123819534257,"rank":242,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.050319469253098985,"rank":242,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.050401243584308364,"rank":242,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05081659566134208,"rank":242,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04923433748226316,"rank":242,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.05073786795332022,"rank":242,"remainingConfigurations":444},{"removed":"briefcase","score":0.050235472903065626,"rank":239,"remainingConfigurations":444},{"removed":"aime","score":0.049832119825791936,"rank":246,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05103523138426041,"rank":241,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04870979922888765,"rank":248,"remainingConfigurations":444},{"removed":"automationbench","score":0.05020269028635815,"rank":242,"remainingConfigurations":444},{"removed":"critpt","score":0.05016720295052273,"rank":243,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.05042386829385479,"rank":241,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05110275060656083,"rank":241,"remainingConfigurations":444},{"removed":"gdpval","score":0.050570395479797275,"rank":238,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0500532580521783,"rank":244,"remainingConfigurations":444},{"removed":"gpqa","score":0.049813116621997104,"rank":244,"remainingConfigurations":444},{"removed":"harvey","score":0.04975377081737898,"rank":241,"remainingConfigurations":444},{"removed":"hle","score":0.055431451148088194,"rank":243,"remainingConfigurations":444},{"removed":"ifbench","score":0.04797365022735617,"rank":249,"remainingConfigurations":444},{"removed":"itbench","score":0.050139135039436955,"rank":241,"remainingConfigurations":444},{"removed":"livecodebench","score":0.052171897202416724,"rank":238,"remainingConfigurations":444},{"removed":"math500","score":0.05081993551979009,"rank":241,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05246613607384972,"rank":241,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05497174985035188,"rank":240,"remainingConfigurations":444},{"removed":"omniscience","score":0.04698207957486827,"rank":247,"remainingConfigurations":444},{"removed":"tau-bench","score":0.05064014286604126,"rank":239,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.050927031313086006,"rank":241,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05021690856058883,"rank":243,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06925673358393457,"rank":233,"remainingConfigurations":444},{"removed":"deepswe","score":0.03919987409986292,"rank":243,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05041243468763882,"rank":242,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04826013315862337,"rank":246,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04898998308623396,"rank":244,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04971706145070812,"rank":242,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04979185646618423,"rank":242,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.050372983000119886,"rank":242,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05017165129121007,"rank":242,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05046701136743686,"rank":242,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0498183749645606,"rank":242,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05115894943787697,"rank":242,"remainingConfigurations":444},{"removed":"livebench-data","score":0.05037639462819573,"rank":242,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.049360094999976234,"rank":242,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.05003486995618986,"rank":242,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05163246875966257,"rank":242,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.057868307776706734,"rank":234,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05058169041775886,"rank":243,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.048032450980391966,"rank":242,"remainingConfigurations":444},{"removed":"simpleqa","score":0.052914391970746634,"rank":241,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05019944510664174,"rank":241,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05018992945897898,"rank":241,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.05023995529979724,"rank":242,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05027318186516547,"rank":241,"remainingConfigurations":444},{"removed":"vibe-code","score":0.05003950354896223,"rank":241,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.05025390499886628,"rank":242,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.6-35b-a3b--effort-non-reasoning":{"score":0.050230563938871764,"rank":243,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08097023855725728,"rank":150,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06395996073335598,"rank":244,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03969171073319907,"rank":242,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04989241843821431,"rank":244,"remainingConfigurations":444},{"removed":"Scale","score":0.05830602442950933,"rank":243,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04996089046300375,"rank":242,"remainingConfigurations":444},{"removed":"Cognition","score":0.04976512117919221,"rank":241,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0518650615370577,"rank":241,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.051417276588239275,"rank":242,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.032746656499557845,"rank":269,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04807878971024648,"rank":241,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.050212948277699974,"rank":243,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.048718603919690816,"rank":243,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.05016380417477833,"rank":243,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.050230563938871764,"rank":243,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.05060485167789219,"rank":243,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04902039918812647,"rank":243,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.050573695779612016,"rank":243,"remainingConfigurations":444},{"removed":"briefcase","score":0.04978907694551216,"rank":242,"remainingConfigurations":444},{"removed":"aime","score":0.05580003895631116,"rank":237,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0508895549392279,"rank":243,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.048307950572512796,"rank":250,"remainingConfigurations":444},{"removed":"automationbench","score":0.04978501675704835,"rank":243,"remainingConfigurations":444},{"removed":"critpt","score":0.05473561414355166,"rank":235,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.050209282180352366,"rank":242,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05090843543302665,"rank":242,"remainingConfigurations":444},{"removed":"gdpval","score":0.0482061309623835,"rank":247,"remainingConfigurations":444},{"removed":"gmmlu","score":0.05044354831233224,"rank":242,"remainingConfigurations":444},{"removed":"gpqa","score":0.04288969266345774,"rank":254,"remainingConfigurations":444},{"removed":"harvey","score":0.04958741760488555,"rank":242,"remainingConfigurations":444},{"removed":"hle","score":0.05333338850254071,"rank":247,"remainingConfigurations":444},{"removed":"ifbench","score":0.05594323730629236,"rank":235,"remainingConfigurations":444},{"removed":"itbench","score":0.049825563379707234,"rank":243,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04979643860389609,"rank":243,"remainingConfigurations":444},{"removed":"math500","score":0.05018034568943896,"rank":243,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.051467559529339214,"rank":244,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.051953468381389055,"rank":247,"remainingConfigurations":444},{"removed":"omniscience","score":0.05119322691176584,"rank":238,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0482632378551578,"rank":243,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.050815932736242096,"rank":243,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.048720683109786535,"rank":245,"remainingConfigurations":444},{"removed":"arc-agi","score":0.061630116865590945,"rank":245,"remainingConfigurations":444},{"removed":"deepswe","score":0.03972374617371053,"rank":242,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.05024229237881856,"rank":243,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04950950565513388,"rank":242,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04976512117919221,"rank":241,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04959025375166188,"rank":243,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04960087077192391,"rank":243,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.050205234949898765,"rank":243,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.05001218196925941,"rank":243,"remainingConfigurations":444},{"removed":"livebench-math","score":0.05033549651542371,"rank":243,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04957238270257475,"rank":243,"remainingConfigurations":444},{"removed":"livebench-language","score":0.051025870392539786,"rank":243,"remainingConfigurations":444},{"removed":"livebench-data","score":0.050253555598884246,"rank":243,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.049202715335913645,"rank":243,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04987834541365845,"rank":243,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05138283037571036,"rank":243,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.051417276588239275,"rank":242,"remainingConfigurations":444},{"removed":"frontiermath","score":0.060658548522593704,"rank":231,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.035146445470421485,"rank":265,"remainingConfigurations":444},{"removed":"simpleqa","score":0.052767207881423785,"rank":243,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.05002938886689325,"rank":243,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.05004428201326112,"rank":242,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0500279228544184,"rank":243,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.05013577804199577,"rank":242,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04990922390449517,"rank":242,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.050077815554119,"rank":243,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-opus-4-6--effort-low":{"score":0.04986829901736858,"rank":244,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04551560140054441,"rank":162,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.011645351288814491,"rank":360,"remainingConfigurations":444},{"removed":"Datacurve","score":0.04063825000776172,"rank":240,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.050329335932179864,"rank":242,"remainingConfigurations":444},{"removed":"Scale","score":0.0580976080911745,"rank":244,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04912898718438028,"rank":244,"remainingConfigurations":444},{"removed":"Cognition","score":0.06383506542475913,"rank":228,"remainingConfigurations":444},{"removed":"LiveBench","score":0.051486168611683904,"rank":244,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.049256557665864543,"rank":247,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.19447749061057115,"rank":139,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04759975607795328,"rank":243,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04985080280631863,"rank":244,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04848889690302547,"rank":244,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04980142227597314,"rank":244,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04986829901736858,"rank":244,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.050210610207827376,"rank":244,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04875700690787799,"rank":244,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.050066958498207116,"rank":244,"remainingConfigurations":444},{"removed":"briefcase","score":0.04939117722297961,"rank":243,"remainingConfigurations":444},{"removed":"aime","score":0.04842134595643246,"rank":249,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05031966237187577,"rank":244,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04973237659119927,"rank":244,"remainingConfigurations":444},{"removed":"automationbench","score":0.04959189224268659,"rank":244,"remainingConfigurations":444},{"removed":"critpt","score":0.05016840295628458,"rank":242,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.049859387098625925,"rank":243,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05011906264008286,"rank":246,"remainingConfigurations":444},{"removed":"gdpval","score":0.049715339403820856,"rank":241,"remainingConfigurations":444},{"removed":"gmmlu","score":0.049906575881247035,"rank":247,"remainingConfigurations":444},{"removed":"gpqa","score":0.048389966807993984,"rank":246,"remainingConfigurations":444},{"removed":"harvey","score":0.0492261264250275,"rank":243,"remainingConfigurations":444},{"removed":"hle","score":0.05444530526438538,"rank":245,"remainingConfigurations":444},{"removed":"ifbench","score":0.04922092660379959,"rank":247,"remainingConfigurations":444},{"removed":"itbench","score":0.04967001700690218,"rank":244,"remainingConfigurations":444},{"removed":"livecodebench","score":0.050290657103070256,"rank":242,"remainingConfigurations":444},{"removed":"math500","score":0.049902786271517445,"rank":244,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05147622232127202,"rank":243,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.053978719171626104,"rank":242,"remainingConfigurations":444},{"removed":"omniscience","score":0.04873709930659708,"rank":241,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04963564572704677,"rank":242,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.049971214135683194,"rank":246,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04937332584157022,"rank":244,"remainingConfigurations":444},{"removed":"arc-agi","score":0.011221346515431788,"rank":360,"remainingConfigurations":444},{"removed":"deepswe","score":0.04066408756373764,"rank":240,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04987900390966007,"rank":244,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.05180594653425386,"rank":238,"remainingConfigurations":444},{"removed":"frontiercode","score":0.06383506542475913,"rank":228,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04926617575761136,"rank":244,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.049223035099339535,"rank":244,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04984551515178678,"rank":244,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04959719067702592,"rank":244,"remainingConfigurations":444},{"removed":"livebench-math","score":0.049947706068747245,"rank":244,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04910074225886502,"rank":244,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05067691446834637,"rank":244,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04989287974542427,"rank":244,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04887223781228411,"rank":244,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04945789077262406,"rank":244,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05116727954036443,"rank":244,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.049256557665864543,"rank":247,"remainingConfigurations":444},{"removed":"frontiermath","score":0.05007053056892724,"rank":244,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.17788991988812186,"rank":145,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05165995567386175,"rank":247,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.049686068004867016,"rank":244,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04967258614436629,"rank":243,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.049697013650142285,"rank":244,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04974245295527124,"rank":243,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0495490816031719,"rank":243,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04968341010607227,"rank":244,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-omni-plus--effort-non-reasoning":{"score":0.04955807522144632,"rank":245,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06446847074285848,"rank":243,"remainingConfigurations":444},{"removed":"Datacurve","score":0.039026639363029816,"rank":244,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04907480120824756,"rank":245,"remainingConfigurations":444},{"removed":"Scale","score":0.057929537986525996,"rank":245,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04905042238376283,"rank":245,"remainingConfigurations":444},{"removed":"Cognition","score":0.04788181238730079,"rank":246,"remainingConfigurations":444},{"removed":"LiveBench","score":0.051522909174339354,"rank":243,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05097275508447228,"rank":243,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.050321195985863675,"rank":237,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04749775207794182,"rank":244,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04953702615279874,"rank":245,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.047992068783303345,"rank":245,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04947070869300455,"rank":245,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04955807522144632,"rank":245,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04995911740240409,"rank":245,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04829596592869744,"rank":245,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.049953634850747386,"rank":245,"remainingConfigurations":444},{"removed":"briefcase","score":0.04917626726847104,"rank":244,"remainingConfigurations":444},{"removed":"aime","score":0.04972859005917968,"rank":247,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05027078161619383,"rank":246,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04850944571999008,"rank":249,"remainingConfigurations":444},{"removed":"automationbench","score":0.04915687934282431,"rank":245,"remainingConfigurations":444},{"removed":"critpt","score":0.04895578447251386,"rank":246,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.049485476769410223,"rank":245,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.050591358154639825,"rank":244,"remainingConfigurations":444},{"removed":"gdpval","score":0.04959346108728014,"rank":243,"remainingConfigurations":444},{"removed":"gmmlu","score":0.050069700903947134,"rank":243,"remainingConfigurations":444},{"removed":"gpqa","score":0.04588456871611812,"rank":250,"remainingConfigurations":444},{"removed":"harvey","score":0.048965263290754124,"rank":244,"remainingConfigurations":444},{"removed":"hle","score":0.05359143693660138,"rank":246,"remainingConfigurations":444},{"removed":"ifbench","score":0.05048542032251816,"rank":242,"remainingConfigurations":444},{"removed":"itbench","score":0.04908508415281238,"rank":246,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0497296331607196,"rank":244,"remainingConfigurations":444},{"removed":"math500","score":0.04986991170082423,"rank":245,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05130890712693773,"rank":245,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.051139374300963526,"rank":250,"remainingConfigurations":444},{"removed":"omniscience","score":0.05304112343144501,"rank":234,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04426512522928417,"rank":250,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.05027775793655439,"rank":244,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05143737544170023,"rank":242,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06216027776666638,"rank":244,"remainingConfigurations":444},{"removed":"deepswe","score":0.039053070421909544,"rank":244,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.049570414290279814,"rank":245,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.048738105577825284,"rank":243,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04788181238730079,"rank":246,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.048876179555551104,"rank":245,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.048977040947640334,"rank":245,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.049528293380249555,"rank":245,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.049337021206381615,"rank":245,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04961645540513749,"rank":245,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04897298461312371,"rank":245,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05036574981365343,"rank":245,"remainingConfigurations":444},{"removed":"livebench-data","score":0.049546846877395884,"rank":245,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04851610331378555,"rank":245,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04921017343309212,"rank":245,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.05071917887548436,"rank":245,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05097275508447228,"rank":243,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04966206550529633,"rank":245,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04648239208567589,"rank":245,"remainingConfigurations":444},{"removed":"simpleqa","score":0.05212319704679952,"rank":245,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04936647926428089,"rank":245,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04935978331456526,"rank":244,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04937379105515618,"rank":245,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0494524592157027,"rank":244,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04922021074383704,"rank":245,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04941083169666097,"rank":245,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-pro-0424--effort-non-reasoning":{"score":0.04950868787942675,"rank":246,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06464862992579452,"rank":242,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03895181690169525,"rank":245,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04901138674808153,"rank":246,"remainingConfigurations":444},{"removed":"Scale","score":0.05786807218948803,"rank":246,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04899792727721267,"rank":246,"remainingConfigurations":444},{"removed":"Cognition","score":0.04756397012666059,"rank":247,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05147031939585022,"rank":245,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05087433302328687,"rank":244,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.05007762341505456,"rank":238,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04748053721229986,"rank":245,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04948756116114864,"rank":246,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.047943769331769005,"rank":246,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04942179155734391,"rank":246,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04950868787942675,"rank":246,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.049911494143398266,"rank":246,"remainingConfigurations":444},{"removed":"All provider reports","score":0.048249743223956754,"rank":246,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04993019557181618,"rank":246,"remainingConfigurations":444},{"removed":"briefcase","score":0.049045023991356025,"rank":245,"remainingConfigurations":444},{"removed":"aime","score":0.04969097052615868,"rank":248,"remainingConfigurations":444},{"removed":"apex-agents","score":0.05027187147452361,"rank":245,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0524747310928858,"rank":237,"remainingConfigurations":444},{"removed":"automationbench","score":0.04904734064727221,"rank":246,"remainingConfigurations":444},{"removed":"critpt","score":0.0465066189815749,"rank":250,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04946405518082938,"rank":246,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.05051788852448368,"rank":245,"remainingConfigurations":444},{"removed":"gdpval","score":0.04934879818097342,"rank":244,"remainingConfigurations":444},{"removed":"gmmlu","score":0.050014309427487115,"rank":246,"remainingConfigurations":444},{"removed":"gpqa","score":0.0560327890928283,"rank":235,"remainingConfigurations":444},{"removed":"harvey","score":0.0489515220090807,"rank":245,"remainingConfigurations":444},{"removed":"hle","score":0.06234317079321743,"rank":234,"remainingConfigurations":444},{"removed":"ifbench","score":0.054559047751784655,"rank":238,"remainingConfigurations":444},{"removed":"itbench","score":0.04910800577715715,"rank":245,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04955702885223037,"rank":245,"remainingConfigurations":444},{"removed":"math500","score":0.04975568504134822,"rank":246,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05113631528022957,"rank":246,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.053697791978737676,"rank":243,"remainingConfigurations":444},{"removed":"omniscience","score":0.038953889558565734,"rank":259,"remainingConfigurations":444},{"removed":"tau-bench","score":0.042777124600842605,"rank":252,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0502569194899222,"rank":245,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.043533611468428456,"rank":258,"remainingConfigurations":444},{"removed":"arc-agi","score":0.062404571477723964,"rank":243,"remainingConfigurations":444},{"removed":"deepswe","score":0.03897820051631056,"rank":245,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.049521083490502014,"rank":246,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.048687513642361006,"rank":244,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04756397012666059,"rank":247,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04882827114949707,"rank":246,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04892976846562309,"rank":246,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.049478712211204305,"rank":246,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0492873791652663,"rank":246,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04956668210822654,"rank":246,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.048922462488309726,"rank":246,"remainingConfigurations":444},{"removed":"livebench-language","score":0.05031634601634997,"rank":246,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0494986451269997,"rank":246,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.048467104366824554,"rank":246,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04916060883190985,"rank":246,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.050670091269094296,"rank":246,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05087433302328687,"rank":244,"remainingConfigurations":444},{"removed":"frontiermath","score":0.049552440743347505,"rank":246,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.046302418876019935,"rank":246,"remainingConfigurations":444},{"removed":"simpleqa","score":0.052072783699484704,"rank":246,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04931730621542466,"rank":246,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04931047700269425,"rank":245,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.049324460688084604,"rank":246,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04940310218253713,"rank":245,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04917076118748778,"rank":246,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0493615715821863,"rank":246,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-none":{"score":0.048869884349991066,"rank":247,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.043770887892926574,"rank":165,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06122785716939708,"rank":247,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03862198195357494,"rank":247,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04867670095570828,"rank":247,"remainingConfigurations":444},{"removed":"Scale","score":0.056518471213392034,"rank":248,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.048579969655679345,"rank":247,"remainingConfigurations":444},{"removed":"Cognition","score":0.04945781603665431,"rank":242,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04934183249113706,"rank":247,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05050138090775639,"rank":245,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04654570879812062,"rank":247,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04885540415026848,"rank":247,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04746918350101246,"rank":247,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04882398403640626,"rank":247,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.048869884349991066,"rank":247,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04920894719768105,"rank":247,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04775935964335417,"rank":247,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04916913488634603,"rank":248,"remainingConfigurations":444},{"removed":"briefcase","score":0.0486998146226866,"rank":247,"remainingConfigurations":444},{"removed":"aime","score":0.06519721298895169,"rank":229,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04946771918968199,"rank":248,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04909013326495401,"rank":246,"remainingConfigurations":444},{"removed":"automationbench","score":0.04871986028953874,"rank":247,"remainingConfigurations":444},{"removed":"critpt","score":0.048382801744066194,"rank":247,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04892841334313059,"rank":247,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0494078455813834,"rank":248,"remainingConfigurations":444},{"removed":"gdpval","score":0.04828980274571973,"rank":246,"remainingConfigurations":444},{"removed":"gmmlu","score":0.049198649687123584,"rank":248,"remainingConfigurations":444},{"removed":"gpqa","score":0.06664921761963631,"rank":225,"remainingConfigurations":444},{"removed":"harvey","score":0.0482307866753558,"rank":247,"remainingConfigurations":444},{"removed":"hle","score":0.05270190950711967,"rank":250,"remainingConfigurations":444},{"removed":"ifbench","score":0.04944689069182684,"rank":246,"remainingConfigurations":444},{"removed":"itbench","score":0.048590780197040724,"rank":247,"remainingConfigurations":444},{"removed":"livecodebench","score":0.048881389242448774,"rank":247,"remainingConfigurations":444},{"removed":"math500","score":0.04897965458192552,"rank":247,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.05073937446297896,"rank":247,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.052721215290247085,"rank":245,"remainingConfigurations":444},{"removed":"omniscience","score":0.04793850882490073,"rank":243,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04658540855082077,"rank":247,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04931513771055534,"rank":248,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04838675698094407,"rank":246,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05870762821399883,"rank":249,"remainingConfigurations":444},{"removed":"deepswe","score":0.03865615641670207,"rank":247,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.048880461136045376,"rank":247,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04828093890220036,"rank":245,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04945781603665431,"rank":242,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04832120193863552,"rank":247,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04818892911863398,"rank":248,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.048853879444518244,"rank":247,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.048668648521311274,"rank":247,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04902529957325208,"rank":247,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.048142557355152084,"rank":248,"remainingConfigurations":444},{"removed":"livebench-language","score":0.049620740272415996,"rank":247,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04891140220811035,"rank":247,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.047915594363918956,"rank":247,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.048511720655568996,"rank":247,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04999437025971201,"rank":247,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05050138090775639,"rank":245,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03678505453070723,"rank":268,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01937595334146124,"rank":303,"remainingConfigurations":444},{"removed":"simpleqa","score":0.052482688477855984,"rank":244,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.048665118147344644,"rank":247,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.048700560217740885,"rank":246,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.048665542048594156,"rank":247,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.048780478488259754,"rank":247,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04856619829145411,"rank":247,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04871670477586831,"rank":247,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-0528--effort-reasoning":{"score":0.04877180621090732,"rank":248,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06333298074981221,"rank":245,"remainingConfigurations":444},{"removed":"Datacurve","score":0.038428996589757757,"rank":248,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04816255893944401,"rank":248,"remainingConfigurations":444},{"removed":"Scale","score":0.057062854754736075,"rank":247,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04827868245007986,"rank":248,"remainingConfigurations":444},{"removed":"Cognition","score":0.04719914446151841,"rank":248,"remainingConfigurations":444},{"removed":"LiveBench","score":0.05066192023005206,"rank":246,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.05006241077223853,"rank":246,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04938805246891475,"rank":240,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04677400395324729,"rank":246,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.048751165566959985,"rank":248,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.047234486923278786,"rank":248,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04868678534988919,"rank":248,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04877180621090732,"rank":248,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.049163486960583036,"rank":248,"remainingConfigurations":444},{"removed":"All provider reports","score":0.047531673952252135,"rank":248,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04918123570462272,"rank":247,"remainingConfigurations":444},{"removed":"briefcase","score":0.048478252976731716,"rank":248,"remainingConfigurations":444},{"removed":"aime","score":0.050715589943110075,"rank":243,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04951166437534086,"rank":247,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0492419492615252,"rank":245,"remainingConfigurations":444},{"removed":"automationbench","score":0.04843999007487984,"rank":248,"remainingConfigurations":444},{"removed":"critpt","score":0.0451702650934532,"rank":252,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04875269741897331,"rank":248,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04981697653711894,"rank":247,"remainingConfigurations":444},{"removed":"gdpval","score":0.04893638812614722,"rank":245,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04700523372668444,"rank":252,"remainingConfigurations":444},{"removed":"gpqa","score":0.046567609009621064,"rank":248,"remainingConfigurations":444},{"removed":"harvey","score":0.04822297681988625,"rank":248,"remainingConfigurations":444},{"removed":"hle","score":0.05291050843356467,"rank":248,"remainingConfigurations":444},{"removed":"ifbench","score":0.05514315141814261,"rank":237,"remainingConfigurations":444},{"removed":"itbench","score":0.04834571920508441,"rank":248,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04708288495965529,"rank":249,"remainingConfigurations":444},{"removed":"math500","score":0.04774026231632502,"rank":248,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.048038560289057286,"rank":250,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05280827468430257,"rank":244,"remainingConfigurations":444},{"removed":"omniscience","score":0.040201743231260606,"rank":258,"remainingConfigurations":444},{"removed":"tau-bench","score":0.052976192353526415,"rank":234,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04951593882336396,"rank":247,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.05168993495315043,"rank":240,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06103138585430091,"rank":246,"remainingConfigurations":444},{"removed":"deepswe","score":0.038455422281659955,"rank":248,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.048784035655501434,"rank":248,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04792798202239274,"rank":247,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04719914446151841,"rank":248,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04809266665690453,"rank":248,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04819427134796714,"rank":247,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.048742652614006066,"rank":248,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0485548519618099,"rank":248,"remainingConfigurations":444},{"removed":"livebench-math","score":0.048830142652817675,"rank":248,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04819540639234427,"rank":247,"remainingConfigurations":444},{"removed":"livebench-language","score":0.049567269532999836,"rank":248,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04875926351424689,"rank":248,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.047745007154182444,"rank":248,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04842924402092246,"rank":248,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04991659016639962,"rank":248,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.05006241077223853,"rank":246,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04887716848376364,"rank":247,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04567019683933968,"rank":247,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0513128351611138,"rank":248,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.048582338123506506,"rank":248,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.048576117610536325,"rank":248,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04859026542550115,"rank":248,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04866781030554498,"rank":248,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04843881625324584,"rank":248,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04862624059931362,"rank":248,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5.2--effort-non-reasoning":{"score":0.047608998416181235,"rank":249,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03956437134345991,"rank":169,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0615009245881665,"rank":246,"remainingConfigurations":444},{"removed":"Datacurve","score":0.037448475067599706,"rank":249,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.047253204803224334,"rank":249,"remainingConfigurations":444},{"removed":"Scale","score":0.05540092091507332,"rank":249,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0472092255402154,"rank":249,"remainingConfigurations":444},{"removed":"Cognition","score":0.04684680726631171,"rank":249,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04908860449859235,"rank":248,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04889041455304319,"rank":249,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04912279114593274,"rank":241,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04557329357131592,"rank":248,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04759109634368385,"rank":249,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.046152735284012404,"rank":249,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.047542423994046686,"rank":249,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.047608998416181235,"rank":249,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04797079407790847,"rank":249,"remainingConfigurations":444},{"removed":"All provider reports","score":0.046440903399395696,"rank":249,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04805719699463196,"rank":249,"remainingConfigurations":444},{"removed":"briefcase","score":0.04752474464190023,"rank":250,"remainingConfigurations":444},{"removed":"aime","score":0.05696873158994484,"rank":235,"remainingConfigurations":444},{"removed":"apex-agents","score":0.048384088805487356,"rank":249,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05195370976452556,"rank":239,"remainingConfigurations":444},{"removed":"automationbench","score":0.047570828367863444,"rank":249,"remainingConfigurations":444},{"removed":"critpt","score":0.04232399305607165,"rank":256,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04773501369911377,"rank":249,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04865685999514604,"rank":249,"remainingConfigurations":444},{"removed":"gdpval","score":0.04122659540786982,"rank":263,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04796495076365894,"rank":249,"remainingConfigurations":444},{"removed":"gpqa","score":0.06281497425689936,"rank":229,"remainingConfigurations":444},{"removed":"harvey","score":0.04703111493836998,"rank":249,"remainingConfigurations":444},{"removed":"hle","score":0.0554000895488043,"rank":244,"remainingConfigurations":444},{"removed":"ifbench","score":0.04687457947605126,"rank":252,"remainingConfigurations":444},{"removed":"itbench","score":0.04736891326386583,"rank":249,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04742652537414673,"rank":248,"remainingConfigurations":444},{"removed":"math500","score":0.04767062425551621,"rank":249,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04911415252694875,"rank":248,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0515690648529993,"rank":249,"remainingConfigurations":444},{"removed":"omniscience","score":0.04775995639310332,"rank":245,"remainingConfigurations":444},{"removed":"tau-bench","score":0.043966329225009,"rank":251,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04820092312250493,"rank":249,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.045871919145680416,"rank":248,"remainingConfigurations":444},{"removed":"arc-agi","score":0.059374598144736834,"rank":247,"remainingConfigurations":444},{"removed":"deepswe","score":0.037475938122744835,"rank":249,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04762048445516614,"rank":249,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04692057461910592,"rank":249,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04684680726631171,"rank":249,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.047006729037676526,"rank":249,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04700359932101542,"rank":249,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04758632136985069,"rank":249,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.047408905440070585,"rank":249,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04770708756206932,"rank":249,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.046980740040791426,"rank":249,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04837099738743785,"rank":249,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0476227953846601,"rank":249,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0466314851036087,"rank":249,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0472685451836524,"rank":249,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04871781705510597,"rank":249,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04889041455304319,"rank":249,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03869451649413613,"rank":266,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.032663638257427956,"rank":271,"remainingConfigurations":444},{"removed":"simpleqa","score":0.050327890211474414,"rank":249,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04741610010281653,"rank":249,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04743125285890996,"rank":249,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04742119325208238,"rank":249,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.047513891536129914,"rank":249,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04729447648395218,"rank":249,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04746256575619273,"rank":249,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-27b--effort-non-reasoning":{"score":0.046850391382862476,"rank":250,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.061146804401130773,"rank":248,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03685509464861759,"rank":250,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.046395736863580915,"rank":250,"remainingConfigurations":444},{"removed":"Scale","score":0.05481457768728997,"rank":250,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04635834130677565,"rank":250,"remainingConfigurations":444},{"removed":"Cognition","score":0.045179155554779464,"rank":250,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04872767375298374,"rank":249,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04811345420072596,"rank":250,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.047512584715222385,"rank":243,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04489873226552344,"rank":249,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04683034211949922,"rank":250,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04536434807136844,"rank":250,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04676773517662781,"rank":250,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.046850391382862476,"rank":250,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04723346914650348,"rank":250,"remainingConfigurations":444},{"removed":"All provider reports","score":0.045655221053094115,"rank":250,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04722930212043247,"rank":250,"remainingConfigurations":444},{"removed":"briefcase","score":0.04636071982037468,"rank":251,"remainingConfigurations":444},{"removed":"aime","score":0.04713622318542809,"rank":251,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04752211388552351,"rank":250,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.045200843094004094,"rank":251,"remainingConfigurations":444},{"removed":"automationbench","score":0.04634630812348766,"rank":250,"remainingConfigurations":444},{"removed":"critpt","score":0.04767065094870065,"rank":248,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0467947429198405,"rank":250,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.047710392445447225,"rank":250,"remainingConfigurations":444},{"removed":"gdpval","score":0.04670696373678238,"rank":249,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04724971317363628,"rank":251,"remainingConfigurations":444},{"removed":"gpqa","score":0.04199602245876937,"rank":257,"remainingConfigurations":444},{"removed":"harvey","score":0.046291779548697363,"rank":250,"remainingConfigurations":444},{"removed":"hle","score":0.05115680602977105,"rank":252,"remainingConfigurations":444},{"removed":"ifbench","score":0.04917244523518182,"rank":248,"remainingConfigurations":444},{"removed":"itbench","score":0.046371037993860255,"rank":250,"remainingConfigurations":444},{"removed":"livecodebench","score":0.047044307639893174,"rank":250,"remainingConfigurations":444},{"removed":"math500","score":0.04705713601125536,"rank":250,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04849332254869503,"rank":249,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.049282610262716554,"rank":253,"remainingConfigurations":444},{"removed":"omniscience","score":0.052351353624479825,"rank":235,"remainingConfigurations":444},{"removed":"tau-bench","score":0.042402358594747835,"rank":254,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.047532994191778526,"rank":250,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04474045514797061,"rank":253,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05893466896396495,"rank":248,"remainingConfigurations":444},{"removed":"deepswe","score":0.03687982636378929,"rank":250,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04686208820718198,"rank":250,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04606865653370032,"rank":250,"remainingConfigurations":444},{"removed":"frontiercode","score":0.045179155554779464,"rank":250,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04619963103717739,"rank":250,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04629804422195826,"rank":250,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04682222606354685,"rank":250,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04664112030668685,"rank":250,"remainingConfigurations":444},{"removed":"livebench-math","score":0.046906011588710696,"rank":250,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.046292716764893965,"rank":250,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0476174709190453,"rank":250,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04683997463051893,"rank":250,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04586043202201318,"rank":250,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04651951634342654,"rank":250,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04795634053541379,"rank":250,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04811345420072596,"rank":250,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04691779931425954,"rank":249,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04376221385468438,"rank":248,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04929041847094787,"rank":250,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0466683108919388,"rank":250,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04666161200140076,"rank":250,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04667555461618098,"rank":250,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04674933345330548,"rank":250,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04652887366613458,"rank":250,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.046710254614093026,"rank":250,"remainingConfigurations":444}],"sharedOrderConflicts":0},"doubao-seed-code--effort-reasoning":{"score":0.046488123687488066,"rank":251,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06022823261003512,"rank":249,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03659726565482412,"rank":251,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04594873351941279,"rank":251,"remainingConfigurations":444},{"removed":"Scale","score":0.054442829874459586,"rank":251,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04600937713735955,"rank":251,"remainingConfigurations":444},{"removed":"Cognition","score":0.044984471481675926,"rank":251,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04830434373502876,"rank":250,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04764242570978585,"rank":251,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0470986509698314,"rank":244,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04457187835591869,"rank":250,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.046468340696284194,"rank":251,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04501467276702642,"rank":251,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.046406211989470654,"rank":251,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.046488123687488066,"rank":251,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0468632790748873,"rank":251,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04529874978421472,"rank":251,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.046861204756171476,"rank":251,"remainingConfigurations":444},{"removed":"briefcase","score":0.046161805119804174,"rank":252,"remainingConfigurations":444},{"removed":"aime","score":0.047511332553045654,"rank":250,"remainingConfigurations":444},{"removed":"apex-agents","score":0.047158715346180595,"rank":251,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.042934745616520976,"rank":256,"remainingConfigurations":444},{"removed":"automationbench","score":0.04613267026260449,"rank":251,"remainingConfigurations":444},{"removed":"critpt","score":0.046722397641691484,"rank":249,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04643886916358083,"rank":251,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.047456854714755296,"rank":251,"remainingConfigurations":444},{"removed":"gdpval","score":0.04662654950725748,"rank":250,"remainingConfigurations":444},{"removed":"gmmlu","score":0.052592416230539125,"rank":237,"remainingConfigurations":444},{"removed":"gpqa","score":0.04647933781632193,"rank":249,"remainingConfigurations":444},{"removed":"harvey","score":0.045944263253450725,"rank":251,"remainingConfigurations":444},{"removed":"hle","score":0.05094693650770445,"rank":253,"remainingConfigurations":444},{"removed":"ifbench","score":0.04610822552025871,"rank":253,"remainingConfigurations":444},{"removed":"itbench","score":0.04604526234713536,"rank":251,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04523297658981238,"rank":252,"remainingConfigurations":444},{"removed":"math500","score":0.04666935605882391,"rank":251,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.045298567648093535,"rank":255,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.050500905929737855,"rank":251,"remainingConfigurations":444},{"removed":"omniscience","score":0.04076848933136415,"rank":256,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04702869253481757,"rank":246,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04718184774454135,"rank":251,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04607980720881969,"rank":247,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05802187858929869,"rank":251,"remainingConfigurations":444},{"removed":"deepswe","score":0.036622362124867885,"rank":251,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04649978674344964,"rank":251,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.045689722936842425,"rank":251,"remainingConfigurations":444},{"removed":"frontiercode","score":0.044984471481675926,"rank":251,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04583727426107367,"rank":251,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04593588954759694,"rank":251,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04646039548627604,"rank":251,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04628072622166041,"rank":251,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04654382359295473,"rank":251,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.045936361817658616,"rank":251,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04724985140269051,"rank":251,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04647604591928578,"rank":251,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04550509257078683,"rank":251,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.046160100306074404,"rank":251,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04758476746954562,"rank":251,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04764242570978585,"rank":251,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04658938828162624,"rank":250,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04347304321300924,"rank":249,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04891921814300478,"rank":251,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04630685659615814,"rank":251,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04630066643987921,"rank":251,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.046314487762397195,"rank":251,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0463881190713654,"rank":251,"remainingConfigurations":444},{"removed":"vibe-code","score":0.046169208133627154,"rank":251,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.046348823272139274,"rank":251,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2.5-pro--effort-non-reasoning":{"score":0.04615301649660867,"rank":252,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06018793325490091,"rank":250,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03628258066060264,"rank":252,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04568968263943832,"rank":252,"remainingConfigurations":444},{"removed":"Scale","score":0.05381353293911853,"rank":252,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04566333689841103,"rank":252,"remainingConfigurations":444},{"removed":"Cognition","score":0.044427858113977294,"rank":254,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04798441966935996,"rank":251,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04731463237136848,"rank":252,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04635737046721669,"rank":245,"remainingConfigurations":431},{"removed":"Vals AI","score":0.044241881525572256,"rank":251,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04613325309988311,"rank":252,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.044687500804808745,"rank":252,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04607186624115476,"rank":252,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04615301649660867,"rank":252,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.046529170694014195,"rank":252,"remainingConfigurations":444},{"removed":"All provider reports","score":0.044973148126106234,"rank":252,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0465588415290982,"rank":252,"remainingConfigurations":444},{"removed":"briefcase","score":0.0457862750627612,"rank":253,"remainingConfigurations":444},{"removed":"aime","score":0.04636126946414546,"rank":253,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04683381741391038,"rank":252,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.05285984991414692,"rank":236,"remainingConfigurations":444},{"removed":"automationbench","score":0.04580158235791331,"rank":252,"remainingConfigurations":444},{"removed":"critpt","score":0.04141712261878285,"rank":259,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.046124218041775585,"rank":252,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04718898587849866,"rank":252,"remainingConfigurations":444},{"removed":"gdpval","score":0.04607304700694268,"rank":252,"remainingConfigurations":444},{"removed":"gmmlu","score":0.046623828418032996,"rank":253,"remainingConfigurations":444},{"removed":"gpqa","score":0.04702611810017676,"rank":247,"remainingConfigurations":444},{"removed":"harvey","score":0.0456182335613276,"rank":252,"remainingConfigurations":444},{"removed":"hle","score":0.04903604497576151,"rank":254,"remainingConfigurations":444},{"removed":"ifbench","score":0.05378872579592912,"rank":239,"remainingConfigurations":444},{"removed":"itbench","score":0.04574164507295967,"rank":253,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04630578626874235,"rank":251,"remainingConfigurations":444},{"removed":"math500","score":0.04643918084481071,"rank":252,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04779700745016783,"rank":251,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04989232716259228,"rank":252,"remainingConfigurations":444},{"removed":"omniscience","score":0.037857264995441925,"rank":263,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04541404524450627,"rank":249,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.046863732172244064,"rank":252,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04072748480320576,"rank":264,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05807031927240957,"rank":250,"remainingConfigurations":444},{"removed":"deepswe","score":0.03630712372287712,"rank":252,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.046164592425390255,"rank":252,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04538320721451026,"rank":252,"remainingConfigurations":444},{"removed":"frontiercode","score":0.044427858113977294,"rank":254,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.045511784321025074,"rank":252,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04560492321964014,"rank":252,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.046125603331998354,"rank":252,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04594627468951163,"rank":252,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04620752262971659,"rank":252,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04560187572849477,"rank":252,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04691046307958097,"rank":252,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04614442036930357,"rank":252,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.045175886481370116,"rank":252,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04582580318424775,"rank":252,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.047244624333822954,"rank":252,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04731463237136848,"rank":252,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04614701591420798,"rank":251,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.043046711929022236,"rank":250,"remainingConfigurations":444},{"removed":"simpleqa","score":0.048561311558816565,"rank":252,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04597337781200888,"rank":252,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.045966949047334595,"rank":252,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.045980191154873944,"rank":252,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0460536620451352,"rank":252,"remainingConfigurations":444},{"removed":"vibe-code","score":0.045835910969428934,"rank":252,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04601489420219725,"rank":252,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-pro-preview--effort-medium":{"score":0.045151986969389844,"rank":253,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05921397283376221,"rank":251,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03553285124573162,"rank":253,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04465931619164981,"rank":253,"remainingConfigurations":444},{"removed":"Scale","score":0.052936171891347396,"rank":253,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04469197696906832,"rank":253,"remainingConfigurations":444},{"removed":"Cognition","score":0.04361398003410013,"rank":255,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0469652207647189,"rank":252,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04653477395971272,"rank":253,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04554441891685427,"rank":246,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04331335118469867,"rank":252,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04513252559422759,"rank":253,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04371565802629045,"rank":253,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.045072819039377265,"rank":253,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.045151986969389844,"rank":253,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.045520696597540156,"rank":253,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04399590737911122,"rank":253,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.045554667418363816,"rank":253,"remainingConfigurations":444},{"removed":"briefcase","score":0.044806509928059346,"rank":254,"remainingConfigurations":444},{"removed":"aime","score":0.04290287673778861,"rank":257,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04587787831948906,"rank":254,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04383246185013926,"rank":255,"remainingConfigurations":444},{"removed":"automationbench","score":0.044776402452439364,"rank":253,"remainingConfigurations":444},{"removed":"critpt","score":0.05216330904836999,"rank":237,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04510466247018929,"rank":254,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04610596479789406,"rank":253,"remainingConfigurations":444},{"removed":"gdpval","score":0.04659542203083628,"rank":251,"remainingConfigurations":444},{"removed":"gmmlu","score":0.045599415476716705,"rank":254,"remainingConfigurations":444},{"removed":"gpqa","score":0.044123680819896344,"rank":251,"remainingConfigurations":444},{"removed":"harvey","score":0.04460680606020923,"rank":253,"remainingConfigurations":444},{"removed":"hle","score":0.05287400830600211,"rank":249,"remainingConfigurations":444},{"removed":"ifbench","score":0.03760130691852401,"rank":265,"remainingConfigurations":444},{"removed":"itbench","score":0.04476970136039251,"rank":254,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04512357560298905,"rank":253,"remainingConfigurations":444},{"removed":"math500","score":0.04543526362045747,"rank":253,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04610460788557375,"rank":252,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.05265995324231307,"rank":246,"remainingConfigurations":444},{"removed":"omniscience","score":0.04167264305364759,"rank":254,"remainingConfigurations":444},{"removed":"tau-bench","score":0.040708797735759375,"rank":261,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04581642109453723,"rank":253,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04577980765567824,"rank":249,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0570602419896995,"rank":252,"remainingConfigurations":444},{"removed":"deepswe","score":0.03555697272048817,"rank":253,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04516332959026378,"rank":253,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04440772036871713,"rank":253,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04361398003410013,"rank":255,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04453316860202907,"rank":253,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04462148665383838,"rank":253,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.045125622084864925,"rank":253,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.044949766134322104,"rank":253,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04520511303768357,"rank":253,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04461384123905302,"rank":253,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04589538022687834,"rank":253,"remainingConfigurations":444},{"removed":"livebench-data","score":0.045142016815196924,"rank":253,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.044193094146516954,"rank":253,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04483189714582147,"rank":253,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04622139937895962,"rank":253,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04653477395971272,"rank":253,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04518289429873029,"rank":252,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.04223407713635716,"rank":251,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04751803078478537,"rank":253,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04497607419414623,"rank":253,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04496924943201327,"rank":253,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04498269812827325,"rank":253,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04505431229893995,"rank":253,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04484054261956544,"rank":253,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04501695393999294,"rank":253,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.7-flash--effort-non-reasoning":{"score":0.043899200525682976,"rank":254,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03962709897850522,"rank":168,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.055131357478466265,"rank":259,"remainingConfigurations":444},{"removed":"Datacurve","score":0.034561539091556,"rank":254,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04372412198449387,"rank":254,"remainingConfigurations":444},{"removed":"Scale","score":0.05085080521374528,"rank":255,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04374756170128818,"rank":254,"remainingConfigurations":444},{"removed":"Cognition","score":0.04478031033724427,"rank":252,"remainingConfigurations":444},{"removed":"LiveBench","score":0.044873570159677405,"rank":254,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04494812640137207,"rank":255,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04216554144382426,"rank":254,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.043886101391597564,"rank":254,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04263233392015766,"rank":254,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04385956540780433,"rank":254,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.043899200525682976,"rank":254,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04420599828517699,"rank":254,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04289681788839977,"rank":254,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.044171353149603916,"rank":254,"remainingConfigurations":444},{"removed":"briefcase","score":0.043716282460716384,"rank":256,"remainingConfigurations":444},{"removed":"aime","score":0.03350940714369111,"rank":273,"remainingConfigurations":444},{"removed":"apex-agents","score":0.044429403502815094,"rank":255,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04405607912255751,"rank":253,"remainingConfigurations":444},{"removed":"automationbench","score":0.04373068576511339,"rank":255,"remainingConfigurations":444},{"removed":"critpt","score":0.043409558484016196,"rank":254,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04395080306085041,"rank":255,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04437089465182744,"rank":255,"remainingConfigurations":444},{"removed":"gdpval","score":0.043351186795643475,"rank":257,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04416549814143467,"rank":255,"remainingConfigurations":444},{"removed":"gpqa","score":0.041111865572328835,"rank":259,"remainingConfigurations":444},{"removed":"harvey","score":0.04331408494902639,"rank":254,"remainingConfigurations":444},{"removed":"hle","score":0.047406799679890345,"rank":257,"remainingConfigurations":444},{"removed":"ifbench","score":0.04453541420445816,"rank":254,"remainingConfigurations":444},{"removed":"itbench","score":0.0436377915172815,"rank":255,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04397583467941093,"rank":255,"remainingConfigurations":444},{"removed":"math500","score":0.04400320262642971,"rank":255,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04554767746649419,"rank":254,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04739051356489337,"rank":254,"remainingConfigurations":444},{"removed":"omniscience","score":0.043130284986626265,"rank":251,"remainingConfigurations":444},{"removed":"tau-bench","score":0.041843937503187156,"rank":257,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04430449961993368,"rank":254,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04360565008997755,"rank":257,"remainingConfigurations":444},{"removed":"arc-agi","score":0.053340418558729015,"rank":260,"remainingConfigurations":444},{"removed":"deepswe","score":0.034593175717538525,"rank":254,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04390882027528945,"rank":254,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04334759200618276,"rank":254,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04478031033724427,"rank":252,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04339146385329785,"rank":254,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04329721332423778,"rank":254,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04388324987503684,"rank":254,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0437135613373634,"rank":254,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04403786138435828,"rank":254,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04324828665012536,"rank":254,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04458504867467341,"rank":254,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04394222105185152,"rank":254,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04302067695834605,"rank":254,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04358360987876708,"rank":254,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0449073243709907,"rank":254,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04494812640137207,"rank":255,"remainingConfigurations":444},{"removed":"frontiermath","score":0.054042519247414746,"rank":236,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03548531179891222,"rank":264,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04632551414386337,"rank":254,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04371219295853641,"rank":254,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04374548920065802,"rank":254,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04371248605802754,"rank":254,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04381938396948165,"rank":254,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04362516106418771,"rank":254,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.043759201637698066,"rank":254,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.5--effort-none":{"score":0.04382318880994294,"rank":255,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.038603847941668115,"rank":171,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05643804029550111,"rank":254,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03454025161842351,"rank":255,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04364327499331582,"rank":255,"remainingConfigurations":444},{"removed":"Scale","score":0.05080005735342153,"rank":256,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04355329973589798,"rank":255,"remainingConfigurations":444},{"removed":"Cognition","score":0.044530357232866434,"rank":253,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04427006446019679,"rank":256,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04521001987061632,"rank":254,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04159474763819589,"rank":256,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04381066403833514,"rank":255,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.042554884599736886,"rank":255,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04377744418290077,"rank":255,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04382318880994294,"rank":255,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04413102229153707,"rank":255,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04281478148912604,"rank":255,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.044098704647874194,"rank":255,"remainingConfigurations":444},{"removed":"briefcase","score":0.04365378185916575,"rank":257,"remainingConfigurations":444},{"removed":"aime","score":0.04664589647597314,"rank":252,"remainingConfigurations":444},{"removed":"apex-agents","score":0.044365389311219576,"rank":256,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.043981779803113186,"rank":254,"remainingConfigurations":444},{"removed":"automationbench","score":0.043681909122640084,"rank":256,"remainingConfigurations":444},{"removed":"critpt","score":0.04293602361835066,"rank":255,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04387551945323636,"rank":256,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04430151086488477,"rank":256,"remainingConfigurations":444},{"removed":"gdpval","score":0.04332957388085503,"rank":258,"remainingConfigurations":444},{"removed":"gmmlu","score":0.044150619336543746,"rank":256,"remainingConfigurations":444},{"removed":"gpqa","score":0.050269409446982986,"rank":242,"remainingConfigurations":444},{"removed":"harvey","score":0.043244781260764496,"rank":255,"remainingConfigurations":444},{"removed":"hle","score":0.04748884229238528,"rank":256,"remainingConfigurations":444},{"removed":"ifbench","score":0.04422721796314049,"rank":255,"remainingConfigurations":444},{"removed":"itbench","score":0.04356540446212656,"rank":256,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04388929123157825,"rank":256,"remainingConfigurations":444},{"removed":"math500","score":0.04392517063768123,"rank":256,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04555692597034885,"rank":253,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04724859203042799,"rank":255,"remainingConfigurations":444},{"removed":"omniscience","score":0.043014145816587114,"rank":252,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0417822870121759,"rank":258,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.044227080914747585,"rank":256,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.043523433748563684,"rank":259,"remainingConfigurations":444},{"removed":"arc-agi","score":0.054312864892335,"rank":255,"remainingConfigurations":444},{"removed":"deepswe","score":0.034570819988443205,"rank":255,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04383311959564198,"rank":255,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04324130498961364,"rank":255,"remainingConfigurations":444},{"removed":"frontiercode","score":0.044530357232866434,"rank":253,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04331824122306268,"rank":255,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04322704049400922,"rank":255,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04380698452121209,"rank":255,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04363395445465426,"rank":255,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04397170136623474,"rank":255,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04315554554888524,"rank":255,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04450744310231819,"rank":255,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04385490716944326,"rank":255,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.042959888100729676,"rank":255,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04349546092696304,"rank":255,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04484652975029888,"rank":255,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04521001987061632,"rank":254,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04389534575415099,"rank":253,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.024263519347577606,"rank":287,"remainingConfigurations":444},{"removed":"simpleqa","score":0.045831232660499266,"rank":256,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04364046238533437,"rank":255,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04366851226798683,"rank":255,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.043638474296917966,"rank":255,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04374338812939923,"rank":255,"remainingConfigurations":444},{"removed":"vibe-code","score":0.043550141845167555,"rank":255,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04367846855073107,"rank":255,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning":{"score":0.04360563536456633,"rank":256,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05620221474530959,"rank":255,"remainingConfigurations":444},{"removed":"Datacurve","score":0.034225494969011026,"rank":256,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.043242470878775814,"rank":256,"remainingConfigurations":444},{"removed":"Scale","score":0.05108961993255484,"rank":254,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04313926479037675,"rank":256,"remainingConfigurations":444},{"removed":"Cognition","score":0.041997152781140266,"rank":258,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04516442750108298,"rank":253,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04469554161398372,"rank":257,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04482955860798691,"rank":247,"remainingConfigurations":431},{"removed":"Vals AI","score":0.041705462277252935,"rank":255,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04358646719274536,"rank":256,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04217587895541136,"rank":256,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04352951166901572,"rank":256,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04360563536456633,"rank":256,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04395255927699449,"rank":256,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04243823808615643,"rank":256,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04391413227919217,"rank":256,"remainingConfigurations":444},{"removed":"briefcase","score":0.048819881337324726,"rank":246,"remainingConfigurations":444},{"removed":"aime","score":0.04322719450147496,"rank":255,"remainingConfigurations":444},{"removed":"apex-agents","score":0.046544915676924904,"rank":253,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.042277229048643526,"rank":257,"remainingConfigurations":444},{"removed":"automationbench","score":0.04338666299567615,"rank":257,"remainingConfigurations":444},{"removed":"critpt","score":0.039442846752943725,"rank":264,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.045513532792762164,"rank":253,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04610548990732031,"rank":254,"remainingConfigurations":444},{"removed":"gdpval","score":0.04501738282550938,"rank":254,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04375331455408813,"rank":257,"remainingConfigurations":444},{"removed":"gpqa","score":0.04170807173480609,"rank":258,"remainingConfigurations":444},{"removed":"harvey","score":0.043064354859595665,"rank":256,"remainingConfigurations":444},{"removed":"hle","score":0.04497984662974549,"rank":264,"remainingConfigurations":444},{"removed":"ifbench","score":0.037506411996801416,"rank":266,"remainingConfigurations":444},{"removed":"itbench","score":0.045948897018022294,"rank":252,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04346208773593299,"rank":258,"remainingConfigurations":444},{"removed":"math500","score":0.04383255262918304,"rank":257,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04499718270156114,"rank":256,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.046946395668512164,"rank":257,"remainingConfigurations":444},{"removed":"omniscience","score":0.04064524829476134,"rank":257,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04266751150254904,"rank":253,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.044266181442690296,"rank":255,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04366659674625708,"rank":256,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05420979440346118,"rank":256,"remainingConfigurations":444},{"removed":"deepswe","score":0.034251413160675696,"rank":256,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04361683165897676,"rank":256,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.042955143316006,"rank":256,"remainingConfigurations":444},{"removed":"frontiercode","score":0.041997152781140266,"rank":258,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04300429581286639,"rank":256,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.043087493909605756,"rank":256,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04358040832107462,"rank":256,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04340537370459326,"rank":256,"remainingConfigurations":444},{"removed":"livebench-math","score":0.043652978044041744,"rank":256,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04310074841241519,"rank":256,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04433769859240841,"rank":256,"remainingConfigurations":444},{"removed":"livebench-data","score":0.043586284921179004,"rank":256,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04267074031404389,"rank":256,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04329820483981025,"rank":256,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04462991803256449,"rank":256,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04469554161398372,"rank":257,"remainingConfigurations":444},{"removed":"frontiermath","score":0.043638814493275786,"rank":254,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.041018727910391704,"rank":252,"remainingConfigurations":444},{"removed":"simpleqa","score":0.045894265915440546,"rank":255,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04343606165005188,"rank":256,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04342850867824316,"rank":256,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04343781395361676,"rank":256,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04351537656524789,"rank":256,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04330706280248644,"rank":256,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04347472934087348,"rank":256,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-k2.6--effort-non-reasoning":{"score":0.043100365196747814,"rank":257,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.014241686691051808,"rank":185,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0558600021991324,"rank":256,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03392910032890618,"rank":257,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04279665544384558,"rank":257,"remainingConfigurations":444},{"removed":"Scale","score":0.05034489442667659,"rank":257,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.042769615133759854,"rank":257,"remainingConfigurations":444},{"removed":"Cognition","score":0.04236684888261965,"rank":256,"remainingConfigurations":444},{"removed":"LiveBench","score":0.044734753218242586,"rank":255,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04483320598107612,"rank":256,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.074973009882206,"rank":216,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04140547910128258,"rank":257,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.043084802831868434,"rank":257,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04178193611313696,"rank":257,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04303795586456189,"rank":257,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.043100365196747814,"rank":257,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04343415384146032,"rank":257,"remainingConfigurations":444},{"removed":"All provider reports","score":0.042047375129878016,"rank":257,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04345006155823827,"rank":257,"remainingConfigurations":444},{"removed":"briefcase","score":0.04301284843742225,"rank":259,"remainingConfigurations":444},{"removed":"aime","score":0.0450918016871343,"rank":254,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04373766013954949,"rank":257,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.042133567544193624,"rank":258,"remainingConfigurations":444},{"removed":"automationbench","score":0.042986724864787634,"rank":258,"remainingConfigurations":444},{"removed":"critpt","score":0.040958382318118554,"rank":260,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04315317758489503,"rank":257,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04395146765942101,"rank":257,"remainingConfigurations":444},{"removed":"gdpval","score":0.04311077023062829,"rank":259,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04367399566822655,"rank":258,"remainingConfigurations":444},{"removed":"gpqa","score":0.04218879568678113,"rank":256,"remainingConfigurations":444},{"removed":"harvey","score":0.04258257271667718,"rank":257,"remainingConfigurations":444},{"removed":"hle","score":0.04617301210329294,"rank":258,"remainingConfigurations":444},{"removed":"ifbench","score":0.04754976989007559,"rank":250,"remainingConfigurations":444},{"removed":"itbench","score":0.042784660910389745,"rank":257,"remainingConfigurations":444},{"removed":"livecodebench","score":0.043486440310266,"rank":257,"remainingConfigurations":444},{"removed":"math500","score":0.043421374294819313,"rank":258,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04497201225713327,"rank":257,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.047075175073761216,"rank":256,"remainingConfigurations":444},{"removed":"omniscience","score":0.04096086608303234,"rank":255,"remainingConfigurations":444},{"removed":"tau-bench","score":0.039200907812919294,"rank":264,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.043650667110587134,"rank":257,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04065300052042781,"rank":265,"remainingConfigurations":444},{"removed":"arc-agi","score":0.053809022524346155,"rank":257,"remainingConfigurations":444},{"removed":"deepswe","score":0.03395326207359424,"rank":257,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04311034087518822,"rank":257,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04258919855590309,"rank":257,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04236684888261965,"rank":256,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.042565082820726435,"rank":257,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04251394254702559,"rank":257,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.043085264560343006,"rank":257,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0429228853038876,"rank":257,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04317324819730431,"rank":257,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04254632608184623,"rank":257,"remainingConfigurations":444},{"removed":"livebench-language","score":0.043788769181902325,"rank":257,"remainingConfigurations":444},{"removed":"livebench-data","score":0.043115251474753,"rank":257,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.042203214853357596,"rank":257,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04279296418719584,"rank":257,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.044119548791409224,"rank":257,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04483320598107612,"rank":256,"remainingConfigurations":444},{"removed":"frontiermath","score":0.043121949037253415,"rank":255,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.06954219803514052,"rank":221,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04530931497193256,"rank":257,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04292382152246544,"rank":257,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.042933147779173175,"rank":257,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0429326191006223,"rank":257,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.043006639566455895,"rank":257,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04280977153380614,"rank":257,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.042974634976729764,"rank":257,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-35b-a3b--effort-non-reasoning":{"score":0.042666785764081006,"rank":258,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05735111960264875,"rank":158,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0553167519310199,"rank":257,"remainingConfigurations":444},{"removed":"Datacurve","score":0.033565368593670826,"rank":258,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04233221102530566,"rank":258,"remainingConfigurations":444},{"removed":"Scale","score":0.04978759005799893,"rank":258,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.042335274143733816,"rank":258,"remainingConfigurations":444},{"removed":"Cognition","score":0.0422919897150091,"rank":257,"remainingConfigurations":444},{"removed":"LiveBench","score":0.043916677088182705,"rank":257,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0435445580426125,"rank":258,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03552540870629633,"rank":263,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04084774435948745,"rank":258,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0426506197621823,"rank":258,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04135652029863622,"rank":258,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04260500908022647,"rank":258,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.042666785764081006,"rank":258,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04299134787726374,"rank":258,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04161323392136617,"rank":258,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0429741620592379,"rank":258,"remainingConfigurations":444},{"removed":"briefcase","score":0.04238950265227506,"rank":260,"remainingConfigurations":444},{"removed":"aime","score":0.04313671957357601,"rank":256,"remainingConfigurations":444},{"removed":"apex-agents","score":0.043251036629273404,"rank":258,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04164367161790836,"rank":259,"remainingConfigurations":444},{"removed":"automationbench","score":0.04240896574240463,"rank":259,"remainingConfigurations":444},{"removed":"critpt","score":0.04091604078615895,"rank":261,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04264741128773301,"rank":258,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04338495503529352,"rank":258,"remainingConfigurations":444},{"removed":"gdpval","score":0.04219299709871213,"rank":260,"remainingConfigurations":444},{"removed":"gmmlu","score":0.043230456434606164,"rank":259,"remainingConfigurations":444},{"removed":"gpqa","score":0.04048026421016523,"rank":262,"remainingConfigurations":444},{"removed":"harvey","score":0.04212573742705864,"rank":258,"remainingConfigurations":444},{"removed":"hle","score":0.04603075588311045,"rank":260,"remainingConfigurations":444},{"removed":"ifbench","score":0.04338569533792682,"rank":256,"remainingConfigurations":444},{"removed":"itbench","score":0.042303000422132774,"rank":258,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04264278182308771,"rank":260,"remainingConfigurations":444},{"removed":"math500","score":0.0428016955114342,"rank":259,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04416229858145344,"rank":258,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.045173030890581084,"rank":261,"remainingConfigurations":444},{"removed":"omniscience","score":0.044047223419852656,"rank":250,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04160136413333895,"rank":259,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04319738451458454,"rank":258,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0431762995146808,"rank":260,"remainingConfigurations":444},{"removed":"arc-agi","score":0.053398434388918836,"rank":259,"remainingConfigurations":444},{"removed":"deepswe","score":0.0335923621078876,"rank":258,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.042677371016283355,"rank":258,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04198689613695399,"rank":258,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0422919897150091,"rank":257,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04210604941314113,"rank":258,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04214255046944468,"rank":258,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0426437965705743,"rank":258,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.042472236742789486,"rank":258,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04276153183989854,"rank":258,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04209544680322203,"rank":258,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0433608598072002,"rank":258,"remainingConfigurations":444},{"removed":"livebench-data","score":0.042674752386786745,"rank":258,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04178125550777412,"rank":258,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.042358140922036436,"rank":258,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0436683236618158,"rank":258,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0435445580426125,"rank":258,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04261449480671461,"rank":256,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.037640079596904484,"rank":260,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04499762725693696,"rank":258,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0424952156848326,"rank":258,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.042504068489087665,"rank":258,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04249562929624484,"rank":258,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04258398844458059,"rank":258,"remainingConfigurations":444},{"removed":"vibe-code","score":0.042386510511751706,"rank":258,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04252937284713235,"rank":258,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-9b--effort-reasoning":{"score":0.04208683126809231,"rank":259,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0546173276723882,"rank":262,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03304727784875209,"rank":260,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.041699294385132514,"rank":259,"remainingConfigurations":444},{"removed":"Scale","score":0.04940930958075029,"rank":259,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04162584760915955,"rank":259,"remainingConfigurations":444},{"removed":"Cognition","score":0.04052326920851487,"rank":262,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04379017227907539,"rank":258,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.043230523011379474,"rank":259,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04336108724678783,"rank":248,"remainingConfigurations":431},{"removed":"Vals AI","score":0.040353337013477354,"rank":259,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04206822558188227,"rank":259,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04072652042961387,"rank":259,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04201094128379625,"rank":259,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04208683126809231,"rank":259,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.042430377521140844,"rank":259,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04098528390627614,"rank":259,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04246152859327124,"rank":259,"remainingConfigurations":444},{"removed":"briefcase","score":0.043584300416673,"rank":258,"remainingConfigurations":444},{"removed":"aime","score":0.04202972517444831,"rank":259,"remainingConfigurations":444},{"removed":"apex-agents","score":0.042743112173723265,"rank":259,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.039315510621580715,"rank":264,"remainingConfigurations":444},{"removed":"automationbench","score":0.044484141824060124,"rank":254,"remainingConfigurations":444},{"removed":"critpt","score":0.04226909708875574,"rank":257,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04199655226233833,"rank":260,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04024197882072505,"rank":265,"remainingConfigurations":444},{"removed":"gdpval","score":0.044879037151361025,"rank":255,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04237202505450224,"rank":261,"remainingConfigurations":444},{"removed":"gpqa","score":0.040222039516341186,"rank":263,"remainingConfigurations":444},{"removed":"harvey","score":0.041549187098367184,"rank":259,"remainingConfigurations":444},{"removed":"hle","score":0.04526308382807375,"rank":262,"remainingConfigurations":444},{"removed":"ifbench","score":0.037731579413929926,"rank":264,"remainingConfigurations":444},{"removed":"itbench","score":0.04164820373839791,"rank":260,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04219745805299179,"rank":261,"remainingConfigurations":444},{"removed":"math500","score":0.04238567964749412,"rank":260,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04366114003080495,"rank":260,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04480242440324849,"rank":262,"remainingConfigurations":444},{"removed":"omniscience","score":0.044516745096062044,"rank":249,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04048235089371272,"rank":262,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04269459127489524,"rank":259,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0411552812300518,"rank":262,"remainingConfigurations":444},{"removed":"arc-agi","score":0.052632453005799794,"rank":263,"remainingConfigurations":444},{"removed":"deepswe","score":0.0330703193979428,"rank":260,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.042097844897228946,"rank":259,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04143783828004446,"rank":259,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04052326920851487,"rank":262,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.04150412046326298,"rank":259,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04158618413434633,"rank":259,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.042062831801449645,"rank":259,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.04189400286952291,"rank":259,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04213436144989543,"rank":259,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04158421884228201,"rank":259,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04278897545468471,"rank":259,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04207895711836762,"rank":259,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04118340203002241,"rank":259,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04178613476906162,"rank":259,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0430892022921309,"rank":259,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.043230523011379474,"rank":259,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04214568779321103,"rank":257,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03960681803444533,"rank":253,"remainingConfigurations":444},{"removed":"simpleqa","score":0.044298748520807146,"rank":259,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04192178880234845,"rank":259,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04191628996462308,"rank":259,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.041926860133223526,"rank":259,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04199693527161243,"rank":259,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04179473600901979,"rank":259,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04196033183833781,"rank":259,"remainingConfigurations":444}],"sharedOrderConflicts":0},"k-exaone-236b-a23b--effort-reasoning":{"score":0.04204243064154283,"rank":260,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.054658974557727225,"rank":261,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03304245302689864,"rank":261,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04158606361341505,"rank":260,"remainingConfigurations":444},{"removed":"Scale","score":0.04932716194630506,"rank":260,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.041604188916938935,"rank":260,"remainingConfigurations":444},{"removed":"Cognition","score":0.040639997576572114,"rank":261,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0437160194709863,"rank":259,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04306130356881929,"rank":261,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04265539209081034,"rank":250,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04030396432509561,"rank":261,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04202428042480086,"rank":260,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04069695684924781,"rank":260,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.041968211405569195,"rank":260,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04204243064154283,"rank":260,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04238397707565278,"rank":260,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04095570646099221,"rank":260,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.042370438410730654,"rank":261,"remainingConfigurations":444},{"removed":"briefcase","score":0.041664268881470644,"rank":262,"remainingConfigurations":444},{"removed":"aime","score":0.039596596309232804,"rank":265,"remainingConfigurations":444},{"removed":"apex-agents","score":0.042628009077719305,"rank":261,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04113432646685252,"rank":260,"remainingConfigurations":444},{"removed":"automationbench","score":0.04167882723430768,"rank":262,"remainingConfigurations":444},{"removed":"critpt","score":0.03956214942472574,"rank":263,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04195601464177424,"rank":261,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0428837566776468,"rank":260,"remainingConfigurations":444},{"removed":"gdpval","score":0.0456800901295007,"rank":253,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04733640971873384,"rank":250,"remainingConfigurations":444},{"removed":"gpqa","score":0.0410738470701394,"rank":260,"remainingConfigurations":444},{"removed":"harvey","score":0.0415413372197378,"rank":260,"remainingConfigurations":444},{"removed":"hle","score":0.04594455294966984,"rank":261,"remainingConfigurations":444},{"removed":"ifbench","score":0.0384556782952949,"rank":263,"remainingConfigurations":444},{"removed":"itbench","score":0.04160251396712084,"rank":261,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04009725017456283,"rank":264,"remainingConfigurations":444},{"removed":"math500","score":0.04230602698837121,"rank":261,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04211977649253603,"rank":261,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04563138636400782,"rank":259,"remainingConfigurations":444},{"removed":"omniscience","score":0.04287311033315908,"rank":253,"remainingConfigurations":444},{"removed":"tau-bench","score":0.040805807473693174,"rank":260,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04266970861700009,"rank":260,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04252854888503755,"rank":261,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05266042756251441,"rank":262,"remainingConfigurations":444},{"removed":"deepswe","score":0.033065155394593725,"rank":261,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.042053116709864634,"rank":260,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.041326093835251904,"rank":260,"remainingConfigurations":444},{"removed":"frontiercode","score":0.040639997576572114,"rank":261,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.041452547620841614,"rank":260,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04154048698020705,"rank":260,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04201789547128706,"rank":260,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.041853142568200864,"rank":260,"remainingConfigurations":444},{"removed":"livebench-math","score":0.042092837732430305,"rank":260,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04153706318154068,"rank":260,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04273830234446738,"rank":260,"remainingConfigurations":444},{"removed":"livebench-data","score":0.042033834041335004,"rank":260,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0411446672375028,"rank":260,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.041742278796269246,"rank":260,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04304507055343696,"rank":260,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04306130356881929,"rank":261,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04211907060247897,"rank":258,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.039264686772878775,"rank":255,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04426196383514783,"rank":260,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04187702927439341,"rank":260,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04187153506444064,"rank":260,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04188376405039449,"rank":260,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.041951200670886785,"rank":260,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04175115545916441,"rank":260,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.041915468227598805,"rank":260,"remainingConfigurations":444}],"sharedOrderConflicts":0},"o1--effort-reasoning":{"score":0.042009003077380785,"rank":261,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.054810313641871757,"rank":260,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03305578032299227,"rank":259,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.04151811259513932,"rank":261,"remainingConfigurations":444},{"removed":"Scale","score":0.04926290690368268,"rank":261,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.04158635454751886,"rank":261,"remainingConfigurations":444},{"removed":"Cognition","score":0.04071357367719201,"rank":260,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04369267175902295,"rank":260,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04318112080232402,"rank":260,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04260632167486842,"rank":251,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04031393399826442,"rank":260,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04199098548481723,"rank":261,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.04066769537530684,"rank":261,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.041935024714468534,"rank":261,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.042009003077380785,"rank":261,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04234958725923146,"rank":261,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04092585088895136,"rank":261,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04238859923722377,"rank":260,"remainingConfigurations":444},{"removed":"briefcase","score":0.041808813167643476,"rank":261,"remainingConfigurations":444},{"removed":"aime","score":0.041784758160379444,"rank":260,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04267139365800937,"rank":260,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.039793535651189586,"rank":263,"remainingConfigurations":444},{"removed":"automationbench","score":0.04179587231538682,"rank":261,"remainingConfigurations":444},{"removed":"critpt","score":0.041747650483633575,"rank":258,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.042044390331888094,"rank":259,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04301218413175986,"rank":259,"remainingConfigurations":444},{"removed":"gdpval","score":0.04217703495386366,"rank":261,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0423854228142018,"rank":260,"remainingConfigurations":444},{"removed":"gpqa","score":0.04293113222515648,"rank":253,"remainingConfigurations":444},{"removed":"harvey","score":0.04153548564105464,"rank":261,"remainingConfigurations":444},{"removed":"hle","score":0.05197392998024105,"rank":251,"remainingConfigurations":444},{"removed":"ifbench","score":0.036430182276901465,"rank":267,"remainingConfigurations":444},{"removed":"itbench","score":0.041653231022964934,"rank":259,"remainingConfigurations":444},{"removed":"livecodebench","score":0.044721838379949586,"rank":254,"remainingConfigurations":444},{"removed":"math500","score":0.044121502448093035,"rank":254,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04086853526812688,"rank":266,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04564835491707558,"rank":258,"remainingConfigurations":444},{"removed":"omniscience","score":0.03240149747170882,"rank":271,"remainingConfigurations":444},{"removed":"tau-bench","score":0.041916924493052204,"rank":256,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04266782838829783,"rank":261,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04561739142683489,"rank":250,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05277142140143356,"rank":261,"remainingConfigurations":444},{"removed":"deepswe","score":0.03307856453505629,"rank":259,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.042019645157463835,"rank":261,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.04128250925777172,"rank":261,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04071357367719201,"rank":260,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.041421814188888344,"rank":261,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04150718178299873,"rank":261,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04198442714497206,"rank":261,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.041820650466155955,"rank":261,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04205961824637464,"rank":261,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04150386822613577,"rank":261,"remainingConfigurations":444},{"removed":"livebench-language","score":0.042703922711636394,"rank":261,"remainingConfigurations":444},{"removed":"livebench-data","score":0.042000229926225395,"rank":261,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0411125710866046,"rank":261,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04170911482748158,"rank":261,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04301057536674958,"rank":261,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04318112080232402,"rank":260,"remainingConfigurations":444},{"removed":"frontiermath","score":0.042096350382464516,"rank":259,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03929150548052892,"rank":254,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04423050842060099,"rank":261,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04184371168563945,"rank":261,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04183811549522815,"rank":261,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04185063935045621,"rank":261,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04191770160980734,"rank":261,"remainingConfigurations":444},{"removed":"vibe-code","score":0.041718052814913455,"rank":261,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04188225505103368,"rank":261,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-235b-a22b-thinking-2507--effort-reasoning":{"score":0.04182271636620328,"rank":262,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05425810291228597,"rank":263,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03284482501314575,"rank":262,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.041345394009615954,"rank":262,"remainingConfigurations":444},{"removed":"Scale","score":0.04909710980127308,"rank":262,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0413685247887473,"rank":262,"remainingConfigurations":444},{"removed":"Cognition","score":0.0403781694027871,"rank":263,"remainingConfigurations":444},{"removed":"LiveBench","score":0.043468526553390036,"rank":261,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04295624819583311,"rank":262,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04277668596181803,"rank":249,"remainingConfigurations":431},{"removed":"Vals AI","score":0.04007630318711506,"rank":262,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04180456095013935,"rank":262,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0404782497910585,"rank":262,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.041748469859381965,"rank":262,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04182271636620328,"rank":262,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04216023715400136,"rank":262,"remainingConfigurations":444},{"removed":"All provider reports","score":0.04073310411732529,"rank":262,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04219250541674064,"rank":262,"remainingConfigurations":444},{"removed":"briefcase","score":0.043721652852148414,"rank":255,"remainingConfigurations":444},{"removed":"aime","score":0.03911834859575113,"rank":267,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04251434163398418,"rank":262,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03867863962239255,"rank":267,"remainingConfigurations":444},{"removed":"automationbench","score":0.042338389920437446,"rank":260,"remainingConfigurations":444},{"removed":"critpt","score":0.046497115824033854,"rank":251,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04182338188437575,"rank":262,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.042307456012899806,"rank":262,"remainingConfigurations":444},{"removed":"gdpval","score":0.04457480734307956,"rank":256,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04083010184039294,"rank":264,"remainingConfigurations":444},{"removed":"gpqa","score":0.04052473274944334,"rank":261,"remainingConfigurations":444},{"removed":"harvey","score":0.04132858486939173,"rank":262,"remainingConfigurations":444},{"removed":"hle","score":0.04512120210357288,"rank":263,"remainingConfigurations":444},{"removed":"ifbench","score":0.040651902825553005,"rank":259,"remainingConfigurations":444},{"removed":"itbench","score":0.04145142319769674,"rank":262,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04002651573927691,"rank":265,"remainingConfigurations":444},{"removed":"math500","score":0.040665310415612846,"rank":263,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.041571620884552844,"rank":264,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.045384645661521755,"rank":260,"remainingConfigurations":444},{"removed":"omniscience","score":0.0381177694142758,"rank":262,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0422552867047474,"rank":255,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04245774260383231,"rank":262,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04430014823395519,"rank":254,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05228441350520757,"rank":264,"remainingConfigurations":444},{"removed":"deepswe","score":0.03286810629539997,"rank":262,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.041833641441734425,"rank":262,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.041132425900845135,"rank":262,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0403781694027871,"rank":263,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.041236224472248055,"rank":262,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.041322965674205854,"rank":262,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04179876495724507,"rank":262,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.041632308455210695,"rank":262,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04187164711475879,"rank":262,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04132415850275,"rank":262,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04251911890929976,"rank":262,"remainingConfigurations":444},{"removed":"livebench-data","score":0.041812067625050804,"rank":262,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.04092625945293145,"rank":262,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04152464271318485,"rank":262,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04281782975191981,"rank":262,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04295624819583311,"rank":262,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04188000926002337,"rank":260,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03925821795209002,"rank":256,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04403224782351633,"rank":262,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04165775050980354,"rank":262,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04165294350524167,"rank":262,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04166397272704294,"rank":262,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04173335652538915,"rank":262,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04153302611056828,"rank":262,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04169643282957978,"rank":262,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-2.5-flash--effort-reasoning":{"score":0.041482930002880995,"rank":263,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.053987387477463684,"rank":264,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03258866241497095,"rank":263,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.040968755641922365,"rank":263,"remainingConfigurations":444},{"removed":"Scale","score":0.04862686090341312,"rank":263,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.041048758379243155,"rank":263,"remainingConfigurations":444},{"removed":"Cognition","score":0.04007913652571216,"rank":264,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04318210733178434,"rank":262,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04251887057491491,"rank":263,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04193719293682119,"rank":252,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03978360017378176,"rank":263,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.041465047677712745,"rank":263,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.040156028254744076,"rank":263,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.041409749203178185,"rank":263,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.041482930002880995,"rank":263,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04182177536875082,"rank":263,"remainingConfigurations":444},{"removed":"All provider reports","score":0.040413157915395174,"rank":263,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0418675771703327,"rank":263,"remainingConfigurations":444},{"removed":"briefcase","score":0.04131051954844401,"rank":263,"remainingConfigurations":444},{"removed":"aime","score":0.0428433023058346,"rank":258,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04211678391107634,"rank":263,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03911910021381363,"rank":265,"remainingConfigurations":444},{"removed":"automationbench","score":0.041294368331385334,"rank":263,"remainingConfigurations":444},{"removed":"critpt","score":0.03822915083163591,"rank":269,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.04149841859917226,"rank":263,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.042506029421133906,"rank":261,"remainingConfigurations":444},{"removed":"gdpval","score":0.04161877413338105,"rank":262,"remainingConfigurations":444},{"removed":"gmmlu","score":0.041691230979184646,"rank":262,"remainingConfigurations":444},{"removed":"gpqa","score":0.04006002723522785,"rank":265,"remainingConfigurations":444},{"removed":"harvey","score":0.04101189427780783,"rank":263,"remainingConfigurations":444},{"removed":"hle","score":0.04606693852495025,"rank":259,"remainingConfigurations":444},{"removed":"ifbench","score":0.04106186726463023,"rank":257,"remainingConfigurations":444},{"removed":"itbench","score":0.0411091993131077,"rank":263,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04277187077956283,"rank":259,"remainingConfigurations":444},{"removed":"math500","score":0.040617504287694,"rank":264,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.041583243951221635,"rank":263,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04441218173843801,"rank":263,"remainingConfigurations":444},{"removed":"omniscience","score":0.03517716092176704,"rank":267,"remainingConfigurations":444},{"removed":"tau-bench","score":0.04591944910282586,"rank":248,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04211983498666188,"rank":263,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.044192920040783734,"rank":255,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05201919441519331,"rank":265,"remainingConfigurations":444},{"removed":"deepswe","score":0.03261083935226528,"rank":263,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04149339291560852,"rank":263,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.040768527845988646,"rank":263,"remainingConfigurations":444},{"removed":"frontiercode","score":0.04007913652571216,"rank":264,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.040900317812409874,"rank":263,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.040988315598979815,"rank":263,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04145872341395931,"rank":263,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0412970178788535,"rank":263,"remainingConfigurations":444},{"removed":"livebench-math","score":0.041532805902099304,"rank":263,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04098373264045783,"rank":263,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04216971074665132,"rank":263,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04147399361978362,"rank":263,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.040596746873113494,"rank":263,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04118660220545369,"rank":263,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04247355939935472,"rank":263,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04251887057491491,"rank":263,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04155341768542992,"rank":261,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03879607539692634,"rank":257,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04367832813939707,"rank":263,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04131977970313997,"rank":263,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.041313757758236654,"rank":263,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.04132672490404228,"rank":263,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.041392126309255685,"rank":263,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04119488830046478,"rank":263,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.04135783338613342,"rank":263,"remainingConfigurations":444}],"sharedOrderConflicts":0},"k-exaone-2.0-750b-a37b--effort-reasoning":{"score":0.04069210747089583,"rank":264,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.052861408075370965,"rank":265,"remainingConfigurations":444},{"removed":"Datacurve","score":0.031887155939819965,"rank":264,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.040312698115072425,"rank":264,"remainingConfigurations":444},{"removed":"Scale","score":0.04770450251705191,"rank":264,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.040249695302565384,"rank":264,"remainingConfigurations":444},{"removed":"Cognition","score":0.03920104783804551,"rank":265,"remainingConfigurations":444},{"removed":"LiveBench","score":0.042357076124007735,"rank":263,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.04179900395789043,"rank":264,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.041486956528101804,"rank":253,"remainingConfigurations":431},{"removed":"Vals AI","score":0.038993989675219096,"rank":264,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.04067429330742547,"rank":264,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03938481206772515,"rank":264,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.04061964455095852,"rank":264,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.04069210747089583,"rank":264,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04102328091012945,"rank":264,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03963499112784424,"rank":264,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04107203000017747,"rank":264,"remainingConfigurations":444},{"removed":"briefcase","score":0.04032114875714487,"rank":264,"remainingConfigurations":444},{"removed":"aime","score":0.04056698585526823,"rank":261,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0413578338803974,"rank":264,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04025393867074894,"rank":262,"remainingConfigurations":444},{"removed":"automationbench","score":0.04038126866231193,"rank":264,"remainingConfigurations":444},{"removed":"critpt","score":0.03597163613876003,"rank":271,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.040653087828178246,"rank":264,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04158515194996206,"rank":263,"remainingConfigurations":444},{"removed":"gdpval","score":0.04060919616986041,"rank":265,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04102687614630495,"rank":263,"remainingConfigurations":444},{"removed":"gpqa","score":0.03415368111265904,"rank":274,"remainingConfigurations":444},{"removed":"harvey","score":0.04019377794517784,"rank":264,"remainingConfigurations":444},{"removed":"hle","score":0.03936395019203823,"rank":272,"remainingConfigurations":444},{"removed":"ifbench","score":0.03919179874258617,"rank":260,"remainingConfigurations":444},{"removed":"itbench","score":0.04030787212305756,"rank":264,"remainingConfigurations":444},{"removed":"livecodebench","score":0.04060748110228812,"rank":262,"remainingConfigurations":444},{"removed":"math500","score":0.04082048371418683,"rank":262,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04196227862038999,"rank":262,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04423297935949944,"rank":264,"remainingConfigurations":444},{"removed":"omniscience","score":0.061480983497017576,"rank":226,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03883699658719211,"rank":266,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.04128801917144171,"rank":264,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04001760885033278,"rank":266,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05103508578782401,"rank":266,"remainingConfigurations":444},{"removed":"deepswe","score":0.03190904799767006,"rank":264,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.04070261907396134,"rank":264,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0400238307088118,"rank":264,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03920104783804551,"rank":265,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.040123173678954537,"rank":264,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.04020510019040852,"rank":264,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.04066863215173063,"rank":264,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.040506977308670596,"rank":264,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04074048758087174,"rank":264,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.04020040727765941,"rank":264,"remainingConfigurations":444},{"removed":"livebench-language","score":0.041368602569918526,"rank":264,"remainingConfigurations":444},{"removed":"livebench-data","score":0.04068665289824246,"rank":264,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03981942221227557,"rank":264,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.04039996677848256,"rank":264,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04166585809134666,"rank":264,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.04179900395789043,"rank":264,"remainingConfigurations":444},{"removed":"frontiermath","score":0.04072161540176562,"rank":262,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03812272931637314,"rank":258,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04283994588010859,"rank":264,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.04053131929028209,"rank":265,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04052708018011073,"rank":265,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.040537565402659625,"rank":264,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04060418392587476,"rank":264,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04040906505239699,"rank":265,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.040569109439885544,"rank":264,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5--effort-low":{"score":0.03998906652773538,"rank":265,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.013922077217993309,"rank":186,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.11747548348264235,"rank":202,"remainingConfigurations":444},{"removed":"Datacurve","score":0.031084739110247128,"rank":265,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03982719718724126,"rank":265,"remainingConfigurations":444},{"removed":"Scale","score":0.04653448375621667,"rank":265,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.039451055124492485,"rank":266,"remainingConfigurations":444},{"removed":"Cognition","score":0.03875431411048439,"rank":266,"remainingConfigurations":444},{"removed":"LiveBench","score":0.04122321334013624,"rank":265,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.040084837504022384,"rank":266,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03938546091263504,"rank":256,"remainingConfigurations":431},{"removed":"Vals AI","score":0.037628104490468495,"rank":266,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03997272487915101,"rank":265,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03877957575179889,"rank":265,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03992490179781614,"rank":265,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03998906652773538,"rank":265,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.04032884957184778,"rank":265,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03904603173856533,"rank":265,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.04030811102476623,"rank":265,"remainingConfigurations":444},{"removed":"briefcase","score":0.03991413801865335,"rank":265,"remainingConfigurations":444},{"removed":"aime","score":0.040166113385559324,"rank":263,"remainingConfigurations":444},{"removed":"apex-agents","score":0.04051055261415006,"rank":265,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.04045394646017549,"rank":261,"remainingConfigurations":444},{"removed":"automationbench","score":0.03993351348219997,"rank":265,"remainingConfigurations":444},{"removed":"critpt","score":0.03968088370977972,"rank":262,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.040021278340332526,"rank":265,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04073972267414403,"rank":264,"remainingConfigurations":444},{"removed":"gdpval","score":0.04038226985618748,"rank":266,"remainingConfigurations":444},{"removed":"gmmlu","score":0.04045942199838678,"rank":265,"remainingConfigurations":444},{"removed":"gpqa","score":0.04012388776042095,"rank":264,"remainingConfigurations":444},{"removed":"harvey","score":0.03948038135230293,"rank":265,"remainingConfigurations":444},{"removed":"hle","score":0.043852361803865376,"rank":265,"remainingConfigurations":444},{"removed":"ifbench","score":0.03876027465754343,"rank":261,"remainingConfigurations":444},{"removed":"itbench","score":0.039757623871923366,"rank":265,"remainingConfigurations":444},{"removed":"livecodebench","score":0.040174431051600165,"rank":263,"remainingConfigurations":444},{"removed":"math500","score":0.03949634849623426,"rank":266,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04090419139763782,"rank":265,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04204224315833721,"rank":267,"remainingConfigurations":444},{"removed":"omniscience","score":0.0352627836866906,"rank":266,"remainingConfigurations":444},{"removed":"tau-bench","score":0.040025596441447334,"rank":263,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.040461788846798345,"rank":265,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.04077358200516769,"rank":263,"remainingConfigurations":444},{"removed":"arc-agi","score":0.11387425870563722,"rank":201,"remainingConfigurations":444},{"removed":"deepswe","score":0.0311005709783725,"rank":265,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03999822605899237,"rank":265,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.037944551494666266,"rank":267,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03875431411048439,"rank":266,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.039424239991169646,"rank":265,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03951550743556915,"rank":265,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.039966858663108014,"rank":265,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03980268927058366,"rank":265,"remainingConfigurations":444},{"removed":"livebench-math","score":0.04004249357855398,"rank":265,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0395193866310658,"rank":265,"remainingConfigurations":444},{"removed":"livebench-language","score":0.040630779206277556,"rank":265,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0399553445122889,"rank":265,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.039133918665391586,"rank":265,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03971518617935181,"rank":265,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.04095930432566297,"rank":265,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.040084837504022384,"rank":266,"remainingConfigurations":444},{"removed":"frontiermath","score":0.040249950011563965,"rank":263,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.036743883093653874,"rank":262,"remainingConfigurations":444},{"removed":"simpleqa","score":0.042050542070791674,"rank":265,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0398251622687843,"rank":266,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03980877781663604,"rank":266,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03986782202418786,"rank":265,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03987778634260628,"rank":266,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03969219545067514,"rank":266,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.039876480356769585,"rank":265,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v4-flash-0424--effort-non-reasoning":{"score":0.03938206476092586,"rank":266,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.051894510632507725,"rank":266,"remainingConfigurations":444},{"removed":"Datacurve","score":0.030919942151476462,"rank":266,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.038970935936598616,"rank":267,"remainingConfigurations":444},{"removed":"Scale","score":0.046260963181807606,"rank":266,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03895938371609932,"rank":267,"remainingConfigurations":444},{"removed":"Cognition","score":0.037947914688234254,"rank":267,"remainingConfigurations":444},{"removed":"LiveBench","score":0.041002698769382256,"rank":266,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0406358868237819,"rank":265,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.04004103993552489,"rank":254,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03776822566536095,"rank":265,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.039364991772220935,"rank":266,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.038116532643083345,"rank":267,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.039312172076958876,"rank":266,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03938206476092586,"rank":266,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.039705114793008874,"rank":266,"remainingConfigurations":444},{"removed":"All provider reports","score":0.038361473443655335,"rank":266,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03973495969075964,"rank":266,"remainingConfigurations":444},{"removed":"briefcase","score":0.03904327805001856,"rank":267,"remainingConfigurations":444},{"removed":"aime","score":0.03954286149486346,"rank":266,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03999899066340307,"rank":266,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.044070591846098905,"rank":252,"remainingConfigurations":444},{"removed":"automationbench","score":0.039043692636500295,"rank":266,"remainingConfigurations":444},{"removed":"critpt","score":0.039189963504617904,"rank":265,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03937393928950945,"rank":266,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.04021806533570941,"rank":266,"remainingConfigurations":444},{"removed":"gdpval","score":0.039301599749742816,"rank":267,"remainingConfigurations":444},{"removed":"gmmlu","score":0.039821349997030416,"rank":266,"remainingConfigurations":444},{"removed":"gpqa","score":0.0431473566412027,"rank":252,"remainingConfigurations":444},{"removed":"harvey","score":0.038930346426819654,"rank":266,"remainingConfigurations":444},{"removed":"hle","score":0.04889099470027561,"rank":255,"remainingConfigurations":444},{"removed":"ifbench","score":0.040790556140159466,"rank":258,"remainingConfigurations":444},{"removed":"itbench","score":0.03907499491772571,"rank":266,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03950213233463982,"rank":266,"remainingConfigurations":444},{"removed":"math500","score":0.03961425645471367,"rank":265,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04081446769180984,"rank":267,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.042857896768951464,"rank":265,"remainingConfigurations":444},{"removed":"omniscience","score":0.032445105115635656,"rank":270,"remainingConfigurations":444},{"removed":"tau-bench","score":0.031436727925504546,"rank":276,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03997965825054358,"rank":266,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03493111517641557,"rank":271,"remainingConfigurations":444},{"removed":"arc-agi","score":0.05002354074132581,"rank":267,"remainingConfigurations":444},{"removed":"deepswe","score":0.03094100775131149,"rank":266,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03939205399708312,"rank":266,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03871693607444502,"rank":265,"remainingConfigurations":444},{"removed":"frontiercode","score":0.037947914688234254,"rank":267,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0388294501703196,"rank":266,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0389134800563404,"rank":266,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03935900288759561,"rank":266,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.039204430707278914,"rank":266,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0394292305444636,"rank":266,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.038904326015748954,"rank":266,"remainingConfigurations":444},{"removed":"livebench-language","score":0.04003722806512067,"rank":266,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03937539330126024,"rank":266,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.038537174172029336,"rank":266,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03909875368343387,"rank":266,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0403279894364923,"rank":266,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0406358868237819,"rank":265,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03936159790364669,"rank":264,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03689812607731476,"rank":261,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0414690789018688,"rank":266,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03922663765428342,"rank":267,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03922096803286968,"rank":267,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.039232792754175405,"rank":266,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03929559999502281,"rank":267,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03910766723290978,"rank":267,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.039262648818734765,"rank":266,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-medium-3.5--effort-high":{"score":0.0390662183459073,"rank":267,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03981283062231603,"rank":167,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04230267144859823,"rank":276,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03046801225946026,"rank":267,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.039192732181867716,"rank":266,"remainingConfigurations":444},{"removed":"Scale","score":0.04560241594610249,"rank":267,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.039604251025148404,"rank":265,"remainingConfigurations":444},{"removed":"Cognition","score":0.0419243883447921,"rank":259,"remainingConfigurations":444},{"removed":"LiveBench","score":0.041584337518797275,"rank":264,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.038042010834513335,"rank":268,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03785794220702323,"rank":257,"remainingConfigurations":431},{"removed":"Vals AI","score":null,"rank":null,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.039058716885125404,"rank":267,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.038174281605002004,"rank":266,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.039005744112209494,"rank":267,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0390662183459073,"rank":267,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03926579938761077,"rank":267,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03831837783894487,"rank":267,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03921639027503688,"rank":267,"remainingConfigurations":444},{"removed":"briefcase","score":0.03891527909735323,"rank":268,"remainingConfigurations":444},{"removed":"aime","score":0.03838096329652987,"rank":269,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03922112567397896,"rank":267,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03900422991763176,"rank":266,"remainingConfigurations":444},{"removed":"automationbench","score":0.03901641276266087,"rank":268,"remainingConfigurations":444},{"removed":"critpt","score":0.03914112920666973,"rank":266,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03916928077535591,"rank":267,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03928249136203877,"rank":268,"remainingConfigurations":444},{"removed":"gdpval","score":0.038971928664173386,"rank":268,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03908471010324822,"rank":267,"remainingConfigurations":444},{"removed":"gpqa","score":0.03825414376457668,"rank":266,"remainingConfigurations":444},{"removed":"harvey","score":0.026862712746894005,"rank":286,"remainingConfigurations":444},{"removed":"hle","score":0.04197371588377157,"rank":267,"remainingConfigurations":444},{"removed":"ifbench","score":0.03871047352742996,"rank":262,"remainingConfigurations":444},{"removed":"itbench","score":0.03883637082072635,"rank":267,"remainingConfigurations":444},{"removed":"livecodebench","score":0.039179761656244726,"rank":267,"remainingConfigurations":444},{"removed":"math500","score":0.03907992343759754,"rank":267,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.04378768872161095,"rank":259,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04205089878852514,"rank":266,"remainingConfigurations":444},{"removed":"omniscience","score":0.03880965615591875,"rank":260,"remainingConfigurations":444},{"removed":"tau-bench","score":0.038909476021696185,"rank":265,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03920743403362857,"rank":267,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.044791116246863376,"rank":252,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03972405851586407,"rank":278,"remainingConfigurations":444},{"removed":"deepswe","score":0.03052322644328172,"rank":267,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03908572874087903,"rank":267,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03825938832040361,"rank":266,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0419243883447921,"rank":259,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0386651591167752,"rank":267,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03862290357978188,"rank":267,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03906858685667767,"rank":267,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03879489024085888,"rank":267,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03934379314757822,"rank":267,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03860863016225408,"rank":267,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03967053836403719,"rank":267,"remainingConfigurations":444},{"removed":"livebench-data","score":0.039015906545530846,"rank":267,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03816692281709399,"rank":267,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.038971500435837976,"rank":267,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03969160969238166,"rank":267,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.038042010834513335,"rank":268,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03928111258531582,"rank":265,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.037862004713903934,"rank":259,"remainingConfigurations":444},{"removed":"simpleqa","score":0.04048957243574607,"rank":267,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0407883544974434,"rank":264,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.04105857211605214,"rank":264,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.037617486184664733,"rank":268,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.04059858799612381,"rank":265,"remainingConfigurations":444},{"removed":"vibe-code","score":0.04114901004127258,"rank":264,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03747307054303823,"rank":268,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-26b-a4b-it--effort-reasoning":{"score":0.03843663959275087,"rank":268,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05001173911424133,"rank":268,"remainingConfigurations":444},{"removed":"Datacurve","score":0.03015440609658122,"rank":268,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.038075902319480534,"rank":268,"remainingConfigurations":444},{"removed":"Scale","score":0.045193656837551284,"rank":268,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.038019485855721465,"rank":268,"remainingConfigurations":444},{"removed":"Cognition","score":0.03707377485221112,"rank":268,"remainingConfigurations":444},{"removed":"LiveBench","score":0.039962569746427,"rank":267,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.039544249523403394,"rank":267,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03951705387479472,"rank":255,"remainingConfigurations":431},{"removed":"Vals AI","score":0.036831493071121706,"rank":267,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03841933179092721,"rank":268,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03718198487567014,"rank":268,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03836740442469846,"rank":268,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03843663959275087,"rank":268,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.038750144921266695,"rank":268,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03741790170948391,"rank":268,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03872323645660296,"rank":268,"remainingConfigurations":444},{"removed":"briefcase","score":0.039876032888783844,"rank":266,"remainingConfigurations":444},{"removed":"aime","score":0.038384575563036503,"rank":268,"remainingConfigurations":444},{"removed":"apex-agents","score":0.039072984053401434,"rank":268,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.036257016202907735,"rank":270,"remainingConfigurations":444},{"removed":"automationbench","score":0.03902280610318531,"rank":267,"remainingConfigurations":444},{"removed":"critpt","score":0.043721414596741205,"rank":253,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03837999779682406,"rank":268,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.039353926491036216,"rank":267,"remainingConfigurations":444},{"removed":"gdpval","score":0.0383912720848364,"rank":269,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03875342833579475,"rank":268,"remainingConfigurations":444},{"removed":"gpqa","score":0.03675217507165815,"rank":269,"remainingConfigurations":444},{"removed":"harvey","score":0.037961627892654254,"rank":267,"remainingConfigurations":444},{"removed":"hle","score":0.04000997615359562,"rank":271,"remainingConfigurations":444},{"removed":"ifbench","score":0.03266137731362905,"rank":271,"remainingConfigurations":444},{"removed":"itbench","score":0.03823017715016724,"rank":268,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0385453512818811,"rank":269,"remainingConfigurations":444},{"removed":"math500","score":0.03869619173466952,"rank":268,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.039895808477900675,"rank":268,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04059784474199401,"rank":270,"remainingConfigurations":444},{"removed":"omniscience","score":0.03769991990339314,"rank":264,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03763678448117981,"rank":267,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0390135727250455,"rank":268,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03922360710800646,"rank":268,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04818377359542624,"rank":268,"remainingConfigurations":444},{"removed":"deepswe","score":0.030175757029590227,"rank":268,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03844659109873945,"rank":268,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03783275734166218,"rank":268,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03707377485221112,"rank":268,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.037902250954243294,"rank":268,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03797978277948436,"rank":268,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03841472695423064,"rank":268,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.038260840210106485,"rank":268,"remainingConfigurations":444},{"removed":"livebench-math","score":0.038480608922559105,"rank":268,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03797626518897664,"rank":268,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03908238279497888,"rank":268,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03842696122452795,"rank":268,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03760713277996206,"rank":268,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03816072656344642,"rank":268,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03935726416253269,"rank":268,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.039544249523403394,"rank":267,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03848592446590895,"rank":267,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0361479401416445,"rank":263,"remainingConfigurations":444},{"removed":"simpleqa","score":0.040475359795674695,"rank":268,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.038285319589761106,"rank":268,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03827909106322495,"rank":268,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03828947650804474,"rank":267,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03835366139728827,"rank":268,"remainingConfigurations":444},{"removed":"vibe-code","score":0.038169148124550564,"rank":268,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.038319865228797774,"rank":267,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-lite--effort-high":{"score":0.03635262996705773,"rank":269,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04806418538408758,"rank":269,"remainingConfigurations":444},{"removed":"Datacurve","score":0.028516891407345618,"rank":269,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.035976884877741706,"rank":269,"remainingConfigurations":444},{"removed":"Scale","score":0.042735144786222,"rank":269,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.035960105514524256,"rank":269,"remainingConfigurations":444},{"removed":"Cognition","score":0.03509471595917244,"rank":269,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03783787240321386,"rank":268,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0373757331123675,"rank":269,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.036960370540170165,"rank":258,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0348480128006323,"rank":268,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03633671522939754,"rank":269,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03517573699173092,"rank":269,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.036287569259340575,"rank":269,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03635262996705773,"rank":269,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.036651013794383173,"rank":269,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03540136931645965,"rank":269,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03664440415601986,"rank":269,"remainingConfigurations":444},{"removed":"briefcase","score":0.03605861514061723,"rank":269,"remainingConfigurations":444},{"removed":"aime","score":0.033551635858503744,"rank":272,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03688826648058776,"rank":269,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03538850807013116,"rank":271,"remainingConfigurations":444},{"removed":"automationbench","score":0.03608478157195769,"rank":269,"remainingConfigurations":444},{"removed":"critpt","score":0.03588341998804239,"rank":272,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.036294980376093515,"rank":269,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03716599616223321,"rank":269,"remainingConfigurations":444},{"removed":"gdpval","score":0.04099588062953848,"rank":264,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03677215247842823,"rank":269,"remainingConfigurations":444},{"removed":"gpqa","score":0.03425089215124285,"rank":273,"remainingConfigurations":444},{"removed":"harvey","score":0.03591363275997462,"rank":268,"remainingConfigurations":444},{"removed":"hle","score":0.04016985754887472,"rank":270,"remainingConfigurations":444},{"removed":"ifbench","score":0.03197499482030267,"rank":273,"remainingConfigurations":444},{"removed":"itbench","score":0.035965794208821025,"rank":269,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03648756039134539,"rank":272,"remainingConfigurations":444},{"removed":"math500","score":0.03675338124577717,"rank":269,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03780163999020276,"rank":269,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04093757469112675,"rank":268,"remainingConfigurations":444},{"removed":"omniscience","score":0.03463785412452069,"rank":268,"remainingConfigurations":444},{"removed":"tau-bench","score":0.034980341954228764,"rank":268,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03690413593485766,"rank":269,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03929515150904473,"rank":267,"remainingConfigurations":444},{"removed":"arc-agi","score":0.046298299203997605,"rank":269,"remainingConfigurations":444},{"removed":"deepswe","score":0.02853651284376066,"rank":269,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03636197232816884,"rank":269,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.035742125189539654,"rank":269,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03509471595917244,"rank":269,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0358419294081447,"rank":269,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03591537861913914,"rank":269,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03633194099181006,"rank":269,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.036187663497563936,"rank":269,"remainingConfigurations":444},{"removed":"livebench-math","score":0.036396285551252204,"rank":269,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03591011221246248,"rank":269,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03696197070061941,"rank":269,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03634619857839588,"rank":269,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03556703820915174,"rank":269,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.036089674309889984,"rank":269,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03723081235966157,"rank":269,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0373757331123675,"rank":269,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03642666036861467,"rank":269,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03394957645116275,"rank":266,"remainingConfigurations":444},{"removed":"simpleqa","score":0.038294889472936765,"rank":269,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03620810583362097,"rank":269,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0362031366251438,"rank":269,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03621392956819985,"rank":269,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03627251263991924,"rank":269,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03609767470393069,"rank":269,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.036241822408323854,"rank":269,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-v3.2--effort-non-reasoning":{"score":0.03617765311863043,"rank":270,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.047427200604094145,"rank":270,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02837811028914893,"rank":270,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03577866287633714,"rank":270,"remainingConfigurations":444},{"removed":"Scale","score":0.04249688647087702,"rank":270,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03578686428145828,"rank":270,"remainingConfigurations":444},{"removed":"Cognition","score":0.03499034145308754,"rank":270,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03765840752258206,"rank":269,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03707100199759523,"rank":270,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.036650560117919666,"rank":259,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03468217305456044,"rank":269,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03616192810884914,"rank":270,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03501014773969553,"rank":270,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.036113449429263436,"rank":270,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03617765311863043,"rank":270,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03647429659150417,"rank":270,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03523500414740549,"rank":270,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03649176407264607,"rank":270,"remainingConfigurations":444},{"removed":"briefcase","score":0.03595972171306249,"rank":270,"remainingConfigurations":444},{"removed":"aime","score":0.0402227289370216,"rank":262,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03673750199312755,"rank":270,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03749356651835654,"rank":268,"remainingConfigurations":444},{"removed":"automationbench","score":0.03595782569341815,"rank":270,"remainingConfigurations":444},{"removed":"critpt","score":0.03349267779031262,"rank":279,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.036158917727257996,"rank":270,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03702143602843077,"rank":270,"remainingConfigurations":444},{"removed":"gdpval","score":0.03631814104245614,"rank":270,"remainingConfigurations":444},{"removed":"gmmlu","score":0.036652476854534086,"rank":270,"remainingConfigurations":444},{"removed":"gpqa","score":0.03617781151562264,"rank":271,"remainingConfigurations":444},{"removed":"harvey","score":0.03575576821551866,"rank":269,"remainingConfigurations":444},{"removed":"hle","score":0.040344713719643065,"rank":269,"remainingConfigurations":444},{"removed":"ifbench","score":0.03575708096870143,"rank":268,"remainingConfigurations":444},{"removed":"itbench","score":0.03583352365930913,"rank":270,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03915685687940868,"rank":268,"remainingConfigurations":444},{"removed":"math500","score":0.036335404748697724,"rank":270,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.035408653534055784,"rank":274,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.039315498111865355,"rank":271,"remainingConfigurations":444},{"removed":"omniscience","score":0.031133383510189377,"rank":275,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03403685633873705,"rank":271,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03674202918699186,"rank":270,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03393363695087041,"rank":273,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04567160863977427,"rank":270,"remainingConfigurations":444},{"removed":"deepswe","score":0.028397547184839122,"rank":270,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.036186875271049294,"rank":270,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03554422878349653,"rank":270,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03499034145308754,"rank":270,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.035661462081553935,"rank":270,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.035742943123018574,"rank":270,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03615654750725166,"rank":270,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.036014413352092906,"rank":270,"remainingConfigurations":444},{"removed":"livebench-math","score":0.036221821369112416,"rank":270,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03573589883420509,"rank":270,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03678264284899118,"rank":270,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03617081552098547,"rank":270,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.035397094343833306,"rank":270,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03591605503108201,"rank":270,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03705266504757205,"rank":270,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03707100199759523,"rank":270,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0362152830556132,"rank":270,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.033728311079878,"rank":267,"remainingConfigurations":444},{"removed":"simpleqa","score":0.038114132763143245,"rank":270,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03603368872591738,"rank":270,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03602852939505333,"rank":270,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.036040020092859344,"rank":270,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0360973541206246,"rank":270,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03592387289273009,"rank":270,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03606716934559098,"rank":270,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.2--effort-non-reasoning":{"score":0.03559174750836326,"rank":271,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04654735767937731,"rank":271,"remainingConfigurations":444},{"removed":"Datacurve","score":0.027899121826958157,"rank":271,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03517894221448124,"rank":271,"remainingConfigurations":444},{"removed":"Scale","score":0.041817792447164596,"rank":271,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03520486893423537,"rank":271,"remainingConfigurations":444},{"removed":"Cognition","score":0.034375917296830545,"rank":271,"remainingConfigurations":444},{"removed":"LiveBench","score":0.037065658281039936,"rank":270,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03652480058766052,"rank":271,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03621595433943701,"rank":260,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03410888259719141,"rank":270,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03557622222430519,"rank":271,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0344395272992676,"rank":271,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03552837235595926,"rank":271,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03559174750836326,"rank":271,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03588408471572623,"rank":271,"remainingConfigurations":444},{"removed":"All provider reports","score":0.034660981515377845,"rank":271,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.035931533236151135,"rank":271,"remainingConfigurations":444},{"removed":"briefcase","score":0.035411441455440056,"rank":271,"remainingConfigurations":444},{"removed":"aime","score":0.03979575030065775,"rank":264,"remainingConfigurations":444},{"removed":"apex-agents","score":0.036182589232080425,"rank":271,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03636203616555412,"rank":269,"remainingConfigurations":444},{"removed":"automationbench","score":0.035413461681856086,"rank":271,"remainingConfigurations":444},{"removed":"critpt","score":0.0338386144003217,"rank":278,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03558779620062503,"rank":271,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.036454538182601436,"rank":271,"remainingConfigurations":444},{"removed":"gdpval","score":0.0356938470831576,"rank":273,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03148504582256639,"rank":277,"remainingConfigurations":444},{"removed":"gpqa","score":0.03686491455839721,"rank":268,"remainingConfigurations":444},{"removed":"harvey","score":0.03518224454911819,"rank":270,"remainingConfigurations":444},{"removed":"hle","score":0.0413787024412346,"rank":268,"remainingConfigurations":444},{"removed":"ifbench","score":0.035236064719174974,"rank":269,"remainingConfigurations":444},{"removed":"itbench","score":0.03529523689412052,"rank":271,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03667572421494458,"rank":271,"remainingConfigurations":444},{"removed":"math500","score":0.03569035746083019,"rank":271,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03739109356936254,"rank":270,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03877439286721487,"rank":274,"remainingConfigurations":444},{"removed":"omniscience","score":0.029145857752742158,"rank":280,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03455813268383106,"rank":269,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03615291740982859,"rank":271,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03399598940956696,"rank":272,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04483947203663888,"rank":271,"remainingConfigurations":444},{"removed":"deepswe","score":0.027918260029159297,"rank":271,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.035600877904086906,"rank":271,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03497863405359023,"rank":271,"remainingConfigurations":444},{"removed":"frontiercode","score":0.034375917296830545,"rank":271,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03508364289420502,"rank":271,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03516399331006636,"rank":271,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03557113021011621,"rank":271,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03543058959343264,"rank":271,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03563524426519625,"rank":271,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03515757074048701,"rank":271,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03618817222904323,"rank":271,"remainingConfigurations":444},{"removed":"livebench-data","score":0.035584615714168544,"rank":271,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03482259255658065,"rank":271,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03533440443046543,"rank":271,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03645266204967309,"rank":271,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03652480058766052,"rank":271,"remainingConfigurations":444},{"removed":"frontiermath","score":0.035642115233101346,"rank":271,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03328795587346378,"rank":268,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03749752684509428,"rank":271,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.035449766642438735,"rank":271,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03544507819646985,"rank":271,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03545608130198336,"rank":271,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.035512853202461656,"rank":271,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03534181612831647,"rank":271,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0354830022213166,"rank":271,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-pro-preview--effort-low":{"score":0.03518155838373191,"rank":272,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04642109735035943,"rank":272,"remainingConfigurations":444},{"removed":"Datacurve","score":0.027616856011359617,"rank":272,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03479088730591489,"rank":272,"remainingConfigurations":444},{"removed":"Scale","score":0.041419915200493575,"rank":272,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.034806857996997315,"rank":272,"remainingConfigurations":444},{"removed":"Cognition","score":0.03405911848251059,"rank":272,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03664725573366557,"rank":271,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.036259126595069816,"rank":272,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.035781252790397906,"rank":261,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03374747769208172,"rank":271,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03516618148563618,"rank":272,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03404284299106299,"rank":272,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03511863703506068,"rank":272,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03518155838373191,"rank":272,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.035471672395590036,"rank":272,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03426253162875497,"rank":272,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03550365471509792,"rank":272,"remainingConfigurations":444},{"removed":"briefcase","score":0.034967491840428404,"rank":272,"remainingConfigurations":444},{"removed":"aime","score":0.037138767990761275,"rank":270,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0357549338576528,"rank":272,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.033301217898161116,"rank":275,"remainingConfigurations":444},{"removed":"automationbench","score":0.03495002474092152,"rank":272,"remainingConfigurations":444},{"removed":"critpt","score":0.03912548946019114,"rank":267,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03518359293190484,"rank":272,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03600045319261703,"rank":272,"remainingConfigurations":444},{"removed":"gdpval","score":0.03609756565910119,"rank":271,"remainingConfigurations":444},{"removed":"gmmlu","score":0.030987570965667965,"rank":279,"remainingConfigurations":444},{"removed":"gpqa","score":0.035022610060014746,"rank":272,"remainingConfigurations":444},{"removed":"harvey","score":0.03476608215497334,"rank":271,"remainingConfigurations":444},{"removed":"hle","score":0.04373398446037643,"rank":266,"remainingConfigurations":444},{"removed":"ifbench","score":0.02903879293580214,"rank":280,"remainingConfigurations":444},{"removed":"itbench","score":0.03488605158663369,"rank":272,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03672505308555477,"rank":270,"remainingConfigurations":444},{"removed":"math500","score":0.03529932973161166,"rank":272,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03578271454552679,"rank":273,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.04064234819626638,"rank":269,"remainingConfigurations":444},{"removed":"omniscience","score":0.03149832832201156,"rank":273,"remainingConfigurations":444},{"removed":"tau-bench","score":0.031514734396312805,"rank":274,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03572120691008518,"rank":272,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03623501951940431,"rank":269,"remainingConfigurations":444},{"removed":"arc-agi","score":0.044674351050810655,"rank":272,"remainingConfigurations":444},{"removed":"deepswe","score":0.02763567703220061,"rank":272,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03519054088338937,"rank":272,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.034576250495968,"rank":272,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03405911848251059,"rank":272,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03468458026478022,"rank":272,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03476283778811692,"rank":272,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.035161114446090366,"rank":272,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03502235257451456,"rank":272,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03522436602410888,"rank":272,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03475128488827895,"rank":272,"remainingConfigurations":444},{"removed":"livebench-language","score":0.035771392804829355,"rank":272,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03517487041744826,"rank":272,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.034420736741341336,"rank":272,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.034926650751464165,"rank":272,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03603444013064132,"rank":272,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.036259126595069816,"rank":272,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0352525131777803,"rank":272,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.032921865117167666,"rank":269,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03706659107372873,"rank":272,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.035041399735642846,"rank":272,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03503624000624997,"rank":272,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03504748431838926,"rank":272,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03510316054305155,"rank":272,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0349341598396286,"rank":272,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.035073939065614616,"rank":272,"remainingConfigurations":444}],"sharedOrderConflicts":0},"exaone-4.5-33b--effort-reasoning":{"score":0.03504746533595311,"rank":273,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04578420994467967,"rank":273,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02747086455796989,"rank":273,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03467263285101208,"rank":273,"remainingConfigurations":444},{"removed":"Scale","score":0.04124341801489093,"rank":273,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03466442438923242,"rank":273,"remainingConfigurations":444},{"removed":"Cognition","score":0.033894442020597444,"rank":273,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03649762787518913,"rank":272,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03601023268562488,"rank":273,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03553004702071142,"rank":262,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03359004946821247,"rank":272,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03503215294568431,"rank":273,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03391083736931485,"rank":273,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03498457630336362,"rank":273,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03504746533595311,"rank":273,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.035334699373220306,"rank":273,"remainingConfigurations":444},{"removed":"All provider reports","score":0.034127825694963844,"rank":273,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03533586278639523,"rank":273,"remainingConfigurations":444},{"removed":"briefcase","score":0.03474095541304199,"rank":273,"remainingConfigurations":444},{"removed":"aime","score":0.03501914290154782,"rank":271,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03556292900802598,"rank":273,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03482825313857449,"rank":272,"remainingConfigurations":444},{"removed":"automationbench","score":0.03476383753693884,"rank":273,"remainingConfigurations":444},{"removed":"critpt","score":0.03428290713248224,"rank":277,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03497103997559986,"rank":273,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.035804544815945784,"rank":273,"remainingConfigurations":444},{"removed":"gdpval","score":0.03594623256300879,"rank":272,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03539419002631466,"rank":271,"remainingConfigurations":444},{"removed":"gpqa","score":0.032771497699191396,"rank":278,"remainingConfigurations":444},{"removed":"harvey","score":0.034622735931717157,"rank":272,"remainingConfigurations":444},{"removed":"hle","score":0.03797730597364644,"rank":275,"remainingConfigurations":444},{"removed":"ifbench","score":0.03227693721125146,"rank":272,"remainingConfigurations":444},{"removed":"itbench","score":0.034681410233333154,"rank":273,"remainingConfigurations":444},{"removed":"livecodebench","score":0.035138166622696344,"rank":273,"remainingConfigurations":444},{"removed":"math500","score":0.035295185381190995,"rank":273,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03636275648158061,"rank":271,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.037283501247348534,"rank":275,"remainingConfigurations":444},{"removed":"omniscience","score":0.037494679728713794,"rank":265,"remainingConfigurations":444},{"removed":"tau-bench","score":0.032565694982697756,"rank":273,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0355762168564725,"rank":273,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03581738333941615,"rank":270,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04410053456829561,"rank":273,"remainingConfigurations":444},{"removed":"deepswe","score":0.027489862068761525,"rank":273,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.035056461414928484,"rank":273,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03446163682267891,"rank":273,"remainingConfigurations":444},{"removed":"frontiercode","score":0.033894442020597444,"rank":273,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03454763721254767,"rank":273,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.034624981408409694,"rank":273,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03502728540564399,"rank":273,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0348883028526125,"rank":273,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03508976403040248,"rank":273,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03461956837410161,"rank":273,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03563636784244174,"rank":273,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03504112072330736,"rank":273,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03428861582661061,"rank":273,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.034793402553189905,"rank":273,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0358961498334072,"rank":273,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03601023268562488,"rank":273,"remainingConfigurations":444},{"removed":"frontiermath","score":0.035109257238642215,"rank":273,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03274636714644025,"rank":270,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03692260400031747,"rank":273,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03490785267221975,"rank":273,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03490295325258918,"rank":273,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03491334020198016,"rank":273,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03496995843932997,"rank":273,"remainingConfigurations":444},{"removed":"vibe-code","score":0.034801296314620346,"rank":273,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03494032811523379,"rank":273,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-nano--effort-medium":{"score":0.033244773911140696,"rank":274,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.013572809490074342,"rank":187,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.06981010904355595,"rank":234,"remainingConfigurations":444},{"removed":"Datacurve","score":0.025836885293351528,"rank":274,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03315178055530144,"rank":274,"remainingConfigurations":444},{"removed":"Scale","score":0.03884281339571142,"rank":274,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.032798941953234635,"rank":274,"remainingConfigurations":444},{"removed":"Cognition","score":0.03232517450746311,"rank":274,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03445890180614322,"rank":273,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.033345930217296905,"rank":276,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03282653513282617,"rank":267,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03136792697134942,"rank":274,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03323086758120144,"rank":274,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.032218180737237284,"rank":274,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03319028461887336,"rank":274,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.033244773911140696,"rank":274,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03352891306519106,"rank":274,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03244000030496772,"rank":274,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03350561920441299,"rank":274,"remainingConfigurations":444},{"removed":"briefcase","score":0.033103252578164925,"rank":274,"remainingConfigurations":444},{"removed":"aime","score":0.033370397239695475,"rank":274,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0336926667139079,"rank":274,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03211771412172019,"rank":278,"remainingConfigurations":444},{"removed":"automationbench","score":0.03312797600505656,"rank":274,"remainingConfigurations":444},{"removed":"critpt","score":0.030270117090170693,"rank":283,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.033249425815824414,"rank":274,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03385531911595026,"rank":274,"remainingConfigurations":444},{"removed":"gdpval","score":0.033482554503420976,"rank":274,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03360254868116256,"rank":273,"remainingConfigurations":444},{"removed":"gpqa","score":0.033600152285879564,"rank":276,"remainingConfigurations":444},{"removed":"harvey","score":0.032813475258451845,"rank":273,"remainingConfigurations":444},{"removed":"hle","score":0.03575918268580256,"rank":277,"remainingConfigurations":444},{"removed":"ifbench","score":0.031040500527148452,"rank":274,"remainingConfigurations":444},{"removed":"itbench","score":0.03302139344818968,"rank":274,"remainingConfigurations":444},{"removed":"livecodebench","score":0.033608831484209824,"rank":274,"remainingConfigurations":444},{"removed":"math500","score":0.033487798008861265,"rank":274,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03477223374518803,"rank":275,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03906783033396275,"rank":272,"remainingConfigurations":444},{"removed":"omniscience","score":0.03137496880297431,"rank":274,"remainingConfigurations":444},{"removed":"tau-bench","score":0.034069226377913486,"rank":270,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.033634372246472276,"rank":274,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.031881435339712876,"rank":276,"remainingConfigurations":444},{"removed":"arc-agi","score":0.06734630680808736,"rank":235,"remainingConfigurations":444},{"removed":"deepswe","score":0.02585056690437029,"rank":274,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.033252539111670136,"rank":274,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03171099271776629,"rank":277,"remainingConfigurations":444},{"removed":"frontiercode","score":0.03232517450746311,"rank":274,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03276655315472113,"rank":274,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.032847917310307326,"rank":274,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03322654125339336,"rank":274,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.033089038166844505,"rank":274,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03329170366755413,"rank":274,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.032837623783725775,"rank":274,"remainingConfigurations":444},{"removed":"livebench-language","score":0.033781205926334046,"rank":274,"remainingConfigurations":444},{"removed":"livebench-data","score":0.033226552386206434,"rank":274,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03252581415755574,"rank":274,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03301151789148651,"rank":274,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03406927628224413,"rank":274,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.033345930217296905,"rank":276,"remainingConfigurations":444},{"removed":"frontiermath","score":0.033453635673322636,"rank":274,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.030491110111962,"rank":274,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03498945510544895,"rank":274,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03310833726792866,"rank":274,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03310240551965272,"rank":274,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03313296059097544,"rank":274,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0331598897379509,"rank":274,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03299995919085729,"rank":274,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03314246044817506,"rank":274,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.5--effort-reasoning":{"score":0.03279278724203677,"rank":275,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04296080999644916,"rank":274,"remainingConfigurations":444},{"removed":"Datacurve","score":0.025709355889449517,"rank":275,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03237769162597307,"rank":275,"remainingConfigurations":444},{"removed":"Scale","score":0.03863794288455004,"rank":275,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.032438616891309065,"rank":275,"remainingConfigurations":444},{"removed":"Cognition","score":0.031779003612702514,"rank":275,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03414310702130371,"rank":274,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03371718877732342,"rank":274,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.033300093272373606,"rank":265,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03145268879673815,"rank":273,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03277849298289134,"rank":275,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03172886106399656,"rank":275,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.032734342900295234,"rank":275,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03279278724203677,"rank":275,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03306134300947885,"rank":275,"remainingConfigurations":444},{"removed":"All provider reports","score":0.031932103038262,"rank":275,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03308172327355189,"rank":275,"remainingConfigurations":444},{"removed":"briefcase","score":0.03261151668551434,"rank":275,"remainingConfigurations":444},{"removed":"aime","score":0.033085095692656344,"rank":276,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0333016233813771,"rank":275,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.032874517794894614,"rank":276,"remainingConfigurations":444},{"removed":"automationbench","score":0.032603562358944696,"rank":275,"remainingConfigurations":444},{"removed":"critpt","score":0.03702948277581448,"rank":270,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03277456421107187,"rank":275,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.033564838172482146,"rank":275,"remainingConfigurations":444},{"removed":"gdpval","score":0.032911473635672685,"rank":275,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03311735727636001,"rank":274,"remainingConfigurations":444},{"removed":"gpqa","score":0.031322466669196754,"rank":280,"remainingConfigurations":444},{"removed":"harvey","score":0.03241170134732418,"rank":274,"remainingConfigurations":444},{"removed":"hle","score":0.03565242537746387,"rank":278,"remainingConfigurations":444},{"removed":"ifbench","score":0.03355924953777307,"rank":270,"remainingConfigurations":444},{"removed":"itbench","score":0.03248428346866216,"rank":275,"remainingConfigurations":444},{"removed":"livecodebench","score":0.031654894113217064,"rank":279,"remainingConfigurations":444},{"removed":"math500","score":0.032245739266647165,"rank":277,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.031865770148435425,"rank":279,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03562220007216641,"rank":277,"remainingConfigurations":444},{"removed":"omniscience","score":0.027084614647768675,"rank":286,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03380832245922387,"rank":272,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0333042191286221,"rank":275,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.032580285906423694,"rank":274,"remainingConfigurations":444},{"removed":"arc-agi","score":0.041355856407498774,"rank":274,"remainingConfigurations":444},{"removed":"deepswe","score":0.02572721135098413,"rank":275,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.032801219879090626,"rank":275,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.032214282401819956,"rank":274,"remainingConfigurations":444},{"removed":"frontiercode","score":0.031779003612702514,"rank":275,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.032321568384307026,"rank":275,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03239651600746832,"rank":275,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03277402370790826,"rank":275,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03264442866520266,"rank":275,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03283308779597515,"rank":275,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.032389857249881755,"rank":275,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03334529439653901,"rank":275,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03278669789694778,"rank":275,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03208036336705661,"rank":275,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03255394821887966,"rank":275,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03359130352344311,"rank":275,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03371718877732342,"rank":274,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03286005535518173,"rank":275,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.03061325873106836,"rank":272,"remainingConfigurations":444},{"removed":"simpleqa","score":0.034565621146627805,"rank":275,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.032661302255462626,"rank":275,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03265670733449733,"rank":275,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.032667156097108525,"rank":275,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.032719547447977254,"rank":275,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03256127680175309,"rank":275,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03269207064514708,"rank":275,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-5--effort-non-reasoning":{"score":0.032631102625596355,"rank":276,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04292141833117466,"rank":275,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02557473201078324,"rank":276,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03228058565198724,"rank":276,"remainingConfigurations":444},{"removed":"Scale","score":0.038476286495873556,"rank":276,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03227205328669053,"rank":276,"remainingConfigurations":444},{"removed":"Cognition","score":0.031577497439965095,"rank":276,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03398927162761397,"rank":275,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03353252434165058,"rank":275,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0333936506473031,"rank":264,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03128236625244962,"rank":275,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03261680073081838,"rank":276,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03157091853936177,"rank":276,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03257282075809981,"rank":276,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.032631102625596355,"rank":276,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03289994163259543,"rank":276,"remainingConfigurations":444},{"removed":"All provider reports","score":0.03177450219446359,"rank":276,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03292452019661358,"rank":276,"remainingConfigurations":444},{"removed":"briefcase","score":0.032375560022776174,"rank":276,"remainingConfigurations":444},{"removed":"aime","score":0.0325697804762606,"rank":277,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03316886663992645,"rank":276,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03424411724860603,"rank":273,"remainingConfigurations":444},{"removed":"automationbench","score":0.03236522519655859,"rank":276,"remainingConfigurations":444},{"removed":"critpt","score":0.038438611468797075,"rank":268,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03263008400927078,"rank":276,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03332391796229225,"rank":276,"remainingConfigurations":444},{"removed":"gdpval","score":0.03256737943394499,"rank":276,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03419968014274108,"rank":272,"remainingConfigurations":444},{"removed":"gpqa","score":0.03661601287106828,"rank":270,"remainingConfigurations":444},{"removed":"harvey","score":0.03224961614494239,"rank":275,"remainingConfigurations":444},{"removed":"hle","score":0.03909384214277413,"rank":273,"remainingConfigurations":444},{"removed":"ifbench","score":0.03028317564718495,"rank":277,"remainingConfigurations":444},{"removed":"itbench","score":0.032362395157721595,"rank":276,"remainingConfigurations":444},{"removed":"livecodebench","score":0.032622306579760126,"rank":276,"remainingConfigurations":444},{"removed":"math500","score":0.032728748974634576,"rank":275,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03375401827895822,"rank":276,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03551016666342763,"rank":278,"remainingConfigurations":444},{"removed":"omniscience","score":0.028165825164329847,"rank":284,"remainingConfigurations":444},{"removed":"tau-bench","score":0.025824261490358363,"rank":285,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03314147717554673,"rank":276,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.027778054647200495,"rank":283,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0413184063860885,"rank":275,"remainingConfigurations":444},{"removed":"deepswe","score":0.025592319730136513,"rank":276,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.032639473764274014,"rank":276,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0320672738342394,"rank":275,"remainingConfigurations":444},{"removed":"frontiercode","score":0.031577497439965095,"rank":276,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03216251028100643,"rank":276,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.032239287277857374,"rank":276,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03261195887303578,"rank":276,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.032482912802691895,"rank":276,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03267108166872661,"rank":276,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03222905882878622,"rank":276,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03318087009345775,"rank":276,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03262529381123444,"rank":276,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03192221232903146,"rank":276,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.032393377403692525,"rank":276,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03342691361957905,"rank":276,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03353252434165058,"rank":275,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03275887704125597,"rank":276,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.030550526701174252,"rank":273,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03438708343923469,"rank":276,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03250041671326504,"rank":276,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03249560771672546,"rank":276,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.032505964292632326,"rank":276,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.032557999712499446,"rank":276,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03240064055340525,"rank":276,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03253060650610396,"rank":276,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-luna--effort-non-reasoning":{"score":0.03228001743325117,"rank":277,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.042085280430264375,"rank":277,"remainingConfigurations":444},{"removed":"Datacurve","score":0.025243234598519262,"rank":277,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.03195558122992657,"rank":277,"remainingConfigurations":444},{"removed":"Scale","score":0.037963184885999604,"rank":277,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03190473234736149,"rank":277,"remainingConfigurations":444},{"removed":"Cognition","score":0.030878607482786674,"rank":278,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03369521195074015,"rank":276,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03317190569715305,"rank":277,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.032822720475281515,"rank":268,"remainingConfigurations":431},{"removed":"Vals AI","score":0.03098789812290863,"rank":276,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.032265393109647815,"rank":277,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03122396497064689,"rank":277,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03222075607100309,"rank":277,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03228001743325117,"rank":277,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03255152987615225,"rank":277,"remainingConfigurations":444},{"removed":"All provider reports","score":0.031428714184287186,"rank":277,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.032659609148011685,"rank":277,"remainingConfigurations":444},{"removed":"briefcase","score":0.031143625307693826,"rank":277,"remainingConfigurations":444},{"removed":"aime","score":0.03201214846219324,"rank":279,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03291068956848335,"rank":277,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03395469909531283,"rank":274,"remainingConfigurations":444},{"removed":"automationbench","score":0.031523840589307434,"rank":278,"remainingConfigurations":444},{"removed":"critpt","score":0.031395507152691834,"rank":282,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.032422628705636766,"rank":277,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.031445970420384745,"rank":279,"remainingConfigurations":444},{"removed":"gdpval","score":0.030239683936675265,"rank":282,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03254175927106096,"rank":275,"remainingConfigurations":444},{"removed":"gpqa","score":0.03712592338295639,"rank":267,"remainingConfigurations":444},{"removed":"harvey","score":0.03190527596441212,"rank":276,"remainingConfigurations":444},{"removed":"hle","score":0.038852661389577846,"rank":274,"remainingConfigurations":444},{"removed":"ifbench","score":0.030723454497403314,"rank":276,"remainingConfigurations":444},{"removed":"itbench","score":0.03210067530793817,"rank":277,"remainingConfigurations":444},{"removed":"livecodebench","score":0.032196270878448764,"rank":277,"remainingConfigurations":444},{"removed":"math500","score":0.032408784025407485,"rank":276,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03332690462567014,"rank":277,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.038947288329026074,"rank":273,"remainingConfigurations":444},{"removed":"omniscience","score":0.02587086616781938,"rank":288,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03099148618536029,"rank":278,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03276345245774342,"rank":277,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.030473841331708985,"rank":279,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04049901493247028,"rank":276,"remainingConfigurations":444},{"removed":"deepswe","score":0.025260432516952022,"rank":277,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03228849210025508,"rank":277,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.031772948283799715,"rank":276,"remainingConfigurations":444},{"removed":"frontiercode","score":0.030878607482786674,"rank":278,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03182212430039481,"rank":277,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03189075507144834,"rank":277,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03226160311239264,"rank":277,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03213183903935896,"rank":277,"remainingConfigurations":444},{"removed":"livebench-math","score":0.032317046160837117,"rank":277,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03188202612928053,"rank":277,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03282814529398694,"rank":277,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03227691401986058,"rank":277,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.03157457478439308,"rank":277,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.03204336107987112,"rank":277,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03306944977311414,"rank":277,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03317190569715305,"rank":277,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03233979201625949,"rank":277,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.030247022135568905,"rank":275,"remainingConfigurations":444},{"removed":"simpleqa","score":0.034013128179611996,"rank":277,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.03215131157489276,"rank":277,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.032146261788750415,"rank":277,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.032155511596905655,"rank":277,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.032208136437448034,"rank":277,"remainingConfigurations":444},{"removed":"vibe-code","score":0.03205089295087221,"rank":277,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03218091581729835,"rank":277,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-4-5-20251001--effort-reasoning":{"score":0.032059245538094985,"rank":278,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04177740854032544,"rank":278,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02508950301396834,"rank":278,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.031706195864253335,"rank":278,"remainingConfigurations":444},{"removed":"Scale","score":0.03776818257452952,"rank":278,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03171083454961391,"rank":278,"remainingConfigurations":444},{"removed":"Cognition","score":0.030980253525468415,"rank":277,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03337745009234908,"rank":277,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03300359288910047,"rank":278,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03302627133292205,"rank":266,"remainingConfigurations":431},{"removed":"Vals AI","score":0.030818104192101157,"rank":277,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.032045006135359315,"rank":278,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.03100252048171398,"rank":278,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03200246372433514,"rank":278,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.032059245538094985,"rank":278,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03231970313843543,"rank":278,"remainingConfigurations":444},{"removed":"All provider reports","score":0.031199498132403084,"rank":278,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.031076425713489383,"rank":279,"remainingConfigurations":444},{"removed":"briefcase","score":0.03092607940764386,"rank":278,"remainingConfigurations":444},{"removed":"aime","score":0.030739337881459838,"rank":280,"remainingConfigurations":444},{"removed":"apex-agents","score":0.03263182591256224,"rank":278,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02968385973301332,"rank":280,"remainingConfigurations":444},{"removed":"automationbench","score":0.03158918315088896,"rank":277,"remainingConfigurations":444},{"removed":"critpt","score":0.03436407661411368,"rank":276,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.031268334897058374,"rank":278,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.032619437992945644,"rank":277,"remainingConfigurations":444},{"removed":"gdpval","score":0.031205239938920753,"rank":279,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03159429480295167,"rank":276,"remainingConfigurations":444},{"removed":"gpqa","score":0.03301599817131067,"rank":277,"remainingConfigurations":444},{"removed":"harvey","score":0.03167926163508435,"rank":277,"remainingConfigurations":444},{"removed":"hle","score":0.03561526084716594,"rank":279,"remainingConfigurations":444},{"removed":"ifbench","score":0.02999965317626631,"rank":278,"remainingConfigurations":444},{"removed":"itbench","score":0.03126702902019628,"rank":278,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03305065975317844,"rank":275,"remainingConfigurations":444},{"removed":"math500","score":0.032084550848984095,"rank":278,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.03614956346755172,"rank":272,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03686745917756202,"rank":276,"remainingConfigurations":444},{"removed":"omniscience","score":0.030743669356097684,"rank":276,"remainingConfigurations":444},{"removed":"tau-bench","score":0.031174703261361004,"rank":277,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03256672069361529,"rank":278,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.03130945295697758,"rank":278,"remainingConfigurations":444},{"removed":"arc-agi","score":0.04023586154399458,"rank":277,"remainingConfigurations":444},{"removed":"deepswe","score":0.02510784251970512,"rank":278,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03206764302668379,"rank":278,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.03154010132849412,"rank":278,"remainingConfigurations":444},{"removed":"frontiercode","score":0.030980253525468415,"rank":277,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.03160258765043491,"rank":278,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.031672512943067326,"rank":278,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.032041134280503515,"rank":278,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.031912324538445024,"rank":278,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03209650763025295,"rank":278,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03167175881042728,"rank":278,"remainingConfigurations":444},{"removed":"livebench-language","score":0.03260578609961264,"rank":278,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0320488311698414,"rank":278,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.031357791672668216,"rank":278,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.031826927755772866,"rank":278,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03283727403722717,"rank":278,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03300359288910047,"rank":278,"remainingConfigurations":444},{"removed":"frontiermath","score":0.032099640180470526,"rank":278,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.030142374536104636,"rank":276,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03379153260800542,"rank":278,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.031931558148259355,"rank":278,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03192574470324523,"rank":278,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03193446663864581,"rank":278,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0319892723795732,"rank":278,"remainingConfigurations":444},{"removed":"vibe-code","score":0.031833415976375415,"rank":278,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03196046695338031,"rank":278,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-lite--effort-medium":{"score":0.030818634320382027,"rank":279,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04098277249892878,"rank":279,"remainingConfigurations":444},{"removed":"Datacurve","score":0.024141179523266925,"rank":279,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.030454255711207,"rank":279,"remainingConfigurations":444},{"removed":"Scale","score":0.03629542150717575,"rank":279,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.030483127647038796,"rank":279,"remainingConfigurations":444},{"removed":"Cognition","score":0.029813275996242897,"rank":279,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03210810702672099,"rank":278,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03162636807740474,"rank":279,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.031188336404123645,"rank":270,"remainingConfigurations":431},{"removed":"Vals AI","score":0.029554940763175,"rank":278,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03080508312736528,"rank":279,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.029813898755519097,"rank":279,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.030763253192176414,"rank":279,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.030818634320382027,"rank":279,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.031073985122980097,"rank":279,"remainingConfigurations":444},{"removed":"All provider reports","score":0.030007188934945795,"rank":279,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03109671151510837,"rank":278,"remainingConfigurations":444},{"removed":"briefcase","score":0.030563929305207533,"rank":279,"remainingConfigurations":444},{"removed":"aime","score":0.02822382734189395,"rank":286,"remainingConfigurations":444},{"removed":"apex-agents","score":0.031294497020400776,"rank":279,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02952857455535492,"rank":281,"remainingConfigurations":444},{"removed":"automationbench","score":0.03056778436187083,"rank":279,"remainingConfigurations":444},{"removed":"critpt","score":0.034626946544075395,"rank":274,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.03081048786239114,"rank":279,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03149564720651699,"rank":278,"remainingConfigurations":444},{"removed":"gdpval","score":0.0307528213927895,"rank":280,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03111091142399899,"rank":278,"remainingConfigurations":444},{"removed":"gpqa","score":0.02952809251328699,"rank":281,"remainingConfigurations":444},{"removed":"harvey","score":0.030455772818587076,"rank":278,"remainingConfigurations":444},{"removed":"hle","score":0.0353655526484768,"rank":280,"remainingConfigurations":444},{"removed":"ifbench","score":0.026430538676945937,"rank":284,"remainingConfigurations":444},{"removed":"itbench","score":0.03050064556032935,"rank":279,"remainingConfigurations":444},{"removed":"livecodebench","score":0.031898576157397725,"rank":278,"remainingConfigurations":444},{"removed":"math500","score":0.031045094944993634,"rank":279,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.032412790933103924,"rank":278,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03504942979667712,"rank":279,"remainingConfigurations":444},{"removed":"omniscience","score":0.029141148998148143,"rank":281,"remainingConfigurations":444},{"removed":"tau-bench","score":0.028903018073587087,"rank":281,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03129255200647972,"rank":279,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0314012877210218,"rank":277,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03944034151636581,"rank":279,"remainingConfigurations":444},{"removed":"deepswe","score":0.024157692613230027,"rank":279,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.030826548741466078,"rank":279,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.030280353891910975,"rank":279,"remainingConfigurations":444},{"removed":"frontiercode","score":0.029813275996242897,"rank":279,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.030375453329679156,"rank":279,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.03044606264418942,"rank":279,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.03080098426286627,"rank":279,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.030678661179900955,"rank":279,"remainingConfigurations":444},{"removed":"livebench-math","score":0.030856430353335115,"rank":279,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.030437653261654127,"rank":279,"remainingConfigurations":444},{"removed":"livebench-language","score":0.031339775430771134,"rank":279,"remainingConfigurations":444},{"removed":"livebench-data","score":0.030813555972532672,"rank":279,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.030146535596598537,"rank":279,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.030593038352811547,"rank":279,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.031573258196542435,"rank":279,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03162636807740474,"rank":279,"remainingConfigurations":444},{"removed":"frontiermath","score":0.030880679109074643,"rank":279,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02870057846232844,"rank":277,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03248793564333116,"rank":279,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0306947879309537,"rank":279,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.03069012495539768,"rank":279,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.030700336225145744,"rank":279,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.03074905134817335,"rank":279,"remainingConfigurations":444},{"removed":"vibe-code","score":0.030599913502316025,"rank":279,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0307236997641223,"rank":279,"remainingConfigurations":444}],"sharedOrderConflicts":0},"hy3-preview--effort-non-reasoning":{"score":0.03055737687252569,"rank":280,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.04035618862055163,"rank":280,"remainingConfigurations":444},{"removed":"Datacurve","score":0.023916023384813592,"rank":280,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.030226588638796344,"rank":280,"remainingConfigurations":444},{"removed":"Scale","score":0.03597624733998165,"rank":280,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.03021460153498957,"rank":280,"remainingConfigurations":444},{"removed":"Cognition","score":0.029518372220115097,"rank":280,"remainingConfigurations":444},{"removed":"LiveBench","score":0.031834431975185665,"rank":279,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.031410256151009334,"rank":280,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03086657125790228,"rank":271,"remainingConfigurations":431},{"removed":"Vals AI","score":0.029288223227231902,"rank":279,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.030543931541289867,"rank":280,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.029560251606257335,"rank":280,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.03050255875520244,"rank":280,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.03055737687252569,"rank":280,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.030810145823860196,"rank":280,"remainingConfigurations":444},{"removed":"All provider reports","score":0.029751600718588043,"rank":280,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03081761242744946,"rank":280,"remainingConfigurations":444},{"removed":"briefcase","score":0.03029130882469846,"rank":280,"remainingConfigurations":444},{"removed":"aime","score":0.030737407502651637,"rank":281,"remainingConfigurations":444},{"removed":"apex-agents","score":0.031026322709869655,"rank":280,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.03263601378613759,"rank":277,"remainingConfigurations":444},{"removed":"automationbench","score":0.030307257991746838,"rank":280,"remainingConfigurations":444},{"removed":"critpt","score":0.029028707120655816,"rank":284,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.030538826721662336,"rank":280,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.031228139978688483,"rank":280,"remainingConfigurations":444},{"removed":"gdpval","score":0.030476740245684805,"rank":281,"remainingConfigurations":444},{"removed":"gmmlu","score":0.030836087401899578,"rank":280,"remainingConfigurations":444},{"removed":"gpqa","score":0.03139841599392438,"rank":279,"remainingConfigurations":444},{"removed":"harvey","score":0.03019855501109817,"rank":279,"remainingConfigurations":444},{"removed":"hle","score":0.03777033072174801,"rank":276,"remainingConfigurations":444},{"removed":"ifbench","score":0.02986612386350128,"rank":279,"remainingConfigurations":444},{"removed":"itbench","score":0.030259966454083815,"rank":280,"remainingConfigurations":444},{"removed":"livecodebench","score":0.030768653814428868,"rank":280,"remainingConfigurations":444},{"removed":"math500","score":0.03084276995227068,"rank":280,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.031841464116340305,"rank":280,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.03324467100380917,"rank":280,"remainingConfigurations":444},{"removed":"omniscience","score":0.025602082615219443,"rank":289,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02905568184141447,"rank":280,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.031044778764992412,"rank":280,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.027283821160845063,"rank":285,"remainingConfigurations":444},{"removed":"arc-agi","score":0.038854640366078434,"rank":280,"remainingConfigurations":444},{"removed":"deepswe","score":0.023932471337985817,"rank":280,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.03056524244646047,"rank":280,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.030032377234964464,"rank":280,"remainingConfigurations":444},{"removed":"frontiercode","score":0.029518372220115097,"rank":280,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.030117717041233047,"rank":280,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.030187497182598135,"rank":280,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0305398433681647,"rank":280,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.03041825142216795,"rank":280,"remainingConfigurations":444},{"removed":"livebench-math","score":0.03059469074600096,"rank":280,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.03017900198852624,"rank":280,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0310747726998498,"rank":280,"remainingConfigurations":444},{"removed":"livebench-data","score":0.030552908597485422,"rank":280,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.029890470381907785,"rank":280,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.030333358525611573,"rank":280,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0313061144459359,"rank":280,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.031410256151009334,"rank":280,"remainingConfigurations":444},{"removed":"frontiermath","score":0.030512977209634723,"rank":280,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.028476488324164998,"rank":278,"remainingConfigurations":444},{"removed":"simpleqa","score":0.032210212702706825,"rank":280,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.030434577272443513,"rank":280,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.030430003424338114,"rank":280,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.030439702687687437,"rank":280,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.030488593232276737,"rank":280,"remainingConfigurations":444},{"removed":"vibe-code","score":0.030340582066182772,"rank":280,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.03046313295096106,"rank":280,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-31b-it--effort-non-reasoning":{"score":0.030207923086756905,"rank":281,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0396097341126316,"rank":282,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02363061693247087,"rank":281,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.029901363741162826,"rank":281,"remainingConfigurations":444},{"removed":"Scale","score":0.03559664109764383,"rank":282,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.029868919868569863,"rank":281,"remainingConfigurations":444},{"removed":"Cognition","score":0.029164304768622976,"rank":281,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03148856436772098,"rank":280,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03103350873022727,"rank":281,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03070819429816018,"rank":272,"remainingConfigurations":431},{"removed":"Vals AI","score":0.028946772252797046,"rank":280,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.03019457313495412,"rank":281,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.029220354283173367,"rank":281,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.030153434783038977,"rank":281,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.030207923086756905,"rank":281,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03045858464831774,"rank":281,"remainingConfigurations":444},{"removed":"All provider reports","score":0.029409926145042464,"rank":281,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03046870779012753,"rank":281,"remainingConfigurations":444},{"removed":"briefcase","score":0.02990106954758542,"rank":281,"remainingConfigurations":444},{"removed":"aime","score":0.030277386917359445,"rank":283,"remainingConfigurations":444},{"removed":"apex-agents","score":0.030671743704771482,"rank":281,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.030691001836682205,"rank":279,"remainingConfigurations":444},{"removed":"automationbench","score":0.029945149276769653,"rank":281,"remainingConfigurations":444},{"removed":"critpt","score":0.03503273668313226,"rank":273,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.030166134106184222,"rank":281,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03085951937107685,"rank":281,"remainingConfigurations":444},{"removed":"gdpval","score":0.02993323401090554,"rank":283,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03046291962185768,"rank":281,"remainingConfigurations":444},{"removed":"gpqa","score":0.029046326301847405,"rank":283,"remainingConfigurations":444},{"removed":"harvey","score":0.02984035777083281,"rank":280,"remainingConfigurations":444},{"removed":"hle","score":0.032518501298250846,"rank":283,"remainingConfigurations":444},{"removed":"ifbench","score":0.027901053477215526,"rank":281,"remainingConfigurations":444},{"removed":"itbench","score":0.02988307187799355,"rank":281,"remainingConfigurations":444},{"removed":"livecodebench","score":0.03032935800278123,"rank":281,"remainingConfigurations":444},{"removed":"math500","score":0.03041364587022448,"rank":281,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0313540489480088,"rank":281,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.030021664918248304,"rank":285,"remainingConfigurations":444},{"removed":"omniscience","score":0.030742955205109185,"rank":277,"remainingConfigurations":444},{"removed":"tau-bench","score":0.028879934153937803,"rank":282,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.030668832388619106,"rank":281,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.028150091552634787,"rank":282,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0381392850385637,"rank":282,"remainingConfigurations":444},{"removed":"deepswe","score":0.02364681597254202,"rank":281,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.030215735486505812,"rank":281,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02969979368821554,"rank":281,"remainingConfigurations":444},{"removed":"frontiercode","score":0.029164304768622976,"rank":281,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.029774417047062598,"rank":281,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.029842077547145508,"rank":281,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.030190784034074592,"rank":281,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0300701131348869,"rank":281,"remainingConfigurations":444},{"removed":"livebench-math","score":0.030244715076902656,"rank":281,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02983416495228233,"rank":281,"remainingConfigurations":444},{"removed":"livebench-language","score":0.030720125707244958,"rank":281,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03020346898005299,"rank":281,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.029547722315924816,"rank":281,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.029986359148007003,"rank":281,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.030948363261473034,"rank":281,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03103350873022727,"rank":281,"remainingConfigurations":444},{"removed":"frontiermath","score":0.030247060325796576,"rank":281,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.028189465542929035,"rank":279,"remainingConfigurations":444},{"removed":"simpleqa","score":0.031841958378261294,"rank":281,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.030086404699600288,"rank":281,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.030082075501739646,"rank":281,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.03009143977670854,"rank":281,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.030140002647194113,"rank":281,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02999336915399375,"rank":281,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.030114751743180495,"rank":281,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-12b-it--effort-reasoning":{"score":0.030070075384174468,"rank":282,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03971934804364468,"rank":281,"remainingConfigurations":444},{"removed":"Datacurve","score":0.023562379134735755,"rank":282,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02977509671281443,"rank":282,"remainingConfigurations":444},{"removed":"Scale","score":0.03545984472720575,"rank":283,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.029741245715446757,"rank":282,"remainingConfigurations":444},{"removed":"Cognition","score":0.029095157131175112,"rank":282,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03135066354605436,"rank":281,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.03094333562221563,"rank":282,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03061371473190048,"rank":273,"remainingConfigurations":431},{"removed":"Vals AI","score":0.02883991551266528,"rank":281,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.030056776889670064,"rank":282,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02908628862872188,"rank":282,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0300158065461483,"rank":282,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.030070075384174468,"rank":282,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.030319370107532537,"rank":282,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0292747513470441,"rank":282,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.03033513117724305,"rank":282,"remainingConfigurations":444},{"removed":"briefcase","score":0.02981421281824986,"rank":282,"remainingConfigurations":444},{"removed":"aime","score":0.03009999155831297,"rank":284,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0305334218598345,"rank":282,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02808149732530627,"rank":285,"remainingConfigurations":444},{"removed":"automationbench","score":0.02984478799642797,"rank":282,"remainingConfigurations":444},{"removed":"critpt","score":0.03452089559160489,"rank":275,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.030038411642727914,"rank":282,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03075354332845383,"rank":282,"remainingConfigurations":444},{"removed":"gdpval","score":0.03131118662176343,"rank":278,"remainingConfigurations":444},{"removed":"gmmlu","score":0.03034730625734099,"rank":282,"remainingConfigurations":444},{"removed":"gpqa","score":0.02942420225636995,"rank":282,"remainingConfigurations":444},{"removed":"harvey","score":0.029704606247191002,"rank":281,"remainingConfigurations":444},{"removed":"hle","score":0.030925163984452664,"rank":286,"remainingConfigurations":444},{"removed":"ifbench","score":0.02367139324159943,"rank":289,"remainingConfigurations":444},{"removed":"itbench","score":0.029740008516806356,"rank":282,"remainingConfigurations":444},{"removed":"livecodebench","score":0.030192515534545716,"rank":282,"remainingConfigurations":444},{"removed":"math500","score":0.030221850852022808,"rank":282,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.031211735244098787,"rank":282,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.030663034637999926,"rank":283,"remainingConfigurations":444},{"removed":"omniscience","score":0.0318933005353547,"rank":272,"remainingConfigurations":444},{"removed":"tau-bench","score":0.03148235078027175,"rank":275,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03053689726991692,"rank":282,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.030195023902860108,"rank":280,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03821432656612727,"rank":281,"remainingConfigurations":444},{"removed":"deepswe","score":0.023578581663981264,"rank":282,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.030077852710158087,"rank":282,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.029565278162205864,"rank":282,"remainingConfigurations":444},{"removed":"frontiercode","score":0.029095157131175112,"rank":282,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.029642022994271225,"rank":282,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.029709084029854328,"rank":282,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.030053048195866763,"rank":282,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.029932809214191326,"rank":282,"remainingConfigurations":444},{"removed":"livebench-math","score":0.030106610717452645,"rank":282,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02969809459085847,"rank":282,"remainingConfigurations":444},{"removed":"livebench-language","score":0.030580322359181806,"rank":282,"remainingConfigurations":444},{"removed":"livebench-data","score":0.03006554989898087,"rank":282,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02941252848311715,"rank":282,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.029849492085466178,"rank":282,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03080727383292196,"rank":282,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.03094333562221563,"rank":282,"remainingConfigurations":444},{"removed":"frontiermath","score":0.03012995590747179,"rank":282,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02806059955602296,"rank":280,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03169705317291269,"rank":282,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.029949149102826755,"rank":282,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.029944721308440756,"rank":282,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.029954040634614414,"rank":282,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.030002484393873787,"rank":282,"remainingConfigurations":444},{"removed":"vibe-code","score":0.029856487134223276,"rank":282,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.029977295839461838,"rank":282,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-next-80b-a3b-thinking--effort-reasoning":{"score":0.029788507640449075,"rank":283,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03900278991432918,"rank":283,"remainingConfigurations":444},{"removed":"Datacurve","score":0.02331812237677139,"rank":283,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.029411259154281475,"rank":283,"remainingConfigurations":444},{"removed":"Scale","score":0.03514392019290615,"rank":284,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.029462554174751784,"rank":283,"remainingConfigurations":444},{"removed":"Cognition","score":0.028855480239980375,"rank":283,"remainingConfigurations":444},{"removed":"LiveBench","score":0.03102499760723999,"rank":282,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.030589558710876444,"rank":283,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.03026947844821426,"rank":274,"remainingConfigurations":431},{"removed":"Vals AI","score":0.028559319383428153,"rank":282,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02977541344868974,"rank":283,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02881520662556143,"rank":283,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02973516347614257,"rank":283,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.029788507640449075,"rank":283,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.03003256674844694,"rank":283,"remainingConfigurations":444},{"removed":"All provider reports","score":0.028999613004908723,"rank":283,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.030019287211552465,"rank":283,"remainingConfigurations":444},{"removed":"briefcase","score":0.029512915059654556,"rank":283,"remainingConfigurations":444},{"removed":"aime","score":0.0279885166615505,"rank":287,"remainingConfigurations":444},{"removed":"apex-agents","score":0.030244023172979154,"rank":283,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.028188764094614866,"rank":284,"remainingConfigurations":444},{"removed":"automationbench","score":0.029536666582773503,"rank":283,"remainingConfigurations":444},{"removed":"critpt","score":0.0329859405529894,"rank":280,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02974171336460918,"rank":283,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.03038926237334422,"rank":284,"remainingConfigurations":444},{"removed":"gdpval","score":0.03236899207784673,"rank":277,"remainingConfigurations":444},{"removed":"gmmlu","score":0.030087397739336854,"rank":283,"remainingConfigurations":444},{"removed":"gpqa","score":0.029042477527817714,"rank":284,"remainingConfigurations":444},{"removed":"harvey","score":0.029437302796671238,"rank":282,"remainingConfigurations":444},{"removed":"hle","score":0.032356099667978984,"rank":284,"remainingConfigurations":444},{"removed":"ifbench","score":0.02705029301466289,"rank":282,"remainingConfigurations":444},{"removed":"itbench","score":0.029497373796676263,"rank":283,"remainingConfigurations":444},{"removed":"livecodebench","score":0.027529414123825178,"rank":285,"remainingConfigurations":444},{"removed":"math500","score":0.029907901996862978,"rank":283,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.029816138471407433,"rank":283,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.032393029222798735,"rank":281,"remainingConfigurations":444},{"removed":"omniscience","score":0.027537208436475766,"rank":285,"remainingConfigurations":444},{"removed":"tau-bench","score":0.030337498240071537,"rank":279,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.03025286682765514,"rank":283,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.032027860355226624,"rank":275,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03755070653381982,"rank":283,"remainingConfigurations":444},{"removed":"deepswe","score":0.02333449096564034,"rank":283,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.029796266362200674,"rank":283,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.029271022900329357,"rank":283,"remainingConfigurations":444},{"removed":"frontiercode","score":0.028855480239980375,"rank":283,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02935784723304336,"rank":283,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.029426809582746825,"rank":283,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.029771626507362637,"rank":283,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02965281584001407,"rank":283,"remainingConfigurations":444},{"removed":"livebench-math","score":0.029825197042648573,"rank":283,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02942072058398903,"rank":283,"remainingConfigurations":444},{"removed":"livebench-language","score":0.030294078056584572,"rank":283,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02978287888674709,"rank":283,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02913695720711552,"rank":283,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.029570280807442038,"rank":283,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.03051833477294157,"rank":283,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.030589558710876444,"rank":283,"remainingConfigurations":444},{"removed":"frontiermath","score":0.029839148223210963,"rank":283,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.027787104716198874,"rank":281,"remainingConfigurations":444},{"removed":"simpleqa","score":0.03140716850426084,"rank":283,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.029668223319909676,"rank":283,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.029664273713309697,"rank":283,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02967343707778002,"rank":283,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.029721784293080405,"rank":283,"remainingConfigurations":444},{"removed":"vibe-code","score":0.029577034603025007,"rank":283,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02969636373560489,"rank":283,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-9b--effort-non-reasoning":{"score":0.028634103379410622,"rank":284,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03486390554267569,"rank":174,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03765669794242083,"rank":284,"remainingConfigurations":444},{"removed":"Datacurve","score":0.022423784107002593,"rank":284,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.028404875696538958,"rank":284,"remainingConfigurations":444},{"removed":"Scale","score":0.03363297662908859,"rank":285,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.028380616210451376,"rank":284,"remainingConfigurations":444},{"removed":"Cognition","score":0.028388846757281757,"rank":284,"remainingConfigurations":444},{"removed":"LiveBench","score":0.029559575884070707,"rank":283,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02932631469914034,"rank":284,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.025826411105704297,"rank":284,"remainingConfigurations":431},{"removed":"Vals AI","score":0.02745914045537159,"rank":283,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.028622860213851815,"rank":284,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02773113510220726,"rank":284,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02859088135877798,"rank":284,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.028634103379410622,"rank":284,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.028857703219843853,"rank":284,"remainingConfigurations":444},{"removed":"All provider reports","score":0.027906910886513953,"rank":284,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.028867406150233536,"rank":284,"remainingConfigurations":444},{"removed":"briefcase","score":0.02844296751450225,"rank":284,"remainingConfigurations":444},{"removed":"aime","score":0.030655853723641758,"rank":282,"remainingConfigurations":444},{"removed":"apex-agents","score":0.029049136775800205,"rank":284,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.028853741517382122,"rank":283,"remainingConfigurations":444},{"removed":"automationbench","score":0.02846648578067371,"rank":284,"remainingConfigurations":444},{"removed":"critpt","score":0.026474036549680283,"rank":290,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.028632222281787592,"rank":284,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.029157035685101692,"rank":285,"remainingConfigurations":444},{"removed":"gdpval","score":0.02846939803494569,"rank":284,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02889798455042722,"rank":284,"remainingConfigurations":444},{"removed":"gpqa","score":0.026006626103277364,"rank":289,"remainingConfigurations":444},{"removed":"harvey","score":0.02827195859337027,"rank":283,"remainingConfigurations":444},{"removed":"hle","score":0.03190528598279765,"rank":285,"remainingConfigurations":444},{"removed":"ifbench","score":0.030990383665443388,"rank":275,"remainingConfigurations":444},{"removed":"itbench","score":0.02840211378601727,"rank":284,"remainingConfigurations":444},{"removed":"livecodebench","score":0.028659877974857223,"rank":283,"remainingConfigurations":444},{"removed":"math500","score":0.028726570854376698,"rank":284,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.029688566469890265,"rank":284,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.030123209819923166,"rank":284,"remainingConfigurations":444},{"removed":"omniscience","score":0.03012487071738616,"rank":278,"remainingConfigurations":444},{"removed":"tau-bench","score":0.025405317403565664,"rank":288,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.029009256641770315,"rank":284,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02851773082527771,"rank":281,"remainingConfigurations":444},{"removed":"arc-agi","score":0.036345593929896135,"rank":284,"remainingConfigurations":444},{"removed":"deepswe","score":0.02244151275665396,"rank":284,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.028641295657966952,"rank":284,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.028157851403271233,"rank":284,"remainingConfigurations":444},{"removed":"frontiercode","score":0.028388846757281757,"rank":284,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02824712206871427,"rank":284,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02827702022620386,"rank":284,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02861910225773308,"rank":284,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02850229700357362,"rank":284,"remainingConfigurations":444},{"removed":"livebench-math","score":0.028697237208748106,"rank":284,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.028240067716041286,"rank":284,"remainingConfigurations":444},{"removed":"livebench-language","score":0.029112936683444012,"rank":284,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02864028893579891,"rank":284,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.028022830083950744,"rank":284,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02842076568278629,"rank":284,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.029329654111276877,"rank":284,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02932631469914034,"rank":284,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02826775248516296,"rank":284,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02479920895572207,"rank":285,"remainingConfigurations":444},{"removed":"simpleqa","score":0.030306189351787083,"rank":284,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.028515876430758907,"rank":284,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02852083390552762,"rank":284,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.028517524821972676,"rank":284,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02857481613856358,"rank":284,"remainingConfigurations":444},{"removed":"vibe-code","score":0.028438974433466307,"rank":284,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.028540170196778847,"rank":284,"remainingConfigurations":444}],"sharedOrderConflicts":0},"command-a-plus-05-2026--effort-reasoning":{"score":0.027806701787512173,"rank":285,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03636865892489454,"rank":285,"remainingConfigurations":444},{"removed":"Datacurve","score":0.021750142303182868,"rank":285,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.027512816546483094,"rank":285,"remainingConfigurations":444},{"removed":"Scale","score":0.03284135708035756,"rank":286,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.027501623228587877,"rank":285,"remainingConfigurations":444},{"removed":"Cognition","score":0.026878376418796934,"rank":286,"remainingConfigurations":444},{"removed":"LiveBench","score":0.028993377609197152,"rank":284,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.028614609966558135,"rank":285,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.028561083373202817,"rank":276,"remainingConfigurations":431},{"removed":"Vals AI","score":0.026700768008267133,"rank":284,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.027794253401000456,"rank":285,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02688917817675647,"rank":285,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.027756174962482092,"rank":285,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.027806701787512173,"rank":285,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.028035706954681272,"rank":285,"remainingConfigurations":444},{"removed":"All provider reports","score":0.02706159479309879,"rank":285,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.028053804512226083,"rank":285,"remainingConfigurations":444},{"removed":"briefcase","score":0.02777065414849,"rank":285,"remainingConfigurations":444},{"removed":"aime","score":0.027635647263562862,"rank":288,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02828157567921791,"rank":285,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.027942739742459238,"rank":286,"remainingConfigurations":444},{"removed":"automationbench","score":0.027781448871609063,"rank":285,"remainingConfigurations":444},{"removed":"critpt","score":0.026605886938376178,"rank":289,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02777204859057621,"rank":285,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.030497565182636424,"rank":283,"remainingConfigurations":444},{"removed":"gdpval","score":0.02756505818399756,"rank":285,"remainingConfigurations":444},{"removed":"gmmlu","score":0.028014805721239374,"rank":285,"remainingConfigurations":444},{"removed":"gpqa","score":0.026669514931323884,"rank":286,"remainingConfigurations":444},{"removed":"harvey","score":0.02746489680079506,"rank":284,"remainingConfigurations":444},{"removed":"hle","score":0.029938248593262592,"rank":288,"remainingConfigurations":444},{"removed":"ifbench","score":0.021896334378999658,"rank":297,"remainingConfigurations":444},{"removed":"itbench","score":0.02754565121341121,"rank":285,"remainingConfigurations":444},{"removed":"livecodebench","score":0.027778606903311884,"rank":284,"remainingConfigurations":444},{"removed":"math500","score":0.027988383112098655,"rank":285,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.028815578818789492,"rank":285,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.031086400989560028,"rank":282,"remainingConfigurations":444},{"removed":"omniscience","score":0.032851580584078686,"rank":269,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02655641382700338,"rank":283,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.028239799371427485,"rank":285,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0265521252727613,"rank":288,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0350071945993288,"rank":285,"remainingConfigurations":444},{"removed":"deepswe","score":0.021765624344743453,"rank":285,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.027814076034482594,"rank":285,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.027357752742311624,"rank":285,"remainingConfigurations":444},{"removed":"frontiercode","score":0.026878376418796934,"rank":286,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02740544512854894,"rank":285,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.027467777617743827,"rank":285,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.027791288371941832,"rank":285,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.027679032343172805,"rank":285,"remainingConfigurations":444},{"removed":"livebench-math","score":0.027839587991215036,"rank":285,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.027463761273673795,"rank":285,"remainingConfigurations":444},{"removed":"livebench-language","score":0.028283389791896388,"rank":285,"remainingConfigurations":444},{"removed":"livebench-data","score":0.027801372389708864,"rank":285,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02719397522747134,"rank":285,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.027602135711167233,"rank":285,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.028490164817540173,"rank":285,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.028614609966558135,"rank":285,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02784145702890668,"rank":285,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.026063435687670652,"rank":282,"remainingConfigurations":444},{"removed":"simpleqa","score":0.029319822851207513,"rank":285,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.027694427226697748,"rank":285,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02769032525738677,"rank":285,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.027698342870479512,"rank":285,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.027744631581765322,"rank":285,"remainingConfigurations":444},{"removed":"vibe-code","score":0.027608316516116293,"rank":285,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.027720670463522765,"rank":285,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.7-flash--effort-reasoning":{"score":0.027260722864651754,"rank":286,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03597967071053058,"rank":287,"remainingConfigurations":444},{"removed":"Datacurve","score":0.021340413373863217,"rank":286,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02696636184956425,"rank":286,"remainingConfigurations":444},{"removed":"Scale","score":0.03223330974105283,"rank":287,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.026960657557978576,"rank":286,"remainingConfigurations":444},{"removed":"Cognition","score":0.026396603047106715,"rank":287,"remainingConfigurations":444},{"removed":"LiveBench","score":0.028428908867931046,"rank":285,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.028158143807302263,"rank":287,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02785112688334967,"rank":277,"remainingConfigurations":431},{"removed":"Vals AI","score":0.026154631079842425,"rank":285,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.027248657561403298,"rank":286,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02636601408661963,"rank":286,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.027211584428320817,"rank":286,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.027260722864651754,"rank":286,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.027486967960219974,"rank":286,"remainingConfigurations":444},{"removed":"All provider reports","score":0.026537149948465937,"rank":286,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.027518995002864612,"rank":286,"remainingConfigurations":444},{"removed":"briefcase","score":0.027033544190682064,"rank":286,"remainingConfigurations":444},{"removed":"aime","score":0.02717406096380072,"rank":289,"remainingConfigurations":444},{"removed":"apex-agents","score":0.027737910052627268,"rank":286,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02909549873906531,"rank":282,"remainingConfigurations":444},{"removed":"automationbench","score":0.027026642620190836,"rank":286,"remainingConfigurations":444},{"removed":"critpt","score":0.02551207496348613,"rank":292,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.027269231061759283,"rank":286,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.027857621146602913,"rank":286,"remainingConfigurations":444},{"removed":"gdpval","score":0.02720206889113075,"rank":286,"remainingConfigurations":444},{"removed":"gmmlu","score":0.027591567220545263,"rank":286,"remainingConfigurations":444},{"removed":"gpqa","score":0.03360419139544595,"rank":275,"remainingConfigurations":444},{"removed":"harvey","score":0.026941931507968826,"rank":285,"remainingConfigurations":444},{"removed":"hle","score":0.03275833306706074,"rank":282,"remainingConfigurations":444},{"removed":"ifbench","score":0.023132484119032386,"rank":292,"remainingConfigurations":444},{"removed":"itbench","score":0.02701429575177569,"rank":286,"remainingConfigurations":444},{"removed":"livecodebench","score":0.027240024156127404,"rank":287,"remainingConfigurations":444},{"removed":"math500","score":0.02736844502276095,"rank":286,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.028170294845928274,"rank":287,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.029759091112878847,"rank":286,"remainingConfigurations":444},{"removed":"omniscience","score":0.028659752077090806,"rank":283,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019454915771996942,"rank":305,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02769549156639568,"rank":286,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.026474556299297694,"rank":290,"remainingConfigurations":444},{"removed":"arc-agi","score":0.034604279906109446,"rank":287,"remainingConfigurations":444},{"removed":"deepswe","score":0.02135513498701827,"rank":286,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02726777929241689,"rank":286,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.026789465886428856,"rank":286,"remainingConfigurations":444},{"removed":"frontiercode","score":0.026396603047106715,"rank":287,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02686842094550374,"rank":286,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.026931552884182527,"rank":286,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.027245193302721345,"rank":286,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.027136149245775912,"rank":286,"remainingConfigurations":444},{"removed":"livebench-math","score":0.027294196761579487,"rank":286,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.026920626942993048,"rank":286,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02772534630774721,"rank":286,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02725700009177312,"rank":286,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.026661927726066983,"rank":286,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02705945533091834,"rank":286,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02793369065070569,"rank":286,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.028158143807302263,"rank":287,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02736825412231785,"rank":286,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.025476634441383206,"rank":283,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02874584742407851,"rank":286,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02715043823241058,"rank":286,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.027146285926481755,"rank":286,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02715513135926098,"rank":286,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02719877794220035,"rank":286,"remainingConfigurations":444},{"removed":"vibe-code","score":0.027065994282340345,"rank":286,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02717611916453777,"rank":286,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-4b--effort-reasoning":{"score":0.027167230954800507,"rank":287,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03582274372905474,"rank":288,"remainingConfigurations":444},{"removed":"Datacurve","score":0.021254068380573102,"rank":287,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.026882519319608004,"rank":287,"remainingConfigurations":444},{"removed":"Scale","score":0.0320666215398583,"rank":288,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.02686296285641003,"rank":287,"remainingConfigurations":444},{"removed":"Cognition","score":0.02628116744370733,"rank":288,"remainingConfigurations":444},{"removed":"LiveBench","score":0.028333167366307577,"rank":286,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.027984009993400293,"rank":289,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.027601718480723014,"rank":278,"remainingConfigurations":431},{"removed":"Vals AI","score":0.02604244024495934,"rank":286,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.027155185754495274,"rank":287,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02627457201904766,"rank":287,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.027118083949633248,"rank":287,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.027167230954800507,"rank":287,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02739291508139266,"rank":287,"remainingConfigurations":444},{"removed":"All provider reports","score":0.02644513650654944,"rank":287,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.027420667587638694,"rank":287,"remainingConfigurations":444},{"removed":"briefcase","score":0.026885096625680963,"rank":287,"remainingConfigurations":444},{"removed":"aime","score":0.027165798644051303,"rank":290,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02759132128474914,"rank":287,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.025070297281429444,"rank":291,"remainingConfigurations":444},{"removed":"automationbench","score":0.026906540369774162,"rank":287,"remainingConfigurations":444},{"removed":"critpt","score":0.031427695213460054,"rank":281,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.027140694292420803,"rank":287,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.027723771043806144,"rank":288,"remainingConfigurations":444},{"removed":"gdpval","score":0.026989007248488187,"rank":288,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02739125122063331,"rank":287,"remainingConfigurations":444},{"removed":"gpqa","score":0.025337533088461383,"rank":291,"remainingConfigurations":444},{"removed":"harvey","score":0.026841524944770923,"rank":287,"remainingConfigurations":444},{"removed":"hle","score":0.03053409745885663,"rank":287,"remainingConfigurations":444},{"removed":"ifbench","score":0.024925774805232285,"rank":286,"remainingConfigurations":444},{"removed":"itbench","score":0.02686616616975364,"rank":287,"remainingConfigurations":444},{"removed":"livecodebench","score":0.027256118770332183,"rank":286,"remainingConfigurations":444},{"removed":"math500","score":0.027303143677371817,"rank":287,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02818415815470852,"rank":286,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.029191193003447066,"rank":287,"remainingConfigurations":444},{"removed":"omniscience","score":0.029347014578288755,"rank":279,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02318182064332547,"rank":294,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.027589891967127907,"rank":287,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.027048027116595066,"rank":286,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03446808456746735,"rank":288,"remainingConfigurations":444},{"removed":"deepswe","score":0.021268702275423792,"rank":287,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.027174281316225634,"rank":287,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02670231460773444,"rank":287,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02628116744370733,"rank":288,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.026775849505199126,"rank":287,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02683897662837396,"rank":287,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.027151857132957227,"rank":287,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.027043014807788566,"rank":287,"remainingConfigurations":444},{"removed":"livebench-math","score":0.027200604320491262,"rank":287,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.026828809290739136,"rank":287,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02763041691691322,"rank":287,"remainingConfigurations":444},{"removed":"livebench-data","score":0.027163330100418038,"rank":287,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02657020923697878,"rank":287,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.026966756233068292,"rank":287,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02783759978891367,"rank":287,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.027984009993400293,"rank":289,"remainingConfigurations":444},{"removed":"frontiermath","score":0.027225438687555448,"rank":287,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02534813096054625,"rank":284,"remainingConfigurations":444},{"removed":"simpleqa","score":0.028647204704775397,"rank":287,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02705722437851224,"rank":287,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.027053287427790906,"rank":287,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.027061969721175416,"rank":287,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02710556675444334,"rank":287,"remainingConfigurations":444},{"removed":"vibe-code","score":0.026973093489391836,"rank":287,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02708294993433838,"rank":287,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.6-terra--effort-none":{"score":0.02668243413713423,"rank":288,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.022902441993642834,"rank":177,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0360381340123098,"rank":286,"remainingConfigurations":444},{"removed":"Datacurve","score":0.021044071861527968,"rank":288,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.026557795987092982,"rank":288,"remainingConfigurations":444},{"removed":"Scale","score":0.03118848085486789,"rank":289,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.026516452650971554,"rank":288,"remainingConfigurations":444},{"removed":"Cognition","score":0.027174278217851237,"rank":285,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02704648424873062,"rank":287,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.027992183900777155,"rank":288,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.025490315546977286,"rank":287,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.026673874352536892,"rank":288,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.025877715193330725,"rank":288,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02665208306252485,"rank":288,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02668243413713423,"rank":288,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.026876389366485485,"rank":288,"remainingConfigurations":444},{"removed":"All provider reports","score":0.026038939513802276,"rank":288,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.026859949621729693,"rank":288,"remainingConfigurations":444},{"removed":"briefcase","score":0.02660245827185609,"rank":289,"remainingConfigurations":444},{"removed":"aime","score":0.033118902325667054,"rank":275,"remainingConfigurations":444},{"removed":"apex-agents","score":0.027041783343233056,"rank":288,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.026794503736727458,"rank":287,"remainingConfigurations":444},{"removed":"automationbench","score":0.02661933238107819,"rank":288,"remainingConfigurations":444},{"removed":"critpt","score":0.0260813000293868,"rank":291,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.026717950946220235,"rank":288,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02700340561902011,"rank":289,"remainingConfigurations":444},{"removed":"gdpval","score":0.026389377674077938,"rank":289,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02691852146449598,"rank":288,"remainingConfigurations":444},{"removed":"gpqa","score":0.021850223662915377,"rank":301,"remainingConfigurations":444},{"removed":"harvey","score":0.026325865290346542,"rank":288,"remainingConfigurations":444},{"removed":"hle","score":0.029024245899185907,"rank":291,"remainingConfigurations":444},{"removed":"ifbench","score":0.026875210598371824,"rank":283,"remainingConfigurations":444},{"removed":"itbench","score":0.02652477731288431,"rank":288,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02670360487809824,"rank":288,"remainingConfigurations":444},{"removed":"math500","score":0.026750685628704394,"rank":288,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0278385070334311,"rank":288,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.028878304535068403,"rank":289,"remainingConfigurations":444},{"removed":"omniscience","score":0.026093787833692362,"rank":287,"remainingConfigurations":444},{"removed":"tau-bench","score":0.025282693810942693,"rank":290,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.026947305328380553,"rank":288,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02648346862033205,"rank":289,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03465779570722299,"rank":286,"remainingConfigurations":444},{"removed":"deepswe","score":0.021062044377495023,"rank":288,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.026688601328773782,"rank":288,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.026287991661119958,"rank":288,"remainingConfigurations":444},{"removed":"frontiercode","score":0.027174278217851237,"rank":285,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02636325441143979,"rank":288,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02630637242447255,"rank":288,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.026673907959170375,"rank":288,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.026566555819517928,"rank":288,"remainingConfigurations":444},{"removed":"livebench-math","score":0.026766478652803877,"rank":288,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.026271888534317212,"rank":288,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0271139357086144,"rank":288,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02670174879235529,"rank":288,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02613511102866195,"rank":288,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.026476627683950274,"rank":288,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02733309943354485,"rank":288,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.027992183900777155,"rank":288,"remainingConfigurations":444},{"removed":"frontiermath","score":0.026180199259979386,"rank":288,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01978897741715493,"rank":301,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02814931268875064,"rank":288,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.026567214529105276,"rank":288,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02658301833238054,"rank":288,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02656885028179801,"rank":288,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.026628480478312466,"rank":288,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02650654193938964,"rank":288,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.026594601550352034,"rank":288,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-32b-thinking--effort-reasoning":{"score":0.025890593221056964,"rank":289,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03401998211410515,"rank":289,"remainingConfigurations":444},{"removed":"Datacurve","score":0.020247644132753793,"rank":289,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.025544995267226308,"rank":290,"remainingConfigurations":444},{"removed":"Scale","score":0.03059428876036728,"rank":290,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.025606069005608995,"rank":289,"remainingConfigurations":444},{"removed":"Cognition","score":0.025108289262996426,"rank":289,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02698409758521328,"rank":288,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.026625671813728435,"rank":290,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02625140794749382,"rank":280,"remainingConfigurations":431},{"removed":"Vals AI","score":0.024830818495839593,"rank":288,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02587915589801791,"rank":289,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.025039611248010796,"rank":289,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02584382777100869,"rank":289,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.025890593221056964,"rank":289,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02610463113006332,"rank":289,"remainingConfigurations":444},{"removed":"All provider reports","score":0.025201270847528906,"rank":289,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.026114877255963117,"rank":289,"remainingConfigurations":444},{"removed":"briefcase","score":0.025707465903038417,"rank":290,"remainingConfigurations":444},{"removed":"aime","score":0.023619244921396842,"rank":296,"remainingConfigurations":444},{"removed":"apex-agents","score":0.026294711183943335,"rank":289,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02500745317268945,"rank":292,"remainingConfigurations":444},{"removed":"automationbench","score":0.025723702892726172,"rank":291,"remainingConfigurations":444},{"removed":"critpt","score":0.02841392474601639,"rank":285,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.025863361044880833,"rank":289,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.026483351311203,"rank":290,"remainingConfigurations":444},{"removed":"gdpval","score":0.02595191780533923,"rank":291,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02619552649037823,"rank":289,"remainingConfigurations":444},{"removed":"gpqa","score":0.02577004518047125,"rank":290,"remainingConfigurations":444},{"removed":"harvey","score":0.025587817220368583,"rank":289,"remainingConfigurations":444},{"removed":"hle","score":0.029032249617574158,"rank":290,"remainingConfigurations":444},{"removed":"ifbench","score":0.02328446046675096,"rank":291,"remainingConfigurations":444},{"removed":"itbench","score":0.025649869109590464,"rank":289,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02447978983449084,"rank":291,"remainingConfigurations":444},{"removed":"math500","score":0.02602078434785487,"rank":289,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.026086816658072273,"rank":293,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02862439469464984,"rank":290,"remainingConfigurations":444},{"removed":"omniscience","score":0.024423934205567946,"rank":290,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02559159833351808,"rank":287,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.026301016566322912,"rank":289,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.027752341542737823,"rank":284,"remainingConfigurations":444},{"removed":"arc-agi","score":0.032729671730089185,"rank":289,"remainingConfigurations":444},{"removed":"deepswe","score":0.020261738310893812,"rank":289,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.025897313201977277,"rank":289,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.025432607161332058,"rank":289,"remainingConfigurations":444},{"removed":"frontiercode","score":0.025108289262996426,"rank":289,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.025512891756938234,"rank":289,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.025574995111855982,"rank":289,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.025875963917361532,"rank":289,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.025772521397486498,"rank":289,"remainingConfigurations":444},{"removed":"livebench-math","score":0.025922797978484916,"rank":289,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.025567436883541975,"rank":289,"remainingConfigurations":444},{"removed":"livebench-language","score":0.026332869459722897,"rank":289,"remainingConfigurations":444},{"removed":"livebench-data","score":0.025886207425145746,"rank":289,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.025320580692397177,"rank":289,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.025699229972696663,"rank":289,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.026530934300872472,"rank":289,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.026625671813728435,"rank":290,"remainingConfigurations":444},{"removed":"frontiermath","score":0.025944232612476418,"rank":289,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02413974841527407,"rank":288,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02731096094075594,"rank":289,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.025785406274407185,"rank":289,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.025781563938490848,"rank":289,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.025790205733439455,"rank":289,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.025831538031202722,"rank":289,"remainingConfigurations":444},{"removed":"vibe-code","score":0.025705201515079466,"rank":289,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.025810033661407255,"rank":289,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-nano--effort-high":{"score":0.0256028256800767,"rank":290,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.02370498635982031,"rank":176,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.030534841629541083,"rank":294,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019917664277086616,"rank":291,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.025720493847048855,"rank":289,"remainingConfigurations":444},{"removed":"Scale","score":0.030295624603220706,"rank":291,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.025274448050708383,"rank":290,"remainingConfigurations":444},{"removed":"Cognition","score":0.02506264745929286,"rank":290,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02652030642820145,"rank":291,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02584506927419594,"rank":294,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.025125128148114757,"rank":285,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0242305193096293,"rank":292,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.025591913701216846,"rank":290,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02479475616071712,"rank":290,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.025559819956836014,"rank":290,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0256028256800767,"rank":290,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.025820880176779012,"rank":290,"remainingConfigurations":444},{"removed":"All provider reports","score":0.024963772402863297,"rank":290,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02579639836743396,"rank":290,"remainingConfigurations":444},{"removed":"briefcase","score":0.025394698532878516,"rank":291,"remainingConfigurations":444},{"removed":"aime","score":0.02436836224240362,"rank":293,"remainingConfigurations":444},{"removed":"apex-agents","score":0.025953463882332415,"rank":291,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.025501922748296546,"rank":290,"remainingConfigurations":444},{"removed":"automationbench","score":0.025413417248543693,"rank":292,"remainingConfigurations":444},{"removed":"critpt","score":0.02687111209956301,"rank":287,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.025592266141028747,"rank":290,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02600100599910941,"rank":292,"remainingConfigurations":444},{"removed":"gdpval","score":0.02561304798572658,"rank":292,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02598745006866074,"rank":290,"remainingConfigurations":444},{"removed":"gpqa","score":0.026050601910686307,"rank":288,"remainingConfigurations":444},{"removed":"harvey","score":0.025272292646582595,"rank":290,"remainingConfigurations":444},{"removed":"hle","score":0.028559012097077688,"rank":292,"remainingConfigurations":444},{"removed":"ifbench","score":0.023017219880510517,"rank":293,"remainingConfigurations":444},{"removed":"itbench","score":0.025417561077619544,"rank":290,"remainingConfigurations":444},{"removed":"livecodebench","score":0.024359451657876476,"rank":292,"remainingConfigurations":444},{"removed":"math500","score":0.025669327919196887,"rank":291,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.027612012772157777,"rank":290,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02860863233605636,"rank":291,"remainingConfigurations":444},{"removed":"omniscience","score":0.023415412914001732,"rank":293,"remainingConfigurations":444},{"removed":"tau-bench","score":0.025668688862533925,"rank":286,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.025920866889571775,"rank":290,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.025794708771364586,"rank":292,"remainingConfigurations":444},{"removed":"arc-agi","score":0.029355529079339335,"rank":294,"remainingConfigurations":444},{"removed":"deepswe","score":0.019929035397433584,"rank":291,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02560903391425945,"rank":290,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.024587029851867153,"rank":293,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02506264745929286,"rank":290,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0252277846034584,"rank":290,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.025294709666727463,"rank":290,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.025588991254958653,"rank":290,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.025482391456590484,"rank":290,"remainingConfigurations":444},{"removed":"livebench-math","score":0.025637243038092117,"rank":290,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.025288430645655714,"rank":290,"remainingConfigurations":444},{"removed":"livebench-language","score":0.026030379569135367,"rank":290,"remainingConfigurations":444},{"removed":"livebench-data","score":0.025586815524529686,"rank":290,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.025039807681173153,"rank":290,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.025419436253875206,"rank":290,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0262419015245243,"rank":290,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02584506927419594,"rank":294,"remainingConfigurations":444},{"removed":"frontiermath","score":0.025745758575218977,"rank":290,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.023400963956532374,"rank":292,"remainingConfigurations":444},{"removed":"simpleqa","score":0.026977478448168262,"rank":290,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.025495878602481297,"rank":290,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02548624463728494,"rank":290,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.025518132036030646,"rank":290,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.025532660092075176,"rank":290,"remainingConfigurations":444},{"removed":"vibe-code","score":0.025410508090204648,"rank":290,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02552782535984331,"rank":290,"remainingConfigurations":444}],"sharedOrderConflicts":1},"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning":{"score":0.025512474704122646,"rank":291,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03350375674854138,"rank":291,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019955480418518485,"rank":290,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.025243052547727022,"rank":291,"remainingConfigurations":444},{"removed":"Scale","score":0.030148966987791195,"rank":292,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.025225703246671154,"rank":291,"remainingConfigurations":444},{"removed":"Cognition","score":0.02468539160249884,"rank":292,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0265988200330968,"rank":290,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02626093920189415,"rank":291,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02621305821344092,"rank":281,"remainingConfigurations":431},{"removed":"Vals AI","score":0.024468291717631135,"rank":289,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.025501033867628514,"rank":291,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02466768416028207,"rank":291,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.025466165995685547,"rank":291,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.025512474704122646,"rank":291,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.025723467532582894,"rank":291,"remainingConfigurations":444},{"removed":"All provider reports","score":0.024826740032367855,"rank":291,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02574136961694111,"rank":292,"remainingConfigurations":444},{"removed":"briefcase","score":0.0266427479673137,"rank":288,"remainingConfigurations":444},{"removed":"aime","score":0.022981409993367008,"rank":298,"remainingConfigurations":444},{"removed":"apex-agents","score":0.025934588943561158,"rank":292,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.026262723162051766,"rank":289,"remainingConfigurations":444},{"removed":"automationbench","score":0.02592130206135347,"rank":290,"remainingConfigurations":444},{"removed":"critpt","score":0.023366528954400095,"rank":298,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.025508760594452593,"rank":292,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.027811789608546023,"rank":287,"remainingConfigurations":444},{"removed":"gdpval","score":0.0263559405259533,"rank":290,"remainingConfigurations":444},{"removed":"gmmlu","score":0.025695618624488836,"rank":293,"remainingConfigurations":444},{"removed":"gpqa","score":0.02472607342489605,"rank":293,"remainingConfigurations":444},{"removed":"harvey","score":0.02521003154264473,"rank":291,"remainingConfigurations":444},{"removed":"hle","score":0.027832825331514547,"rank":295,"remainingConfigurations":444},{"removed":"ifbench","score":0.021756624193906674,"rank":298,"remainingConfigurations":444},{"removed":"itbench","score":0.025267265488253355,"rank":292,"remainingConfigurations":444},{"removed":"livecodebench","score":0.024253208184472214,"rank":294,"remainingConfigurations":444},{"removed":"math500","score":0.025728417029183742,"rank":290,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.027616210237720058,"rank":289,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.027872575666713875,"rank":292,"remainingConfigurations":444},{"removed":"omniscience","score":0.024385475070883317,"rank":291,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02585479537843734,"rank":284,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02591795701936948,"rank":291,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.026724414416233258,"rank":287,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03223574023705989,"rank":291,"remainingConfigurations":444},{"removed":"deepswe","score":0.019969575028570753,"rank":290,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.025519250218399583,"rank":291,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02508470338146324,"rank":290,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02468539160249884,"rank":292,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02514557734215304,"rank":291,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.025203970887800006,"rank":291,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02549836693458446,"rank":291,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02539547759531063,"rank":291,"remainingConfigurations":444},{"removed":"livebench-math","score":0.025543177420843378,"rank":291,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02519501991403798,"rank":291,"remainingConfigurations":444},{"removed":"livebench-language","score":0.025950910803892075,"rank":291,"remainingConfigurations":444},{"removed":"livebench-data","score":0.025508396105261264,"rank":291,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.024948406733374635,"rank":291,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02532363468239694,"rank":291,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.026143480321396306,"rank":291,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02626093920189415,"rank":291,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02554577287988834,"rank":291,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.023862141760757554,"rank":289,"remainingConfigurations":444},{"removed":"simpleqa","score":0.026910694417359843,"rank":291,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.025408821128138814,"rank":291,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.025405212446381553,"rank":291,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02541289605597348,"rank":291,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02545497426899127,"rank":291,"remainingConfigurations":444},{"removed":"vibe-code","score":0.025329533673900912,"rank":291,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.025433166162498046,"rank":291,"remainingConfigurations":444}],"sharedOrderConflicts":0},"grok-4.3--effort-non-reasoning":{"score":0.025473723382126754,"rank":292,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03355388599536065,"rank":290,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019889427165758988,"rank":292,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.025218088069041886,"rank":292,"remainingConfigurations":444},{"removed":"Scale","score":0.030128161518958575,"rank":293,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.02518079081739095,"rank":292,"remainingConfigurations":444},{"removed":"Cognition","score":0.02453930499939401,"rank":294,"remainingConfigurations":444},{"removed":"LiveBench","score":0.026611398873568032,"rank":289,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.026231548280597216,"rank":292,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02608790930230109,"rank":282,"remainingConfigurations":431},{"removed":"Vals AI","score":0.024435543806799565,"rank":290,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.025462180633064185,"rank":292,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.024630580603813818,"rank":292,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.025426961350260263,"rank":292,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.025473723382126754,"rank":292,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02568740960940151,"rank":292,"remainingConfigurations":444},{"removed":"All provider reports","score":0.024791636894911383,"rank":292,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.025742843414534033,"rank":291,"remainingConfigurations":444},{"removed":"briefcase","score":0.02314220984736201,"rank":296,"remainingConfigurations":444},{"removed":"aime","score":0.025355880477916443,"rank":291,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02596617587498345,"rank":290,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.026746234157722915,"rank":288,"remainingConfigurations":444},{"removed":"automationbench","score":0.026568941278629757,"rank":289,"remainingConfigurations":444},{"removed":"critpt","score":0.02759216483829179,"rank":286,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.025537807502088467,"rank":291,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02598221190928669,"rank":293,"remainingConfigurations":444},{"removed":"gdpval","score":0.02257197579331416,"rank":296,"remainingConfigurations":444},{"removed":"gmmlu","score":0.025716086552807396,"rank":292,"remainingConfigurations":444},{"removed":"gpqa","score":0.026946472164065458,"rank":285,"remainingConfigurations":444},{"removed":"harvey","score":0.025181567538777015,"rank":292,"remainingConfigurations":444},{"removed":"hle","score":0.029667937595199836,"rank":289,"remainingConfigurations":444},{"removed":"ifbench","score":0.023999159824153207,"rank":288,"remainingConfigurations":444},{"removed":"itbench","score":0.025285902393804818,"rank":291,"remainingConfigurations":444},{"removed":"livecodebench","score":0.025522043551052826,"rank":290,"remainingConfigurations":444},{"removed":"math500","score":0.025630217764925193,"rank":292,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0264638972804848,"rank":291,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.027467873235109103,"rank":293,"remainingConfigurations":444},{"removed":"omniscience","score":0.022381439987847945,"rank":296,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02422631951157177,"rank":292,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.025884824768956108,"rank":292,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.024587829471592715,"rank":294,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03229084217945719,"rank":290,"remainingConfigurations":444},{"removed":"deepswe","score":0.01990315155473991,"rank":292,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02548046982848154,"rank":292,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02506402665824989,"rank":291,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02453930499939401,"rank":294,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02510700192205666,"rank":292,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.025164267764094583,"rank":292,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02545954329585837,"rank":292,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.025356615990341783,"rank":292,"remainingConfigurations":444},{"removed":"livebench-math","score":0.025503755160206865,"rank":292,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.025155506432577093,"rank":292,"remainingConfigurations":444},{"removed":"livebench-language","score":0.025911892653563473,"rank":292,"remainingConfigurations":444},{"removed":"livebench-data","score":0.025470660445390262,"rank":292,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.024910036053226906,"rank":292,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02528463019204989,"rank":292,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02610552545445458,"rank":292,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.026231548280597216,"rank":292,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02546851064269035,"rank":293,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.023858475016138508,"rank":290,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02686249342424583,"rank":292,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.025370187985111554,"rank":292,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.025366601277507683,"rank":292,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.025374689323101385,"rank":292,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.025415588156259147,"rank":292,"remainingConfigurations":444},{"removed":"vibe-code","score":0.025290177260907983,"rank":292,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.025394544097219144,"rank":292,"remainingConfigurations":444}],"sharedOrderConflicts":0},"magistral-medium-2509--effort-reasoning":{"score":0.02544159787647754,"rank":293,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.033397714106807204,"rank":292,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019886962543157135,"rank":293,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02510980623504176,"rank":293,"remainingConfigurations":444},{"removed":"Scale","score":0.0300661095627006,"rank":294,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.02515466064001408,"rank":293,"remainingConfigurations":444},{"removed":"Cognition","score":0.024649472053087238,"rank":293,"remainingConfigurations":444},{"removed":"LiveBench","score":0.026516727109612625,"rank":292,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.026151100248789055,"rank":293,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.025857820536141555,"rank":283,"remainingConfigurations":431},{"removed":"Vals AI","score":0.024386334224116606,"rank":291,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.025430330321402902,"rank":293,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02460360770090003,"rank":293,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.025395622457515286,"rank":293,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02544159787647754,"rank":293,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.025651365946630245,"rank":293,"remainingConfigurations":444},{"removed":"All provider reports","score":0.024761899413671597,"rank":293,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02564986858575194,"rank":293,"remainingConfigurations":444},{"removed":"briefcase","score":0.02524182010040425,"rank":292,"remainingConfigurations":444},{"removed":"aime","score":0.024240289523254636,"rank":294,"remainingConfigurations":444},{"removed":"apex-agents","score":0.025835565857999065,"rank":293,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02485459496597615,"rank":293,"remainingConfigurations":444},{"removed":"automationbench","score":0.025269513569378958,"rank":293,"remainingConfigurations":444},{"removed":"critpt","score":0.024115102554246527,"rank":294,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.025410330905564594,"rank":293,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.026004894695785527,"rank":291,"remainingConfigurations":444},{"removed":"gdpval","score":0.027128695931728244,"rank":287,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02586087450538309,"rank":291,"remainingConfigurations":444},{"removed":"gpqa","score":0.025053586435889452,"rank":292,"remainingConfigurations":444},{"removed":"harvey","score":0.02514318952766373,"rank":293,"remainingConfigurations":444},{"removed":"hle","score":0.02830067072716244,"rank":294,"remainingConfigurations":444},{"removed":"ifbench","score":0.025315009365080365,"rank":285,"remainingConfigurations":444},{"removed":"itbench","score":0.025198449742551154,"rank":293,"remainingConfigurations":444},{"removed":"livecodebench","score":0.023954197380143812,"rank":295,"remainingConfigurations":444},{"removed":"math500","score":0.025571119580294992,"rank":293,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.026103955591908635,"rank":292,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.029084044513136714,"rank":288,"remainingConfigurations":444},{"removed":"omniscience","score":0.02241136674427407,"rank":295,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02525627154964506,"rank":291,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.025845249173860305,"rank":293,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02625098793228575,"rank":291,"remainingConfigurations":444},{"removed":"arc-agi","score":0.03214145540168416,"rank":292,"remainingConfigurations":444},{"removed":"deepswe","score":0.01990092412769629,"rank":293,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02544825350763601,"rank":293,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.024996559890766993,"rank":292,"remainingConfigurations":444},{"removed":"frontiercode","score":0.024649472053087238,"rank":293,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02507017067034527,"rank":293,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.025131061469823402,"rank":293,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.025427309736838415,"rank":293,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.025325355266297308,"rank":293,"remainingConfigurations":444},{"removed":"livebench-math","score":0.025473186739621224,"rank":293,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02512447940443226,"rank":293,"remainingConfigurations":444},{"removed":"livebench-language","score":0.025877110107239785,"rank":293,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02543686019310677,"rank":293,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.024880538843149166,"rank":293,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.025253534934301273,"rank":293,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.026070987077140704,"rank":293,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.026151100248789055,"rank":293,"remainingConfigurations":444},{"removed":"frontiermath","score":0.025485225858071735,"rank":292,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02371857481305859,"rank":291,"remainingConfigurations":444},{"removed":"simpleqa","score":0.026837712302175003,"rank":293,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.025338015200444777,"rank":293,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.025334469234259388,"rank":293,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.025342659612666213,"rank":293,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.025383773231063778,"rank":293,"remainingConfigurations":444},{"removed":"vibe-code","score":0.025259348300016995,"rank":293,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02536227034232792,"rank":293,"remainingConfigurations":444}],"sharedOrderConflicts":0},"o3-mini--effort-high":{"score":0.02461501377346285,"rank":294,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.021036547929694695,"rank":179,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.025621543713147107,"rank":306,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019167414789260585,"rank":294,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02461578393504485,"rank":294,"remainingConfigurations":444},{"removed":"Scale","score":0.03595212103112164,"rank":281,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.024223199247039556,"rank":294,"remainingConfigurations":444},{"removed":"Cognition","score":0.023909314129430887,"rank":295,"remainingConfigurations":444},{"removed":"LiveBench","score":0.025637232662651433,"rank":293,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02500835260779516,"rank":296,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.024569528753816784,"rank":287,"remainingConfigurations":431},{"removed":"Vals AI","score":0.023288889976131686,"rank":294,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.024603408019806653,"rank":294,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02385768414382507,"rank":294,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.024573375093237218,"rank":294,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02461501377346285,"rank":294,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.024814867285463577,"rank":294,"remainingConfigurations":444},{"removed":"All provider reports","score":0.024009281916601382,"rank":294,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02480308037499672,"rank":294,"remainingConfigurations":444},{"removed":"briefcase","score":0.024839014385385955,"rank":293,"remainingConfigurations":444},{"removed":"aime","score":0.02445504029523472,"rank":292,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02494068817871874,"rank":294,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.024769886695877198,"rank":294,"remainingConfigurations":444},{"removed":"automationbench","score":0.025148842552489503,"rank":294,"remainingConfigurations":444},{"removed":"critpt","score":0.024042509443790622,"rank":295,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.024620168473835104,"rank":294,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02516814594093637,"rank":294,"remainingConfigurations":444},{"removed":"gdpval","score":0.02533136376411856,"rank":293,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02456255074552391,"rank":295,"remainingConfigurations":444},{"removed":"gpqa","score":0.023899181572854988,"rank":296,"remainingConfigurations":444},{"removed":"harvey","score":0.024301260758334883,"rank":294,"remainingConfigurations":444},{"removed":"hle","score":0.033149691155293586,"rank":281,"remainingConfigurations":444},{"removed":"ifbench","score":0.022935392750451315,"rank":294,"remainingConfigurations":444},{"removed":"itbench","score":0.024451020665981565,"rank":294,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02426583163719742,"rank":293,"remainingConfigurations":444},{"removed":"math500","score":0.023754110099179254,"rank":296,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02590292266883963,"rank":294,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.026794572715403465,"rank":294,"remainingConfigurations":444},{"removed":"omniscience","score":0.022375590404308827,"rank":297,"remainingConfigurations":444},{"removed":"tau-bench","score":0.025287505086303456,"rank":289,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.024895607184988188,"rank":294,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.025241524063665446,"rank":293,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02469094630032258,"rank":305,"remainingConfigurations":444},{"removed":"deepswe","score":0.019178834226133725,"rank":294,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02462092444992089,"rank":294,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.023808549820192912,"rank":295,"remainingConfigurations":444},{"removed":"frontiercode","score":0.023909314129430887,"rank":295,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.023825458514968135,"rank":295,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02434379125189619,"rank":294,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.024625585308441264,"rank":294,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.024511783540577092,"rank":294,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02463480730045035,"rank":294,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.024287213897125372,"rank":294,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02501994010771322,"rank":294,"remainingConfigurations":444},{"removed":"livebench-data","score":0.024609699983815514,"rank":294,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.024116248700394822,"rank":294,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0244482017765776,"rank":294,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.025210794515857837,"rank":294,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02500835260779516,"rank":296,"remainingConfigurations":444},{"removed":"frontiermath","score":0.024698118708053062,"rank":294,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.022809164923733537,"rank":293,"remainingConfigurations":444},{"removed":"simpleqa","score":0.025891142487282946,"rank":294,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.024514501724564427,"rank":294,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.024509327188274744,"rank":294,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02453227500138368,"rank":294,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02455136009571515,"rank":294,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02443477269820667,"rank":294,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.024543427703308363,"rank":294,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-sonnet-4-5-20250929--effort-non-reasoning":{"score":0.02442047944613883,"rank":295,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.03232052604991209,"rank":293,"remainingConfigurations":444},{"removed":"Datacurve","score":0.019089126932613536,"rank":295,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.024153035514206552,"rank":295,"remainingConfigurations":444},{"removed":"Scale","score":0.028831119330003457,"rank":295,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.02414588361612204,"rank":295,"remainingConfigurations":444},{"removed":"Cognition","score":0.023658791535837928,"rank":296,"remainingConfigurations":444},{"removed":"LiveBench","score":0.025470203630402755,"rank":294,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.025138933035485655,"rank":295,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.024701856109717854,"rank":286,"remainingConfigurations":431},{"removed":"Vals AI","score":0.023415235814429433,"rank":293,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.024409640124645998,"rank":295,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02361563536632491,"rank":295,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.024376312863679712,"rank":295,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02442047944613883,"rank":295,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02462374533659381,"rank":295,"remainingConfigurations":444},{"removed":"All provider reports","score":0.023769332289665494,"rank":295,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02465863925140892,"rank":295,"remainingConfigurations":444},{"removed":"briefcase","score":0.024299756166004497,"rank":294,"remainingConfigurations":444},{"removed":"aime","score":0.02897983113121763,"rank":285,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02482490105114633,"rank":295,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.023529166196019247,"rank":297,"remainingConfigurations":444},{"removed":"automationbench","score":0.02430838797712366,"rank":295,"remainingConfigurations":444},{"removed":"critpt","score":0.02661866321104828,"rank":288,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02443675788890194,"rank":295,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02504290236520101,"rank":295,"remainingConfigurations":444},{"removed":"gdpval","score":0.024536232049990513,"rank":294,"remainingConfigurations":444},{"removed":"gmmlu","score":0.024708808966998324,"rank":294,"remainingConfigurations":444},{"removed":"gpqa","score":0.02425969531229571,"rank":295,"remainingConfigurations":444},{"removed":"harvey","score":0.024142096943470692,"rank":295,"remainingConfigurations":444},{"removed":"hle","score":0.028416364603967514,"rank":293,"remainingConfigurations":444},{"removed":"ifbench","score":0.024708196143746572,"rank":287,"remainingConfigurations":444},{"removed":"itbench","score":0.024213342668994702,"rank":295,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02557285595220192,"rank":289,"remainingConfigurations":444},{"removed":"math500","score":0.024567514796228356,"rank":294,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.022286152688828036,"rank":300,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.026165107584021255,"rank":295,"remainingConfigurations":444},{"removed":"omniscience","score":0.019024495729070907,"rank":305,"remainingConfigurations":444},{"removed":"tau-bench","score":0.022779044237098423,"rank":295,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.024822263251292057,"rank":295,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.022815450525898468,"rank":298,"remainingConfigurations":444},{"removed":"arc-agi","score":0.031091522280887355,"rank":293,"remainingConfigurations":444},{"removed":"deepswe","score":0.01910229059882568,"rank":295,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.024426817744266454,"rank":295,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.023987059352806997,"rank":294,"remainingConfigurations":444},{"removed":"frontiercode","score":0.023658791535837928,"rank":296,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02406425883149624,"rank":294,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02412293500495097,"rank":295,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.024406709017785324,"rank":295,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02430886718470665,"rank":295,"remainingConfigurations":444},{"removed":"livebench-math","score":0.024450923941881725,"rank":295,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02411411923816244,"rank":295,"remainingConfigurations":444},{"removed":"livebench-language","score":0.024838666081846577,"rank":295,"remainingConfigurations":444},{"removed":"livebench-data","score":0.024416819397824058,"rank":295,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02388135210982258,"rank":295,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.024239297716662198,"rank":295,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.025026974558649967,"rank":295,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.025138933035485655,"rank":295,"remainingConfigurations":444},{"removed":"frontiermath","score":0.024472948348020145,"rank":295,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.022746742011272723,"rank":294,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02576382613642318,"rank":295,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02432102755839861,"rank":295,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.024317270945173913,"rank":295,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02432565601625238,"rank":295,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.024364380003148205,"rank":295,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02424494463480432,"rank":295,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.024344316545326903,"rank":295,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash-lite--effort-low":{"score":0.023772444483604077,"rank":296,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01953747238404806,"rank":180,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.05775441269680672,"rank":253,"remainingConfigurations":444},{"removed":"Datacurve","score":0.018500025383566505,"rank":296,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.023689595022756044,"rank":296,"remainingConfigurations":444},{"removed":"Scale","score":0.02778529514455848,"rank":296,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.023449809719577473,"rank":296,"remainingConfigurations":444},{"removed":"Cognition","score":0.02498260516401089,"rank":291,"remainingConfigurations":444},{"removed":"LiveBench","score":0.024411439516031155,"rank":295,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.023623096986567765,"rank":297,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.008830043171403987,"rank":348,"remainingConfigurations":431},{"removed":"Vals AI","score":0.022428234885880905,"rank":295,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.023763347677272003,"rank":296,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.023066758172757693,"rank":296,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.023739730295233793,"rank":296,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.023772444483604077,"rank":296,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02396332552912143,"rank":296,"remainingConfigurations":444},{"removed":"All provider reports","score":0.023220137579616985,"rank":296,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02390494318470039,"rank":296,"remainingConfigurations":444},{"removed":"briefcase","score":0.023592825242097062,"rank":295,"remainingConfigurations":444},{"removed":"aime","score":0.023666512393086075,"rank":295,"remainingConfigurations":444},{"removed":"apex-agents","score":0.024032630010908638,"rank":296,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02369738913922151,"rank":296,"remainingConfigurations":444},{"removed":"automationbench","score":0.02363360323270874,"rank":296,"remainingConfigurations":444},{"removed":"critpt","score":0.023789810500147574,"rank":297,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.023771754889295015,"rank":296,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02395330696003511,"rank":296,"remainingConfigurations":444},{"removed":"gdpval","score":0.02366765352044946,"rank":295,"remainingConfigurations":444},{"removed":"gmmlu","score":0.023840324965672965,"rank":297,"remainingConfigurations":444},{"removed":"gpqa","score":0.024442796694710445,"rank":294,"remainingConfigurations":444},{"removed":"harvey","score":0.02343574579683343,"rank":296,"remainingConfigurations":444},{"removed":"hle","score":0.025931558796273572,"rank":296,"remainingConfigurations":444},{"removed":"ifbench","score":0.023431500364173657,"rank":290,"remainingConfigurations":444},{"removed":"itbench","score":0.023653569713419934,"rank":296,"remainingConfigurations":444},{"removed":"livecodebench","score":0.023697016247396605,"rank":296,"remainingConfigurations":444},{"removed":"math500","score":0.023808800254987703,"rank":295,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.024723968873051404,"rank":295,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.025848967870032987,"rank":296,"remainingConfigurations":444},{"removed":"omniscience","score":0.023022437744835544,"rank":294,"remainingConfigurations":444},{"removed":"tau-bench","score":0.023366648436193415,"rank":293,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.023934567310090544,"rank":296,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02350706305258379,"rank":297,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0557942113180049,"rank":253,"remainingConfigurations":444},{"removed":"deepswe","score":0.018510833160932393,"rank":296,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.023777797757214603,"rank":296,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02274283148165088,"rank":296,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02498260516401089,"rank":291,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02344662196308311,"rank":296,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02347464218103107,"rank":296,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02376117818834728,"rank":296,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02365297647985788,"rank":296,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02381668425258703,"rank":296,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.023443428206908642,"rank":296,"remainingConfigurations":444},{"removed":"livebench-language","score":0.024161280652816874,"rank":296,"remainingConfigurations":444},{"removed":"livebench-data","score":0.023764670610457148,"rank":296,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.023263604933780657,"rank":296,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02359084108050699,"rank":296,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.024388182564924588,"rank":296,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.023623096986567765,"rank":297,"remainingConfigurations":444},{"removed":"frontiermath","score":0.023741820629802467,"rank":296,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.013260051898088125,"rank":324,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02492814367114159,"rank":296,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02367495724088894,"rank":296,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.023667589248203943,"rank":296,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.023694991198617222,"rank":296,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.023707295822332584,"rank":296,"remainingConfigurations":444},{"removed":"vibe-code","score":0.023601817263305406,"rank":296,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.02369709596247137,"rank":296,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minicpm5-2b--effort-reasoning":{"score":0.02271322030577259,"rank":297,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02979192839549678,"rank":295,"remainingConfigurations":444},{"removed":"Datacurve","score":0.017739018508304227,"rank":297,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.022469140381543,"rank":298,"remainingConfigurations":444},{"removed":"Scale","score":0.026878584120192783,"rank":297,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.022454538311511705,"rank":297,"remainingConfigurations":444},{"removed":"Cognition","score":0.021935537725156693,"rank":298,"remainingConfigurations":444},{"removed":"LiveBench","score":0.023710180017681912,"rank":296,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.023406854689273403,"rank":298,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.023535219079867487,"rank":288,"remainingConfigurations":431},{"removed":"Vals AI","score":0.021821615493640253,"rank":296,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02270287763793437,"rank":297,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.021957491127047146,"rank":297,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02267145772639383,"rank":297,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02271322030577259,"rank":297,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.022901866263525802,"rank":297,"remainingConfigurations":444},{"removed":"All provider reports","score":0.022099201748192885,"rank":297,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.022955939449564405,"rank":297,"remainingConfigurations":444},{"removed":"briefcase","score":0.021901114982015673,"rank":299,"remainingConfigurations":444},{"removed":"aime","score":0.022531299400215043,"rank":300,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02314241712773016,"rank":297,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.02096908865718324,"rank":302,"remainingConfigurations":444},{"removed":"automationbench","score":0.022511170748976364,"rank":298,"remainingConfigurations":444},{"removed":"critpt","score":0.0207561316358331,"rank":304,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.022743040684168808,"rank":297,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02393130000544745,"rank":297,"remainingConfigurations":444},{"removed":"gdpval","score":0.020908632690598835,"rank":303,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02292619569899317,"rank":298,"remainingConfigurations":444},{"removed":"gpqa","score":0.023042541264246527,"rank":297,"remainingConfigurations":444},{"removed":"harvey","score":0.022448820170081544,"rank":297,"remainingConfigurations":444},{"removed":"hle","score":0.025440339069551423,"rank":297,"remainingConfigurations":444},{"removed":"ifbench","score":0.021605054049274333,"rank":299,"remainingConfigurations":444},{"removed":"itbench","score":0.022543871737911225,"rank":297,"remainingConfigurations":444},{"removed":"livecodebench","score":0.022670724656886715,"rank":299,"remainingConfigurations":444},{"removed":"math500","score":0.02282554561621505,"rank":297,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.023551740194289624,"rank":296,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.024848406809313394,"rank":297,"remainingConfigurations":444},{"removed":"omniscience","score":0.02883382442659467,"rank":282,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019134913471144422,"rank":308,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.023085871473102,"rank":297,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02354632691125542,"rank":296,"remainingConfigurations":444},{"removed":"arc-agi","score":0.028664287201852618,"rank":295,"remainingConfigurations":444},{"removed":"deepswe","score":0.017751595109721272,"rank":297,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.022719323075170255,"rank":297,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.022345228605461148,"rank":297,"remainingConfigurations":444},{"removed":"frontiercode","score":0.021935537725156693,"rank":298,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.022382703264112614,"rank":297,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.022434805063342,"rank":297,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.022700775570036035,"rank":297,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0226087655016769,"rank":297,"remainingConfigurations":444},{"removed":"livebench-math","score":0.022740258575014535,"rank":297,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02242829891103752,"rank":297,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02310649308123928,"rank":297,"remainingConfigurations":444},{"removed":"livebench-data","score":0.022710596042577177,"rank":297,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02220752614245662,"rank":297,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.022543831746811332,"rank":297,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.023279074139254587,"rank":297,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.023406854689273403,"rank":298,"remainingConfigurations":444},{"removed":"frontiermath","score":0.022734581032572632,"rank":298,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02130922519289707,"rank":295,"remainingConfigurations":444},{"removed":"simpleqa","score":0.023963338379189448,"rank":297,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02262056321766681,"rank":297,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.022617307996094432,"rank":297,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.022623881096935906,"rank":297,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.022661785137928672,"rank":297,"remainingConfigurations":444},{"removed":"vibe-code","score":0.022549238139558683,"rank":297,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.022642231237845117,"rank":297,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-4-5-20251001--effort-thinking-32k":{"score":0.022389577200460323,"rank":298,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.018785379115720324,"rank":183,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0038120595599538186,"rank":412,"remainingConfigurations":444},{"removed":"Datacurve","score":0.017055131327590282,"rank":299,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.023030172093735323,"rank":297,"remainingConfigurations":444},{"removed":"Scale","score":0.026736678131571403,"rank":298,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.022010610566859618,"rank":298,"remainingConfigurations":444},{"removed":"Cognition","score":0.022063141250199304,"rank":297,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02288222194388308,"rank":298,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.022155400073470232,"rank":302,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.048194477014483546,"rank":242,"remainingConfigurations":431},{"removed":"Vals AI","score":0.020535975608813973,"rank":300,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02237815480810179,"rank":298,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.021741111704701336,"rank":298,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02240149238160663,"rank":298,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.022389577200460323,"rank":298,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.022572529900983494,"rank":298,"remainingConfigurations":444},{"removed":"All provider reports","score":0.02192789302917982,"rank":298,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.022500624490566085,"rank":298,"remainingConfigurations":444},{"removed":"briefcase","score":0.022204078747679438,"rank":297,"remainingConfigurations":444},{"removed":"aime","score":0.023504343421125524,"rank":297,"remainingConfigurations":444},{"removed":"apex-agents","score":0.02259538619238204,"rank":298,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.022234579507903158,"rank":299,"remainingConfigurations":444},{"removed":"automationbench","score":0.022237673051332698,"rank":299,"remainingConfigurations":444},{"removed":"critpt","score":0.022666526244757443,"rank":301,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.022378641742882937,"rank":298,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.022513973001580537,"rank":299,"remainingConfigurations":444},{"removed":"gdpval","score":0.02233157525097874,"rank":297,"remainingConfigurations":444},{"removed":"gmmlu","score":0.022382170186189796,"rank":299,"remainingConfigurations":444},{"removed":"gpqa","score":0.026532039026321928,"rank":287,"remainingConfigurations":444},{"removed":"harvey","score":0.02202956042227827,"rank":298,"remainingConfigurations":444},{"removed":"hle","score":0.02495503749074535,"rank":298,"remainingConfigurations":444},{"removed":"ifbench","score":0.02197944585464855,"rank":296,"remainingConfigurations":444},{"removed":"itbench","score":0.022286077666838208,"rank":298,"remainingConfigurations":444},{"removed":"livecodebench","score":0.022975650120546105,"rank":298,"remainingConfigurations":444},{"removed":"math500","score":0.02241115142186559,"rank":298,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02323945739002622,"rank":297,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02438254762037094,"rank":298,"remainingConfigurations":444},{"removed":"omniscience","score":0.021707194887123235,"rank":298,"remainingConfigurations":444},{"removed":"tau-bench","score":0.022361616636737885,"rank":296,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02252637296215819,"rank":299,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.022066622705348135,"rank":299,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0036863084757577844,"rank":412,"remainingConfigurations":444},{"removed":"deepswe","score":0.017066219231753374,"rank":299,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.022394139990568992,"rank":298,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.02073439475067154,"rank":301,"remainingConfigurations":444},{"removed":"frontiercode","score":0.022063141250199304,"rank":297,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.022059105762847142,"rank":298,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.022119078809235675,"rank":298,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.022376123488253342,"rank":298,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.022279854005073884,"rank":298,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02241515476966807,"rank":298,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02209117612121614,"rank":298,"remainingConfigurations":444},{"removed":"livebench-language","score":0.022770111093783876,"rank":298,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02238303305205742,"rank":298,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02189987073161691,"rank":298,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02222608499287527,"rank":298,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.022962491689549797,"rank":298,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.022155400073470232,"rank":302,"remainingConfigurations":444},{"removed":"frontiermath","score":0.023305829736369844,"rank":297,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.020239788573432668,"rank":299,"remainingConfigurations":444},{"removed":"simpleqa","score":0.023729996294918718,"rank":298,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0222863034874311,"rank":298,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02229175092270678,"rank":298,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.022318279566435895,"rank":298,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02232973568847241,"rank":298,"remainingConfigurations":444},{"removed":"vibe-code","score":0.022221288665702752,"rank":298,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.022327225232883916,"rank":298,"remainingConfigurations":444}],"sharedOrderConflicts":0},"seed-oss-36b-instruct--effort-reasoning":{"score":0.022214702646003667,"rank":299,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.029192295529375915,"rank":296,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01735321765406227,"rank":298,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02193631865239169,"rank":299,"remainingConfigurations":444},{"removed":"Scale","score":0.02629326506617533,"rank":299,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.021963372736891754,"rank":299,"remainingConfigurations":444},{"removed":"Cognition","score":0.02154765182424681,"rank":299,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02316624864493938,"rank":297,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02284184811950503,"rank":299,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02255221655574298,"rank":289,"remainingConfigurations":431},{"removed":"Vals AI","score":0.021299119262764746,"rank":297,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02220482782421925,"rank":299,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.021480377299822218,"rank":299,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.022174537720028337,"rank":299,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.022214702646003667,"rank":299,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02239876848941182,"rank":299,"remainingConfigurations":444},{"removed":"All provider reports","score":0.021619397539606917,"rank":299,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.022409860929181596,"rank":299,"remainingConfigurations":444},{"removed":"briefcase","score":0.02204906014799297,"rank":298,"remainingConfigurations":444},{"removed":"aime","score":0.019976643657156897,"rank":306,"remainingConfigurations":444},{"removed":"apex-agents","score":0.022572082879076933,"rank":299,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.020728891401429698,"rank":303,"remainingConfigurations":444},{"removed":"automationbench","score":0.022069985582765305,"rank":300,"remainingConfigurations":444},{"removed":"critpt","score":0.023925143047351605,"rank":296,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02220473021035577,"rank":299,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02271889390883806,"rank":298,"remainingConfigurations":444},{"removed":"gdpval","score":0.02226351338468503,"rank":298,"remainingConfigurations":444},{"removed":"gmmlu","score":0.024421591060640596,"rank":296,"remainingConfigurations":444},{"removed":"gpqa","score":0.022000098721098597,"rank":299,"remainingConfigurations":444},{"removed":"harvey","score":0.021956894550509518,"rank":299,"remainingConfigurations":444},{"removed":"hle","score":0.024761837074781756,"rank":299,"remainingConfigurations":444},{"removed":"ifbench","score":0.0223517187098386,"rank":295,"remainingConfigurations":444},{"removed":"itbench","score":0.02200828014251556,"rank":299,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02029145168837294,"rank":305,"remainingConfigurations":444},{"removed":"math500","score":0.022317091816780817,"rank":299,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02237809307721937,"rank":299,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.024192998515787188,"rank":299,"remainingConfigurations":444},{"removed":"omniscience","score":0.02014819304627788,"rank":300,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02124134323519856,"rank":298,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02257105692351408,"rank":298,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.023877262427797547,"rank":295,"remainingConfigurations":444},{"removed":"arc-agi","score":0.028082466745314654,"rank":296,"remainingConfigurations":444},{"removed":"deepswe","score":0.017365372384696442,"rank":298,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02222051305331745,"rank":299,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.021817546579359814,"rank":298,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02154765182424681,"rank":299,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.021887302811681702,"rank":299,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.021942754029529884,"rank":299,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.022202180364191273,"rank":299,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.022113004559256407,"rank":299,"remainingConfigurations":444},{"removed":"livebench-math","score":0.022242627140622997,"rank":299,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02193477332313085,"rank":299,"remainingConfigurations":444},{"removed":"livebench-language","score":0.022596882308422803,"rank":299,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02221122244216607,"rank":299,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.021722190009335295,"rank":299,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.02204921797197906,"rank":299,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02276888344737474,"rank":299,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02284184811950503,"rank":299,"remainingConfigurations":444},{"removed":"frontiermath","score":0.022260488366443506,"rank":299,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.020690440961706223,"rank":296,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02344433168726932,"rank":299,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.022123728464499576,"rank":299,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.022120419738049752,"rank":299,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0221279481125079,"rank":299,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.022163545000104364,"rank":299,"remainingConfigurations":444},{"removed":"vibe-code","score":0.022054459894158152,"rank":299,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.022145002674030318,"rank":299,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-235b-a22b-instruct-2507--effort-non-reasoning":{"score":0.021769470191213364,"rank":300,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.028651952364190495,"rank":297,"remainingConfigurations":444},{"removed":"Datacurve","score":0.017007149455780444,"rank":300,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.021480253096526344,"rank":300,"remainingConfigurations":444},{"removed":"Scale","score":0.025738597961705478,"rank":300,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.021524629604092887,"rank":300,"remainingConfigurations":444},{"removed":"Cognition","score":0.02112272805338662,"rank":300,"remainingConfigurations":444},{"removed":"LiveBench","score":0.022706904351011286,"rank":299,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.022406824883325658,"rank":300,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.022120581557028247,"rank":291,"remainingConfigurations":431},{"removed":"Vals AI","score":0.020878485113014086,"rank":298,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02175978977555666,"rank":300,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.021049348584470617,"rank":300,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02173009211126992,"rank":300,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.021769470191213364,"rank":300,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.021950003088621568,"rank":300,"remainingConfigurations":444},{"removed":"All provider reports","score":0.021185711699978543,"rank":300,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.021968413892319034,"rank":300,"remainingConfigurations":444},{"removed":"briefcase","score":0.021642296848670552,"rank":300,"remainingConfigurations":444},{"removed":"aime","score":0.021503471549897398,"rank":302,"remainingConfigurations":444},{"removed":"apex-agents","score":0.022122526074483617,"rank":300,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.022656699166940252,"rank":298,"remainingConfigurations":444},{"removed":"automationbench","score":0.021650585148418413,"rank":302,"remainingConfigurations":444},{"removed":"critpt","score":0.0233147196029537,"rank":299,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0217673169317959,"rank":301,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.022297656112083352,"rank":301,"remainingConfigurations":444},{"removed":"gdpval","score":0.021855069786657706,"rank":299,"remainingConfigurations":444},{"removed":"gmmlu","score":0.022023767566429264,"rank":300,"remainingConfigurations":444},{"removed":"gpqa","score":0.020728082286496034,"rank":302,"remainingConfigurations":444},{"removed":"harvey","score":0.02151763154983556,"rank":300,"remainingConfigurations":444},{"removed":"hle","score":0.023433470281105036,"rank":301,"remainingConfigurations":444},{"removed":"ifbench","score":0.020786074371008424,"rank":300,"remainingConfigurations":444},{"removed":"itbench","score":0.021571246099998737,"rank":300,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02298427592255867,"rank":297,"remainingConfigurations":444},{"removed":"math500","score":0.020407945510395303,"rank":305,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.020875809681956053,"rank":305,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.023756835289105906,"rank":300,"remainingConfigurations":444},{"removed":"omniscience","score":0.019227865486617795,"rank":303,"remainingConfigurations":444},{"removed":"tau-bench","score":0.022356796691506458,"rank":297,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02212073277250091,"rank":300,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.021775450159275584,"rank":301,"remainingConfigurations":444},{"removed":"arc-agi","score":0.027558379347940587,"rank":297,"remainingConfigurations":444},{"removed":"deepswe","score":0.01701905756348109,"rank":300,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.021775167982238223,"rank":300,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.021379254513984706,"rank":299,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02112272805338662,"rank":300,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02144915962113382,"rank":300,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.02150285173213924,"rank":300,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02175732294091313,"rank":300,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0216698810106434,"rank":300,"remainingConfigurations":444},{"removed":"livebench-math","score":0.021796835624057456,"rank":300,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.02149483090702092,"rank":300,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02214438101777673,"rank":300,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02176626712687461,"rank":300,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.021286371848277436,"rank":300,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0216070731447527,"rank":300,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.022313031153711402,"rank":300,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.022406824883325658,"rank":300,"remainingConfigurations":444},{"removed":"frontiermath","score":0.021813951376177834,"rank":300,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.020276756840047986,"rank":297,"remainingConfigurations":444},{"removed":"simpleqa","score":0.022977485842252125,"rank":300,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.021680243690183256,"rank":300,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.021677005166750734,"rank":300,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.021684412512832485,"rank":300,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0217192812232809,"rank":300,"remainingConfigurations":444},{"removed":"vibe-code","score":0.021612268977603405,"rank":300,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.021701182731061638,"rank":300,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning":{"score":0.021641359437863206,"rank":301,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02837827560338516,"rank":298,"remainingConfigurations":444},{"removed":"Datacurve","score":0.016893979750193848,"rank":301,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.021410229064355413,"rank":301,"remainingConfigurations":444},{"removed":"Scale","score":0.02564086321034136,"rank":301,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.021396684836809888,"rank":301,"remainingConfigurations":444},{"removed":"Cognition","score":0.02090264989783921,"rank":302,"remainingConfigurations":444},{"removed":"LiveBench","score":0.022585857992637487,"rank":300,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.022307633028969046,"rank":301,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.022452050054540332,"rank":290,"remainingConfigurations":431},{"removed":"Vals AI","score":0.020767460316675545,"rank":299,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.021631573415650918,"rank":301,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.020917050247723876,"rank":301,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.021602061720106217,"rank":301,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.021641359437863206,"rank":301,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.021820357762448454,"rank":301,"remainingConfigurations":444},{"removed":"All provider reports","score":0.021051958477400944,"rank":301,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.021839171516963296,"rank":301,"remainingConfigurations":444},{"removed":"briefcase","score":0.020187892266739203,"rank":305,"remainingConfigurations":444},{"removed":"aime","score":0.021524703919639333,"rank":301,"remainingConfigurations":444},{"removed":"apex-agents","score":0.022022662072755397,"rank":301,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.020589383449653904,"rank":305,"remainingConfigurations":444},{"removed":"automationbench","score":0.02253818161125855,"rank":297,"remainingConfigurations":444},{"removed":"critpt","score":0.02459066057977781,"rank":293,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02210630366448015,"rank":300,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02149904258286467,"rank":302,"remainingConfigurations":444},{"removed":"gdpval","score":0.020099099961715428,"rank":305,"remainingConfigurations":444},{"removed":"gmmlu","score":0.021870510511176857,"rank":302,"remainingConfigurations":444},{"removed":"gpqa","score":0.020472208693434944,"rank":303,"remainingConfigurations":444},{"removed":"harvey","score":0.021379090281994088,"rank":301,"remainingConfigurations":444},{"removed":"hle","score":0.023013778664243516,"rank":302,"remainingConfigurations":444},{"removed":"ifbench","score":0.020511571799036392,"rank":302,"remainingConfigurations":444},{"removed":"itbench","score":0.02144110133748488,"rank":301,"remainingConfigurations":444},{"removed":"livecodebench","score":0.021667748687297164,"rank":300,"remainingConfigurations":444},{"removed":"math500","score":0.021763719036382256,"rank":300,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02252034215542305,"rank":298,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02363102085530455,"rank":301,"remainingConfigurations":444},{"removed":"omniscience","score":0.02416570693013978,"rank":292,"remainingConfigurations":444},{"removed":"tau-bench","score":0.020631426045307082,"rank":300,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.02198836331142633,"rank":301,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.020412958396112995,"rank":306,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02730840873767987,"rank":298,"remainingConfigurations":444},{"removed":"deepswe","score":0.016906217010220662,"rank":301,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.02164717632637939,"rank":301,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.021294983583823878,"rank":300,"remainingConfigurations":444},{"removed":"frontiercode","score":0.02090264989783921,"rank":302,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02132667337618691,"rank":301,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.021375978577392745,"rank":301,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.021629586855306648,"rank":301,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02154171331082323,"rank":301,"remainingConfigurations":444},{"removed":"livebench-math","score":0.021666803141861885,"rank":301,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.021370961878531426,"rank":301,"remainingConfigurations":444},{"removed":"livebench-language","score":0.022018000031625923,"rank":301,"remainingConfigurations":444},{"removed":"livebench-data","score":0.021637725226015547,"rank":301,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.021157909545725006,"rank":301,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.021479900636608134,"rank":301,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.022180666363211754,"rank":301,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.022307633028969046,"rank":301,"remainingConfigurations":444},{"removed":"frontiermath","score":0.021659948185484418,"rank":301,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.020272794883423113,"rank":298,"remainingConfigurations":444},{"removed":"simpleqa","score":0.022836623908635858,"rank":301,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.021552981084844974,"rank":301,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.021549735726482933,"rank":301,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.02155566342955448,"rank":301,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0215926066423872,"rank":301,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02148482990008818,"rank":301,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.021573748775608605,"rank":301,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.7--effort-non-reasoning":{"score":0.020840972137258922,"rank":302,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.027552792738161552,"rank":299,"remainingConfigurations":444},{"removed":"Datacurve","score":0.016283250493333706,"rank":302,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.020601532979696396,"rank":302,"remainingConfigurations":444},{"removed":"Scale","score":0.02469754077588378,"rank":302,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.02060448548042409,"rank":302,"remainingConfigurations":444},{"removed":"Cognition","score":0.020225124710410273,"rank":303,"remainingConfigurations":444},{"removed":"LiveBench","score":0.021747348961303748,"rank":301,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.021477866080525237,"rank":303,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02138195884489036,"rank":292,"remainingConfigurations":431},{"removed":"Vals AI","score":0.019984679894445398,"rank":301,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.020831670160871067,"rank":302,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.02015020042427243,"rank":302,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02080321709925279,"rank":302,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.020840972137258922,"rank":302,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02101447117438081,"rank":302,"remainingConfigurations":444},{"removed":"All provider reports","score":0.02028129558512571,"rank":302,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.021039235981150203,"rank":302,"remainingConfigurations":444},{"removed":"briefcase","score":0.02073585516428658,"rank":302,"remainingConfigurations":444},{"removed":"aime","score":0.022634843377217523,"rank":299,"remainingConfigurations":444},{"removed":"apex-agents","score":0.021199346758735537,"rank":302,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.021224924212479897,"rank":301,"remainingConfigurations":444},{"removed":"automationbench","score":0.020747245527356673,"rank":303,"remainingConfigurations":444},{"removed":"critpt","score":0.022216289946568348,"rank":302,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.020853965367151787,"rank":302,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02136474585757889,"rank":303,"remainingConfigurations":444},{"removed":"gdpval","score":0.020953452160075724,"rank":302,"remainingConfigurations":444},{"removed":"gmmlu","score":0.021870612385118577,"rank":301,"remainingConfigurations":444},{"removed":"gpqa","score":0.021869063167838532,"rank":300,"remainingConfigurations":444},{"removed":"harvey","score":0.020599876335658133,"rank":302,"remainingConfigurations":444},{"removed":"hle","score":0.024398372337979268,"rank":300,"remainingConfigurations":444},{"removed":"ifbench","score":0.0188346994370754,"rank":305,"remainingConfigurations":444},{"removed":"itbench","score":0.020657964801727786,"rank":302,"remainingConfigurations":444},{"removed":"livecodebench","score":0.02151112566188894,"rank":301,"remainingConfigurations":444},{"removed":"math500","score":0.020919568448252653,"rank":302,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.022057558149876283,"rank":301,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.022849505596490016,"rank":302,"remainingConfigurations":444},{"removed":"omniscience","score":0.017048737475321867,"rank":309,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017221533903065116,"rank":317,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.021182938723672107,"rank":302,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.019180410107208782,"rank":309,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02649145556463856,"rank":299,"remainingConfigurations":444},{"removed":"deepswe","score":0.016294584338186233,"rank":302,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.020846423068251015,"rank":302,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.020466953527298857,"rank":302,"remainingConfigurations":444},{"removed":"frontiercode","score":0.020225124710410273,"rank":303,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02053439008182961,"rank":302,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.020586870094762975,"rank":302,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02082921676376284,"rank":302,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.020745334485512298,"rank":302,"remainingConfigurations":444},{"removed":"livebench-math","score":0.020867246386901902,"rank":302,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.020577217984663224,"rank":302,"remainingConfigurations":444},{"removed":"livebench-language","score":0.021200330407503448,"rank":302,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02083793639313862,"rank":302,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02037776617902786,"rank":302,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0206852336907165,"rank":302,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.021362811200289336,"rank":302,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.021477866080525237,"rank":303,"remainingConfigurations":444},{"removed":"frontiermath","score":0.02088166000833747,"rank":302,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01945149454549631,"rank":302,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02199729051005574,"rank":303,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.020755421376758967,"rank":302,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02075222419271468,"rank":302,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.020759466418348648,"rank":302,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.020792664985647965,"rank":302,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0206901357329185,"rank":302,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.020775407755001456,"rank":302,"remainingConfigurations":444}],"sharedOrderConflicts":0},"diffusiongemma-26b-a4b--effort-reasoning":{"score":0.020775337355918685,"rank":303,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02735925484429939,"rank":300,"remainingConfigurations":444},{"removed":"Datacurve","score":0.016217045906651975,"rank":303,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.020533206852694334,"rank":303,"remainingConfigurations":444},{"removed":"Scale","score":0.024588136344256786,"rank":303,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.020543891943351083,"rank":303,"remainingConfigurations":444},{"removed":"Cognition","score":0.020131286274907744,"rank":304,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02169170994559795,"rank":302,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.021369385277442785,"rank":304,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02101295428971237,"rank":294,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01992791338753481,"rank":302,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.020766017126334795,"rank":303,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.020084964569327932,"rank":303,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02073741850618307,"rank":303,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.020775337355918685,"rank":303,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.020948539556755134,"rank":303,"remainingConfigurations":444},{"removed":"All provider reports","score":0.020215579601952548,"rank":303,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.020966219931817156,"rank":303,"remainingConfigurations":444},{"removed":"briefcase","score":0.020590014028289447,"rank":303,"remainingConfigurations":444},{"removed":"aime","score":0.02064974214167456,"rank":304,"remainingConfigurations":444},{"removed":"apex-agents","score":0.021102646175564944,"rank":303,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.024375341772929413,"rank":295,"remainingConfigurations":444},{"removed":"automationbench","score":0.020627320858947387,"rank":304,"remainingConfigurations":444},{"removed":"critpt","score":0.018627981070638792,"rank":309,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.020766249226269257,"rank":303,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02125364429519992,"rank":305,"remainingConfigurations":444},{"removed":"gdpval","score":0.021542768845335403,"rank":300,"remainingConfigurations":444},{"removed":"gmmlu","score":0.020995125117527314,"rank":303,"remainingConfigurations":444},{"removed":"gpqa","score":0.022256148586453497,"rank":298,"remainingConfigurations":444},{"removed":"harvey","score":0.020530248171405252,"rank":303,"remainingConfigurations":444},{"removed":"hle","score":0.021817450344940818,"rank":305,"remainingConfigurations":444},{"removed":"ifbench","score":0.01695021746952881,"rank":314,"remainingConfigurations":444},{"removed":"itbench","score":0.020580654326607953,"rank":303,"remainingConfigurations":444},{"removed":"livecodebench","score":0.020798948251914594,"rank":302,"remainingConfigurations":444},{"removed":"math500","score":0.020932492337992353,"rank":301,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.021577767137019834,"rank":302,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02097974747694775,"rank":307,"remainingConfigurations":444},{"removed":"omniscience","score":0.02055148131834969,"rank":299,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019943747101425765,"rank":302,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.021109424463041798,"rank":303,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.021289316372095357,"rank":303,"remainingConfigurations":444},{"removed":"arc-agi","score":0.026321288777519422,"rank":300,"remainingConfigurations":444},{"removed":"deepswe","score":0.016228353597579747,"rank":303,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.020780798949132085,"rank":303,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0204182971717717,"rank":303,"remainingConfigurations":444},{"removed":"frontiercode","score":0.020131286274907744,"rank":304,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02047079883997028,"rank":303,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0205210454718039,"rank":303,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02076378620170891,"rank":303,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.020679869749642223,"rank":303,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02080118793931818,"rank":303,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.020512699581525403,"rank":303,"remainingConfigurations":444},{"removed":"livebench-language","score":0.021134437696912343,"rank":303,"remainingConfigurations":444},{"removed":"livebench-data","score":0.020772676808818533,"rank":303,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.020312910134923288,"rank":303,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.020619934486240603,"rank":303,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0212952467800929,"rank":303,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.021369385277442785,"rank":304,"remainingConfigurations":444},{"removed":"frontiermath","score":0.020804960715421112,"rank":303,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0193412732025345,"rank":304,"remainingConfigurations":444},{"removed":"simpleqa","score":0.021925076511754422,"rank":304,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.020690159939314407,"rank":303,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.02068704321230058,"rank":303,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.020693818826933424,"rank":303,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.020727433022082076,"rank":303,"remainingConfigurations":444},{"removed":"vibe-code","score":0.020625002856484925,"rank":303,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.020710070238157016,"rank":303,"remainingConfigurations":444}],"sharedOrderConflicts":1},"solar-pro3-260323--effort-reasoning":{"score":0.02061362277214507,"rank":304,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.027080738400901156,"rank":302,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01610071195954023,"rank":305,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.02040182529623455,"rank":305,"remainingConfigurations":444},{"removed":"Scale","score":0.02439392876599587,"rank":304,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.020385853935914175,"rank":305,"remainingConfigurations":444},{"removed":"Cognition","score":0.019963205371597296,"rank":305,"remainingConfigurations":444},{"removed":"LiveBench","score":0.021522472812495922,"rank":303,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.021243766836153814,"rank":305,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02117904124512762,"rank":293,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01979025392898982,"rank":304,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.020604294242636146,"rank":304,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.019926017991518653,"rank":305,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.020575974402938606,"rank":304,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.02061362277214507,"rank":304,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.02078469667437131,"rank":304,"remainingConfigurations":444},{"removed":"All provider reports","score":0.02005481333074844,"rank":305,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.020784430388836626,"rank":304,"remainingConfigurations":444},{"removed":"briefcase","score":0.021177266868039512,"rank":301,"remainingConfigurations":444},{"removed":"aime","score":0.020431880734141584,"rank":305,"remainingConfigurations":444},{"removed":"apex-agents","score":0.020964091473775783,"rank":304,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.021443270272784545,"rank":300,"remainingConfigurations":444},{"removed":"automationbench","score":0.021758808050776762,"rank":301,"remainingConfigurations":444},{"removed":"critpt","score":0.022728122301804977,"rank":300,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.02059710269595436,"rank":305,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.021268637886613272,"rank":304,"remainingConfigurations":444},{"removed":"gdpval","score":0.021492210702107658,"rank":301,"remainingConfigurations":444},{"removed":"gmmlu","score":0.020756022160395068,"rank":304,"remainingConfigurations":444},{"removed":"gpqa","score":0.020244495573207805,"rank":304,"remainingConfigurations":444},{"removed":"harvey","score":0.02036793735575226,"rank":304,"remainingConfigurations":444},{"removed":"hle","score":0.022297740777695668,"rank":304,"remainingConfigurations":444},{"removed":"ifbench","score":0.015815427910110025,"rank":317,"remainingConfigurations":444},{"removed":"itbench","score":0.020408895708441087,"rank":305,"remainingConfigurations":444},{"removed":"livecodebench","score":0.020583834956381327,"rank":304,"remainingConfigurations":444},{"removed":"math500","score":0.020739987162994657,"rank":303,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.021369527963493205,"rank":304,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02239467404743274,"rank":303,"remainingConfigurations":444},{"removed":"omniscience","score":0.019181380383328357,"rank":304,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017996420407163694,"rank":311,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.020947238309496685,"rank":304,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02147161074707501,"rank":302,"remainingConfigurations":444},{"removed":"arc-agi","score":0.026040509834980602,"rank":302,"remainingConfigurations":444},{"removed":"deepswe","score":0.0161122152384118,"rank":305,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.020619141067321538,"rank":304,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.020273520489221226,"rank":305,"remainingConfigurations":444},{"removed":"frontiercode","score":0.019963205371597296,"rank":305,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.020313292578655568,"rank":305,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.020362022686927352,"rank":304,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.020602367283720918,"rank":304,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.02051893415269691,"rank":304,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02063849762590296,"rank":304,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.020354399346320776,"rank":304,"remainingConfigurations":444},{"removed":"livebench-language","score":0.020971756799396793,"rank":304,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02061050361124014,"rank":304,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02015330448173775,"rank":304,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.020459460431081797,"rank":304,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.021128997751049716,"rank":304,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.021243766836153814,"rank":305,"remainingConfigurations":444},{"removed":"frontiermath","score":0.020639912407998375,"rank":304,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.019287062455133456,"rank":305,"remainingConfigurations":444},{"removed":"simpleqa","score":0.021755367803364952,"rank":305,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02052916605817511,"rank":304,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.020526026842218267,"rank":304,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.020532274287620857,"rank":304,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.02056660306202602,"rank":304,"remainingConfigurations":444},{"removed":"vibe-code","score":0.02046438699488783,"rank":304,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.020548916703538565,"rank":304,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m3--effort-non-reasoning":{"score":0.020572967901827808,"rank":305,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.018952162437638694,"rank":182,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.027085165180771333,"rank":301,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01620000622622073,"rank":304,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.020469602910097515,"rank":304,"remainingConfigurations":444},{"removed":"Scale","score":0.024125657381222503,"rank":305,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.020513120366436512,"rank":304,"remainingConfigurations":444},{"removed":"Cognition","score":0.021016844770923002,"rank":301,"remainingConfigurations":444},{"removed":"LiveBench","score":0.021093768776180372,"rank":304,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.021209796427748052,"rank":306,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.019832074933589874,"rank":303,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.02056614237706064,"rank":305,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01994307595543148,"rank":304,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.02054861584866114,"rank":305,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.020572967901827808,"rank":305,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.020725779159411723,"rank":305,"remainingConfigurations":444},{"removed":"All provider reports","score":0.020069445045272267,"rank":304,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02071555113116337,"rank":305,"remainingConfigurations":444},{"removed":"briefcase","score":0.02049867077398998,"rank":304,"remainingConfigurations":444},{"removed":"aime","score":0.03243514138932783,"rank":278,"remainingConfigurations":444},{"removed":"apex-agents","score":0.020854484723201217,"rank":305,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0206736160770182,"rank":304,"remainingConfigurations":444},{"removed":"automationbench","score":0.020508639861307316,"rank":305,"remainingConfigurations":444},{"removed":"critpt","score":0.020032435590210052,"rank":306,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.020601357754984857,"rank":304,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.020827792083992814,"rank":306,"remainingConfigurations":444},{"removed":"gdpval","score":0.020339081838137048,"rank":304,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02075005538693432,"rank":305,"remainingConfigurations":444},{"removed":"gpqa","score":0.008559814313668137,"rank":361,"remainingConfigurations":444},{"removed":"harvey","score":0.020296181712706977,"rank":305,"remainingConfigurations":444},{"removed":"hle","score":0.022439921595437024,"rank":303,"remainingConfigurations":444},{"removed":"ifbench","score":0.020758735581572093,"rank":301,"remainingConfigurations":444},{"removed":"itbench","score":0.020447427569615824,"rank":304,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0206464460355361,"rank":303,"remainingConfigurations":444},{"removed":"math500","score":0.020632145135998328,"rank":304,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.021471623454920794,"rank":303,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02228568841719208,"rank":305,"remainingConfigurations":444},{"removed":"omniscience","score":0.020084184095870858,"rank":301,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019404204125124072,"rank":307,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.020786405848078948,"rank":305,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02048159682591889,"rank":305,"remainingConfigurations":444},{"removed":"arc-agi","score":0.026106151929605286,"rank":301,"remainingConfigurations":444},{"removed":"deepswe","score":0.016213750516050635,"rank":304,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.020577827855224304,"rank":305,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.020288676422765016,"rank":304,"remainingConfigurations":444},{"removed":"frontiercode","score":0.021016844770923002,"rank":301,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.02032066446425511,"rank":304,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.020285702456506703,"rank":305,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.02056599390383353,"rank":305,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.020481585446206305,"rank":305,"remainingConfigurations":444},{"removed":"livebench-math","score":0.02063543055980841,"rank":305,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.020258859175868327,"rank":305,"remainingConfigurations":444},{"removed":"livebench-language","score":0.02091168231497516,"rank":305,"remainingConfigurations":444},{"removed":"livebench-data","score":0.02058788150912218,"rank":305,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.02014086518711246,"rank":305,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.020414815108646282,"rank":305,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.021079158405902045,"rank":305,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.021209796427748052,"rank":306,"remainingConfigurations":444},{"removed":"frontiermath","score":0.020445901547842683,"rank":305,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02016210364121929,"rank":300,"remainingConfigurations":444},{"removed":"simpleqa","score":0.022092549370478467,"rank":302,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.02048317210578692,"rank":305,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.020494571097142075,"rank":305,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.020484905856763123,"rank":305,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.020530490420759214,"rank":305,"remainingConfigurations":444},{"removed":"vibe-code","score":0.020435018090173823,"rank":305,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.020504377948852216,"rank":305,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-26b-a4b-it--effort-non-reasoning":{"score":0.019856432545557415,"rank":306,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.026356545796578295,"rank":303,"remainingConfigurations":444},{"removed":"Datacurve","score":0.015497427788250884,"rank":306,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.019631279994292216,"rank":306,"remainingConfigurations":444},{"removed":"Scale","score":0.02350117342516259,"rank":306,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.019627653037829533,"rank":306,"remainingConfigurations":444},{"removed":"Cognition","score":0.019247575932964837,"rank":306,"remainingConfigurations":444},{"removed":"LiveBench","score":0.020733679148788434,"rank":305,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02040890229841129,"rank":307,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.020088087535657644,"rank":297,"remainingConfigurations":431},{"removed":"Vals AI","score":0.019035274805685034,"rank":305,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.019847533599326457,"rank":306,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.019196371248721124,"rank":306,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01982022372798391,"rank":306,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.019856432545557415,"rank":306,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.020022842955379604,"rank":306,"remainingConfigurations":444},{"removed":"All provider reports","score":0.019322073422154012,"rank":306,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.02004174971404466,"rank":306,"remainingConfigurations":444},{"removed":"briefcase","score":0.019700491181120577,"rank":306,"remainingConfigurations":444},{"removed":"aime","score":0.019951947354349492,"rank":307,"remainingConfigurations":444},{"removed":"apex-agents","score":0.020182613053626577,"rank":306,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.019924433919885402,"rank":306,"remainingConfigurations":444},{"removed":"automationbench","score":0.019719770398110882,"rank":307,"remainingConfigurations":444},{"removed":"critpt","score":0.021993225585892524,"rank":303,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.019857952941771926,"rank":306,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02032248625553745,"rank":307,"remainingConfigurations":444},{"removed":"gdpval","score":0.019794554835194954,"rank":306,"remainingConfigurations":444},{"removed":"gmmlu","score":0.02001025557997221,"rank":306,"remainingConfigurations":444},{"removed":"gpqa","score":0.01967355197680795,"rank":305,"remainingConfigurations":444},{"removed":"harvey","score":0.01962215906951345,"rank":306,"remainingConfigurations":444},{"removed":"hle","score":0.020401719844540592,"rank":311,"remainingConfigurations":444},{"removed":"ifbench","score":0.018796015854538137,"rank":306,"remainingConfigurations":444},{"removed":"itbench","score":0.019658160029455234,"rank":306,"remainingConfigurations":444},{"removed":"livecodebench","score":0.019985567836585446,"rank":306,"remainingConfigurations":444},{"removed":"math500","score":0.020036008675565813,"rank":306,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.020694095490878944,"rank":306,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01985119520746063,"rank":311,"remainingConfigurations":444},{"removed":"omniscience","score":0.02005157119395427,"rank":302,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019587463026933438,"rank":304,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.020177797978064734,"rank":306,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.018233306967479306,"rank":313,"remainingConfigurations":444},{"removed":"arc-agi","score":0.025332274028055407,"rank":303,"remainingConfigurations":444},{"removed":"deepswe","score":0.015508150117196142,"rank":306,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.019861627041906946,"rank":306,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.019508212086641767,"rank":306,"remainingConfigurations":444},{"removed":"frontiercode","score":0.019247575932964837,"rank":306,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01956407555434833,"rank":306,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.019613214029606786,"rank":306,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.019845316958723755,"rank":306,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01976507675467859,"rank":306,"remainingConfigurations":444},{"removed":"livebench-math","score":0.019881284036969954,"rank":306,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.019604530793045062,"rank":306,"remainingConfigurations":444},{"removed":"livebench-language","score":0.020199749424659633,"rank":306,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01985395857851359,"rank":306,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.019414100736905682,"rank":306,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.019707584723778353,"rank":306,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.02035475783209749,"rank":306,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02040890229841129,"rank":307,"remainingConfigurations":444},{"removed":"frontiermath","score":0.019858932791849755,"rank":306,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01845669445551171,"rank":306,"remainingConfigurations":444},{"removed":"simpleqa","score":0.020957971839790396,"rank":306,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.019774898265215297,"rank":306,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01977173986829547,"rank":306,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01977859490292417,"rank":306,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.019810277745700173,"rank":306,"remainingConfigurations":444},{"removed":"vibe-code","score":0.019712403914827172,"rank":306,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01979395276431899,"rank":306,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-small-4--effort-reasoning":{"score":0.019515233566960808,"rank":307,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.025670592652425384,"rank":305,"remainingConfigurations":444},{"removed":"Datacurve","score":0.015222661016499953,"rank":307,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.019308769398997654,"rank":307,"remainingConfigurations":444},{"removed":"Scale","score":0.023141210750423403,"rank":307,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.019294691503851755,"rank":307,"remainingConfigurations":444},{"removed":"Cognition","score":0.018868067918191865,"rank":307,"remainingConfigurations":444},{"removed":"LiveBench","score":0.020377846842174724,"rank":306,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.020082032597835798,"rank":308,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02009284005159268,"rank":296,"remainingConfigurations":431},{"removed":"Vals AI","score":0.018720665399813093,"rank":306,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01950634914822251,"rank":307,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.018861454757963438,"rank":307,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.019479328838586867,"rank":307,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.019515233566960808,"rank":307,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.019677615259172918,"rank":307,"remainingConfigurations":444},{"removed":"All provider reports","score":0.018983488284380512,"rank":307,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.019905798309259818,"rank":307,"remainingConfigurations":444},{"removed":"briefcase","score":0.01935628370804127,"rank":307,"remainingConfigurations":444},{"removed":"aime","score":0.019448611634134975,"rank":309,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01984932082337042,"rank":307,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.018950861237758455,"rank":307,"remainingConfigurations":444},{"removed":"automationbench","score":0.019795706660171688,"rank":306,"remainingConfigurations":444},{"removed":"critpt","score":0.01816127725405283,"rank":311,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.019493439756145838,"rank":307,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.02229791099251473,"rank":300,"remainingConfigurations":444},{"removed":"gdpval","score":0.019776789566778592,"rank":307,"remainingConfigurations":444},{"removed":"gmmlu","score":0.019650741970147687,"rank":307,"remainingConfigurations":444},{"removed":"gpqa","score":0.01813545498731411,"rank":309,"remainingConfigurations":444},{"removed":"harvey","score":0.019286088659904138,"rank":307,"remainingConfigurations":444},{"removed":"hle","score":0.021448742384674712,"rank":308,"remainingConfigurations":444},{"removed":"ifbench","score":0.01790658733933815,"rank":309,"remainingConfigurations":444},{"removed":"itbench","score":0.019313104418073625,"rank":307,"remainingConfigurations":444},{"removed":"livecodebench","score":0.019600061878940447,"rank":307,"remainingConfigurations":444},{"removed":"math500","score":0.019701514402429728,"rank":307,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.020354546127649215,"rank":308,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02231180991783069,"rank":304,"remainingConfigurations":444},{"removed":"omniscience","score":0.017021746873165843,"rank":310,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019794443248172578,"rank":303,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.019838170435638496,"rank":307,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.019249549354192676,"rank":308,"remainingConfigurations":444},{"removed":"arc-agi","score":0.024685218673362982,"rank":306,"remainingConfigurations":444},{"removed":"deepswe","score":0.01523349581904706,"rank":307,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.019520457400704853,"rank":307,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.019194114417615416,"rank":307,"remainingConfigurations":444},{"removed":"frontiercode","score":0.018868067918191865,"rank":307,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.019229420909423395,"rank":307,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.019275751153410122,"rank":307,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.019504570759192638,"rank":307,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.019425503498968214,"rank":307,"remainingConfigurations":444},{"removed":"livebench-math","score":0.019538814971154853,"rank":307,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.019269099090825807,"rank":307,"remainingConfigurations":444},{"removed":"livebench-language","score":0.019854805381986872,"rank":307,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01951239270633495,"rank":307,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01907841813601596,"rank":307,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.019369094096232043,"rank":307,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.020004632669580847,"rank":307,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.020082032597835798,"rank":308,"remainingConfigurations":444},{"removed":"frontiermath","score":0.019537220815722647,"rank":307,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.018248444312614912,"rank":307,"remainingConfigurations":444},{"removed":"simpleqa","score":0.02059824027571738,"rank":307,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.019435355598838532,"rank":307,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.019432040341958497,"rank":307,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.019438048728161992,"rank":307,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.019470520255438432,"rank":307,"remainingConfigurations":444},{"removed":"vibe-code","score":0.019373680807247443,"rank":307,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.019453727713015092,"rank":307,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m1-80k--effort-reasoning":{"score":0.019232218562264383,"rank":308,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.025371253369243684,"rank":307,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01501397963915557,"rank":308,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.018975940028176812,"rank":308,"remainingConfigurations":444},{"removed":"Scale","score":0.022779942902194688,"rank":308,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.019014191801324264,"rank":308,"remainingConfigurations":444},{"removed":"Cognition","score":0.018667292727648513,"rank":308,"remainingConfigurations":444},{"removed":"LiveBench","score":0.02006927185223476,"rank":307,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.019812233630481794,"rank":309,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.019535592611151578,"rank":298,"remainingConfigurations":431},{"removed":"Vals AI","score":0.018446338368919003,"rank":307,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.019223627501067757,"rank":308,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.018593200369358173,"rank":308,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.019197311202801222,"rank":308,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.019232218562264383,"rank":308,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01939216678837263,"rank":308,"remainingConfigurations":444},{"removed":"All provider reports","score":0.018713960434294668,"rank":308,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.019409307005428093,"rank":308,"remainingConfigurations":444},{"removed":"briefcase","score":0.019125312736150604,"rank":309,"remainingConfigurations":444},{"removed":"aime","score":0.019832070868263624,"rank":308,"remainingConfigurations":444},{"removed":"apex-agents","score":0.019549435969390044,"rank":308,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01801689359047644,"rank":312,"remainingConfigurations":444},{"removed":"automationbench","score":0.019130993749645678,"rank":309,"remainingConfigurations":444},{"removed":"critpt","score":0.020284161977516126,"rank":305,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01923415531037832,"rank":308,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.019711442595801175,"rank":308,"remainingConfigurations":444},{"removed":"gdpval","score":0.01930330234901226,"rank":308,"remainingConfigurations":444},{"removed":"gmmlu","score":0.019458302690628513,"rank":308,"remainingConfigurations":444},{"removed":"gpqa","score":0.01925733252247883,"rank":307,"remainingConfigurations":444},{"removed":"harvey","score":0.019010153778872982,"rank":308,"remainingConfigurations":444},{"removed":"hle","score":0.021498826568983307,"rank":307,"remainingConfigurations":444},{"removed":"ifbench","score":0.019132654888695155,"rank":304,"remainingConfigurations":444},{"removed":"itbench","score":0.01905835938408994,"rank":308,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01813655780073187,"rank":309,"remainingConfigurations":444},{"removed":"math500","score":0.01789336188504963,"rank":311,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.018976213530333255,"rank":310,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.020999338925898406,"rank":306,"remainingConfigurations":444},{"removed":"omniscience","score":0.015651624131142277,"rank":316,"remainingConfigurations":444},{"removed":"tau-bench","score":0.019434207515796168,"rank":306,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01954518451935036,"rank":308,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.022066560540761407,"rank":300,"remainingConfigurations":444},{"removed":"arc-agi","score":0.024397636267816155,"rank":307,"remainingConfigurations":444},{"removed":"deepswe","score":0.015024512380841232,"rank":308,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.019237272866072155,"rank":308,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.018886239828659588,"rank":308,"remainingConfigurations":444},{"removed":"frontiercode","score":0.018667292727648513,"rank":308,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01894775151626471,"rank":308,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01899596176909397,"rank":308,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.019221551573213168,"rank":308,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.019144026196761806,"rank":308,"remainingConfigurations":444},{"removed":"livebench-math","score":0.019256526054272607,"rank":308,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01898811014840306,"rank":308,"remainingConfigurations":444},{"removed":"livebench-language","score":0.019565099144336264,"rank":308,"remainingConfigurations":444},{"removed":"livebench-data","score":0.019229569354006,"rank":308,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01880334645996555,"rank":308,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01908795883876074,"rank":308,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01971519251939979,"rank":308,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.019812233630481794,"rank":309,"remainingConfigurations":444},{"removed":"frontiermath","score":0.019271657345918437,"rank":308,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.017912989365288172,"rank":308,"remainingConfigurations":444},{"removed":"simpleqa","score":0.020306092637353338,"rank":308,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.019152992540328664,"rank":308,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.019150094942403936,"rank":308,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.019156734289009106,"rank":308,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.019187557796611302,"rank":308,"remainingConfigurations":444},{"removed":"vibe-code","score":0.019092619973774483,"rank":308,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01917159651538875,"rank":308,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.5-air--effort-reasoning":{"score":0.018882664271900038,"rank":309,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.024924382342560118,"rank":308,"remainingConfigurations":444},{"removed":"Datacurve","score":0.014739635198275529,"rank":309,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01864050233497368,"rank":309,"remainingConfigurations":444},{"removed":"Scale","score":0.02236572115797669,"rank":309,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.018668378052588294,"rank":309,"remainingConfigurations":444},{"removed":"Cognition","score":0.018328920444826233,"rank":309,"remainingConfigurations":444},{"removed":"LiveBench","score":0.019705725000005055,"rank":308,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.019445878450683202,"rank":310,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01921556258763724,"rank":299,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01811127129361992,"rank":308,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.018874224096662954,"rank":309,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.018254877707364812,"rank":309,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0188483752842012,"rank":309,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.018882664271900038,"rank":309,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.019039767059694172,"rank":309,"remainingConfigurations":444},{"removed":"All provider reports","score":0.018373482064954868,"rank":309,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.019058276954611188,"rank":309,"remainingConfigurations":444},{"removed":"briefcase","score":0.01876386279610708,"rank":310,"remainingConfigurations":444},{"removed":"aime","score":0.017408613372770842,"rank":315,"remainingConfigurations":444},{"removed":"apex-agents","score":0.019194474053226163,"rank":309,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.018463627583778824,"rank":308,"remainingConfigurations":444},{"removed":"automationbench","score":0.01877776245373993,"rank":310,"remainingConfigurations":444},{"removed":"critpt","score":0.019880955625211926,"rank":307,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.018882505888268567,"rank":309,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01933604032738246,"rank":309,"remainingConfigurations":444},{"removed":"gdpval","score":0.018948216829879527,"rank":309,"remainingConfigurations":444},{"removed":"gmmlu","score":0.019121461568586847,"rank":309,"remainingConfigurations":444},{"removed":"gpqa","score":0.01831079532983643,"rank":308,"remainingConfigurations":444},{"removed":"harvey","score":0.01866267298509783,"rank":309,"remainingConfigurations":444},{"removed":"hle","score":0.02158104604524662,"rank":306,"remainingConfigurations":444},{"removed":"ifbench","score":0.020018830596017903,"rank":303,"remainingConfigurations":444},{"removed":"itbench","score":0.01871599821420662,"rank":310,"remainingConfigurations":444},{"removed":"livecodebench","score":0.018376922610808175,"rank":308,"remainingConfigurations":444},{"removed":"math500","score":0.018985140115581087,"rank":308,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01886268326798352,"rank":311,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.02062783627560489,"rank":308,"remainingConfigurations":444},{"removed":"omniscience","score":0.017546031198139595,"rank":306,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01804685023671122,"rank":310,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.019188226919546705,"rank":309,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.018126998580998397,"rank":314,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02396718802116385,"rank":308,"remainingConfigurations":444},{"removed":"deepswe","score":0.01474997823797513,"rank":309,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.018887629505967465,"rank":309,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01854280677277717,"rank":309,"remainingConfigurations":444},{"removed":"frontiercode","score":0.018328920444826233,"rank":309,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.018603167648431524,"rank":309,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01865060549595043,"rank":309,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01887219992690058,"rank":309,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.018796047045423214,"rank":309,"remainingConfigurations":444},{"removed":"livebench-math","score":0.018906548026850625,"rank":309,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.018642791876729927,"rank":309,"remainingConfigurations":444},{"removed":"livebench-language","score":0.019209720309928065,"rank":309,"remainingConfigurations":444},{"removed":"livebench-data","score":0.018880087933631096,"rank":309,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.018461305475436753,"rank":309,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01874091938884664,"rank":309,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.019357234804042615,"rank":309,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.019445878450683202,"rank":310,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01892141384609187,"rank":309,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01757951726851228,"rank":309,"remainingConfigurations":444},{"removed":"simpleqa","score":0.019937932867512723,"rank":309,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.018804824122295626,"rank":309,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.018801974315217705,"rank":309,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0188085058472197,"rank":309,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01883877171076641,"rank":309,"remainingConfigurations":444},{"removed":"vibe-code","score":0.018745505531952922,"rank":309,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01882310423838209,"rank":309,"remainingConfigurations":444}],"sharedOrderConflicts":0},"o3-mini--effort-reasoning":{"score":0.018721271632127022,"rank":310,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.024743308834244998,"rank":309,"remainingConfigurations":444},{"removed":"Datacurve","score":0.014614707318994278,"rank":310,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.018480000250271106,"rank":310,"remainingConfigurations":444},{"removed":"Scale","score":0.022159627759347298,"rank":310,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01850857839347814,"rank":310,"remainingConfigurations":444},{"removed":"Cognition","score":0.0181696877122208,"rank":310,"remainingConfigurations":444},{"removed":"LiveBench","score":0.019539167534533913,"rank":309,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.019268037096141288,"rank":311,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.018905684269324954,"rank":300,"remainingConfigurations":431},{"removed":"Vals AI","score":0.017954166164835327,"rank":309,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0187129012622894,"rank":310,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01809857743710463,"rank":310,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01868729034401054,"rank":310,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.018721271632127022,"rank":310,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.018877352680013417,"rank":310,"remainingConfigurations":444},{"removed":"All provider reports","score":0.018216484112949367,"rank":310,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01889486264654869,"rank":310,"remainingConfigurations":444},{"removed":"briefcase","score":0.018607960376998623,"rank":311,"remainingConfigurations":444},{"removed":"aime","score":0.018745930739441443,"rank":311,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01903149055127886,"rank":310,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.018450527041299056,"rank":309,"remainingConfigurations":444},{"removed":"automationbench","score":0.01862339610580303,"rank":311,"remainingConfigurations":444},{"removed":"critpt","score":0.01800730947435116,"rank":312,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01873088138840258,"rank":311,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.019176211564448997,"rank":310,"remainingConfigurations":444},{"removed":"gdpval","score":0.01872609336128844,"rank":310,"remainingConfigurations":444},{"removed":"gmmlu","score":0.018853829402273554,"rank":310,"remainingConfigurations":444},{"removed":"gpqa","score":0.017063748655907766,"rank":314,"remainingConfigurations":444},{"removed":"harvey","score":0.01850310713795337,"rank":310,"remainingConfigurations":444},{"removed":"hle","score":0.020930813100778697,"rank":309,"remainingConfigurations":444},{"removed":"ifbench","score":0.018111670955419167,"rank":308,"remainingConfigurations":444},{"removed":"itbench","score":0.018549439566612726,"rank":311,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01649065168021802,"rank":319,"remainingConfigurations":444},{"removed":"math500","score":0.017691186982653293,"rank":313,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.02050061247989437,"rank":307,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.020341742705151312,"rank":309,"remainingConfigurations":444},{"removed":"omniscience","score":0.01650873220764711,"rank":313,"remainingConfigurations":444},{"removed":"tau-bench","score":0.020964728991710323,"rank":299,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0190248788210213,"rank":310,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.02101195527084676,"rank":304,"remainingConfigurations":444},{"removed":"arc-agi","score":0.023788002106945594,"rank":309,"remainingConfigurations":444},{"removed":"deepswe","score":0.014624907703985971,"rank":310,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01872618437374571,"rank":310,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.018381407468637995,"rank":310,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0181696877122208,"rank":310,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.018445308580623085,"rank":310,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.018491566073470005,"rank":310,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.018710847672950507,"rank":310,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.018635291121128512,"rank":310,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01874503120487678,"rank":310,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01848322739936185,"rank":310,"remainingConfigurations":444},{"removed":"livebench-language","score":0.019045433147100714,"rank":310,"remainingConfigurations":444},{"removed":"livebench-data","score":0.018718810636112974,"rank":310,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.018303430066073652,"rank":310,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.018580670640384784,"rank":310,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.019192141899373728,"rank":310,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.019268037096141288,"rank":311,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0187247238839492,"rank":310,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.017380840040933175,"rank":310,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01976858382295671,"rank":310,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.018644057676149968,"rank":310,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.018641206086939473,"rank":310,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01864782039361976,"rank":310,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.018677622960301718,"rank":310,"remainingConfigurations":444},{"removed":"vibe-code","score":0.018585160965914917,"rank":310,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.018662220183041554,"rank":310,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-oss-120b--effort-high":{"score":0.018381497384409726,"rank":311,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.003595751493692662,"rank":197,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.023699233667866554,"rank":311,"remainingConfigurations":444},{"removed":"Datacurve","score":0.014265079665616699,"rank":311,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01827877763408327,"rank":311,"remainingConfigurations":444},{"removed":"Scale","score":0.021742308209507996,"rank":311,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01815271858710939,"rank":311,"remainingConfigurations":444},{"removed":"Cognition","score":0.017930886962644044,"rank":312,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01898290974128672,"rank":310,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.02820918218241934,"rank":286,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.026817151937959097,"rank":279,"remainingConfigurations":431},{"removed":"Vals AI","score":0.017515572280551395,"rank":310,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.018374089193224297,"rank":311,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.017789807655252798,"rank":311,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.018352179857189458,"rank":311,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.018381497384409726,"rank":311,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01853071505030074,"rank":311,"remainingConfigurations":444},{"removed":"All provider reports","score":0.017906251522161465,"rank":311,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01853150062538104,"rank":311,"remainingConfigurations":444},{"removed":"briefcase","score":0.019280386233117765,"rank":308,"remainingConfigurations":444},{"removed":"aime","score":0.017472631800377104,"rank":314,"remainingConfigurations":444},{"removed":"apex-agents","score":0.018876412755249542,"rank":311,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01838738925332157,"rank":311,"remainingConfigurations":444},{"removed":"automationbench","score":0.019255023856563157,"rank":308,"remainingConfigurations":444},{"removed":"critpt","score":0.017831538469456173,"rank":314,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0187856658956571,"rank":310,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.018654462211948417,"rank":312,"remainingConfigurations":444},{"removed":"gdpval","score":0.018367500544882415,"rank":311,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01834268963865418,"rank":311,"remainingConfigurations":444},{"removed":"gpqa","score":0.017344462697643503,"rank":311,"remainingConfigurations":444},{"removed":"harvey","score":0.018145967867534463,"rank":311,"remainingConfigurations":444},{"removed":"hle","score":0.019798096568449792,"rank":313,"remainingConfigurations":444},{"removed":"ifbench","score":0.017099605654874728,"rank":313,"remainingConfigurations":444},{"removed":"itbench","score":0.018752382824977713,"rank":309,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01759578444582635,"rank":312,"remainingConfigurations":444},{"removed":"math500","score":0.018469020429861618,"rank":309,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.019408905978325255,"rank":309,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.020077972977933334,"rank":310,"remainingConfigurations":444},{"removed":"omniscience","score":0.017117038127456942,"rank":308,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017779979935917897,"rank":313,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.018621865306023354,"rank":311,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.01854098568109759,"rank":311,"remainingConfigurations":444},{"removed":"arc-agi","score":0.022823882625435984,"rank":311,"remainingConfigurations":444},{"removed":"deepswe","score":0.014274858274891057,"rank":311,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.018386047389034755,"rank":311,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.017984223162783777,"rank":311,"remainingConfigurations":444},{"removed":"frontiercode","score":0.017930886962644044,"rank":312,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.018124231653759513,"rank":311,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01813916179058964,"rank":311,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.018373281693331234,"rank":311,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0182977012756198,"rank":311,"remainingConfigurations":444},{"removed":"livebench-math","score":0.018408722831200718,"rank":311,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01814591515352977,"rank":311,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01868814400843143,"rank":311,"remainingConfigurations":444},{"removed":"livebench-data","score":0.018379907096225247,"rank":311,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.017976707300909386,"rank":311,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01823995293230091,"rank":311,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01885007580060315,"rank":311,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.02820918218241934,"rank":286,"remainingConfigurations":444},{"removed":"frontiermath","score":0.017941529710646012,"rank":311,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.02457412794207245,"rank":286,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01938591386009383,"rank":311,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01830356073421356,"rank":311,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01830338003780972,"rank":311,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.018309965548031243,"rank":311,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0183373206471452,"rank":311,"remainingConfigurations":444},{"removed":"vibe-code","score":0.018248035000487623,"rank":311,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01832386103921078,"rank":311,"remainingConfigurations":444}],"sharedOrderConflicts":2},"qwen3-vl-235b-a22b-instruct--effort-non-reasoning":{"score":0.01788232469423187,"rank":312,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.023623299744247126,"rank":312,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0139527697128684,"rank":312,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.017652070720097987,"rank":313,"remainingConfigurations":444},{"removed":"Scale","score":0.02118904087264636,"rank":312,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01767845529342825,"rank":312,"remainingConfigurations":444},{"removed":"Cognition","score":0.017357082718880815,"rank":313,"remainingConfigurations":444},{"removed":"LiveBench","score":0.018670726507498344,"rank":311,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.018415877417083885,"rank":312,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.018157003253749183,"rank":301,"remainingConfigurations":431},{"removed":"Vals AI","score":0.017150101369212085,"rank":311,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.017874312523062874,"rank":312,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01728640031982974,"rank":312,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01784971622273944,"rank":312,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01788232469423187,"rank":312,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01803144406250418,"rank":312,"remainingConfigurations":444},{"removed":"All provider reports","score":0.017398897823650658,"rank":312,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01805126501567192,"rank":312,"remainingConfigurations":444},{"removed":"briefcase","score":0.017774336391937456,"rank":313,"remainingConfigurations":444},{"removed":"aime","score":0.01736526754426535,"rank":316,"remainingConfigurations":444},{"removed":"apex-agents","score":0.018177143762796836,"rank":312,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.018429430592643098,"rank":310,"remainingConfigurations":444},{"removed":"automationbench","score":0.017785847796533298,"rank":312,"remainingConfigurations":444},{"removed":"critpt","score":0.018771533904210668,"rank":308,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.017887359763865737,"rank":312,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01833012298669282,"rank":313,"remainingConfigurations":444},{"removed":"gdpval","score":0.01794297941206091,"rank":313,"remainingConfigurations":444},{"removed":"gmmlu","score":0.018090980651685972,"rank":313,"remainingConfigurations":444},{"removed":"gpqa","score":0.017617889686197104,"rank":310,"remainingConfigurations":444},{"removed":"harvey","score":0.01767491949038598,"rank":312,"remainingConfigurations":444},{"removed":"hle","score":0.020620871570546827,"rank":310,"remainingConfigurations":444},{"removed":"ifbench","score":0.017457929897931376,"rank":312,"remainingConfigurations":444},{"removed":"itbench","score":0.017721849645627074,"rank":312,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01797232191373021,"rank":310,"remainingConfigurations":444},{"removed":"math500","score":0.018001723213156955,"rank":310,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01705395860574887,"rank":318,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.018126350184802003,"rank":315,"remainingConfigurations":444},{"removed":"omniscience","score":0.015110695988459745,"rank":317,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01774940472271722,"rank":314,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.018174023159860126,"rank":312,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.01887044912060858,"rank":310,"remainingConfigurations":444},{"removed":"arc-agi","score":0.022711747858924186,"rank":312,"remainingConfigurations":444},{"removed":"deepswe","score":0.013962548039497485,"rank":312,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01788702880322016,"rank":312,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.017561744214984163,"rank":312,"remainingConfigurations":444},{"removed":"frontiercode","score":0.017357082718880815,"rank":313,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.017617096596551852,"rank":312,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01766225257715756,"rank":312,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.017872412077607352,"rank":312,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01780014294368137,"rank":312,"remainingConfigurations":444},{"removed":"livebench-math","score":0.017904953838733362,"rank":312,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.017654764120457588,"rank":312,"remainingConfigurations":444},{"removed":"livebench-language","score":0.018192685334428426,"rank":312,"remainingConfigurations":444},{"removed":"livebench-data","score":0.017879847430249646,"rank":312,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.017482516909910602,"rank":312,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.017747827515957642,"rank":312,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0183327228067712,"rank":312,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.018415877417083885,"rank":312,"remainingConfigurations":444},{"removed":"frontiermath","score":0.017919451848631068,"rank":312,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.016648352428882435,"rank":311,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01888263187443515,"rank":312,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.017808495013519006,"rank":312,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.017805742582065926,"rank":312,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01781198480026045,"rank":312,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01784060724230185,"rank":312,"remainingConfigurations":444},{"removed":"vibe-code","score":0.017752167012412185,"rank":312,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.017825821593311707,"rank":312,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-flash-lite--effort-low":{"score":0.017768073338641256,"rank":313,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.016096369349636933,"rank":184,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02242681340429756,"rank":315,"remainingConfigurations":444},{"removed":"Datacurve","score":0.013919734708776313,"rank":313,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.017677184578830128,"rank":312,"remainingConfigurations":444},{"removed":"Scale","score":0.020865947585059316,"rank":313,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.017650990816989905,"rank":313,"remainingConfigurations":444},{"removed":"Cognition","score":0.01803686347091739,"rank":311,"remainingConfigurations":444},{"removed":"LiveBench","score":0.018031894677467693,"rank":314,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.018179553570509623,"rank":313,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01696939538083557,"rank":312,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.017761845465423504,"rank":313,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01722022909935863,"rank":313,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.017747514386279847,"rank":313,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.017768073338641256,"rank":313,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.017899821011610008,"rank":313,"remainingConfigurations":444},{"removed":"All provider reports","score":0.017329335104438886,"rank":313,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01789388679785528,"rank":313,"remainingConfigurations":444},{"removed":"briefcase","score":0.017702585309193854,"rank":314,"remainingConfigurations":444},{"removed":"aime","score":0.02114648561048517,"rank":303,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01801714110418193,"rank":313,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.017907143828487102,"rank":313,"remainingConfigurations":444},{"removed":"automationbench","score":0.01772212468379618,"rank":313,"remainingConfigurations":444},{"removed":"critpt","score":0.017407462666881812,"rank":316,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01778788407138233,"rank":313,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.018006671038907174,"rank":314,"remainingConfigurations":444},{"removed":"gdpval","score":0.017570369386498665,"rank":314,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01796721253753131,"rank":314,"remainingConfigurations":444},{"removed":"gpqa","score":0.015788902220068974,"rank":320,"remainingConfigurations":444},{"removed":"harvey","score":0.01752622107852694,"rank":313,"remainingConfigurations":444},{"removed":"hle","score":0.019375296524657335,"rank":314,"remainingConfigurations":444},{"removed":"ifbench","score":0.017812811803953273,"rank":311,"remainingConfigurations":444},{"removed":"itbench","score":0.017651120778927006,"rank":313,"remainingConfigurations":444},{"removed":"livecodebench","score":0.017813008853987403,"rank":311,"remainingConfigurations":444},{"removed":"math500","score":0.017812497294760393,"rank":312,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.018596152452310284,"rank":312,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.019264066920514904,"rank":312,"remainingConfigurations":444},{"removed":"omniscience","score":0.01729783790353046,"rank":307,"remainingConfigurations":444},{"removed":"tau-bench","score":0.016666411405019937,"rank":318,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.017955189557831038,"rank":313,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.017641325216959228,"rank":315,"remainingConfigurations":444},{"removed":"arc-agi","score":0.021655805973921805,"rank":315,"remainingConfigurations":444},{"removed":"deepswe","score":0.013932019519618458,"rank":313,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.017772357068024155,"rank":313,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01747366920437551,"rank":313,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01803686347091739,"rank":311,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01754199901897082,"rank":313,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.017528593896947848,"rank":313,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.017760646242115805,"rank":313,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.017686636963505753,"rank":313,"remainingConfigurations":444},{"removed":"livebench-math","score":0.017824642133854283,"rank":313,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.017491347840385613,"rank":313,"remainingConfigurations":444},{"removed":"livebench-language","score":0.018064497496173886,"rank":313,"remainingConfigurations":444},{"removed":"livebench-data","score":0.017779372756579998,"rank":313,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.017394427992405773,"rank":313,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.017629319663846465,"rank":313,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.018208294259869796,"rank":313,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.018179553570509623,"rank":313,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01586056743690863,"rank":322,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012326684866020086,"rank":332,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0187998757561962,"rank":313,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.017690286782688993,"rank":313,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.017700262315338947,"rank":313,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01769149437335749,"rank":313,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.017732027277294837,"rank":313,"remainingConfigurations":444},{"removed":"vibe-code","score":0.017648152275595557,"rank":313,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0177077348642686,"rank":313,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-30b-a3b-thinking-2507--effort-reasoning":{"score":0.01742053049610111,"rank":314,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.022917600517602863,"rank":313,"remainingConfigurations":444},{"removed":"Datacurve","score":0.013587377160791185,"rank":314,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.017204826758071567,"rank":314,"remainingConfigurations":444},{"removed":"Scale","score":0.020646570679105972,"rank":314,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.017219393272169144,"rank":314,"remainingConfigurations":444},{"removed":"Cognition","score":0.01688016465914025,"rank":314,"remainingConfigurations":444},{"removed":"LiveBench","score":0.018188876084254353,"rank":312,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.017945559852876766,"rank":314,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01782856799953968,"rank":303,"remainingConfigurations":431},{"removed":"Vals AI","score":0.016713317179102773,"rank":313,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01741266729175998,"rank":314,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01683744342854317,"rank":314,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.017388678967253626,"rank":314,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01742053049610111,"rank":314,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0175654835970583,"rank":314,"remainingConfigurations":444},{"removed":"All provider reports","score":0.016946626412525364,"rank":314,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01758833625484444,"rank":314,"remainingConfigurations":444},{"removed":"briefcase","score":0.01779285964304321,"rank":312,"remainingConfigurations":444},{"removed":"aime","score":0.017814707221454194,"rank":312,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01772805570812892,"rank":314,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01614983363532194,"rank":317,"remainingConfigurations":444},{"removed":"automationbench","score":0.01767571135379618,"rank":314,"remainingConfigurations":444},{"removed":"critpt","score":0.015940320105150375,"rank":321,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.017433897961849607,"rank":314,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.018846280163964238,"rank":311,"remainingConfigurations":444},{"removed":"gdpval","score":0.01821288724368796,"rank":312,"remainingConfigurations":444},{"removed":"gmmlu","score":0.017587727877836013,"rank":316,"remainingConfigurations":444},{"removed":"gpqa","score":0.01716234336289569,"rank":313,"remainingConfigurations":444},{"removed":"harvey","score":0.017215544700200935,"rank":314,"remainingConfigurations":444},{"removed":"hle","score":0.018940637912873377,"rank":316,"remainingConfigurations":444},{"removed":"ifbench","score":0.015856572763425236,"rank":316,"remainingConfigurations":444},{"removed":"itbench","score":0.01726862490834717,"rank":314,"remainingConfigurations":444},{"removed":"livecodebench","score":0.016608811171948908,"rank":318,"remainingConfigurations":444},{"removed":"math500","score":0.01668755540282896,"rank":317,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.017971635645437703,"rank":315,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.019026027817390233,"rank":313,"remainingConfigurations":444},{"removed":"omniscience","score":0.016226301650290098,"rank":314,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017743160335198575,"rank":315,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.017703217602450333,"rank":314,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.018495589621749107,"rank":312,"remainingConfigurations":444},{"removed":"arc-agi","score":0.022043469214714017,"rank":313,"remainingConfigurations":444},{"removed":"deepswe","score":0.013597051951526473,"rank":314,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0174251894341076,"rank":314,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01711714360558513,"rank":314,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01688016465914025,"rank":314,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.017162730881443232,"rank":314,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.017205875973868707,"rank":314,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.017411070397601057,"rank":314,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.017340779978698047,"rank":314,"remainingConfigurations":444},{"removed":"livebench-math","score":0.017442123426445254,"rank":314,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01719957896259498,"rank":314,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0177243040002331,"rank":314,"remainingConfigurations":444},{"removed":"livebench-data","score":0.017417853207293648,"rank":314,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01702982663342934,"rank":314,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.017289424975530193,"rank":314,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01785919600972855,"rank":314,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.017945559852876766,"rank":314,"remainingConfigurations":444},{"removed":"frontiermath","score":0.017445893089689024,"rank":313,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01625198357612849,"rank":312,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01839634409455082,"rank":314,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01734852623334084,"rank":314,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01734596376500618,"rank":314,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.017351664114079252,"rank":314,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.017380241041939005,"rank":314,"remainingConfigurations":444},{"removed":"vibe-code","score":0.017293640810496575,"rank":314,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.017365465924938834,"rank":314,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-coder-next--effort-non-reasoning":{"score":0.01736851356285756,"rank":315,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.022856615451242884,"rank":314,"remainingConfigurations":444},{"removed":"Datacurve","score":0.013543192770123507,"rank":315,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01717998856987804,"rank":315,"remainingConfigurations":444},{"removed":"Scale","score":0.020630253468185974,"rank":315,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.017167842466450124,"rank":315,"remainingConfigurations":444},{"removed":"Cognition","score":0.01681512302510158,"rank":315,"remainingConfigurations":444},{"removed":"LiveBench","score":0.018138945404461267,"rank":313,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01789829913751663,"rank":315,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.017895367911889767,"rank":302,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01666621910749563,"rank":314,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.017360638300624075,"rank":315,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01678646054874646,"rank":315,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01733664810302669,"rank":315,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01736851356285756,"rank":315,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.017513139926538843,"rank":315,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01689528518697167,"rank":315,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.017541359198669053,"rank":315,"remainingConfigurations":444},{"removed":"briefcase","score":0.016702460520695035,"rank":316,"remainingConfigurations":444},{"removed":"aime","score":0.017284224546089164,"rank":318,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01769167140560369,"rank":315,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01675401278435756,"rank":314,"remainingConfigurations":444},{"removed":"automationbench","score":0.01718638594609,"rank":316,"remainingConfigurations":444},{"removed":"critpt","score":0.01847098874202309,"rank":310,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.017378741453451665,"rank":315,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.017429224214341135,"rank":315,"remainingConfigurations":444},{"removed":"gdpval","score":0.01673664300736649,"rank":316,"remainingConfigurations":444},{"removed":"gmmlu","score":0.018156767779725903,"rank":312,"remainingConfigurations":444},{"removed":"gpqa","score":0.016558974800454745,"rank":316,"remainingConfigurations":444},{"removed":"harvey","score":0.017162624887685666,"rank":315,"remainingConfigurations":444},{"removed":"hle","score":0.018741391603137866,"rank":317,"remainingConfigurations":444},{"removed":"ifbench","score":0.018577881913556565,"rank":307,"remainingConfigurations":444},{"removed":"itbench","score":0.017221108569113717,"rank":315,"remainingConfigurations":444},{"removed":"livecodebench","score":0.017422529027578623,"rank":313,"remainingConfigurations":444},{"removed":"math500","score":0.017505741354217223,"rank":314,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.018109985494297806,"rank":314,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.018996221619842792,"rank":314,"remainingConfigurations":444},{"removed":"omniscience","score":0.016910445407042864,"rank":312,"remainingConfigurations":444},{"removed":"tau-bench","score":0.016072775340291636,"rank":320,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01765029427812299,"rank":315,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.016556566949814378,"rank":320,"remainingConfigurations":444},{"removed":"arc-agi","score":0.021984682632967892,"rank":314,"remainingConfigurations":444},{"removed":"deepswe","score":0.013552850126738432,"rank":315,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.017373169305572558,"rank":315,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.017073450277069937,"rank":315,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01681512302510158,"rank":315,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.017111057210214223,"rank":315,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.017154248130784148,"rank":315,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.017358992335979363,"rank":315,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.017288783295768467,"rank":315,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01738988515039387,"rank":315,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.017148122391082127,"rank":315,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01767166210708285,"rank":315,"remainingConfigurations":444},{"removed":"livebench-data","score":0.017365977927455437,"rank":315,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01697870718090636,"rank":315,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01723776382542033,"rank":315,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01780607636795853,"rank":315,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01789829913751663,"rank":315,"remainingConfigurations":444},{"removed":"frontiermath","score":0.017393201090514208,"rank":314,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01622184984484785,"rank":313,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01833823643195666,"rank":315,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.017296806748737518,"rank":315,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.017294190891163966,"rank":315,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0172997016846259,"rank":315,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01732841252396852,"rank":315,"remainingConfigurations":444},{"removed":"vibe-code","score":0.017241999473789068,"rank":315,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.017313560995068835,"rank":315,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-omni-flash--effort-non-reasoning":{"score":0.016642007184632244,"rank":316,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02208177589848811,"rank":316,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012989233536149739,"rank":316,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.016451033839000172,"rank":316,"remainingConfigurations":444},{"removed":"Scale","score":0.019729016918604233,"rank":316,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01645136339546129,"rank":316,"remainingConfigurations":444},{"removed":"Cognition","score":0.016164557174359075,"rank":317,"remainingConfigurations":444},{"removed":"LiveBench","score":0.017377901301348284,"rank":315,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01715583971509644,"rank":316,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0168816442618213,"rank":304,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015961736210304032,"rank":315,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.016634524709279622,"rank":316,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01608579235188668,"rank":316,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.016611583324128255,"rank":316,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.016642007184632244,"rank":316,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016781266236928608,"rank":316,"remainingConfigurations":444},{"removed":"All provider reports","score":0.016190853514169504,"rank":316,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0168027933999613,"rank":316,"remainingConfigurations":444},{"removed":"briefcase","score":0.01653822217136044,"rank":317,"remainingConfigurations":444},{"removed":"aime","score":0.016544225551292265,"rank":320,"remainingConfigurations":444},{"removed":"apex-agents","score":0.016922691193937824,"rank":317,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015613604863879334,"rank":320,"remainingConfigurations":444},{"removed":"automationbench","score":0.016556128148904514,"rank":317,"remainingConfigurations":444},{"removed":"critpt","score":0.017966986131229386,"rank":313,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01664895983499511,"rank":316,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.017057417806463696,"rank":316,"remainingConfigurations":444},{"removed":"gdpval","score":0.016681473800561255,"rank":318,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01685149189023181,"rank":317,"remainingConfigurations":444},{"removed":"gpqa","score":0.015428104899046717,"rank":321,"remainingConfigurations":444},{"removed":"harvey","score":0.01644704371519111,"rank":316,"remainingConfigurations":444},{"removed":"hle","score":0.01868776101608174,"rank":319,"remainingConfigurations":444},{"removed":"ifbench","score":0.017818885182884502,"rank":310,"remainingConfigurations":444},{"removed":"itbench","score":0.016499636810152752,"rank":316,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0166968226246083,"rank":316,"remainingConfigurations":444},{"removed":"math500","score":0.016735339895316084,"rank":316,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.017313654404502655,"rank":317,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017054420626460415,"rank":323,"remainingConfigurations":444},{"removed":"omniscience","score":0.01692410137450397,"rank":311,"remainingConfigurations":444},{"removed":"tau-bench","score":0.013417098193830954,"rank":329,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.016913026485412076,"rank":316,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.01704726423383975,"rank":318,"remainingConfigurations":444},{"removed":"arc-agi","score":0.021218157524801964,"rank":316,"remainingConfigurations":444},{"removed":"deepswe","score":0.012998315549025438,"rank":316,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.016646388976565323,"rank":316,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01634721637032185,"rank":316,"remainingConfigurations":444},{"removed":"frontiercode","score":0.016164557174359075,"rank":317,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.016396410570361637,"rank":316,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01643743892133649,"rank":316,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.016632755908719075,"rank":316,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01656530757894532,"rank":316,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016663072645625294,"rank":316,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.016429431134792373,"rank":316,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016931613582210386,"rank":316,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0166399593866491,"rank":316,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.016269038832551857,"rank":316,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.016516475809920484,"rank":316,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.017062384696377008,"rank":316,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01715583971509644,"rank":316,"remainingConfigurations":444},{"removed":"frontiermath","score":0.016675340810617043,"rank":315,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.015496215700713266,"rank":314,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01757314632983599,"rank":316,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.016573185132581797,"rank":316,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.016570577951668372,"rank":316,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01657635327366827,"rank":316,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01660305512766928,"rank":316,"remainingConfigurations":444},{"removed":"vibe-code","score":0.016520590726738223,"rank":316,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01658930720973454,"rank":316,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-oss-20b--effort-high":{"score":0.016476402348954963,"rank":317,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.006534739322014586,"rank":192,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.021568216273763614,"rank":319,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012869630358300863,"rank":317,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01631151724470774,"rank":317,"remainingConfigurations":444},{"removed":"Scale","score":0.01951832884254772,"rank":318,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.016308959751734534,"rank":317,"remainingConfigurations":444},{"removed":"Cognition","score":0.016166225128080726,"rank":316,"remainingConfigurations":444},{"removed":"LiveBench","score":0.017053141631556173,"rank":318,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.016916331641203656,"rank":318,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.02039445175369516,"rank":295,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01578909706672112,"rank":317,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.016469386256366843,"rank":317,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01593377241504374,"rank":317,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.016448966134174476,"rank":317,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.016476402348954963,"rank":317,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016609741338547274,"rank":317,"remainingConfigurations":444},{"removed":"All provider reports","score":0.016036454961240613,"rank":317,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.016627848781067402,"rank":318,"remainingConfigurations":444},{"removed":"briefcase","score":0.017181178448715233,"rank":315,"remainingConfigurations":444},{"removed":"aime","score":0.012925374155532285,"rank":333,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01709723464459555,"rank":316,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.016669004817669458,"rank":315,"remainingConfigurations":444},{"removed":"automationbench","score":0.017442442141447165,"rank":315,"remainingConfigurations":444},{"removed":"critpt","score":0.014680859459152852,"rank":324,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.016491279542800826,"rank":318,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.016844901833881154,"rank":318,"remainingConfigurations":444},{"removed":"gdpval","score":0.016684756216998026,"rank":317,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0177303143474027,"rank":315,"remainingConfigurations":444},{"removed":"gpqa","score":0.019447724644752234,"rank":306,"remainingConfigurations":444},{"removed":"harvey","score":0.016273821406575333,"rank":318,"remainingConfigurations":444},{"removed":"hle","score":0.01788257428965287,"rank":321,"remainingConfigurations":444},{"removed":"ifbench","score":0.014700587603313863,"rank":323,"remainingConfigurations":444},{"removed":"itbench","score":0.016343456137628908,"rank":318,"remainingConfigurations":444},{"removed":"livecodebench","score":0.015365925846575819,"rank":322,"remainingConfigurations":444},{"removed":"math500","score":0.016565601696046386,"rank":318,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01842110689393526,"rank":313,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01797958981778583,"rank":316,"remainingConfigurations":444},{"removed":"omniscience","score":0.015812418820496603,"rank":315,"remainingConfigurations":444},{"removed":"tau-bench","score":0.015595375963535454,"rank":321,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.016721067905777348,"rank":318,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.016627871404077683,"rank":319,"remainingConfigurations":444},{"removed":"arc-agi","score":0.020761172013738952,"rank":319,"remainingConfigurations":444},{"removed":"deepswe","score":0.012879481560752056,"rank":317,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.016480745516520522,"rank":317,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01619029110623991,"rank":317,"remainingConfigurations":444},{"removed":"frontiercode","score":0.016166225128080726,"rank":316,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01623996383481574,"rank":317,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.016269768831120458,"rank":317,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01646782636981654,"rank":317,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.016400558444695745,"rank":317,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016504530334928342,"rank":317,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.016257455331611773,"rank":318,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01676260453116181,"rank":317,"remainingConfigurations":444},{"removed":"livebench-data","score":0.016474223365517782,"rank":317,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.016111622508633138,"rank":317,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01635107871999377,"rank":317,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.016889804387298972,"rank":317,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.016916331641203656,"rank":318,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01636597910164655,"rank":318,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.014324371086334003,"rank":322,"remainingConfigurations":444},{"removed":"simpleqa","score":0.017433894710610773,"rank":317,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.016407346638774193,"rank":317,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01640728766025875,"rank":317,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01640966757169262,"rank":317,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.016439551564908852,"rank":317,"remainingConfigurations":444},{"removed":"vibe-code","score":0.016358729125723667,"rank":317,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.016422914334003634,"rank":317,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-2.5-flash--effort-non-reasoning":{"score":0.016471285089639194,"rank":318,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02188497557023193,"rank":317,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01285462576113102,"rank":318,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01627430547116517,"rank":318,"remainingConfigurations":444},{"removed":"Scale","score":0.01953136149491296,"rank":317,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01628356627255474,"rank":318,"remainingConfigurations":444},{"removed":"Cognition","score":0.015991421126471218,"rank":318,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01721645048380856,"rank":316,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.016976929073884508,"rank":317,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01681309885890905,"rank":305,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015803462259874345,"rank":316,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.016463876089538244,"rank":318,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015921084926919262,"rank":318,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.016441254677535527,"rank":318,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.016471285089639194,"rank":318,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01660916513417217,"rank":318,"remainingConfigurations":444},{"removed":"All provider reports","score":0.016025188169481397,"rank":318,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01665134868672818,"rank":317,"remainingConfigurations":444},{"removed":"briefcase","score":0.016456097725469316,"rank":318,"remainingConfigurations":444},{"removed":"aime","score":0.016561997821352956,"rank":319,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01676906527793302,"rank":318,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015470480984008278,"rank":321,"remainingConfigurations":444},{"removed":"automationbench","score":0.016468884241722458,"rank":318,"remainingConfigurations":444},{"removed":"critpt","score":0.013611949486455601,"rank":332,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0165190470236795,"rank":317,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.016965818508631096,"rank":317,"remainingConfigurations":444},{"removed":"gdpval","score":0.016644711332186053,"rank":319,"remainingConfigurations":444},{"removed":"gmmlu","score":0.016683231610193083,"rank":318,"remainingConfigurations":444},{"removed":"gpqa","score":0.01647047326116223,"rank":317,"remainingConfigurations":444},{"removed":"harvey","score":0.0162878600233956,"rank":317,"remainingConfigurations":444},{"removed":"hle","score":0.020143253761570338,"rank":312,"remainingConfigurations":444},{"removed":"ifbench","score":0.016718221158707868,"rank":315,"remainingConfigurations":444},{"removed":"itbench","score":0.01634643138101512,"rank":317,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01728311765009306,"rank":314,"remainingConfigurations":444},{"removed":"math500","score":0.017485859901957865,"rank":315,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.016269526317502628,"rank":321,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01709465686760908,"rank":322,"remainingConfigurations":444},{"removed":"omniscience","score":0.012702942829279995,"rank":327,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01879302850202113,"rank":309,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01674798344128349,"rank":317,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.016462867343696303,"rank":321,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02103097280109535,"rank":317,"remainingConfigurations":444},{"removed":"deepswe","score":0.012863602872128557,"rank":318,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.016475623131011526,"rank":318,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.016175166419522352,"rank":318,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015991421126471218,"rank":318,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01622707824828989,"rank":318,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.016268846647236313,"rank":318,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.016462196469292523,"rank":318,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.016395424974888596,"rank":318,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016492171792532786,"rank":318,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01626086013171498,"rank":317,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016757925629129134,"rank":318,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01646916249383307,"rank":318,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.016101998068317334,"rank":318,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.016347019740848085,"rank":318,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01688761391870728,"rank":318,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.016976929073884508,"rank":317,"remainingConfigurations":444},{"removed":"frontiermath","score":0.016508507186998162,"rank":316,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.015352136169134388,"rank":315,"remainingConfigurations":444},{"removed":"simpleqa","score":0.017396259896734184,"rank":318,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.016403112577983003,"rank":318,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.016400496072102984,"rank":318,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01640638211324357,"rank":318,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.016432637385599965,"rank":318,"remainingConfigurations":444},{"removed":"vibe-code","score":0.016350970762764056,"rank":318,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.016419131376070324,"rank":318,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-oss-120b--effort-low":{"score":0.016403654580936906,"rank":319,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.021668069972473076,"rank":318,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012794161321521226,"rank":319,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.016207496625776415,"rank":319,"remainingConfigurations":444},{"removed":"Scale","score":0.019454227373913103,"rank":319,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.016214748143917598,"rank":319,"remainingConfigurations":444},{"removed":"Cognition","score":0.015914435834309657,"rank":319,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0171298093505546,"rank":317,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01688006852287619,"rank":319,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01678457946807664,"rank":306,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015732734522146626,"rank":318,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.016396262312164924,"rank":319,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015855210766647476,"rank":319,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.016373710500730193,"rank":319,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.016403654580936906,"rank":319,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016540738967431887,"rank":319,"remainingConfigurations":444},{"removed":"All provider reports","score":0.015958622937371266,"rank":319,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.016554461571667123,"rank":319,"remainingConfigurations":444},{"removed":"briefcase","score":0.016271886292155285,"rank":319,"remainingConfigurations":444},{"removed":"aime","score":0.016026937518990713,"rank":322,"remainingConfigurations":444},{"removed":"apex-agents","score":0.016677679083650258,"rank":319,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015900135589901578,"rank":318,"remainingConfigurations":444},{"removed":"automationbench","score":0.016294621057514763,"rank":319,"remainingConfigurations":444},{"removed":"critpt","score":0.01699322722606724,"rank":317,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.016405533209484412,"rank":319,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01678926122987531,"rank":319,"remainingConfigurations":444},{"removed":"gdpval","score":0.01690106373071491,"rank":315,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01658092976765128,"rank":319,"remainingConfigurations":444},{"removed":"gpqa","score":0.016580322817107782,"rank":315,"remainingConfigurations":444},{"removed":"harvey","score":0.016213411678227093,"rank":319,"remainingConfigurations":444},{"removed":"hle","score":0.01912071736798766,"rank":315,"remainingConfigurations":444},{"removed":"ifbench","score":0.014157069307214045,"rank":329,"remainingConfigurations":444},{"removed":"itbench","score":0.016253495492885853,"rank":319,"remainingConfigurations":444},{"removed":"livecodebench","score":0.015342962730005941,"rank":323,"remainingConfigurations":444},{"removed":"math500","score":0.016556708939230756,"rank":319,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.017853645395274013,"rank":316,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017902284138777824,"rank":317,"remainingConfigurations":444},{"removed":"omniscience","score":0.013920366450352035,"rank":324,"remainingConfigurations":444},{"removed":"tau-bench","score":0.016151050785463635,"rank":319,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01667411552697028,"rank":319,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.017308377887205083,"rank":317,"remainingConfigurations":444},{"removed":"arc-agi","score":0.020832267277872858,"rank":318,"remainingConfigurations":444},{"removed":"deepswe","score":0.012803128515578391,"rank":319,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01640799300624537,"rank":319,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.016111707913463478,"rank":319,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015914435834309657,"rank":319,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.016160322752586106,"rank":319,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.016201820715944434,"rank":319,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.016394597801984438,"rank":319,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01632809120772419,"rank":319,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016424414900286323,"rank":319,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.016194001531318544,"rank":319,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016689286465873424,"rank":319,"remainingConfigurations":444},{"removed":"livebench-data","score":0.016401709625559258,"rank":319,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.016035709047396398,"rank":319,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.016279821718847537,"rank":319,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.016818363493448226,"rank":319,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01688006852287619,"rank":319,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01643608434591965,"rank":317,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.015269360506251814,"rank":316,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01732362319791989,"rank":319,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.016335717214333318,"rank":319,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.016333233984320072,"rank":319,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01633888494715702,"rank":319,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.016365291310213036,"rank":319,"remainingConfigurations":444},{"removed":"vibe-code","score":0.016283874463097658,"rank":319,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.016351646003576983,"rank":319,"remainingConfigurations":444}],"sharedOrderConflicts":0},"solar-open-100b--effort-reasoning":{"score":0.016279157175417468,"rank":320,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.021547043003351442,"rank":320,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012693604071674932,"rank":320,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.016086185111036776,"rank":320,"remainingConfigurations":444},{"removed":"Scale","score":0.019302072597193392,"rank":320,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.016090874393915572,"rank":320,"remainingConfigurations":444},{"removed":"Cognition","score":0.015798778866010596,"rank":320,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01699374267856498,"rank":319,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01673259442209308,"rank":320,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01652760311031579,"rank":307,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015610389291633367,"rank":319,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.016271835494511323,"rank":320,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015735007895878353,"rank":320,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01624946872080462,"rank":320,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.016279157175417468,"rank":320,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016415109847069155,"rank":320,"remainingConfigurations":444},{"removed":"All provider reports","score":0.015837589719212213,"rank":320,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.016435144231167105,"rank":320,"remainingConfigurations":444},{"removed":"briefcase","score":0.016180711822218845,"rank":320,"remainingConfigurations":444},{"removed":"aime","score":0.016181236206570897,"rank":321,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01655320658367135,"rank":320,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01626500522985525,"rank":316,"remainingConfigurations":444},{"removed":"automationbench","score":0.016199995912229818,"rank":320,"remainingConfigurations":444},{"removed":"critpt","score":0.01752211787584309,"rank":315,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.016282411224418904,"rank":320,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01668419485937803,"rank":320,"remainingConfigurations":444},{"removed":"gdpval","score":0.016314612419096663,"rank":320,"remainingConfigurations":444},{"removed":"gmmlu","score":0.015583604134177928,"rank":325,"remainingConfigurations":444},{"removed":"gpqa","score":0.017291536802529293,"rank":312,"remainingConfigurations":444},{"removed":"harvey","score":0.016091006310365648,"rank":320,"remainingConfigurations":444},{"removed":"hle","score":0.01694969549082692,"rank":325,"remainingConfigurations":444},{"removed":"ifbench","score":0.013452549916121938,"rank":330,"remainingConfigurations":444},{"removed":"itbench","score":0.016134269884375864,"rank":320,"remainingConfigurations":444},{"removed":"livecodebench","score":0.016307488819187376,"rank":320,"remainingConfigurations":444},{"removed":"math500","score":0.01634684389477039,"rank":320,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.016932186067054204,"rank":319,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01777233075577434,"rank":318,"remainingConfigurations":444},{"removed":"omniscience","score":0.014056067303209819,"rank":322,"remainingConfigurations":444},{"removed":"tau-bench","score":0.014828700639737917,"rank":324,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.016546000170642425,"rank":320,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.019589847200376594,"rank":307,"remainingConfigurations":444},{"removed":"arc-agi","score":0.020720898529828048,"rank":320,"remainingConfigurations":444},{"removed":"deepswe","score":0.012702520219158802,"rank":320,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.016283452852950474,"rank":320,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.015989416359883418,"rank":320,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015798778866010596,"rank":320,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.016036491180470618,"rank":320,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.016078833401120356,"rank":320,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.016270054303364454,"rank":320,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.016204094593085538,"rank":320,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016299825139588907,"rank":320,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.016070922704448442,"rank":320,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016562602085075,"rank":320,"remainingConfigurations":444},{"removed":"livebench-data","score":0.016277160952823715,"rank":320,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.015914108205380192,"rank":320,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.016156287431775763,"rank":320,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.016690776470184684,"rank":320,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01673259442209308,"rank":320,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01631151157329648,"rank":319,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.015143846528208507,"rank":317,"remainingConfigurations":444},{"removed":"simpleqa","score":0.017190951343957116,"rank":320,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01621174665100045,"rank":320,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01620923695388669,"rank":320,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.016214845800983608,"rank":320,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01624105882780705,"rank":320,"remainingConfigurations":444},{"removed":"vibe-code","score":0.016160334377167872,"rank":320,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01622750283793004,"rank":320,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5--effort-non-reasoning":{"score":0.01610822792625556,"rank":321,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.021249654919839486,"rank":321,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01256366541609877,"rank":321,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.015919202245718612,"rank":321,"remainingConfigurations":444},{"removed":"Scale","score":0.019128312913820854,"rank":321,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.015921897064791645,"rank":321,"remainingConfigurations":444},{"removed":"Cognition","score":0.015631851962995855,"rank":321,"remainingConfigurations":444},{"removed":"LiveBench","score":0.016820928657952518,"rank":320,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01658899663413948,"rank":321,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.016512301366468165,"rank":308,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015448298496547734,"rank":320,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01610098082457084,"rank":321,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015569582998283921,"rank":321,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.016078802402704366,"rank":321,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01610822792625556,"rank":321,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016243051003614256,"rank":321,"remainingConfigurations":444},{"removed":"All provider reports","score":0.015671321311962597,"rank":321,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.016259546431441816,"rank":321,"remainingConfigurations":444},{"removed":"briefcase","score":0.016015980547293047,"rank":321,"remainingConfigurations":444},{"removed":"aime","score":0.017339411682319852,"rank":317,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01637812904436672,"rank":321,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.012131578118442789,"rank":335,"remainingConfigurations":444},{"removed":"automationbench","score":0.016026181922706103,"rank":321,"remainingConfigurations":444},{"removed":"critpt","score":0.015545541318330039,"rank":322,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.016112470593847603,"rank":321,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.016516637768547,"rank":321,"remainingConfigurations":444},{"removed":"gdpval","score":0.016204960625839548,"rank":321,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01632588795286624,"rank":321,"remainingConfigurations":444},{"removed":"gpqa","score":0.016170618321272222,"rank":319,"remainingConfigurations":444},{"removed":"harvey","score":0.01591984156398394,"rank":321,"remainingConfigurations":444},{"removed":"hle","score":0.018659727711711947,"rank":320,"remainingConfigurations":444},{"removed":"ifbench","score":0.015139071084660784,"rank":320,"remainingConfigurations":444},{"removed":"itbench","score":0.01595432531020094,"rank":321,"remainingConfigurations":444},{"removed":"livecodebench","score":0.016621998419844842,"rank":317,"remainingConfigurations":444},{"removed":"math500","score":0.016210042949257698,"rank":321,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01496359216320261,"rank":325,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017644062745627336,"rank":319,"remainingConfigurations":444},{"removed":"omniscience","score":0.014314856814225202,"rank":319,"remainingConfigurations":444},{"removed":"tau-bench","score":0.02023791321493843,"rank":301,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.016369145456717703,"rank":321,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.015950843836693956,"rank":323,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0204198300442243,"rank":321,"remainingConfigurations":444},{"removed":"deepswe","score":0.012572456099650688,"rank":321,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.016112476531512158,"rank":321,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.015820273489330305,"rank":321,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015631851962995855,"rank":321,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.015869069798611017,"rank":321,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.015909939625822395,"rank":321,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.016099323225289463,"rank":321,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.016033960279404836,"rank":321,"remainingConfigurations":444},{"removed":"livebench-math","score":0.016128671865058758,"rank":321,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.015902035120296306,"rank":321,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0163887270056379,"rank":321,"remainingConfigurations":444},{"removed":"livebench-data","score":0.016106430272284134,"rank":321,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01574687611436622,"rank":321,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.015986497039825225,"rank":321,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01651580802689059,"rank":321,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01658899663413948,"rank":321,"remainingConfigurations":444},{"removed":"frontiermath","score":0.016152272914744963,"rank":320,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.015018267938314582,"rank":318,"remainingConfigurations":444},{"removed":"simpleqa","score":0.017013213165201824,"rank":321,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.016041497072791802,"rank":321,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.016039003933485382,"rank":321,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.016044637228725598,"rank":321,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.016070459415411124,"rank":321,"remainingConfigurations":444},{"removed":"vibe-code","score":0.01599055025651229,"rank":321,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.016057144607579094,"rank":321,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-30b-a3b-thinking--effort-reasoning":{"score":0.01595291809020305,"rank":322,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.021105164960542867,"rank":322,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01244111021966055,"rank":322,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.015750470110751806,"rank":322,"remainingConfigurations":444},{"removed":"Scale","score":0.01891657499874444,"rank":322,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0157702171612298,"rank":322,"remainingConfigurations":444},{"removed":"Cognition","score":0.015491305689604629,"rank":322,"remainingConfigurations":444},{"removed":"LiveBench","score":0.016654644184941583,"rank":321,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.016425131669603733,"rank":322,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01618405437951719,"rank":309,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015299988362001618,"rank":321,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01594574948305585,"rank":322,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015419552203568132,"rank":322,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.015923788238829336,"rank":322,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01595291809020305,"rank":322,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.016086246868592235,"rank":322,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01552014217582177,"rank":322,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.016101547619272856,"rank":322,"remainingConfigurations":444},{"removed":"briefcase","score":0.01583410761298788,"rank":322,"remainingConfigurations":444},{"removed":"aime","score":0.01409584552217795,"rank":327,"remainingConfigurations":444},{"removed":"apex-agents","score":0.016217103850765278,"rank":322,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015687003319286307,"rank":319,"remainingConfigurations":444},{"removed":"automationbench","score":0.01585232246770313,"rank":322,"remainingConfigurations":444},{"removed":"critpt","score":0.016620546635614825,"rank":318,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.015956052717582377,"rank":322,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.016330434905483693,"rank":322,"remainingConfigurations":444},{"removed":"gdpval","score":0.01600346465899635,"rank":322,"remainingConfigurations":444},{"removed":"gmmlu","score":0.016144827472427254,"rank":322,"remainingConfigurations":444},{"removed":"gpqa","score":0.01539616637336646,"rank":322,"remainingConfigurations":444},{"removed":"harvey","score":0.01576849343080408,"rank":322,"remainingConfigurations":444},{"removed":"hle","score":0.017467894784049743,"rank":323,"remainingConfigurations":444},{"removed":"ifbench","score":0.014860763432925564,"rank":322,"remainingConfigurations":444},{"removed":"itbench","score":0.01580995398841869,"rank":322,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01488693548953926,"rank":325,"remainingConfigurations":444},{"removed":"math500","score":0.016093831039751844,"rank":322,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01600303891485778,"rank":322,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017540797168628452,"rank":320,"remainingConfigurations":444},{"removed":"omniscience","score":0.014253902532792377,"rank":320,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017847706653004915,"rank":312,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.016215152504328516,"rank":322,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.017364457408455967,"rank":316,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02028723774329807,"rank":322,"remainingConfigurations":444},{"removed":"deepswe","score":0.01244983770835196,"rank":322,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.015957124399992254,"rank":322,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01566548584749695,"rank":322,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015491305689604629,"rank":322,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01571537796024221,"rank":322,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.015756179933069644,"rank":322,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.015944112277901577,"rank":322,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.015879445039253388,"rank":322,"remainingConfigurations":444},{"removed":"livebench-math","score":0.015973208673028722,"rank":322,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.015748963921728098,"rank":322,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016230805517268364,"rank":322,"remainingConfigurations":444},{"removed":"livebench-data","score":0.015950804386493326,"rank":322,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.015594963998624934,"rank":322,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01583244694038931,"rank":322,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.016356473229837593,"rank":322,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.016425131669603733,"rank":322,"remainingConfigurations":444},{"removed":"frontiermath","score":0.015986714020671918,"rank":321,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.014837806167254101,"rank":319,"remainingConfigurations":444},{"removed":"simpleqa","score":0.016849623341923674,"rank":322,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01588680112061133,"rank":322,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.015884308088683474,"rank":322,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0158899699798209,"rank":322,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.015915476340936808,"rank":322,"remainingConfigurations":444},{"removed":"vibe-code","score":0.01583633819838459,"rank":322,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.015902333098053962,"rank":322,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.1--effort-non-reasoning":{"score":0.015773104053979286,"rank":323,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02097289886074695,"rank":323,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012302859649130825,"rank":323,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.015590774443977584,"rank":323,"remainingConfigurations":444},{"removed":"Scale","score":0.018700686158661908,"rank":323,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.015591527745388295,"rank":323,"remainingConfigurations":444},{"removed":"Cognition","score":0.015313799889869237,"rank":323,"remainingConfigurations":444},{"removed":"LiveBench","score":0.016476078179531898,"rank":322,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.016226709954776267,"rank":323,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.016052930235765515,"rank":310,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015128207867130858,"rank":322,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.015765998731476306,"rank":323,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015245453588841417,"rank":323,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.015744266174210562,"rank":323,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.015773104053979286,"rank":323,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.015905410962314067,"rank":323,"remainingConfigurations":444},{"removed":"All provider reports","score":0.015345315951942239,"rank":323,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01593386244750891,"rank":323,"remainingConfigurations":444},{"removed":"briefcase","score":0.015718001076771092,"rank":323,"remainingConfigurations":444},{"removed":"aime","score":0.01762076180760082,"rank":313,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01604682190144575,"rank":323,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015336105756856963,"rank":322,"remainingConfigurations":444},{"removed":"automationbench","score":0.015728241311139684,"rank":323,"remainingConfigurations":444},{"removed":"critpt","score":0.016312969960802035,"rank":320,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.015794415678653837,"rank":323,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0162100974016875,"rank":323,"remainingConfigurations":444},{"removed":"gdpval","score":0.015884128206113252,"rank":323,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01596050206428762,"rank":323,"remainingConfigurations":444},{"removed":"gpqa","score":0.016447510552780084,"rank":318,"remainingConfigurations":444},{"removed":"harvey","score":0.015596170778850733,"rank":323,"remainingConfigurations":444},{"removed":"hle","score":0.018719737183260064,"rank":318,"remainingConfigurations":444},{"removed":"ifbench","score":0.01502786141385441,"rank":321,"remainingConfigurations":444},{"removed":"itbench","score":0.01564612255512358,"rank":323,"remainingConfigurations":444},{"removed":"livecodebench","score":0.016702057241647496,"rank":315,"remainingConfigurations":444},{"removed":"math500","score":0.01587458589020299,"rank":323,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.015998790931107856,"rank":323,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017048333503213626,"rank":324,"remainingConfigurations":444},{"removed":"omniscience","score":0.011554283500659464,"rank":331,"remainingConfigurations":444},{"removed":"tau-bench","score":0.014821039521186257,"rank":325,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01604345689980845,"rank":323,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.014745792669619022,"rank":325,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02015529841218874,"rank":323,"remainingConfigurations":444},{"removed":"deepswe","score":0.012311435437415768,"rank":323,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0157772615957024,"rank":323,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.015489784619258559,"rank":323,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015313799889869237,"rank":323,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01553884704931379,"rank":323,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.015578969414243068,"rank":323,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.015764395491115094,"rank":323,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01570036587275879,"rank":323,"remainingConfigurations":444},{"removed":"livebench-math","score":0.015793134008901304,"rank":323,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.015571151414184045,"rank":323,"remainingConfigurations":444},{"removed":"livebench-language","score":0.016047922251751223,"rank":323,"remainingConfigurations":444},{"removed":"livebench-data","score":0.015771225087159804,"rank":323,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01541903143890151,"rank":323,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01565387536430411,"rank":323,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01617250310946511,"rank":323,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.016226709954776267,"rank":323,"remainingConfigurations":444},{"removed":"frontiermath","score":0.015805774460592184,"rank":323,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01467369897835285,"rank":320,"remainingConfigurations":444},{"removed":"simpleqa","score":0.016659351237639834,"rank":323,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01570773323154453,"rank":323,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01570523112539139,"rank":323,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.015710878072584793,"rank":323,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.015736015135919903,"rank":323,"remainingConfigurations":444},{"removed":"vibe-code","score":0.015657738261112983,"rank":323,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.015723084501025497,"rank":323,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-next-80b-a3b-instruct--effort-non-reasoning":{"score":0.015734897031312218,"rank":324,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.020816111499925977,"rank":324,"remainingConfigurations":444},{"removed":"Datacurve","score":0.012270705659283052,"rank":324,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.015536183909971725,"rank":324,"remainingConfigurations":444},{"removed":"Scale","score":0.018668096091510704,"rank":324,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.015554231619347708,"rank":324,"remainingConfigurations":444},{"removed":"Cognition","score":0.015278335761754039,"rank":324,"remainingConfigurations":444},{"removed":"LiveBench","score":0.016429035251895065,"rank":323,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01621116073722216,"rank":324,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.015994765188330467,"rank":311,"remainingConfigurations":431},{"removed":"Vals AI","score":0.015092590177614178,"rank":323,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.015727822033428294,"rank":324,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.015208782712535904,"rank":324,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.015706194831514333,"rank":324,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.015734897031312218,"rank":324,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.015866315754371623,"rank":324,"remainingConfigurations":444},{"removed":"All provider reports","score":0.015307939670056345,"rank":324,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0158826127492688,"rank":324,"remainingConfigurations":444},{"removed":"briefcase","score":0.015635651571184687,"rank":324,"remainingConfigurations":444},{"removed":"aime","score":0.015364614627506807,"rank":323,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01599852034578998,"rank":324,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014818035938212445,"rank":324,"remainingConfigurations":444},{"removed":"automationbench","score":0.015647432027273655,"rank":324,"remainingConfigurations":444},{"removed":"critpt","score":0.016367492451213578,"rank":319,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.015740482296116208,"rank":324,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01612771590028274,"rank":324,"remainingConfigurations":444},{"removed":"gdpval","score":0.015785701529837586,"rank":324,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01592550550043676,"rank":324,"remainingConfigurations":444},{"removed":"gpqa","score":0.0148726258397708,"rank":324,"remainingConfigurations":444},{"removed":"harvey","score":0.015553473386617023,"rank":324,"remainingConfigurations":444},{"removed":"hle","score":0.01754790031377736,"rank":322,"remainingConfigurations":444},{"removed":"ifbench","score":0.01578796137789429,"rank":318,"remainingConfigurations":444},{"removed":"itbench","score":0.015594392043305023,"rank":324,"remainingConfigurations":444},{"removed":"livecodebench","score":0.014931389030192234,"rank":324,"remainingConfigurations":444},{"removed":"math500","score":0.015853120552118655,"rank":324,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.014897142763286355,"rank":326,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.017199103853135878,"rank":321,"remainingConfigurations":444},{"removed":"omniscience","score":0.013943038213836375,"rank":323,"remainingConfigurations":444},{"removed":"tau-bench","score":0.017328307926084804,"rank":316,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01599371450782071,"rank":324,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.016218907137906316,"rank":322,"remainingConfigurations":444},{"removed":"arc-agi","score":0.020012388325465084,"rank":324,"remainingConfigurations":444},{"removed":"deepswe","score":0.012279331998377838,"rank":324,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01573905476201339,"rank":324,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.015451325562320912,"rank":324,"remainingConfigurations":444},{"removed":"frontiercode","score":0.015278335761754039,"rank":324,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.015500581902567678,"rank":324,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.015540816506088496,"rank":324,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.015726221191154324,"rank":324,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01566245702212259,"rank":324,"remainingConfigurations":444},{"removed":"livebench-math","score":0.015754918677027687,"rank":324,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.015533475059454257,"rank":324,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01600913433697933,"rank":324,"remainingConfigurations":444},{"removed":"livebench-data","score":0.015732985559364254,"rank":324,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.015381646938279384,"rank":324,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.015615957547272241,"rank":324,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01613320950678279,"rank":324,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01621116073722216,"rank":324,"remainingConfigurations":444},{"removed":"frontiermath","score":0.015766853092543123,"rank":324,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.014643846458519225,"rank":321,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01662015873807528,"rank":324,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01566963723778376,"rank":324,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.015667217743418883,"rank":324,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.015672742848951742,"rank":324,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.015697994216803537,"rank":324,"remainingConfigurations":444},{"removed":"vibe-code","score":0.015619870501995821,"rank":324,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01568496836346503,"rank":324,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.1-flash-lite--effort-minimal":{"score":0.0144772218398164,"rank":325,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01354495473787635,"rank":188,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01819179122960995,"rank":330,"remainingConfigurations":444},{"removed":"Datacurve","score":0.011356933470779323,"rank":325,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.014399387073314661,"rank":325,"remainingConfigurations":444},{"removed":"Scale","score":0.01703459398624947,"rank":326,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.014383841792079263,"rank":325,"remainingConfigurations":444},{"removed":"Cognition","score":0.014714290322342114,"rank":325,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014734583803847361,"rank":326,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014823588446619657,"rank":326,"remainingConfigurations":444},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013851509753918247,"rank":325,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.014472055569701886,"rank":325,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.014026606510305151,"rank":325,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.014459896047830767,"rank":325,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0144772218398164,"rank":325,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.014585642334176224,"rank":325,"remainingConfigurations":444},{"removed":"All provider reports","score":0.014115896671700953,"rank":325,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.014582130581317632,"rank":326,"remainingConfigurations":444},{"removed":"briefcase","score":0.014424496507704991,"rank":325,"remainingConfigurations":444},{"removed":"aime","score":0.01901472508507889,"rank":310,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014684668227797341,"rank":326,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014598625338272673,"rank":325,"remainingConfigurations":444},{"removed":"automationbench","score":0.014440888669666302,"rank":325,"remainingConfigurations":444},{"removed":"critpt","score":0.014139104428230728,"rank":329,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.014493783161820525,"rank":325,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.014678226066945722,"rank":326,"remainingConfigurations":444},{"removed":"gdpval","score":0.014322741226815953,"rank":325,"remainingConfigurations":444},{"removed":"gmmlu","score":0.014649641533645895,"rank":327,"remainingConfigurations":444},{"removed":"gpqa","score":0.011360838832185124,"rank":342,"remainingConfigurations":444},{"removed":"harvey","score":0.014280447450110118,"rank":326,"remainingConfigurations":444},{"removed":"hle","score":0.015813690142457853,"rank":329,"remainingConfigurations":444},{"removed":"ifbench","score":0.0144864020620714,"rank":324,"remainingConfigurations":444},{"removed":"itbench","score":0.014380855847937676,"rank":325,"remainingConfigurations":444},{"removed":"livecodebench","score":0.014527155767051892,"rank":327,"remainingConfigurations":444},{"removed":"math500","score":0.014514026735916915,"rank":327,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.015174826580561374,"rank":324,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.015709231447588647,"rank":326,"remainingConfigurations":444},{"removed":"omniscience","score":0.014058809605823563,"rank":321,"remainingConfigurations":444},{"removed":"tau-bench","score":0.013535829191686529,"rank":328,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01463382501688268,"rank":326,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.014382329789202184,"rank":326,"remainingConfigurations":444},{"removed":"arc-agi","score":0.017550236550891204,"rank":330,"remainingConfigurations":444},{"removed":"deepswe","score":0.011366855795109007,"rank":325,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.014480744437845626,"rank":325,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.014234445699882059,"rank":325,"remainingConfigurations":444},{"removed":"frontiercode","score":0.014714290322342114,"rank":325,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.014291200607439396,"rank":325,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01428186682914583,"rank":325,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.014471185066325644,"rank":325,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.014410523217560416,"rank":325,"remainingConfigurations":444},{"removed":"livebench-math","score":0.014522146330627159,"rank":325,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01425224862220219,"rank":326,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01472074180613781,"rank":325,"remainingConfigurations":444},{"removed":"livebench-data","score":0.014486100478305312,"rank":325,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.014169810329751245,"rank":325,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.014363634152163502,"rank":325,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014838899404875166,"rank":325,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014823588446619657,"rank":326,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013229823762267147,"rank":334,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.009524519398409405,"rank":352,"remainingConfigurations":444},{"removed":"simpleqa","score":0.015380179606135096,"rank":325,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.014413594454541365,"rank":325,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.014421218441452647,"rank":325,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.014414809728335943,"rank":325,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.014447269644287351,"rank":325,"remainingConfigurations":444},{"removed":"vibe-code","score":0.014378420019419661,"rank":325,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01442794448264359,"rank":325,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mimo-v2-flash--effort-non-reasoning":{"score":0.014454121022876435,"rank":326,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.019168692356994987,"rank":325,"remainingConfigurations":444},{"removed":"Datacurve","score":0.01127279328269072,"rank":326,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01429223586818098,"rank":326,"remainingConfigurations":444},{"removed":"Scale","score":0.017156169768525777,"rank":325,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.014286869711620775,"rank":326,"remainingConfigurations":444},{"removed":"Cognition","score":0.014040217979795641,"rank":327,"remainingConfigurations":444},{"removed":"LiveBench","score":0.015105963088361938,"rank":324,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014895863900107303,"rank":325,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.014761634502868888,"rank":312,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013869899960767935,"rank":324,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01444758790251457,"rank":326,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01396918546263712,"rank":326,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01442767125490631,"rank":326,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.014454121022876435,"rank":326,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01457511888914432,"rank":326,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01406042716017971,"rank":326,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.014602638377602511,"rank":325,"remainingConfigurations":444},{"removed":"briefcase","score":0.014381740894467962,"rank":326,"remainingConfigurations":444},{"removed":"aime","score":0.013864293590836478,"rank":329,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014720323304962571,"rank":325,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014470924407659217,"rank":327,"remainingConfigurations":444},{"removed":"automationbench","score":0.014388696286414732,"rank":326,"remainingConfigurations":444},{"removed":"critpt","score":0.01470731786490811,"rank":323,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.014482676705612875,"rank":326,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01482919446184256,"rank":325,"remainingConfigurations":444},{"removed":"gdpval","score":0.013177648627266022,"rank":333,"remainingConfigurations":444},{"removed":"gmmlu","score":0.016528574427645416,"rank":320,"remainingConfigurations":444},{"removed":"gpqa","score":0.01485182287341351,"rank":325,"remainingConfigurations":444},{"removed":"harvey","score":0.014288271220468428,"rank":325,"remainingConfigurations":444},{"removed":"hle","score":0.015809446564065303,"rank":330,"remainingConfigurations":444},{"removed":"ifbench","score":0.014164025547700571,"rank":327,"remainingConfigurations":444},{"removed":"itbench","score":0.014337160147686752,"rank":326,"remainingConfigurations":444},{"removed":"livecodebench","score":0.015915773576036137,"rank":321,"remainingConfigurations":444},{"removed":"math500","score":0.014540985244186596,"rank":326,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.016318037347817876,"rank":320,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01577660885079875,"rank":325,"remainingConfigurations":444},{"removed":"omniscience","score":0.013389310654135164,"rank":325,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012367839887848535,"rank":333,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.014695423359158749,"rank":325,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012052291066574322,"rank":341,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01841891717609311,"rank":325,"remainingConfigurations":444},{"removed":"deepswe","score":0.011280719164362704,"rank":326,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.014457954625222867,"rank":326,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.014195858624190665,"rank":326,"remainingConfigurations":444},{"removed":"frontiercode","score":0.014040217979795641,"rank":327,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.014239497794420025,"rank":326,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01427575450883667,"rank":326,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.014446187119375233,"rank":326,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.014387463973304496,"rank":326,"remainingConfigurations":444},{"removed":"livebench-math","score":0.014472486757632741,"rank":326,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.014268594032968178,"rank":325,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01470679565452853,"rank":326,"remainingConfigurations":444},{"removed":"livebench-data","score":0.014452450624785599,"rank":326,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01412869476850078,"rank":326,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.014344562701472637,"rank":326,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014821100988401425,"rank":326,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014895863900107303,"rank":325,"remainingConfigurations":444},{"removed":"frontiermath","score":0.014477697073775928,"rank":325,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.013440308642775492,"rank":323,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01526873687401479,"rank":326,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.014394034519002943,"rank":326,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.014391803258902767,"rank":326,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.014396850922925671,"rank":326,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01442013414840834,"rank":326,"remainingConfigurations":444},{"removed":"vibe-code","score":0.014348173667788261,"rank":326,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.014408125964372243,"rank":326,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-4b--effort-non-reasoning":{"score":0.014229137459939709,"rank":327,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.021323131490502727,"rank":178,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.018969269560146346,"rank":326,"remainingConfigurations":444},{"removed":"Datacurve","score":0.011132299469743924,"rank":327,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.014094653419436451,"rank":327,"remainingConfigurations":444},{"removed":"Scale","score":0.0168436503196325,"rank":327,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.014089913619613854,"rank":327,"remainingConfigurations":444},{"removed":"Cognition","score":0.014048600338673653,"rank":326,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014748373089320059,"rank":325,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014623645438428616,"rank":327,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01272538867241576,"rank":321,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01364450117018666,"rank":326,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.014223027840323392,"rank":327,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.013762408801174464,"rank":327,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.014205579615453068,"rank":327,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.014229137459939709,"rank":327,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01434445280354337,"rank":327,"remainingConfigurations":444},{"removed":"All provider reports","score":0.013851279118745343,"rank":327,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01435819515240726,"rank":327,"remainingConfigurations":444},{"removed":"briefcase","score":0.014126470229759441,"rank":327,"remainingConfigurations":444},{"removed":"aime","score":0.012508974983226588,"rank":335,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014460147015892275,"rank":327,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014248012210690409,"rank":328,"remainingConfigurations":444},{"removed":"automationbench","score":0.014141723637116618,"rank":327,"remainingConfigurations":444},{"removed":"critpt","score":0.014423454793808603,"rank":326,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.014236461254900913,"rank":327,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.014510183700425769,"rank":327,"remainingConfigurations":444},{"removed":"gdpval","score":0.01417479984941405,"rank":326,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01436013463933504,"rank":328,"remainingConfigurations":444},{"removed":"gpqa","score":0.014255932953034256,"rank":327,"remainingConfigurations":444},{"removed":"harvey","score":0.014054367581390883,"rank":327,"remainingConfigurations":444},{"removed":"hle","score":0.015271976706917557,"rank":332,"remainingConfigurations":444},{"removed":"ifbench","score":0.015213005182768727,"rank":319,"remainingConfigurations":444},{"removed":"itbench","score":0.014114933022769853,"rank":327,"remainingConfigurations":444},{"removed":"livecodebench","score":0.014171814802161434,"rank":328,"remainingConfigurations":444},{"removed":"math500","score":0.014264977900354815,"rank":329,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.014734218450480644,"rank":328,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01521949671804137,"rank":330,"remainingConfigurations":444},{"removed":"omniscience","score":0.014713017148515209,"rank":318,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012320167066775904,"rank":334,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.014437975134449952,"rank":327,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.013788021447963506,"rank":329,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01824624048022674,"rank":326,"remainingConfigurations":444},{"removed":"deepswe","score":0.011140692774177076,"rank":327,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01423283657727245,"rank":327,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013977186379491207,"rank":327,"remainingConfigurations":444},{"removed":"frontiercode","score":0.014048600338673653,"rank":326,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01402720603948291,"rank":327,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.014050476930735247,"rank":327,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01422180013009939,"rank":327,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.014163089056154229,"rank":327,"remainingConfigurations":444},{"removed":"livebench-math","score":0.014256249783766056,"rank":327,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.014033225529949895,"rank":327,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01447512006678641,"rank":327,"remainingConfigurations":444},{"removed":"livebench-data","score":0.014230093535008129,"rank":327,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013915040538935075,"rank":327,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.014119492432434988,"rank":327,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014589263848161208,"rank":327,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014623645438428616,"rank":327,"remainingConfigurations":444},{"removed":"frontiermath","score":0.014196285323040686,"rank":326,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012764756910093366,"rank":328,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01508390343090036,"rank":327,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.014169092446908381,"rank":327,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.014169709749489065,"rank":327,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.014171231719608915,"rank":327,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.014197004447003824,"rank":327,"remainingConfigurations":444},{"removed":"vibe-code","score":0.014127202078250854,"rank":327,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.014182477307583943,"rank":327,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-mini--effort-non-reasoning":{"score":0.014051279628643906,"rank":328,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.018727809459539967,"rank":327,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010955974243600888,"rank":328,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013900889770889567,"rank":328,"remainingConfigurations":444},{"removed":"Scale","score":0.016670373797118113,"rank":328,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.013890332309743203,"rank":328,"remainingConfigurations":444},{"removed":"Cognition","score":0.013643821349645877,"rank":328,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014681254748032205,"rank":327,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014485317408842036,"rank":328,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.014331641325002234,"rank":313,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013480764362697588,"rank":327,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.014044856388121918,"rank":328,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.013577973659494815,"rank":328,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.014025417809399783,"rank":328,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.014051279628643906,"rank":328,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.014169465449327562,"rank":328,"remainingConfigurations":444},{"removed":"All provider reports","score":0.013667006429407172,"rank":328,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.014197233473106129,"rank":328,"remainingConfigurations":444},{"removed":"briefcase","score":0.014036674738286936,"rank":328,"remainingConfigurations":444},{"removed":"aime","score":0.013928830416254872,"rank":328,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014317310456626509,"rank":328,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014054488018318803,"rank":329,"remainingConfigurations":444},{"removed":"automationbench","score":0.014050178523189466,"rank":328,"remainingConfigurations":444},{"removed":"critpt","score":0.014637857686597025,"rank":325,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.014085325395172718,"rank":328,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.014487211879753359,"rank":328,"remainingConfigurations":444},{"removed":"gdpval","score":0.012746637560050393,"rank":335,"remainingConfigurations":444},{"removed":"gmmlu","score":0.014194616754924035,"rank":329,"remainingConfigurations":444},{"removed":"gpqa","score":0.015069407569758103,"rank":323,"remainingConfigurations":444},{"removed":"harvey","score":0.013890982786626503,"rank":328,"remainingConfigurations":444},{"removed":"hle","score":0.016255705611289608,"rank":328,"remainingConfigurations":444},{"removed":"ifbench","score":0.014171140779864684,"rank":326,"remainingConfigurations":444},{"removed":"itbench","score":0.013805592283040903,"rank":328,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01406702870530465,"rank":329,"remainingConfigurations":444},{"removed":"math500","score":0.01416238773341167,"rank":330,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.014607608091473906,"rank":329,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.015381839531622121,"rank":327,"remainingConfigurations":444},{"removed":"omniscience","score":0.010467003910351073,"rank":340,"remainingConfigurations":444},{"removed":"tau-bench","score":0.014969684747786968,"rank":323,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.014295351206925195,"rank":328,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.013044103116148988,"rank":332,"remainingConfigurations":444},{"removed":"arc-agi","score":0.017968192788163764,"rank":327,"remainingConfigurations":444},{"removed":"deepswe","score":0.010963678241946962,"rank":328,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.014054993674964683,"rank":328,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013806079412898844,"rank":328,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013643821349645877,"rank":328,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013842671429809232,"rank":328,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013878139680057916,"rank":328,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0140435424788853,"rank":328,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.013986251395010146,"rank":328,"remainingConfigurations":444},{"removed":"livebench-math","score":0.014068744396374388,"rank":328,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013871017807565755,"rank":328,"remainingConfigurations":444},{"removed":"livebench-language","score":0.014297548721777733,"rank":328,"remainingConfigurations":444},{"removed":"livebench-data","score":0.014049958032759763,"rank":328,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01373459635831818,"rank":328,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013944544590165116,"rank":328,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01440802297073287,"rank":328,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014485317408842036,"rank":328,"remainingConfigurations":444},{"removed":"frontiermath","score":0.014081571122491143,"rank":327,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.013100656621518545,"rank":325,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014841869116678187,"rank":328,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0139930666119894,"rank":328,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.013990574128286179,"rank":328,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013995415623332686,"rank":328,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.014018283018924342,"rank":328,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013948411356903223,"rank":328,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.014006498951749886,"rank":328,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.6--effort-non-reasoning":{"score":0.01391283717616073,"rank":329,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.018571342469827768,"rank":328,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010848097471995404,"rank":329,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013755038857126659,"rank":329,"remainingConfigurations":444},{"removed":"Scale","score":0.016507795259891506,"rank":329,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.013751607071389274,"rank":329,"remainingConfigurations":444},{"removed":"Cognition","score":0.013519988719232613,"rank":330,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014537000908758146,"rank":328,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014338696691400763,"rank":329,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.014205630357805988,"rank":314,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013344998463267041,"rank":328,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.013906552818890784,"rank":329,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.013446060437785826,"rank":329,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013887379966474553,"rank":329,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01391283717616073,"rank":329,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01402960516692734,"rank":329,"remainingConfigurations":444},{"removed":"All provider reports","score":0.013534174917710584,"rank":329,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.014047854559120517,"rank":329,"remainingConfigurations":444},{"removed":"briefcase","score":0.013848324229913016,"rank":329,"remainingConfigurations":444},{"removed":"aime","score":0.014765029124649068,"rank":325,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014152448840110432,"rank":329,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.014517938188191713,"rank":326,"remainingConfigurations":444},{"removed":"automationbench","score":0.013857574653682267,"rank":329,"remainingConfigurations":444},{"removed":"critpt","score":0.014240443992557887,"rank":327,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01392962910115862,"rank":329,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.014281968325950557,"rank":329,"remainingConfigurations":444},{"removed":"gdpval","score":0.014001196093292883,"rank":327,"remainingConfigurations":444},{"removed":"gmmlu","score":0.014079983051843816,"rank":330,"remainingConfigurations":444},{"removed":"gpqa","score":0.014479195060786697,"rank":326,"remainingConfigurations":444},{"removed":"harvey","score":0.013752850102305694,"rank":329,"remainingConfigurations":444},{"removed":"hle","score":0.01626421810966065,"rank":327,"remainingConfigurations":444},{"removed":"ifbench","score":0.014447773948450421,"rank":325,"remainingConfigurations":444},{"removed":"itbench","score":0.013797004074903719,"rank":329,"remainingConfigurations":444},{"removed":"livecodebench","score":0.013898414768793369,"rank":331,"remainingConfigurations":444},{"removed":"math500","score":0.014028696089017995,"rank":331,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.014577217853717942,"rank":330,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.015273346348159878,"rank":329,"remainingConfigurations":444},{"removed":"omniscience","score":0.01100500478313389,"rank":337,"remainingConfigurations":444},{"removed":"tau-bench","score":0.011910236658197243,"rank":339,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.014148833035353053,"rank":329,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012302984622052704,"rank":336,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01784153731726948,"rank":328,"remainingConfigurations":444},{"removed":"deepswe","score":0.010855691855356215,"rank":329,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0139165188042754,"rank":329,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.01366140768680555,"rank":329,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013519988719232613,"rank":330,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013705424278664518,"rank":329,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013741155781992288,"rank":329,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013905196668361814,"rank":329,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01384859299918593,"rank":329,"remainingConfigurations":444},{"removed":"livebench-math","score":0.013930583501894715,"rank":329,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013733854932462687,"rank":329,"remainingConfigurations":444},{"removed":"livebench-language","score":0.014156138298439001,"rank":329,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013911336675933425,"rank":329,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013599401761024378,"rank":329,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013807223309102468,"rank":329,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014266635123622723,"rank":329,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014338696691400763,"rank":329,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01393399087933607,"rank":328,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012936735059193313,"rank":326,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014698662229943371,"rank":329,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.013854945275804118,"rank":329,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.013852744321011766,"rank":329,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013857746214558595,"rank":329,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013879978392914041,"rank":329,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013810704554044928,"rank":329,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.013868548555834678,"rank":329,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-4.1--effort-non-reasoning":{"score":0.013766154724758057,"rank":330,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.018265088038130626,"rank":329,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010731405007337408,"rank":330,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013597823759620464,"rank":331,"remainingConfigurations":444},{"removed":"Scale","score":0.016353967105216832,"rank":330,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01360779810082695,"rank":330,"remainingConfigurations":444},{"removed":"Cognition","score":0.013372157351060494,"rank":331,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014381983228157013,"rank":329,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01419163051547716,"rank":330,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.014021766810773236,"rank":315,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013208417150386486,"rank":329,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01375994422154117,"rank":330,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.013304219443728895,"rank":330,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013740936314432515,"rank":330,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013766154724758057,"rank":330,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013881416315402455,"rank":330,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01339112177303657,"rank":330,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01390860218505522,"rank":330,"remainingConfigurations":444},{"removed":"briefcase","score":0.013710640431092993,"rank":330,"remainingConfigurations":444},{"removed":"aime","score":0.015275464486576356,"rank":324,"remainingConfigurations":444},{"removed":"apex-agents","score":0.014009261133955333,"rank":330,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.012016847871647432,"rank":336,"remainingConfigurations":444},{"removed":"automationbench","score":0.01372078589815435,"rank":330,"remainingConfigurations":444},{"removed":"critpt","score":0.013911720685713233,"rank":330,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.013789059577632731,"rank":330,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.014139375058222575,"rank":330,"remainingConfigurations":444},{"removed":"gdpval","score":0.013867265492549278,"rank":328,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01396438897082368,"rank":331,"remainingConfigurations":444},{"removed":"gpqa","score":0.013892930650541696,"rank":329,"remainingConfigurations":444},{"removed":"harvey","score":0.013609579173622556,"rank":330,"remainingConfigurations":444},{"removed":"hle","score":0.017288191250293117,"rank":324,"remainingConfigurations":444},{"removed":"ifbench","score":0.013008143641764657,"rank":332,"remainingConfigurations":444},{"removed":"itbench","score":0.013655655662703698,"rank":330,"remainingConfigurations":444},{"removed":"livecodebench","score":0.014697682938396102,"rank":326,"remainingConfigurations":444},{"removed":"math500","score":0.014879080472123352,"rank":325,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.013784870580863065,"rank":332,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0149719201839293,"rank":331,"remainingConfigurations":444},{"removed":"omniscience","score":0.010240964481695055,"rank":343,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012742715168324975,"rank":331,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.013996546896468544,"rank":330,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.013434921996010743,"rank":331,"remainingConfigurations":444},{"removed":"arc-agi","score":0.017553697108090627,"rank":329,"remainingConfigurations":444},{"removed":"deepswe","score":0.010738956418662134,"rank":330,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013769801954226517,"rank":330,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013517068226007399,"rank":330,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013372157351060494,"rank":331,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013560240434201077,"rank":330,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013595929241829572,"rank":330,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013758617339703724,"rank":330,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01370272007512225,"rank":330,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01378374828975413,"rank":330,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013589239431317244,"rank":330,"remainingConfigurations":444},{"removed":"livebench-language","score":0.014007023618606985,"rank":330,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013764442997122636,"rank":330,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013455956133896533,"rank":330,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013661700726409468,"rank":330,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014116092486727615,"rank":330,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01419163051547716,"rank":330,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013794968172601724,"rank":329,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012805040209908919,"rank":327,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014545109474106947,"rank":330,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.013708838559756914,"rank":330,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01370669106643252,"rank":330,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013711613333938078,"rank":330,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013733670941533944,"rank":330,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013665118048425443,"rank":330,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.013722311263575463,"rank":330,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-nano--effort-medium":{"score":0.013698431444022628,"rank":331,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.004691363885800493,"rank":194,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.02606811907833172,"rank":304,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010667116877053726,"rank":331,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013600069294477088,"rank":330,"remainingConfigurations":444},{"removed":"Scale","score":0.016211551979014208,"rank":331,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.013530309215718274,"rank":331,"remainingConfigurations":444},{"removed":"Cognition","score":0.013582413454763643,"rank":329,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014249882655369509,"rank":330,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.013966477428182073,"rank":332,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.013453731839319137,"rank":318,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013008891068919582,"rank":331,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01369243515689153,"rank":331,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01325487267969855,"rank":331,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013674912984334599,"rank":331,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013698431444022628,"rank":331,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013816349807556144,"rank":331,"remainingConfigurations":444},{"removed":"All provider reports","score":0.013345900580527629,"rank":331,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.013813679692672276,"rank":331,"remainingConfigurations":444},{"removed":"briefcase","score":0.013625236376253532,"rank":331,"remainingConfigurations":444},{"removed":"aime","score":0.013021035881921232,"rank":332,"remainingConfigurations":444},{"removed":"apex-agents","score":0.013900696076721966,"rank":331,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.013626308531953455,"rank":330,"remainingConfigurations":444},{"removed":"automationbench","score":0.013642704892130873,"rank":331,"remainingConfigurations":444},{"removed":"critpt","score":0.01421373972436682,"rank":328,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0137046962940641,"rank":331,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.013973625763929349,"rank":331,"remainingConfigurations":444},{"removed":"gdpval","score":0.013769669450190203,"rank":329,"remainingConfigurations":444},{"removed":"gmmlu","score":0.013842159889913504,"rank":332,"remainingConfigurations":444},{"removed":"gpqa","score":0.013976249850838576,"rank":328,"remainingConfigurations":444},{"removed":"harvey","score":0.01352337702201987,"rank":331,"remainingConfigurations":444},{"removed":"hle","score":0.015255398321592438,"rank":333,"remainingConfigurations":444},{"removed":"ifbench","score":0.012050873627043296,"rank":338,"remainingConfigurations":444},{"removed":"itbench","score":0.013599900661014542,"rank":331,"remainingConfigurations":444},{"removed":"livecodebench","score":0.012742230322193902,"rank":335,"remainingConfigurations":444},{"removed":"math500","score":0.01381969698761514,"rank":332,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.014850981684058663,"rank":327,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01537749415910694,"rank":328,"remainingConfigurations":444},{"removed":"omniscience","score":0.012538332891102543,"rank":328,"remainingConfigurations":444},{"removed":"tau-bench","score":0.013991691239966098,"rank":326,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.013881332576272214,"rank":331,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.013477510724086888,"rank":330,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02504425900831934,"rank":304,"remainingConfigurations":444},{"removed":"deepswe","score":0.010673433787048313,"rank":331,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013701849865684635,"rank":331,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013229534650710695,"rank":332,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013582413454763643,"rank":329,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01349348477525754,"rank":331,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013532146110291264,"rank":331,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013691388824289509,"rank":331,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.013633303256309084,"rank":331,"remainingConfigurations":444},{"removed":"livebench-math","score":0.013717082923163206,"rank":331,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013524543187911726,"rank":331,"remainingConfigurations":444},{"removed":"livebench-language","score":0.013933511255300261,"rank":331,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013691534004307742,"rank":331,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013390312844117187,"rank":331,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013597197024784957,"rank":331,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.014049187064482549,"rank":331,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.013966477428182073,"rank":332,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01377457055974318,"rank":330,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012428863101601954,"rank":330,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014457387567397164,"rank":331,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01364005701413998,"rank":331,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01363478697873769,"rank":331,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013651423328786086,"rank":331,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01366022226084338,"rank":331,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013593542554568573,"rank":331,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.013657464104573544,"rank":331,"remainingConfigurations":444}],"sharedOrderConflicts":0},"exaone-4.0-32b--effort-reasoning":{"score":0.013624041019591984,"rank":332,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01807490946692197,"rank":331,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010618711908702687,"rank":332,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013457715700788334,"rank":332,"remainingConfigurations":444},{"removed":"Scale","score":0.016176871747809796,"rank":332,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.013465779974644702,"rank":332,"remainingConfigurations":444},{"removed":"Cognition","score":0.013231058691920067,"rank":334,"remainingConfigurations":444},{"removed":"LiveBench","score":0.014230803962161127,"rank":331,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.014039574668835368,"rank":331,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.013808687966969671,"rank":316,"remainingConfigurations":431},{"removed":"Vals AI","score":0.013064946209168102,"rank":330,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.013617888921840493,"rank":332,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01316688159942426,"rank":332,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013599136079670449,"rank":332,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013624041019591984,"rank":332,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013738220067378596,"rank":332,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01325303379288694,"rank":332,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.013753154426945894,"rank":332,"remainingConfigurations":444},{"removed":"briefcase","score":0.013537024738341369,"rank":332,"remainingConfigurations":444},{"removed":"aime","score":0.012321317265564846,"rank":336,"remainingConfigurations":444},{"removed":"apex-agents","score":0.013854245956815432,"rank":332,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.013461334796767171,"rank":331,"remainingConfigurations":444},{"removed":"automationbench","score":0.013537743046511863,"rank":332,"remainingConfigurations":444},{"removed":"critpt","score":0.013757685273950973,"rank":331,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.013633698167105837,"rank":332,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.013949459912329725,"rank":332,"remainingConfigurations":444},{"removed":"gdpval","score":0.013653921534949738,"rank":330,"remainingConfigurations":444},{"removed":"gmmlu","score":0.015492315594786981,"rank":326,"remainingConfigurations":444},{"removed":"gpqa","score":0.012809367605302201,"rank":332,"remainingConfigurations":444},{"removed":"harvey","score":0.013466308723556747,"rank":332,"remainingConfigurations":444},{"removed":"hle","score":0.014095493337020114,"rank":336,"remainingConfigurations":444},{"removed":"ifbench","score":0.014158684596809787,"rank":328,"remainingConfigurations":444},{"removed":"itbench","score":0.013504018352249852,"rank":332,"remainingConfigurations":444},{"removed":"livecodebench","score":0.012070802346960017,"rank":340,"remainingConfigurations":444},{"removed":"math500","score":0.012675019885001098,"rank":335,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.013092908186425792,"rank":335,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.014888522841186443,"rank":332,"remainingConfigurations":444},{"removed":"omniscience","score":0.012883450977587668,"rank":326,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01509930192551797,"rank":322,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.013850007690956808,"rank":332,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.014843414860167622,"rank":324,"remainingConfigurations":444},{"removed":"arc-agi","score":0.017370899895940907,"rank":331,"remainingConfigurations":444},{"removed":"deepswe","score":0.010626163297374204,"rank":332,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013627647887686063,"rank":332,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013376035556326438,"rank":331,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013231058691920067,"rank":334,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013420093936162794,"rank":332,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013455854787860828,"rank":332,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013616522310575583,"rank":332,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.013561098647706762,"rank":332,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01364149722382173,"rank":332,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013448714336426254,"rank":332,"remainingConfigurations":444},{"removed":"livebench-language","score":0.013862347566182343,"rank":332,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013622388061307708,"rank":332,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013317020965860923,"rank":332,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01352064789998444,"rank":332,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.013970674000796804,"rank":332,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.014039574668835368,"rank":331,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013649647592348282,"rank":331,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012657262079371205,"rank":329,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014394600852013911,"rank":332,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.013567290329416228,"rank":332,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.013565143296580396,"rank":332,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013570079783305754,"rank":332,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013591825779546573,"rank":332,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013523984151863023,"rank":332,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.013580605744543955,"rank":332,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-mini--effort-minimal":{"score":0.013438812536982784,"rank":333,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.010228258531247954,"rank":190,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.017002816792733622,"rank":335,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010463379163798489,"rank":333,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013399572072875543,"rank":333,"remainingConfigurations":444},{"removed":"Scale","score":0.015900201739637295,"rank":333,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.013272979297457322,"rank":333,"remainingConfigurations":444},{"removed":"Cognition","score":0.013323847237072695,"rank":332,"remainingConfigurations":444},{"removed":"LiveBench","score":0.013982587588255416,"rank":332,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0137312534561495,"rank":333,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.013135958511964786,"rank":320,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01276322765181011,"rank":333,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01343292311521196,"rank":333,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.013003245637199753,"rank":333,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013415717705909035,"rank":333,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013438812536982784,"rank":333,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013554511269942717,"rank":333,"remainingConfigurations":444},{"removed":"All provider reports","score":0.013092538626342,"rank":333,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01355122640783774,"rank":333,"remainingConfigurations":444},{"removed":"briefcase","score":0.013355234910964757,"rank":333,"remainingConfigurations":444},{"removed":"aime","score":0.013767924650844393,"rank":330,"remainingConfigurations":444},{"removed":"apex-agents","score":0.013637215806091037,"rank":333,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.013261260361576392,"rank":333,"remainingConfigurations":444},{"removed":"automationbench","score":0.013371056088357458,"rank":333,"remainingConfigurations":444},{"removed":"critpt","score":0.013600107497722995,"rank":333,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.013443195195391304,"rank":333,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.013700478198677883,"rank":333,"remainingConfigurations":444},{"removed":"gdpval","score":0.013479048347015113,"rank":331,"remainingConfigurations":444},{"removed":"gmmlu","score":0.013540395170347481,"rank":333,"remainingConfigurations":444},{"removed":"gpqa","score":0.013208515015570915,"rank":330,"remainingConfigurations":444},{"removed":"harvey","score":0.01326736428602295,"rank":333,"remainingConfigurations":444},{"removed":"hle","score":0.015419159449389314,"rank":331,"remainingConfigurations":444},{"removed":"ifbench","score":0.012517042557690183,"rank":333,"remainingConfigurations":444},{"removed":"itbench","score":0.013340749264863451,"rank":333,"remainingConfigurations":444},{"removed":"livecodebench","score":0.013480907212273881,"rank":333,"remainingConfigurations":444},{"removed":"math500","score":0.013500816524598246,"rank":333,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01421396198887942,"rank":331,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.014808137778264015,"rank":333,"remainingConfigurations":444},{"removed":"omniscience","score":0.01166195818469132,"rank":330,"remainingConfigurations":444},{"removed":"tau-bench","score":0.013268479180899406,"rank":330,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.013619090689648205,"rank":333,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.013034540088915034,"rank":333,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01632166933900027,"rank":335,"remainingConfigurations":444},{"removed":"deepswe","score":0.010469592492960223,"rank":333,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013442170399768654,"rank":333,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.012984964013808347,"rank":334,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013323847237072695,"rank":332,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013237668698571734,"rank":333,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01327571807674065,"rank":333,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013431905853071502,"rank":333,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.013374930508463683,"rank":333,"remainingConfigurations":444},{"removed":"livebench-math","score":0.013457110525781782,"rank":333,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013268072934355786,"rank":333,"remainingConfigurations":444},{"removed":"livebench-language","score":0.013669704577920468,"rank":333,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013432088339754525,"rank":333,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013136350400859682,"rank":333,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013339476279364668,"rank":333,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.013782992905773278,"rank":333,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0137312534561495,"rank":333,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013513725218499225,"rank":332,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012186754515046675,"rank":333,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014184209509275953,"rank":333,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01338153383650364,"rank":333,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.013376362594300055,"rank":333,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013392614133644768,"rank":333,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013401349633290316,"rank":333,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013335902387534071,"rank":333,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01339859675772998,"rank":333,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-235b-a22b--effort-reasoning":{"score":0.013316006333473851,"rank":334,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.017705837655707567,"rank":332,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010380144627586739,"rank":334,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.013152008860331493,"rank":334,"remainingConfigurations":444},{"removed":"Scale","score":0.015804860901545852,"rank":334,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01316198429504179,"rank":334,"remainingConfigurations":444},{"removed":"Cognition","score":0.012933232618853529,"rank":335,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01391276230618531,"rank":333,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.013730933783240994,"rank":334,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.013552638651685801,"rank":317,"remainingConfigurations":431},{"removed":"Vals AI","score":0.012773209102890487,"rank":332,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.013309987976245633,"rank":334,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.012868867455979052,"rank":334,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013291634399250097,"rank":334,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013316006333473851,"rank":334,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013427759787628897,"rank":334,"remainingConfigurations":444},{"removed":"All provider reports","score":0.012953187181034652,"rank":334,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01344722148851867,"rank":334,"remainingConfigurations":444},{"removed":"briefcase","score":0.013243174417551183,"rank":334,"remainingConfigurations":444},{"removed":"aime","score":0.011703323043480379,"rank":342,"remainingConfigurations":444},{"removed":"apex-agents","score":0.013543782663020172,"rank":334,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.015255813411205568,"rank":323,"remainingConfigurations":444},{"removed":"automationbench","score":0.013254013264022563,"rank":334,"remainingConfigurations":444},{"removed":"critpt","score":0.013473736473554737,"rank":334,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.013333292692899163,"rank":334,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01365626857782746,"rank":334,"remainingConfigurations":444},{"removed":"gdpval","score":0.013379321927501901,"rank":332,"remainingConfigurations":444},{"removed":"gmmlu","score":0.013491414386857773,"rank":334,"remainingConfigurations":444},{"removed":"gpqa","score":0.012879894387456306,"rank":331,"remainingConfigurations":444},{"removed":"harvey","score":0.013163165307614329,"rank":334,"remainingConfigurations":444},{"removed":"hle","score":0.013786965840975255,"rank":339,"remainingConfigurations":444},{"removed":"ifbench","score":0.013406428193063404,"rank":331,"remainingConfigurations":444},{"removed":"itbench","score":0.013200538149277269,"rank":334,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01285828369188409,"rank":334,"remainingConfigurations":444},{"removed":"math500","score":0.014285577032662714,"rank":328,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012210413254445185,"rank":340,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.014626267896109463,"rank":334,"remainingConfigurations":444},{"removed":"omniscience","score":0.011216454336753237,"rank":335,"remainingConfigurations":444},{"removed":"tau-bench","score":0.013893078197501635,"rank":327,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.013542069634478187,"rank":334,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.014004303525416465,"rank":328,"remainingConfigurations":444},{"removed":"arc-agi","score":0.017012677554101466,"rank":332,"remainingConfigurations":444},{"removed":"deepswe","score":0.01038741934859841,"rank":334,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013319533877582333,"rank":334,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.013074335678835815,"rank":333,"remainingConfigurations":444},{"removed":"frontiercode","score":0.012933232618853529,"rank":335,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.013117174728784075,"rank":334,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.013151571753864473,"rank":334,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.013308714949916282,"rank":334,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.013254519214881756,"rank":334,"remainingConfigurations":444},{"removed":"livebench-math","score":0.013333039315429146,"rank":334,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.013144460511872942,"rank":334,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01354912820974822,"rank":334,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013314574760801815,"rank":334,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.013015695947793776,"rank":334,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.013214809378272028,"rank":334,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.013655049391334275,"rank":334,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.013730933783240994,"rank":334,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013339300192014217,"rank":333,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012372700554421974,"rank":331,"remainingConfigurations":444},{"removed":"simpleqa","score":0.014070064248906632,"rank":334,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.013260520348607419,"rank":334,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.013258420762317749,"rank":334,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.013263231664295891,"rank":334,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013284505218482902,"rank":334,"remainingConfigurations":444},{"removed":"vibe-code","score":0.013218138970065236,"rank":334,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.013273567917157917,"rank":334,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-lite--effort-low":{"score":0.013033506625445154,"rank":335,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01737763669559306,"rank":334,"remainingConfigurations":444},{"removed":"Datacurve","score":0.010159371843233822,"rank":335,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.012881571545385455,"rank":335,"remainingConfigurations":444},{"removed":"Scale","score":0.015490090666719318,"rank":335,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.012883117124646347,"rank":335,"remainingConfigurations":444},{"removed":"Cognition","score":0.012672271670446924,"rank":336,"remainingConfigurations":444},{"removed":"LiveBench","score":0.013618693959988002,"rank":334,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.013420348773356986,"rank":335,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.013372610992751006,"rank":319,"remainingConfigurations":431},{"removed":"Vals AI","score":0.012502934700390456,"rank":334,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01302760385013777,"rank":335,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.012595436913268107,"rank":335,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.013009577434294458,"rank":335,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.013033506625445154,"rank":335,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.013143183537603081,"rank":335,"remainingConfigurations":444},{"removed":"All provider reports","score":0.012678165882621488,"rank":335,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.013167743155022884,"rank":335,"remainingConfigurations":444},{"removed":"briefcase","score":0.012974220558477965,"rank":335,"remainingConfigurations":444},{"removed":"aime","score":0.013516307954394699,"rank":331,"remainingConfigurations":444},{"removed":"apex-agents","score":0.013261051949869524,"rank":335,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011935647296470224,"rank":338,"remainingConfigurations":444},{"removed":"automationbench","score":0.012984715281175572,"rank":335,"remainingConfigurations":444},{"removed":"critpt","score":0.013222398996154114,"rank":335,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.013047465587072751,"rank":335,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01338427814530832,"rank":335,"remainingConfigurations":444},{"removed":"gdpval","score":0.013107270480698078,"rank":334,"remainingConfigurations":444},{"removed":"gmmlu","score":0.013214243687344149,"rank":335,"remainingConfigurations":444},{"removed":"gpqa","score":0.01264997430408782,"rank":333,"remainingConfigurations":444},{"removed":"harvey","score":0.012883312348314739,"rank":335,"remainingConfigurations":444},{"removed":"hle","score":0.016861544883511725,"rank":326,"remainingConfigurations":444},{"removed":"ifbench","score":0.01066961837612288,"rank":344,"remainingConfigurations":444},{"removed":"itbench","score":0.012919073578359542,"rank":335,"remainingConfigurations":444},{"removed":"livecodebench","score":0.013759788378104107,"rank":332,"remainingConfigurations":444},{"removed":"math500","score":0.013091802745625969,"rank":334,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01347242898482178,"rank":333,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.014527621640233968,"rank":335,"remainingConfigurations":444},{"removed":"omniscience","score":0.011247260394672975,"rank":334,"remainingConfigurations":444},{"removed":"tau-bench","score":0.011364063261074697,"rank":340,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01325446726736755,"rank":335,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.014213332535491391,"rank":327,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01667949109960276,"rank":334,"remainingConfigurations":444},{"removed":"deepswe","score":0.010166471420336144,"rank":335,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.013036958902856013,"rank":335,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.012798571152966986,"rank":335,"remainingConfigurations":444},{"removed":"frontiercode","score":0.012672271670446924,"rank":336,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.012838900334740928,"rank":335,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.012872599390033093,"rank":335,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01302635408575585,"rank":335,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01297321715359831,"rank":335,"remainingConfigurations":444},{"removed":"livebench-math","score":0.013050127272122486,"rank":335,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.012865525636527377,"rank":335,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01326184191119015,"rank":335,"remainingConfigurations":444},{"removed":"livebench-data","score":0.013032123830232487,"rank":335,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.012739369481433374,"rank":335,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.012934387257147668,"rank":335,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.013365621135052894,"rank":335,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.013420348773356986,"rank":335,"remainingConfigurations":444},{"removed":"frontiermath","score":0.013087285549560124,"rank":335,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.012132093905747569,"rank":334,"remainingConfigurations":444},{"removed":"simpleqa","score":0.013770711795908884,"rank":335,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.012979199068614463,"rank":335,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.012977099400367243,"rank":335,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.012981832841903742,"rank":335,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.013002621591485318,"rank":335,"remainingConfigurations":444},{"removed":"vibe-code","score":0.01293763662089704,"rank":335,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.012991955549734993,"rank":335,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-3.5-flash-lite--effort-minimal":{"score":0.01238039921200581,"rank":336,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.010531439789624399,"rank":189,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.024456337249377066,"rank":310,"remainingConfigurations":444},{"removed":"Datacurve","score":0.009674946145719896,"rank":336,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.012388760425874806,"rank":336,"remainingConfigurations":444},{"removed":"Scale","score":0.014587521647006238,"rank":336,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.012224955096315528,"rank":336,"remainingConfigurations":444},{"removed":"Cognition","score":0.013237068886417777,"rank":333,"remainingConfigurations":444},{"removed":"LiveBench","score":0.012772336935652781,"rank":335,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.012431709300397957,"rank":339,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004902988817050444,"rank":372,"remainingConfigurations":431},{"removed":"Vals AI","score":0.011723353100708845,"rank":335,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.012375490320608052,"rank":336,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.012002585962305433,"rank":336,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01236266678809376,"rank":336,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01238039921200581,"rank":336,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.012481842291959542,"rank":336,"remainingConfigurations":444},{"removed":"All provider reports","score":0.012083617042351022,"rank":336,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.012454043600353083,"rank":336,"remainingConfigurations":444},{"removed":"briefcase","score":0.0122888152531454,"rank":337,"remainingConfigurations":444},{"removed":"aime","score":0.011221272850616247,"rank":348,"remainingConfigurations":444},{"removed":"apex-agents","score":0.012524346935450197,"rank":336,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.012351236817310068,"rank":334,"remainingConfigurations":444},{"removed":"automationbench","score":0.01231032384157246,"rank":336,"remainingConfigurations":444},{"removed":"critpt","score":0.012355560508305429,"rank":336,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0123812763039369,"rank":336,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.012487774124182852,"rank":336,"remainingConfigurations":444},{"removed":"gdpval","score":0.012332434354905705,"rank":337,"remainingConfigurations":444},{"removed":"gmmlu","score":0.012423827530159257,"rank":337,"remainingConfigurations":444},{"removed":"gpqa","score":0.010929740297365147,"rank":349,"remainingConfigurations":444},{"removed":"harvey","score":0.012203241047251893,"rank":336,"remainingConfigurations":444},{"removed":"hle","score":0.013584695035614556,"rank":340,"remainingConfigurations":444},{"removed":"ifbench","score":0.012166639813996821,"rank":336,"remainingConfigurations":444},{"removed":"itbench","score":0.012315295918779135,"rank":336,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01240393866828715,"rank":337,"remainingConfigurations":444},{"removed":"math500","score":0.012404672773249097,"rank":336,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012921197724886169,"rank":336,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0135022657480049,"rank":336,"remainingConfigurations":444},{"removed":"omniscience","score":0.01191991555157109,"rank":329,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012108674927336282,"rank":336,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.012473034145806583,"rank":336,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012263850357462684,"rank":337,"remainingConfigurations":444},{"removed":"arc-agi","score":0.02358032089296842,"rank":310,"remainingConfigurations":444},{"removed":"deepswe","score":0.009680636419473945,"rank":336,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.012383266442504202,"rank":336,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011908360393188785,"rank":338,"remainingConfigurations":444},{"removed":"frontiercode","score":0.013237068886417777,"rank":333,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01220606938022955,"rank":336,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.012224882017917672,"rank":336,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01237482169803692,"rank":336,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.012317506483735773,"rank":336,"remainingConfigurations":444},{"removed":"livebench-math","score":0.012403176558081758,"rank":336,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.012206077627728436,"rank":336,"remainingConfigurations":444},{"removed":"livebench-language","score":0.012588571021478217,"rank":336,"remainingConfigurations":444},{"removed":"livebench-data","score":0.012376870270030163,"rank":336,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.012108505083860348,"rank":336,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.012284233778477248,"rank":336,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.012707757396374373,"rank":336,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.012431709300397957,"rank":339,"remainingConfigurations":444},{"removed":"frontiermath","score":0.012457858269295677,"rank":336,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00846804016932915,"rank":359,"remainingConfigurations":444},{"removed":"simpleqa","score":0.013059117839832666,"rank":336,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.012328101244241996,"rank":336,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.012323666137980561,"rank":336,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.012339513300416403,"rank":336,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.012344779856777543,"rank":336,"remainingConfigurations":444},{"removed":"vibe-code","score":0.012288357450899366,"rank":336,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.012341154604682136,"rank":336,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-32b--effort-reasoning":{"score":0.012189538147372456,"rank":337,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.016125903561123457,"rank":337,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00949718428779144,"rank":337,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.012044936144882114,"rank":337,"remainingConfigurations":444},{"removed":"Scale","score":0.01448452145790709,"rank":337,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0120481353601777,"rank":337,"remainingConfigurations":444},{"removed":"Cognition","score":0.011824693566556285,"rank":337,"remainingConfigurations":444},{"removed":"LiveBench","score":0.012742344590241353,"rank":336,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.012568463868552147,"rank":336,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.012496814887480024,"rank":322,"remainingConfigurations":431},{"removed":"Vals AI","score":0.011703262528272208,"rank":336,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.012183985219979309,"rank":337,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01177784514739483,"rank":337,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.012167105887297762,"rank":337,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.012189538147372456,"rank":337,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01229167205542978,"rank":337,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011854734380513912,"rank":337,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.012312166028697885,"rank":337,"remainingConfigurations":444},{"removed":"briefcase","score":0.012635009662105257,"rank":336,"remainingConfigurations":444},{"removed":"aime","score":0.011397318183796993,"rank":345,"remainingConfigurations":444},{"removed":"apex-agents","score":0.012408485561686172,"rank":337,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.013312491320724347,"rank":332,"remainingConfigurations":444},{"removed":"automationbench","score":0.01199172263141948,"rank":338,"remainingConfigurations":444},{"removed":"critpt","score":0.010592561618707799,"rank":351,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.012202922458033415,"rank":337,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.012211270034331688,"rank":339,"remainingConfigurations":444},{"removed":"gdpval","score":0.012610609399016405,"rank":336,"remainingConfigurations":444},{"removed":"gmmlu","score":0.012306854328404726,"rank":339,"remainingConfigurations":444},{"removed":"gpqa","score":0.012112259237723433,"rank":335,"remainingConfigurations":444},{"removed":"harvey","score":0.012049379914524108,"rank":337,"remainingConfigurations":444},{"removed":"hle","score":0.013458145358449844,"rank":342,"remainingConfigurations":444},{"removed":"ifbench","score":0.01218140301322307,"rank":335,"remainingConfigurations":444},{"removed":"itbench","score":0.012084652821296962,"rank":337,"remainingConfigurations":444},{"removed":"livecodebench","score":0.012161422445261928,"rank":339,"remainingConfigurations":444},{"removed":"math500","score":0.012055671062742494,"rank":339,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012405025110376345,"rank":338,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.013336697074539014,"rank":338,"remainingConfigurations":444},{"removed":"omniscience","score":0.010633698188289213,"rank":339,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012001997786660655,"rank":337,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.012393457343975364,"rank":337,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012727821136415018,"rank":334,"remainingConfigurations":444},{"removed":"arc-agi","score":0.015501323440613932,"rank":337,"remainingConfigurations":444},{"removed":"deepswe","score":0.00950394804696677,"rank":337,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.012192816356567757,"rank":337,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011975235742725984,"rank":336,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011824693566556285,"rank":337,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.012007398675870778,"rank":337,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.012038538547445715,"rank":337,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.012182979025645973,"rank":337,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01213375582368977,"rank":337,"remainingConfigurations":444},{"removed":"livebench-math","score":0.012204843815906837,"rank":337,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.012032840627804284,"rank":337,"remainingConfigurations":444},{"removed":"livebench-language","score":0.012404174116707667,"rank":337,"remainingConfigurations":444},{"removed":"livebench-data","score":0.012187992841424822,"rank":337,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.011913494395507788,"rank":337,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.012096740767670117,"rank":337,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.012500232148051961,"rank":337,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.012568463868552147,"rank":336,"remainingConfigurations":444},{"removed":"frontiermath","score":0.012208119751344183,"rank":337,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.011359031228895422,"rank":335,"remainingConfigurations":444},{"removed":"simpleqa","score":0.012880945073565284,"rank":337,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.012138651826487018,"rank":337,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.012136774548535357,"rank":337,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.012140929213581486,"rank":337,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.012160876017107606,"rank":337,"remainingConfigurations":444},{"removed":"vibe-code","score":0.012099791313713774,"rank":337,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.012150626180221362,"rank":337,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-32b-instruct--effort-non-reasoning":{"score":0.012165564860530593,"rank":338,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.016139666438466288,"rank":336,"remainingConfigurations":444},{"removed":"Datacurve","score":0.009478409281403883,"rank":338,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.012014308524155614,"rank":338,"remainingConfigurations":444},{"removed":"Scale","score":0.014446726628873698,"rank":338,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.012025159442757375,"rank":338,"remainingConfigurations":444},{"removed":"Cognition","score":0.011821600872837753,"rank":338,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01271039586410243,"rank":337,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.012535996008865305,"rank":337,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01235931635126043,"rank":324,"remainingConfigurations":431},{"removed":"Vals AI","score":0.011670488394122394,"rank":337,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.012160061477301384,"rank":338,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.011756186098177385,"rank":338,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.012143245576406829,"rank":338,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.012165564860530593,"rank":338,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01226764822331472,"rank":338,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011833153416408858,"rank":338,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01228241243627245,"rank":338,"remainingConfigurations":444},{"removed":"briefcase","score":0.012094783722803057,"rank":338,"remainingConfigurations":444},{"removed":"aime","score":0.011333257983256148,"rank":347,"remainingConfigurations":444},{"removed":"apex-agents","score":0.012371820855303297,"rank":338,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011989666881831269,"rank":337,"remainingConfigurations":444},{"removed":"automationbench","score":0.01210972384491969,"rank":337,"remainingConfigurations":444},{"removed":"critpt","score":0.012254923453973244,"rank":337,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.012174294693992692,"rank":338,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.012480663086273117,"rank":337,"remainingConfigurations":444},{"removed":"gdpval","score":0.012233776869435877,"rank":338,"remainingConfigurations":444},{"removed":"gmmlu","score":0.012324593025430921,"rank":338,"remainingConfigurations":444},{"removed":"gpqa","score":0.012034046534619041,"rank":336,"remainingConfigurations":444},{"removed":"harvey","score":0.012024470221227495,"rank":338,"remainingConfigurations":444},{"removed":"hle","score":0.013546024017858224,"rank":341,"remainingConfigurations":444},{"removed":"ifbench","score":0.012015304362738864,"rank":339,"remainingConfigurations":444},{"removed":"itbench","score":0.01205969587344275,"rank":338,"remainingConfigurations":444},{"removed":"livecodebench","score":0.012310437919767351,"rank":338,"remainingConfigurations":444},{"removed":"math500","score":0.012267385042228018,"rank":337,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012379325485999728,"rank":339,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012517086646917348,"rank":345,"remainingConfigurations":444},{"removed":"omniscience","score":0.011357517649470891,"rank":332,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012154630454276547,"rank":335,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.012367261707933813,"rank":338,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012077635314178057,"rank":340,"remainingConfigurations":444},{"removed":"arc-agi","score":0.015507914991232247,"rank":336,"remainingConfigurations":444},{"removed":"deepswe","score":0.00948508107742403,"rank":338,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.012168793610076063,"rank":338,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011945064085000885,"rank":337,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011821600872837753,"rank":338,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01198309165240786,"rank":338,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.012014879026503014,"rank":338,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0121589139747722,"rank":338,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.012109355286441541,"rank":338,"remainingConfigurations":444},{"removed":"livebench-math","score":0.012181171020263115,"rank":338,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.012008597044734039,"rank":338,"remainingConfigurations":444},{"removed":"livebench-language","score":0.012379069398128197,"rank":338,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01216414770453407,"rank":338,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.011890607720804114,"rank":338,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.012072933954336694,"rank":338,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.012475958021717264,"rank":338,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.012535996008865305,"rank":337,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0121916865522171,"rank":338,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.011307761455084058,"rank":336,"remainingConfigurations":444},{"removed":"simpleqa","score":0.012856126504262974,"rank":338,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01211475939170197,"rank":338,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.012112831411508254,"rank":338,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.012117233724565793,"rank":338,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01213671316424384,"rank":338,"remainingConfigurations":444},{"removed":"vibe-code","score":0.012075978802156969,"rank":338,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.012126706864258352,"rank":338,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-large-3--effort-non-reasoning":{"score":0.012075232831022275,"rank":339,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.015990132420137335,"rank":338,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00940665480399114,"rank":339,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011933198386583717,"rank":339,"remainingConfigurations":444},{"removed":"Scale","score":0.014378271302767408,"rank":339,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011934606339931854,"rank":339,"remainingConfigurations":444},{"removed":"Cognition","score":0.011714874498574354,"rank":339,"remainingConfigurations":444},{"removed":"LiveBench","score":0.012621137496003581,"rank":338,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.012454404394113536,"rank":338,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.012411232717220262,"rank":323,"remainingConfigurations":431},{"removed":"Vals AI","score":0.011598759484773966,"rank":338,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01206974099620159,"rank":339,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.011667630695898082,"rank":339,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.012052990073229228,"rank":339,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.012075232831022275,"rank":339,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01217637046704654,"rank":339,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011743747869014732,"rank":339,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.012194173281749328,"rank":339,"remainingConfigurations":444},{"removed":"briefcase","score":0.011784623514753559,"rank":339,"remainingConfigurations":444},{"removed":"aime","score":0.01272563462667149,"rank":334,"remainingConfigurations":444},{"removed":"apex-agents","score":0.012295479323757269,"rank":339,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011872021101089736,"rank":339,"remainingConfigurations":444},{"removed":"automationbench","score":0.011688705970077503,"rank":340,"remainingConfigurations":444},{"removed":"critpt","score":0.012041442932083141,"rank":338,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.012087575473769116,"rank":339,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.012363126915201904,"rank":338,"remainingConfigurations":444},{"removed":"gdpval","score":0.011757124569318505,"rank":339,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011827413791179698,"rank":341,"remainingConfigurations":444},{"removed":"gpqa","score":0.01187967342332149,"rank":338,"remainingConfigurations":444},{"removed":"harvey","score":0.01193481759880633,"rank":339,"remainingConfigurations":444},{"removed":"hle","score":0.014830983263955889,"rank":334,"remainingConfigurations":444},{"removed":"ifbench","score":0.012145514016421449,"rank":337,"remainingConfigurations":444},{"removed":"itbench","score":0.01197345787555548,"rank":339,"remainingConfigurations":444},{"removed":"livecodebench","score":0.012560261610560052,"rank":336,"remainingConfigurations":444},{"removed":"math500","score":0.01217486700538367,"rank":338,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012044166646658826,"rank":342,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.013421287684680256,"rank":337,"remainingConfigurations":444},{"removed":"omniscience","score":0.009556076918094536,"rank":348,"remainingConfigurations":444},{"removed":"tau-bench","score":0.011993829649541295,"rank":338,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.012274183873270889,"rank":339,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.01177850594664058,"rank":344,"remainingConfigurations":444},{"removed":"arc-agi","score":0.015371570197692972,"rank":338,"remainingConfigurations":444},{"removed":"deepswe","score":0.009413354111457823,"rank":339,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.012078475954666703,"rank":339,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011861786022198909,"rank":339,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011714874498574354,"rank":339,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011894241310109578,"rank":339,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011925495137040483,"rank":339,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.012068700697505383,"rank":339,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.012019949476588293,"rank":339,"remainingConfigurations":444},{"removed":"livebench-math","score":0.012090465556698385,"rank":339,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011920040035753867,"rank":339,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01228780413356684,"rank":339,"remainingConfigurations":444},{"removed":"livebench-data","score":0.012073512269056097,"rank":339,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01180181357333889,"rank":339,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011983340641452416,"rank":339,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01238306470918834,"rank":339,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.012454404394113536,"rank":338,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01209425778623094,"rank":339,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.011253288353582726,"rank":337,"remainingConfigurations":444},{"removed":"simpleqa","score":0.012760157034792571,"rank":339,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.012024788335661014,"rank":339,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.012022936830125182,"rank":339,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.012027096391324316,"rank":339,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.012046797030771633,"rank":339,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011986330665695898,"rank":339,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.012036638725846259,"rank":339,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-2.5-flash-lite--effort-reasoning":{"score":0.011679492035361285,"rank":340,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.015507814175769562,"rank":339,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00910077601614776,"rank":340,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011536970698238199,"rank":340,"remainingConfigurations":444},{"removed":"Scale","score":0.013881145749384675,"rank":340,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011545506077174144,"rank":340,"remainingConfigurations":444},{"removed":"Cognition","score":0.011350209881870035,"rank":340,"remainingConfigurations":444},{"removed":"LiveBench","score":0.012206830819779255,"rank":339,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.012039855012966743,"rank":340,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011902892207672383,"rank":325,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01120531121514179,"rank":339,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011674195096015597,"rank":340,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.011286146165896365,"rank":340,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011658081026765242,"rank":340,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011679492035361285,"rank":340,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011777693778754731,"rank":340,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01136023074585558,"rank":340,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011798078982681731,"rank":340,"remainingConfigurations":444},{"removed":"briefcase","score":0.011626124061784572,"rank":340,"remainingConfigurations":444},{"removed":"aime","score":0.011753315982266333,"rank":341,"remainingConfigurations":444},{"removed":"apex-agents","score":0.011882671910936421,"rank":340,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010701290461319875,"rank":347,"remainingConfigurations":444},{"removed":"automationbench","score":0.011637384568194938,"rank":341,"remainingConfigurations":444},{"removed":"critpt","score":0.011587238217797564,"rank":340,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011693074550847754,"rank":340,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011991110044982245,"rank":340,"remainingConfigurations":444},{"removed":"gdpval","score":0.01174398704067064,"rank":340,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01181443871175912,"rank":342,"remainingConfigurations":444},{"removed":"gpqa","score":0.011930419163485423,"rank":337,"remainingConfigurations":444},{"removed":"harvey","score":0.011546166734271801,"rank":340,"remainingConfigurations":444},{"removed":"hle","score":0.01296317536331826,"rank":346,"remainingConfigurations":444},{"removed":"ifbench","score":0.010282114290172147,"rank":347,"remainingConfigurations":444},{"removed":"itbench","score":0.011578076565096967,"rank":340,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011348740998854539,"rank":345,"remainingConfigurations":444},{"removed":"math500","score":0.011178652975659375,"rank":348,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012742562697850951,"rank":337,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01287722509155416,"rank":340,"remainingConfigurations":444},{"removed":"omniscience","score":0.009915063996797582,"rank":347,"remainingConfigurations":444},{"removed":"tau-bench","score":0.012603534154086347,"rank":332,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011877709560652159,"rank":340,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012367125834513737,"rank":335,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014894489112247408,"rank":339,"remainingConfigurations":444},{"removed":"deepswe","score":0.00910717156822815,"rank":340,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01168259399102336,"rank":340,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011468566015319537,"rank":340,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011350209881870035,"rank":340,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011504644967231773,"rank":340,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01153506780225517,"rank":340,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011673126219747787,"rank":340,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011625457066172842,"rank":340,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011694449029174367,"rank":340,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011528611305191484,"rank":340,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011884712126569658,"rank":340,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011678174438727757,"rank":340,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01141520713723476,"rank":340,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01159046768512875,"rank":340,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011977872524042017,"rank":340,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.012039855012966743,"rank":340,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011702437618576854,"rank":340,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01086147927195938,"rank":338,"remainingConfigurations":444},{"removed":"simpleqa","score":0.012343571696766227,"rank":340,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011630689819949679,"rank":340,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011628793087224943,"rank":340,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011633058737350916,"rank":340,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011651735719813794,"rank":340,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011593356237842843,"rank":340,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011642169705083564,"rank":340,"remainingConfigurations":444}],"sharedOrderConflicts":0},"k-exaone-236b-a23b--effort-non-reasoning":{"score":0.011594002705820389,"rank":341,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.015465039005496707,"rank":340,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00903252724036788,"rank":341,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011461225398444368,"rank":341,"remainingConfigurations":444},{"removed":"Scale","score":0.013781029452648037,"rank":341,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01145846739731714,"rank":341,"remainingConfigurations":444},{"removed":"Cognition","score":0.011269903288293076,"rank":341,"remainingConfigurations":444},{"removed":"LiveBench","score":0.012116907892580055,"rank":340,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011939320515623604,"rank":341,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011794682729661643,"rank":327,"remainingConfigurations":431},{"removed":"Vals AI","score":0.011120370638455036,"rank":340,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011588743231828116,"rank":341,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.011203431360723853,"rank":341,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011572718844399197,"rank":341,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011594002705820389,"rank":341,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011691502557984908,"rank":341,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011276959481166332,"rank":341,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01170776069470855,"rank":341,"remainingConfigurations":444},{"removed":"briefcase","score":0.011521971428644856,"rank":342,"remainingConfigurations":444},{"removed":"aime","score":0.012202041452401035,"rank":338,"remainingConfigurations":444},{"removed":"apex-agents","score":0.011794536996706823,"rank":341,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010476836394359987,"rank":351,"remainingConfigurations":444},{"removed":"automationbench","score":0.011530678985181538,"rank":343,"remainingConfigurations":444},{"removed":"critpt","score":0.011645471989795748,"rank":339,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01160347441723916,"rank":341,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011885414145490873,"rank":342,"remainingConfigurations":444},{"removed":"gdpval","score":0.011617503614478391,"rank":343,"remainingConfigurations":444},{"removed":"gmmlu","score":0.012764880648836229,"rank":336,"remainingConfigurations":444},{"removed":"gpqa","score":0.011124991609116418,"rank":345,"remainingConfigurations":444},{"removed":"harvey","score":0.011460080186844598,"rank":341,"remainingConfigurations":444},{"removed":"hle","score":0.013250859162731323,"rank":344,"remainingConfigurations":444},{"removed":"ifbench","score":0.011328591281174472,"rank":340,"remainingConfigurations":444},{"removed":"itbench","score":0.011493703224636727,"rank":341,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011661074089393294,"rank":343,"remainingConfigurations":444},{"removed":"math500","score":0.01172212954825076,"rank":341,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.010987131196903146,"rank":352,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01272533552503491,"rank":342,"remainingConfigurations":444},{"removed":"omniscience","score":0.011071442465833919,"rank":336,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010156896943428202,"rank":353,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011788829019424381,"rank":341,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.011828636231413692,"rank":343,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014856220386741033,"rank":340,"remainingConfigurations":444},{"removed":"deepswe","score":0.009038870727589363,"rank":341,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011597083270122358,"rank":341,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011384318808712083,"rank":341,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011269903288293076,"rank":341,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011420049767446103,"rank":341,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011450561310536482,"rank":341,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011587638803788028,"rank":341,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011540330414113712,"rank":341,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011608870725294743,"rank":341,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011444041037943229,"rank":341,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011797679670361832,"rank":341,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01159280767554074,"rank":341,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.011331665150371033,"rank":341,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011505577072414388,"rank":341,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011890361316072693,"rank":341,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011939320515623604,"rank":341,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011617873897482917,"rank":341,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010764734431007618,"rank":339,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01225219766444001,"rank":341,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011545535876049083,"rank":341,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011543687138947711,"rank":341,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011547885207118814,"rank":341,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011566453883901458,"rank":341,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011508510825710761,"rank":341,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011556909035965604,"rank":341,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-coder-480b-a35b-instruct--effort-non-reasoning":{"score":0.011581192991304707,"rank":342,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.015376022621683536,"rank":341,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0090227439264802,"rank":342,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01144000117316723,"rank":342,"remainingConfigurations":444},{"removed":"Scale","score":0.013762106948000568,"rank":342,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011447469143495667,"rank":342,"remainingConfigurations":444},{"removed":"Cognition","score":0.01125535923016898,"rank":342,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01210259612033561,"rank":341,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011938885809331548,"rank":342,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011798679035968864,"rank":326,"remainingConfigurations":431},{"removed":"Vals AI","score":0.01111233443603822,"rank":341,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011575949288851665,"rank":342,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.011191242437355796,"rank":342,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011559957126647423,"rank":342,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011581192991304707,"rank":342,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01167833440899098,"rank":342,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01126448350586482,"rank":342,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011697073251414197,"rank":342,"remainingConfigurations":444},{"removed":"briefcase","score":0.011526411776672576,"rank":341,"remainingConfigurations":444},{"removed":"aime","score":0.012209605791603996,"rank":337,"remainingConfigurations":444},{"removed":"apex-agents","score":0.011780895454627844,"rank":342,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010983194653075236,"rank":344,"remainingConfigurations":444},{"removed":"automationbench","score":0.011538009005764752,"rank":342,"remainingConfigurations":444},{"removed":"critpt","score":0.011506400453078517,"rank":341,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011591899631764066,"rank":342,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01189018843707667,"rank":341,"remainingConfigurations":444},{"removed":"gdpval","score":0.0116539919521981,"rank":342,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011758648199575996,"rank":343,"remainingConfigurations":444},{"removed":"gpqa","score":0.011871891448997056,"rank":339,"remainingConfigurations":444},{"removed":"harvey","score":0.011447503783783784,"rank":342,"remainingConfigurations":444},{"removed":"hle","score":0.014069993080918204,"rank":337,"remainingConfigurations":444},{"removed":"ifbench","score":0.011119341367943432,"rank":342,"remainingConfigurations":444},{"removed":"itbench","score":0.011483197639120436,"rank":342,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011289366079467,"rank":346,"remainingConfigurations":444},{"removed":"math500","score":0.011458933922343076,"rank":343,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011845212312624082,"rank":345,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012730245134241267,"rank":341,"remainingConfigurations":444},{"removed":"omniscience","score":0.010380283483380114,"rank":341,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010699010489507695,"rank":345,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011773830907153025,"rank":342,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010734094056301678,"rank":347,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014774849958897232,"rank":341,"remainingConfigurations":444},{"removed":"deepswe","score":0.009029111718171522,"rank":342,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011584274367947222,"rank":342,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011370680997998116,"rank":342,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01125535923016898,"rank":342,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011407286905577558,"rank":342,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011437652937839956,"rank":342,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011574888557001296,"rank":342,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01152774931787782,"rank":342,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011596085628640083,"rank":342,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011431471392504654,"rank":342,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011784687943029013,"rank":342,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011579940597108096,"rank":342,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0113191439481097,"rank":342,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.01149287540878186,"rank":342,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011877085854838555,"rank":342,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011938885809331548,"rank":342,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011605771704758515,"rank":342,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010762932025443145,"rank":340,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01224070490892556,"rank":342,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011532753931026414,"rank":342,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011530946902793266,"rank":342,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011535114796511469,"rank":342,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.01155371385949139,"rank":342,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011495819267075914,"rank":342,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011544148702082598,"rank":342,"remainingConfigurations":444}],"sharedOrderConflicts":0},"devstral-2512--effort-non-reasoning":{"score":0.011380471022361784,"rank":343,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.015078837581087927,"rank":342,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008862775368810742,"rank":343,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011243745209807478,"rank":343,"remainingConfigurations":444},{"removed":"Scale","score":0.013555362536086303,"rank":343,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011247839948933447,"rank":343,"remainingConfigurations":444},{"removed":"Cognition","score":0.011041987669897895,"rank":343,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011897125613500823,"rank":342,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01174615465568126,"rank":343,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011735838263260662,"rank":328,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010931547574702952,"rank":342,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011375287267725387,"rank":343,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010995918103612787,"rank":343,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011359517377686099,"rank":343,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011380471022361784,"rank":343,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011475828845669488,"rank":343,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011067696130016853,"rank":343,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011498414702955082,"rank":343,"remainingConfigurations":444},{"removed":"briefcase","score":0.010622290527626838,"rank":350,"remainingConfigurations":444},{"removed":"aime","score":0.012110288567638931,"rank":339,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01159451397037417,"rank":343,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011329994528033195,"rank":341,"remainingConfigurations":444},{"removed":"automationbench","score":0.010629389622881687,"rank":350,"remainingConfigurations":444},{"removed":"critpt","score":0.01130790408603497,"rank":342,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011398057040316864,"rank":343,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011280176827955832,"rank":348,"remainingConfigurations":444},{"removed":"gdpval","score":0.010691915718587809,"rank":353,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011743070528056147,"rank":344,"remainingConfigurations":444},{"removed":"gpqa","score":0.011720433557354392,"rank":340,"remainingConfigurations":444},{"removed":"harvey","score":0.011251601332658004,"rank":343,"remainingConfigurations":444},{"removed":"hle","score":0.0144460006381417,"rank":335,"remainingConfigurations":444},{"removed":"ifbench","score":0.011158024193946951,"rank":341,"remainingConfigurations":444},{"removed":"itbench","score":0.011288073646623318,"rank":343,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011900278240770293,"rank":341,"remainingConfigurations":444},{"removed":"math500","score":0.01148744098905092,"rank":342,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01218380154649639,"rank":341,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012524819682031911,"rank":344,"remainingConfigurations":444},{"removed":"omniscience","score":0.009341357412336814,"rank":351,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010779826079719869,"rank":344,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011570483282455335,"rank":343,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010728307110379942,"rank":348,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014495388802113906,"rank":342,"remainingConfigurations":444},{"removed":"deepswe","score":0.008869095887542151,"rank":343,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011383532445503422,"rank":343,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011179160193058655,"rank":343,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011041987669897895,"rank":343,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011209672529227513,"rank":343,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011239225928943128,"rank":343,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011374326845260163,"rank":343,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011328377323826841,"rank":343,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011394847097670122,"rank":343,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01123387666759123,"rank":343,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011581084504202808,"rank":343,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011378968663490576,"rank":343,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.011122435272369106,"rank":343,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011293708386313647,"rank":343,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011671093454366309,"rank":343,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01174615465568126,"rank":343,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011398365869924848,"rank":343,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010603541129548111,"rank":341,"remainingConfigurations":444},{"removed":"simpleqa","score":0.012027382529080567,"rank":343,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011332867034903072,"rank":343,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01133111672393741,"rank":343,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011335032621824672,"rank":343,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011353631426056098,"rank":343,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011296562586283282,"rank":343,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011344049847222966,"rank":343,"remainingConfigurations":444}],"sharedOrderConflicts":0},"magistral-small-2509--effort-reasoning":{"score":0.01133333059998985,"rank":344,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014985785232176224,"rank":343,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008825815251213813,"rank":344,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011194587920241835,"rank":344,"remainingConfigurations":444},{"removed":"Scale","score":0.013461077986234372,"rank":344,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.01120131896811115,"rank":344,"remainingConfigurations":444},{"removed":"Cognition","score":0.011003465984751942,"rank":344,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01184587000944673,"rank":343,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01167746147292728,"rank":344,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.01155763090875951,"rank":329,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010875382781092,"rank":343,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011328182296531186,"rank":344,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01095081962986861,"rank":344,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01131247470753779,"rank":344,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01133333059998985,"rank":344,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011428344061161338,"rank":344,"remainingConfigurations":444},{"removed":"All provider reports","score":0.011022365740684768,"rank":344,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011443270655607045,"rank":344,"remainingConfigurations":444},{"removed":"briefcase","score":0.011222137231896292,"rank":343,"remainingConfigurations":444},{"removed":"aime","score":0.01010952409253995,"rank":353,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01153155172418433,"rank":344,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011792803564293004,"rank":340,"remainingConfigurations":444},{"removed":"automationbench","score":0.011841166490074684,"rank":339,"remainingConfigurations":444},{"removed":"critpt","score":0.009917476663359468,"rank":353,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011341578878326873,"rank":344,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011584860174144824,"rank":343,"remainingConfigurations":444},{"removed":"gdpval","score":0.011706310485888756,"rank":341,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011923784336900145,"rank":340,"remainingConfigurations":444},{"removed":"gpqa","score":0.011352471146221906,"rank":343,"remainingConfigurations":444},{"removed":"harvey","score":0.011201793299894158,"rank":344,"remainingConfigurations":444},{"removed":"hle","score":0.012627606167945804,"rank":349,"remainingConfigurations":444},{"removed":"ifbench","score":0.010338146932776711,"rank":346,"remainingConfigurations":444},{"removed":"itbench","score":0.01123723109025903,"rank":344,"remainingConfigurations":444},{"removed":"livecodebench","score":0.010233715937090037,"rank":351,"remainingConfigurations":444},{"removed":"math500","score":0.01140430402102994,"rank":344,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.012014212551851927,"rank":343,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012681584899706173,"rank":343,"remainingConfigurations":444},{"removed":"omniscience","score":0.010769377625154774,"rank":338,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01133579646765145,"rank":341,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011521381741997488,"rank":344,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.011886307499097222,"rank":342,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014403539262961874,"rank":343,"remainingConfigurations":444},{"removed":"deepswe","score":0.008832076308485962,"rank":344,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011336362431764365,"rank":344,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011130667133794963,"rank":344,"remainingConfigurations":444},{"removed":"frontiercode","score":0.011003465984751942,"rank":344,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011163108197919524,"rank":344,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011192691409233776,"rank":344,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011327181693859689,"rank":344,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011281221865996298,"rank":344,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011347783325404336,"rank":344,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011187135115340684,"rank":344,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011532854423513568,"rank":344,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011331881553250149,"rank":344,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.011076551001443814,"rank":344,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011246920167758323,"rank":344,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011622859449465013,"rank":344,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01167746147292728,"rank":344,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011353128079931949,"rank":344,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010538038710471107,"rank":342,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01197756306300562,"rank":344,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011285906917197129,"rank":344,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011284161385444838,"rank":344,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011288144818693174,"rank":344,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011306508092128622,"rank":344,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011249761607664147,"rank":344,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011297049220589375,"rank":344,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.6v--effort-reasoning":{"score":0.011205602913103156,"rank":345,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014911501100799472,"rank":344,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008729035888210872,"rank":345,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.011071788337873653,"rank":345,"remainingConfigurations":444},{"removed":"Scale","score":0.013316621731395336,"rank":345,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011075044188293902,"rank":345,"remainingConfigurations":444},{"removed":"Cognition","score":0.010887396214206311,"rank":345,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011711280771740542,"rank":344,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01153606302179267,"rank":345,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011419266354643041,"rank":331,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010747964287296574,"rank":344,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011200516847505207,"rank":345,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010827846619837654,"rank":345,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011185004908996073,"rank":345,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011205602913103156,"rank":345,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011299909403187735,"rank":345,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010898951722137033,"rank":345,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01131314009817312,"rank":345,"remainingConfigurations":444},{"removed":"briefcase","score":0.011137467330958216,"rank":344,"remainingConfigurations":444},{"removed":"aime","score":0.00934918127412717,"rank":354,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01140049988427525,"rank":345,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01046663564992209,"rank":352,"remainingConfigurations":444},{"removed":"automationbench","score":0.011152884743029869,"rank":345,"remainingConfigurations":444},{"removed":"critpt","score":0.01116229345372142,"rank":344,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01121702166876553,"rank":345,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011489833722792992,"rank":345,"remainingConfigurations":444},{"removed":"gdpval","score":0.011243241233630333,"rank":344,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010950885982512941,"rank":349,"remainingConfigurations":444},{"removed":"gpqa","score":0.01057040712226571,"rank":351,"remainingConfigurations":444},{"removed":"harvey","score":0.011076119867816375,"rank":345,"remainingConfigurations":444},{"removed":"hle","score":0.011875378678490983,"rank":352,"remainingConfigurations":444},{"removed":"ifbench","score":0.012280225680754318,"rank":334,"remainingConfigurations":444},{"removed":"itbench","score":0.011109858890562353,"rank":345,"remainingConfigurations":444},{"removed":"livecodebench","score":0.014009154356096008,"rank":330,"remainingConfigurations":444},{"removed":"math500","score":0.01124824186816685,"rank":346,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011166318251075877,"rank":350,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0131508373592035,"rank":339,"remainingConfigurations":444},{"removed":"omniscience","score":0.009991515304487901,"rank":345,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010898301754085212,"rank":342,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011393481606017017,"rank":345,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010709862028074968,"rank":349,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014323221604700315,"rank":344,"remainingConfigurations":444},{"removed":"deepswe","score":0.008735160480141333,"rank":345,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011208580646164071,"rank":345,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.011002334127691074,"rank":345,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010887396214206311,"rank":345,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011037366387412836,"rank":345,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011066965764201889,"rank":345,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011199462517587957,"rank":345,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011153701263221863,"rank":345,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01121999408801999,"rank":345,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011060589573858567,"rank":345,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011402589439714913,"rank":345,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011204403673395336,"rank":345,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010951877217371087,"rank":345,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011120092482305444,"rank":345,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011492250493658063,"rank":345,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01153606302179267,"rank":345,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01122761972403541,"rank":345,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.01040417761345147,"rank":343,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011842490257253731,"rank":345,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011158722614764784,"rank":345,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.01115692411910743,"rank":345,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011161027088378234,"rank":345,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011178927088963309,"rank":345,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011122897899527818,"rank":345,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011169735793376082,"rank":345,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-4.1-mini--effort-non-reasoning":{"score":0.011186459297061732,"rank":346,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01484030425993612,"rank":345,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008713212136059759,"rank":346,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01104530707640617,"rank":346,"remainingConfigurations":444},{"removed":"Scale","score":0.013306079676302061,"rank":346,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011057201022923098,"rank":346,"remainingConfigurations":444},{"removed":"Cognition","score":0.01086718731679643,"rank":346,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011692814079184035,"rank":345,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011532410154173897,"rank":346,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011398154555215185,"rank":332,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010735466379533274,"rank":345,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011181384181569077,"rank":346,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010809100514291502,"rank":346,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011165896655645768,"rank":346,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011186459297061732,"rank":346,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011280274021739959,"rank":346,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010879775981639804,"rank":346,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011297850472893257,"rank":346,"remainingConfigurations":444},{"removed":"briefcase","score":0.011135564743973524,"rank":345,"remainingConfigurations":444},{"removed":"aime","score":0.011430042295523432,"rank":344,"remainingConfigurations":444},{"removed":"apex-agents","score":0.01138010183001621,"rank":346,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010667546925300413,"rank":349,"remainingConfigurations":444},{"removed":"automationbench","score":0.011156943122156997,"rank":344,"remainingConfigurations":444},{"removed":"critpt","score":0.011051292031270985,"rank":346,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011196797558712543,"rank":346,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011495417705440242,"rank":344,"remainingConfigurations":444},{"removed":"gdpval","score":0.01114237843094014,"rank":345,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011364522963499317,"rank":345,"remainingConfigurations":444},{"removed":"gpqa","score":0.011152358982752181,"rank":344,"remainingConfigurations":444},{"removed":"harvey","score":0.011058401800357658,"rank":346,"remainingConfigurations":444},{"removed":"hle","score":0.012945976743313893,"rank":347,"remainingConfigurations":444},{"removed":"ifbench","score":0.010982878855116602,"rank":343,"remainingConfigurations":444},{"removed":"itbench","score":0.011091199716960903,"rank":346,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011410076668350366,"rank":344,"remainingConfigurations":444},{"removed":"math500","score":0.011741971956818873,"rank":340,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01153073126032761,"rank":347,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012160288270654296,"rank":348,"remainingConfigurations":444},{"removed":"omniscience","score":0.009112723251251611,"rank":353,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010440894658591151,"rank":349,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011374635625643573,"rank":346,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.011215254363630038,"rank":345,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014260962456178887,"rank":345,"remainingConfigurations":444},{"removed":"deepswe","score":0.00871938013515562,"rank":346,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.011189446179147092,"rank":346,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010985165917580357,"rank":346,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01086718731679643,"rank":346,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.011018542569678666,"rank":346,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01104764025812878,"rank":346,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011180413837906007,"rank":346,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011134987063386878,"rank":346,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011200791933536042,"rank":346,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.01104196058328935,"rank":346,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011383340874727426,"rank":346,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011185150235575292,"rank":346,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010933026592018282,"rank":346,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011101110113430032,"rank":346,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011472359539598735,"rank":346,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011532410154173897,"rank":346,"remainingConfigurations":444},{"removed":"frontiermath","score":0.01120726837307904,"rank":346,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010398480807599184,"rank":345,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011823557071127625,"rank":346,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01113962929634666,"rank":346,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011137914761535165,"rank":346,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011141875116292575,"rank":346,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011159947955119875,"rank":346,"remainingConfigurations":444},{"removed":"vibe-code","score":0.011103948386768142,"rank":346,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011150652917099177,"rank":346,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-medium-2508--effort-non-reasoning":{"score":0.01116247581387981,"rank":347,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014803402677115857,"rank":346,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008693151158165135,"rank":347,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01102693224158433,"rank":347,"remainingConfigurations":444},{"removed":"Scale","score":0.013290052267430554,"rank":347,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.011032843023475595,"rank":347,"remainingConfigurations":444},{"removed":"Cognition","score":0.010831434335926572,"rank":347,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011671098321916616,"rank":346,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011524106118061872,"rank":347,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011484980846463613,"rank":330,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010724094133052765,"rank":346,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.011157389128554662,"rank":347,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010784998853161068,"rank":347,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.011141881304284893,"rank":347,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.01116247581387981,"rank":347,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011256101404666013,"rank":347,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010855449254583394,"rank":347,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011281303204910024,"rank":347,"remainingConfigurations":444},{"removed":"briefcase","score":0.010189101459228885,"rank":353,"remainingConfigurations":444},{"removed":"aime","score":0.011672575100136496,"rank":343,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0113689825176021,"rank":347,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010699740035961906,"rank":348,"remainingConfigurations":444},{"removed":"automationbench","score":0.010289041597431147,"rank":353,"remainingConfigurations":444},{"removed":"critpt","score":0.011066730567549211,"rank":345,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011182311138779754,"rank":347,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011391299702472981,"rank":346,"remainingConfigurations":444},{"removed":"gdpval","score":0.01086169529217656,"rank":347,"remainingConfigurations":444},{"removed":"gmmlu","score":0.01135343713158299,"rank":346,"remainingConfigurations":444},{"removed":"gpqa","score":0.011519088647812667,"rank":341,"remainingConfigurations":444},{"removed":"harvey","score":0.011036110862042687,"rank":347,"remainingConfigurations":444},{"removed":"hle","score":0.013144925331663483,"rank":345,"remainingConfigurations":444},{"removed":"ifbench","score":0.010632025164565526,"rank":345,"remainingConfigurations":444},{"removed":"itbench","score":0.011074125339048476,"rank":347,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01179799043033007,"rank":342,"remainingConfigurations":444},{"removed":"math500","score":0.011274417394901528,"rank":345,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.013224839737739582,"rank":334,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01249953642649451,"rank":346,"remainingConfigurations":444},{"removed":"omniscience","score":0.009185949008090657,"rank":352,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01034744914715229,"rank":350,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.011349556230139633,"rank":347,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010900727271066682,"rank":346,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014228599765853958,"rank":346,"remainingConfigurations":444},{"removed":"deepswe","score":0.008699342395574627,"rank":347,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01116547698692468,"rank":347,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010965426985642674,"rank":347,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010831434335926572,"rank":347,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.010995114132245777,"rank":347,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.011023900349667035,"rank":347,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011156471772062762,"rank":347,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011111396701895862,"rank":347,"remainingConfigurations":444},{"removed":"livebench-math","score":0.011176558538869855,"rank":347,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.011018669599294408,"rank":347,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011359361315737407,"rank":347,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011161017395158129,"rank":347,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010909268753914776,"rank":347,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.011077326874084826,"rank":347,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011447619502826946,"rank":347,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011524106118061872,"rank":347,"remainingConfigurations":444},{"removed":"frontiermath","score":0.011180076790961646,"rank":347,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010400788439800633,"rank":344,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011797303603374276,"rank":347,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011115776888275227,"rank":347,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011114048564796314,"rank":347,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.011117903261799988,"rank":347,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011136124598861341,"rank":347,"remainingConfigurations":444},{"removed":"vibe-code","score":0.01108013380074756,"rank":347,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.011126761940747043,"rank":347,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-12b-it--effort-non-reasoning":{"score":0.011071167585896602,"rank":348,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014729601014376384,"rank":347,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008626081971693778,"rank":348,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.010942140058675472,"rank":348,"remainingConfigurations":444},{"removed":"Scale","score":0.013175361482164971,"rank":348,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010942178350945313,"rank":348,"remainingConfigurations":444},{"removed":"Cognition","score":0.010764016395097623,"rank":348,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01157410309743555,"rank":347,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01139848050155725,"rank":348,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011226435180564832,"rank":334,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010620652178355179,"rank":347,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01106613431443406,"rank":348,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01069765237300341,"rank":348,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.01105077513188383,"rank":348,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.011071167585896602,"rank":348,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011164597023836037,"rank":348,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010768100904159335,"rank":348,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011180927812181477,"rank":348,"remainingConfigurations":444},{"removed":"briefcase","score":0.010997678556496119,"rank":346,"remainingConfigurations":444},{"removed":"aime","score":0.01105529847901822,"rank":349,"remainingConfigurations":444},{"removed":"apex-agents","score":0.011263901830949311,"rank":348,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010883554818511868,"rank":346,"remainingConfigurations":444},{"removed":"automationbench","score":0.011007464072587507,"rank":346,"remainingConfigurations":444},{"removed":"critpt","score":0.011211665686413852,"rank":343,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.011080024674997175,"rank":348,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011350062073736733,"rank":347,"remainingConfigurations":444},{"removed":"gdpval","score":0.011070717825974255,"rank":346,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011189507057259976,"rank":347,"remainingConfigurations":444},{"removed":"gpqa","score":0.011110277435228548,"rank":346,"remainingConfigurations":444},{"removed":"harvey","score":0.010943487121366594,"rank":348,"remainingConfigurations":444},{"removed":"hle","score":0.012308473743056698,"rank":350,"remainingConfigurations":444},{"removed":"ifbench","score":0.009620905931054214,"rank":352,"remainingConfigurations":444},{"removed":"itbench","score":0.010969750919165931,"rank":348,"remainingConfigurations":444},{"removed":"livecodebench","score":0.01117158209437707,"rank":348,"remainingConfigurations":444},{"removed":"math500","score":0.011197667366209606,"rank":347,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011604787673428091,"rank":346,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.011537320330389761,"rank":353,"remainingConfigurations":444},{"removed":"omniscience","score":0.011315224413424455,"rank":333,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010642906129929769,"rank":346,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01126020707796508,"rank":348,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.01055331538584496,"rank":351,"remainingConfigurations":444},{"removed":"arc-agi","score":0.014133532360852128,"rank":347,"remainingConfigurations":444},{"removed":"deepswe","score":0.00863211887032058,"rank":348,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.01107410906704353,"rank":348,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010873196618935871,"rank":348,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010764016395097623,"rank":348,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01090532182662867,"rank":348,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.010934249494440511,"rank":348,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.011065110223492007,"rank":348,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.011019870387025439,"rank":348,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01108532051278592,"rank":348,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010927802113330146,"rank":348,"remainingConfigurations":444},{"removed":"livebench-language","score":0.01126592737571102,"rank":348,"remainingConfigurations":444},{"removed":"livebench-data","score":0.011070107011613817,"rank":348,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010820367108457069,"rank":348,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010986607583703104,"rank":348,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011354503560907434,"rank":348,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01139848050155725,"rank":348,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0110868329264798,"rank":348,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010292660438972498,"rank":346,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011699418760628355,"rank":348,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.011024878661015534,"rank":348,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.011023074229313668,"rank":348,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.01102708152729312,"rank":348,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.011044814574137885,"rank":348,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010989435063816222,"rank":348,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.01103573549841806,"rank":348,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-pro-preview--effort-non-reasoning":{"score":0.010933988905502484,"rank":349,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014508176458935559,"rank":348,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008518769594834191,"rank":349,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.010812574526889258,"rank":349,"remainingConfigurations":444},{"removed":"Scale","score":0.013012409541610504,"rank":349,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010806286945422414,"rank":349,"remainingConfigurations":444},{"removed":"Cognition","score":0.010636716947900138,"rank":349,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01142990936906426,"rank":348,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011254656551601969,"rank":349,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.011245333735939998,"rank":333,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010489663000131731,"rank":348,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.010929018899565051,"rank":349,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.01056516433474724,"rank":349,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.010913888341327768,"rank":349,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.010933988905502484,"rank":349,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.011026002241643648,"rank":349,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010634532244908049,"rank":349,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.011041722980333303,"rank":349,"remainingConfigurations":444},{"removed":"briefcase","score":0.010874032898900958,"rank":347,"remainingConfigurations":444},{"removed":"aime","score":0.012048328782225004,"rank":340,"remainingConfigurations":444},{"removed":"apex-agents","score":0.011125998848925392,"rank":349,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011005021839653557,"rank":343,"remainingConfigurations":444},{"removed":"automationbench","score":0.010890687791464413,"rank":347,"remainingConfigurations":444},{"removed":"critpt","score":0.01084602821248299,"rank":347,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01094555746443066,"rank":349,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.011221467189401473,"rank":349,"remainingConfigurations":444},{"removed":"gdpval","score":0.010816954096381224,"rank":348,"remainingConfigurations":444},{"removed":"gmmlu","score":0.011143116206032163,"rank":348,"remainingConfigurations":444},{"removed":"gpqa","score":0.011086966963082,"rank":347,"remainingConfigurations":444},{"removed":"harvey","score":0.010808740734138005,"rank":349,"remainingConfigurations":444},{"removed":"hle","score":0.013800939665566753,"rank":338,"remainingConfigurations":444},{"removed":"ifbench","score":0.009315378251079661,"rank":353,"remainingConfigurations":444},{"removed":"itbench","score":0.010837317936180738,"rank":349,"remainingConfigurations":444},{"removed":"livecodebench","score":0.011234186134770459,"rank":347,"remainingConfigurations":444},{"removed":"math500","score":0.011015280292598968,"rank":349,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011495036096864732,"rank":348,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012022037069172495,"rank":350,"remainingConfigurations":444},{"removed":"omniscience","score":0.009462965802507434,"rank":349,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009436307690476873,"rank":356,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.01112053524837813,"rank":349,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010233480916980078,"rank":354,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01392708282920551,"rank":348,"remainingConfigurations":444},{"removed":"deepswe","score":0.008524758339159545,"rank":349,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.010936900831765128,"rank":349,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010736939874807137,"rank":349,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010636716947900138,"rank":349,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.010769831309242901,"rank":349,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.010798593817701261,"rank":349,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.010928012039968666,"rank":349,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01088337531441247,"rank":349,"remainingConfigurations":444},{"removed":"livebench-math","score":0.01094800682563101,"rank":349,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010792355766415157,"rank":349,"remainingConfigurations":444},{"removed":"livebench-language","score":0.011126373630551233,"rank":349,"remainingConfigurations":444},{"removed":"livebench-data","score":0.010932900635581446,"rank":349,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010686225470003382,"rank":349,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010850466727336291,"rank":349,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011213903412982881,"rank":349,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011254656551601969,"rank":349,"remainingConfigurations":444},{"removed":"frontiermath","score":0.010965754274841576,"rank":349,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.010168713378601306,"rank":347,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011555818603475697,"rank":349,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.010888221617600587,"rank":349,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.010886480861365422,"rank":349,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.010890429476611944,"rank":349,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.010907975602180662,"rank":349,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010853252368704913,"rank":349,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.010898959011727202,"rank":349,"remainingConfigurations":444}],"sharedOrderConflicts":0},"claude-haiku-4-5-20251001--effort-non-reasoning":{"score":0.010727941997460697,"rank":350,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014281999846111544,"rank":349,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008358070244162595,"rank":350,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01060341559015156,"rank":350,"remainingConfigurations":444},{"removed":"Scale","score":0.012752666759250048,"rank":350,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010604113365722074,"rank":350,"remainingConfigurations":444},{"removed":"Cognition","score":0.010428810178837048,"rank":350,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011215735656877559,"rank":349,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.01105042830651356,"rank":351,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010943534181655766,"rank":335,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010293192943124864,"rank":349,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.01072306840998121,"rank":350,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010366025732450736,"rank":350,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.010708224748985327,"rank":350,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.010727941997460697,"rank":350,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.01081829155637535,"rank":350,"remainingConfigurations":444},{"removed":"All provider reports","score":0.01043415973786313,"rank":350,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.010838969453105687,"rank":350,"remainingConfigurations":444},{"removed":"briefcase","score":0.010685936171663442,"rank":348,"remainingConfigurations":444},{"removed":"aime","score":0.011364033751355517,"rank":346,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010919786916372605,"rank":350,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.009891321817744657,"rank":357,"remainingConfigurations":444},{"removed":"automationbench","score":0.010694925546581989,"rank":348,"remainingConfigurations":444},{"removed":"critpt","score":0.010611846633296292,"rank":349,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.010748878462255237,"rank":350,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.01102506983086479,"rank":350,"remainingConfigurations":444},{"removed":"gdpval","score":0.01078548575174832,"rank":349,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010869085598020259,"rank":350,"remainingConfigurations":444},{"removed":"gpqa","score":0.010804042825199383,"rank":350,"remainingConfigurations":444},{"removed":"harvey","score":0.010604637596273302,"rank":350,"remainingConfigurations":444},{"removed":"hle","score":0.013322719623975724,"rank":343,"remainingConfigurations":444},{"removed":"ifbench","score":0.010003995794891684,"rank":350,"remainingConfigurations":444},{"removed":"itbench","score":0.010640632912440018,"rank":350,"remainingConfigurations":444},{"removed":"livecodebench","score":0.010823746578464818,"rank":349,"remainingConfigurations":444},{"removed":"math500","score":0.010813060280829621,"rank":350,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.01054888124130944,"rank":353,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012061672052637981,"rank":349,"remainingConfigurations":444},{"removed":"omniscience","score":0.009942394558803148,"rank":346,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010300346550906508,"rank":351,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010910243728448801,"rank":350,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.009436335931887245,"rank":358,"remainingConfigurations":444},{"removed":"arc-agi","score":0.013714923083572613,"rank":349,"remainingConfigurations":444},{"removed":"deepswe","score":0.00836393789218738,"rank":350,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.010730795085053764,"rank":350,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010533809270044403,"rank":350,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010428810178837048,"rank":350,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.010567139901815147,"rank":350,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.010595236593755124,"rank":350,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.01072209811278881,"rank":350,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.010678259540558859,"rank":350,"remainingConfigurations":444},{"removed":"livebench-math","score":0.010741712679635826,"rank":350,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010588992321312779,"rank":350,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010916758439220638,"rank":350,"remainingConfigurations":444},{"removed":"livebench-data","score":0.010726821894612585,"rank":350,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010484766170446328,"rank":350,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010645982497069583,"rank":350,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.011002642242633956,"rank":350,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.01105042830651356,"rank":351,"remainingConfigurations":444},{"removed":"frontiermath","score":0.010748950645972746,"rank":350,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.009966876153994466,"rank":348,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01133881902338791,"rank":350,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.010683027854041701,"rank":350,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.010681287532220833,"rank":350,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.010685226066390557,"rank":350,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.010702373143119262,"rank":350,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010648674000229667,"rank":350,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.010693593570117052,"rank":350,"remainingConfigurations":444}],"sharedOrderConflicts":0},"minimax-m1-40k--effort-reasoning":{"score":0.010722110361001158,"rank":351,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014264042275887468,"rank":350,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008352654992273176,"rank":351,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.010587759162628378,"rank":351,"remainingConfigurations":444},{"removed":"Scale","score":0.012751760590105882,"rank":351,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010597852007246352,"rank":351,"remainingConfigurations":444},{"removed":"Cognition","score":0.01042718523964608,"rank":351,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011204400267105877,"rank":350,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011058220944150127,"rank":350,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010875719851104334,"rank":336,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010285747160101473,"rank":350,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.010717256062719296,"rank":351,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010360594355395129,"rank":351,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.010702457399854995,"rank":351,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.010722110361001158,"rank":351,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.010812132312130912,"rank":351,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010428492796347484,"rank":351,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.010830354525795212,"rank":351,"remainingConfigurations":444},{"removed":"briefcase","score":0.010659391311186662,"rank":349,"remainingConfigurations":444},{"removed":"aime","score":0.014409282198229,"rank":326,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010909297952098924,"rank":351,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.01055053845496867,"rank":350,"remainingConfigurations":444},{"removed":"automationbench","score":0.01066559145279316,"rank":349,"remainingConfigurations":444},{"removed":"critpt","score":0.010188943505161157,"rank":352,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01073514285958304,"rank":351,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.010986903285123714,"rank":351,"remainingConfigurations":444},{"removed":"gdpval","score":0.010756612924006252,"rank":350,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010855787103064155,"rank":351,"remainingConfigurations":444},{"removed":"gpqa","score":0.01031288417594308,"rank":353,"remainingConfigurations":444},{"removed":"harvey","score":0.01059776101281075,"rank":351,"remainingConfigurations":444},{"removed":"hle","score":0.011421458025974905,"rank":353,"remainingConfigurations":444},{"removed":"ifbench","score":0.010141047408417687,"rank":348,"remainingConfigurations":444},{"removed":"itbench","score":0.010633132130810926,"rank":351,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009815894263280488,"rank":354,"remainingConfigurations":444},{"removed":"math500","score":0.009647983542683595,"rank":357,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.010060646985461127,"rank":354,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.011756358683789872,"rank":351,"remainingConfigurations":444},{"removed":"omniscience","score":0.00937949608829944,"rank":350,"remainingConfigurations":444},{"removed":"tau-bench","score":0.01048034308106281,"rank":348,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010900304232255556,"rank":351,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0122227718264925,"rank":338,"remainingConfigurations":444},{"removed":"arc-agi","score":0.013705396340445375,"rank":350,"remainingConfigurations":444},{"removed":"deepswe","score":0.008358544116919714,"rank":351,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.010724961571464254,"rank":351,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010525307255245706,"rank":351,"remainingConfigurations":444},{"removed":"frontiercode","score":0.01042718523964608,"rank":351,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.010561027709237456,"rank":351,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0105893228841488,"rank":351,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.010716282962356488,"rank":351,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0106725107932314,"rank":351,"remainingConfigurations":444},{"removed":"livebench-math","score":0.010735971946386475,"rank":351,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010583201405833976,"rank":351,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010910732442139,"rank":351,"remainingConfigurations":444},{"removed":"livebench-data","score":0.010720948922178649,"rank":351,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010479174846777043,"rank":351,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010640216188452798,"rank":351,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01099657782090862,"rank":351,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011058220944150127,"rank":350,"remainingConfigurations":444},{"removed":"frontiermath","score":0.010746179614873425,"rank":351,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.009964965333640611,"rank":349,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011334517497965206,"rank":351,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.01067717611199974,"rank":351,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.010675487132953179,"rank":351,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.010679428139905385,"rank":351,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.010696569045755305,"rank":351,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010642923654118413,"rank":351,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.010687764512101912,"rank":351,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-4b-thinking-2507--effort-reasoning":{"score":0.010685893159719115,"rank":352,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014187068302241437,"rank":352,"remainingConfigurations":444},{"removed":"Datacurve","score":0.008322953016149118,"rank":353,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.010554501114049172,"rank":353,"remainingConfigurations":444},{"removed":"Scale","score":0.012697207501670674,"rank":353,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010562044977495551,"rank":352,"remainingConfigurations":444},{"removed":"Cognition","score":0.010386038823683759,"rank":352,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011168526284220446,"rank":351,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011016481857907087,"rank":352,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010857609920417859,"rank":338,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010253348557728217,"rank":352,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.010681045936526077,"rank":352,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010325475821086932,"rank":352,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.010666270539155758,"rank":352,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.010685893159719115,"rank":352,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.010775638669330442,"rank":352,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010393128826411167,"rank":352,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.010790702821273146,"rank":352,"remainingConfigurations":444},{"removed":"briefcase","score":0.010608244133835645,"rank":351,"remainingConfigurations":444},{"removed":"aime","score":0.008858012987452188,"rank":356,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010868806663148484,"rank":352,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010394022452953832,"rank":353,"remainingConfigurations":444},{"removed":"automationbench","score":0.010618815916296263,"rank":352,"remainingConfigurations":444},{"removed":"critpt","score":0.010599515994845378,"rank":350,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.01069424119708238,"rank":352,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.010947683677701632,"rank":353,"remainingConfigurations":444},{"removed":"gdpval","score":0.010719683922679113,"rank":352,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010847272021789285,"rank":352,"remainingConfigurations":444},{"removed":"gpqa","score":0.010559142695025515,"rank":352,"remainingConfigurations":444},{"removed":"harvey","score":0.010562523192632475,"rank":352,"remainingConfigurations":444},{"removed":"hle","score":0.011965997643195343,"rank":351,"remainingConfigurations":444},{"removed":"ifbench","score":0.009210297719918275,"rank":354,"remainingConfigurations":444},{"removed":"itbench","score":0.010593648677177533,"rank":352,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009963424385134355,"rank":353,"remainingConfigurations":444},{"removed":"math500","score":0.010785086588948833,"rank":351,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011942450992161334,"rank":344,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01173025045456126,"rank":352,"remainingConfigurations":444},{"removed":"omniscience","score":0.010313959688471394,"rank":342,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010869665011226675,"rank":343,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010864072198792004,"rank":352,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.012222543026973119,"rank":339,"remainingConfigurations":444},{"removed":"arc-agi","score":0.013631585345683416,"rank":352,"remainingConfigurations":444},{"removed":"deepswe","score":0.008328828079305453,"rank":353,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.010688739976397655,"rank":352,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010491861505360326,"rank":352,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010386038823683759,"rank":352,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.01052521306091767,"rank":352,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.010553330308036915,"rank":352,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.010680076742715441,"rank":352,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.01063651510684508,"rank":352,"remainingConfigurations":444},{"removed":"livebench-math","score":0.010699650945501009,"rank":352,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010547442157995683,"rank":352,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010873989581004377,"rank":352,"remainingConfigurations":444},{"removed":"livebench-data","score":0.010684798125336209,"rank":352,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.01044367984212585,"rank":352,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010604237144113807,"rank":352,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.010959480375509508,"rank":352,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011016481857907087,"rank":352,"remainingConfigurations":444},{"removed":"frontiermath","score":0.010708269925684036,"rank":352,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.009929692355269339,"rank":351,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011295139619890761,"rank":352,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.010641125355719235,"rank":352,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.010639445325694242,"rank":352,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.010643305033990037,"rank":352,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.010660473407118204,"rank":352,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010606975737250106,"rank":352,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.010651656074410083,"rank":352,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning":{"score":0.010680256566454459,"rank":353,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.014195920090263084,"rank":351,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00832358110711009,"rank":352,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.01055455498164804,"rank":352,"remainingConfigurations":444},{"removed":"Scale","score":0.012701564648434497,"rank":352,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.010561017873605916,"rank":353,"remainingConfigurations":444},{"removed":"Cognition","score":0.010385456680063751,"rank":353,"remainingConfigurations":444},{"removed":"LiveBench","score":0.011166836233437713,"rank":352,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.011016018907723933,"rank":353,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010862590045350744,"rank":337,"remainingConfigurations":431},{"removed":"Vals AI","score":0.010256017336640886,"rank":351,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.010675400243992904,"rank":353,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.010319521675270655,"rank":353,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.010660581510944199,"rank":353,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.010680256566454459,"rank":353,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.010770061208039606,"rank":353,"remainingConfigurations":444},{"removed":"All provider reports","score":0.010387172369186489,"rank":353,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.01078811222146779,"rank":353,"remainingConfigurations":444},{"removed":"briefcase","score":0.010606300245005947,"rank":352,"remainingConfigurations":444},{"removed":"aime","score":0.010595336258304172,"rank":351,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010865454540075821,"rank":353,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010282754768057425,"rank":354,"remainingConfigurations":444},{"removed":"automationbench","score":0.010626206666705504,"rank":351,"remainingConfigurations":444},{"removed":"critpt","score":0.010777410830894113,"rank":348,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.010691576692358637,"rank":353,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.010952164668757198,"rank":352,"remainingConfigurations":444},{"removed":"gdpval","score":0.010751391295655199,"rank":351,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010820325854076359,"rank":353,"remainingConfigurations":444},{"removed":"gpqa","score":0.012393386122398806,"rank":334,"remainingConfigurations":444},{"removed":"harvey","score":0.010557589758456448,"rank":353,"remainingConfigurations":444},{"removed":"hle","score":0.012815896365396137,"rank":348,"remainingConfigurations":444},{"removed":"ifbench","score":0.007825817005097388,"rank":363,"remainingConfigurations":444},{"removed":"itbench","score":0.010588863617322475,"rank":353,"remainingConfigurations":444},{"removed":"livecodebench","score":0.010721046546709356,"rank":350,"remainingConfigurations":444},{"removed":"math500","score":0.010781585786388569,"rank":352,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011144891704864364,"rank":351,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.012254102215094452,"rank":347,"remainingConfigurations":444},{"removed":"omniscience","score":0.010029788213815964,"rank":344,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009429964577275443,"rank":357,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010860802493934946,"rank":353,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010636519758598468,"rank":350,"remainingConfigurations":444},{"removed":"arc-agi","score":0.013631628863985992,"rank":351,"remainingConfigurations":444},{"removed":"deepswe","score":0.008329455545333543,"rank":352,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.010683104865575497,"rank":353,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.010490530780266035,"rank":353,"remainingConfigurations":444},{"removed":"frontiercode","score":0.010385456680063751,"rank":353,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.010520049738538359,"rank":353,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.01054788807899055,"rank":353,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.010674448042711561,"rank":353,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.010630952424169941,"rank":353,"remainingConfigurations":444},{"removed":"livebench-math","score":0.010693923538107454,"rank":353,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.010541966908770526,"rank":353,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010868425093736792,"rank":353,"remainingConfigurations":444},{"removed":"livebench-data","score":0.01067918057986097,"rank":353,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.010438059127914567,"rank":353,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.010598642359631058,"rank":353,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.01095362929136874,"rank":353,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.011016018907723933,"rank":353,"remainingConfigurations":444},{"removed":"frontiermath","score":0.010700570469734117,"rank":353,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.009931231584363666,"rank":350,"remainingConfigurations":444},{"removed":"simpleqa","score":0.011287242878099667,"rank":353,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.010635552476187348,"rank":353,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.010633867827647069,"rank":353,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.010637621670046246,"rank":353,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.010654901000753414,"rank":353,"remainingConfigurations":444},{"removed":"vibe-code","score":0.010601406790795376,"rank":353,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.010646038678066285,"rank":353,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.5v--effort-reasoning":{"score":0.009912915322283385,"rank":354,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.013209829708163937,"rank":353,"remainingConfigurations":444},{"removed":"Datacurve","score":0.007721484287848249,"rank":355,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009794638408463603,"rank":354,"remainingConfigurations":444},{"removed":"Scale","score":0.011783105727540072,"rank":354,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.009797679219464254,"rank":354,"remainingConfigurations":444},{"removed":"Cognition","score":0.009636916706958812,"rank":355,"remainingConfigurations":444},{"removed":"LiveBench","score":0.01036423640601832,"rank":353,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.010215670859720215,"rank":354,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010097682578542025,"rank":340,"remainingConfigurations":431},{"removed":"Vals AI","score":0.009510386375660356,"rank":353,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.009908406480055523,"rank":354,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00957800650954333,"rank":354,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.009894662577352125,"rank":354,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009912915322283385,"rank":354,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.009996497915858578,"rank":354,"remainingConfigurations":444},{"removed":"All provider reports","score":0.009641019528408679,"rank":354,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.010010788297686427,"rank":354,"remainingConfigurations":444},{"removed":"briefcase","score":0.009862446760186728,"rank":354,"remainingConfigurations":444},{"removed":"aime","score":0.008771490090976365,"rank":357,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010085701337288595,"rank":354,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.011154481072847248,"rank":342,"remainingConfigurations":444},{"removed":"automationbench","score":0.009869720118848697,"rank":354,"remainingConfigurations":444},{"removed":"critpt","score":0.00971974968028338,"rank":354,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.00992755988253055,"rank":354,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.010175812531877675,"rank":354,"remainingConfigurations":444},{"removed":"gdpval","score":0.009967173507383624,"rank":355,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010043264962597274,"rank":355,"remainingConfigurations":444},{"removed":"gpqa","score":0.009514977609802498,"rank":355,"remainingConfigurations":444},{"removed":"harvey","score":0.009799775391078458,"rank":354,"remainingConfigurations":444},{"removed":"hle","score":0.010987486463480836,"rank":355,"remainingConfigurations":444},{"removed":"ifbench","score":0.01012113855261529,"rank":349,"remainingConfigurations":444},{"removed":"itbench","score":0.009830085657677208,"rank":354,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009330558663028057,"rank":358,"remainingConfigurations":444},{"removed":"math500","score":0.010016883887339009,"rank":355,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.009976315454146208,"rank":355,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.011522826401513787,"rank":354,"remainingConfigurations":444},{"removed":"omniscience","score":0.007734619126339912,"rank":360,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010163334111872984,"rank":352,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010084415451155633,"rank":354,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010283531384084128,"rank":353,"remainingConfigurations":444},{"removed":"arc-agi","score":0.012683981918392116,"rank":353,"remainingConfigurations":444},{"removed":"deepswe","score":0.0077269040746017386,"rank":355,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0099155549447575,"rank":354,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009732858466122637,"rank":354,"remainingConfigurations":444},{"removed":"frontiercode","score":0.009636916706958812,"rank":355,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.009763994141986107,"rank":354,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009790107909663998,"rank":354,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009907523034281817,"rank":354,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.009866978734957373,"rank":354,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00992567573783743,"rank":354,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00978422817027011,"rank":354,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010087635878434581,"rank":354,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0099119438303525,"rank":354,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.009687889044895948,"rank":354,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.009837037908676073,"rank":354,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.010167232886434433,"rank":354,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.010215670859720215,"rank":354,"remainingConfigurations":444},{"removed":"frontiermath","score":0.009932489753788748,"rank":354,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00921222179679849,"rank":353,"remainingConfigurations":444},{"removed":"simpleqa","score":0.010478511275316607,"rank":355,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.009871340197887511,"rank":354,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.009869737965313362,"rank":354,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.009873394104638675,"rank":354,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009889232786227083,"rank":354,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009839554615151385,"rank":354,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009881121200260317,"rank":354,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-oss-20b--effort-low":{"score":0.009901681666533815,"rank":355,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.007847520062287628,"rank":191,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01313751206976603,"rank":354,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0077293965754671,"rank":354,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009793032573041278,"rank":355,"remainingConfigurations":444},{"removed":"Scale","score":0.011759496775227064,"rank":355,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.009797132685620588,"rank":355,"remainingConfigurations":444},{"removed":"Cognition","score":0.009722738950195793,"rank":354,"remainingConfigurations":444},{"removed":"LiveBench","score":0.010299341076302261,"rank":354,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.010191349018122511,"rank":355,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.010648119307234062,"rank":339,"remainingConfigurations":431},{"removed":"Vals AI","score":0.009503055165833822,"rank":354,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.009897349564736115,"rank":355,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.009571549188676193,"rank":355,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.009884474978787845,"rank":355,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009901681666533815,"rank":355,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.009983381990122981,"rank":355,"remainingConfigurations":444},{"removed":"All provider reports","score":0.009633930716563594,"rank":355,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009995918564340156,"rank":355,"remainingConfigurations":444},{"removed":"briefcase","score":0.009843306133055379,"rank":355,"remainingConfigurations":444},{"removed":"aime","score":0.00860293636732475,"rank":359,"remainingConfigurations":444},{"removed":"apex-agents","score":0.010068752431827824,"rank":355,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.009938142397413086,"rank":356,"remainingConfigurations":444},{"removed":"automationbench","score":0.009849875195251502,"rank":355,"remainingConfigurations":444},{"removed":"critpt","score":0.009713394341550254,"rank":355,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009911930107827099,"rank":355,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.010136417616983051,"rank":355,"remainingConfigurations":444},{"removed":"gdpval","score":0.00991887636979164,"rank":356,"remainingConfigurations":444},{"removed":"gmmlu","score":0.010506192676940316,"rank":354,"remainingConfigurations":444},{"removed":"gpqa","score":0.011009020945290082,"rank":348,"remainingConfigurations":444},{"removed":"harvey","score":0.009783772301193221,"rank":355,"remainingConfigurations":444},{"removed":"hle","score":0.0112460746965243,"rank":354,"remainingConfigurations":444},{"removed":"ifbench","score":0.008526090292232344,"rank":359,"remainingConfigurations":444},{"removed":"itbench","score":0.009821031069995836,"rank":355,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009366034266163526,"rank":357,"remainingConfigurations":444},{"removed":"math500","score":0.009971957859528249,"rank":356,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.011204137538007702,"rank":349,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.01084622998111842,"rank":355,"remainingConfigurations":444},{"removed":"omniscience","score":0.00910299505349966,"rank":354,"remainingConfigurations":444},{"removed":"tau-bench","score":0.00883273697379649,"rank":362,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.010056587450665308,"rank":355,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.010343257927205056,"rank":352,"remainingConfigurations":444},{"removed":"arc-agi","score":0.012627498207244835,"rank":354,"remainingConfigurations":444},{"removed":"deepswe","score":0.00773507623385094,"rank":354,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.009904291608112839,"rank":355,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009721995012225157,"rank":355,"remainingConfigurations":444},{"removed":"frontiercode","score":0.009722738950195793,"rank":354,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.009756240103859786,"rank":355,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009777024931236033,"rank":355,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009896483187920179,"rank":355,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.009855717076476216,"rank":355,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009917899814550072,"rank":355,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00976807160712284,"rank":355,"remainingConfigurations":444},{"removed":"livebench-language","score":0.010075072719308523,"rank":355,"remainingConfigurations":444},{"removed":"livebench-data","score":0.009901735939724635,"rank":355,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.009679353982349584,"rank":355,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.009825256883224675,"rank":355,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.010155177187309667,"rank":355,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.010191349018122511,"rank":355,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00989231242459322,"rank":355,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008777831882551866,"rank":355,"remainingConfigurations":444},{"removed":"simpleqa","score":0.010497473871379703,"rank":354,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.009859786059636952,"rank":355,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.009859320430167335,"rank":355,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.009861584324795213,"rank":355,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009878576723342882,"rank":355,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009829365273389517,"rank":355,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009869377968916812,"rank":355,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5--effort-minimal":{"score":0.009527646248020022,"rank":356,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.002216576833204592,"rank":199,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01738031302035287,"rank":333,"remainingConfigurations":444},{"removed":"Datacurve","score":0.007412123618355517,"rank":356,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009544960635986604,"rank":356,"remainingConfigurations":444},{"removed":"Scale","score":0.011346821510665893,"rank":356,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.009407022098763866,"rank":356,"remainingConfigurations":444},{"removed":"Cognition","score":0.009472378321108256,"rank":356,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009915774084015316,"rank":355,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.009851583255435547,"rank":356,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.00943545569314268,"rank":344,"remainingConfigurations":431},{"removed":"Vals AI","score":0.009059029238193872,"rank":356,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00952346534544227,"rank":356,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.009217319173219397,"rank":356,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.009511126691887398,"rank":356,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009527646248020022,"rank":356,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00960991486258622,"rank":356,"remainingConfigurations":444},{"removed":"All provider reports","score":0.009280699572665732,"rank":356,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009613958579872945,"rank":356,"remainingConfigurations":444},{"removed":"briefcase","score":0.009508006367539042,"rank":357,"remainingConfigurations":444},{"removed":"aime","score":0.01015031926704396,"rank":352,"remainingConfigurations":444},{"removed":"apex-agents","score":0.009675912126075588,"rank":356,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.009504809928874657,"rank":358,"remainingConfigurations":444},{"removed":"automationbench","score":0.009518658231385065,"rank":357,"remainingConfigurations":444},{"removed":"critpt","score":0.009698706672734043,"rank":356,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009543993700414406,"rank":356,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00974322629095077,"rank":357,"remainingConfigurations":444},{"removed":"gdpval","score":0.009619327524265987,"rank":357,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00869991024095697,"rank":361,"remainingConfigurations":444},{"removed":"gpqa","score":0.009591671524176388,"rank":354,"remainingConfigurations":444},{"removed":"harvey","score":0.009408346783005435,"rank":356,"remainingConfigurations":444},{"removed":"hle","score":0.010908892968055507,"rank":356,"remainingConfigurations":444},{"removed":"ifbench","score":0.009063748541834558,"rank":355,"remainingConfigurations":444},{"removed":"itbench","score":0.009468702731702344,"rank":356,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009722516582067537,"rank":355,"remainingConfigurations":444},{"removed":"math500","score":0.010421045206713992,"rank":353,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.009779052691270268,"rank":357,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.010422811874710653,"rank":356,"remainingConfigurations":444},{"removed":"omniscience","score":0.007732145571141176,"rank":361,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009063736685231838,"rank":360,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0096578776400377,"rank":356,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00935755411661793,"rank":360,"remainingConfigurations":444},{"removed":"arc-agi","score":0.016716828790424267,"rank":333,"remainingConfigurations":444},{"removed":"deepswe","score":0.007416500968226933,"rank":356,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0095300324677466,"rank":356,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009234187902963051,"rank":357,"remainingConfigurations":444},{"removed":"frontiercode","score":0.009472378321108256,"rank":356,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.009384293865696301,"rank":356,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009411276266875258,"rank":356,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009522843734938639,"rank":356,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.009482131858713647,"rank":356,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009540741752238213,"rank":356,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.009405470659557739,"rank":356,"remainingConfigurations":444},{"removed":"livebench-language","score":0.009691578441725418,"rank":356,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00952340500104824,"rank":356,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00931209060150154,"rank":356,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.009455820923299425,"rank":356,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009774749657501039,"rank":356,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.009851583255435547,"rank":356,"remainingConfigurations":444},{"removed":"frontiermath","score":0.009578989409770292,"rank":356,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008707243248341276,"rank":356,"remainingConfigurations":444},{"removed":"simpleqa","score":0.01005923941813833,"rank":356,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00948672388173844,"rank":356,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.009483580466435855,"rank":356,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00949425477132229,"rank":356,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009501222370237867,"rank":356,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009454260755223801,"rank":356,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009498440989132693,"rank":356,"remainingConfigurations":444}],"sharedOrderConflicts":0},"llama-4-maverick--effort-non-reasoning":{"score":0.009454575985417091,"rank":357,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.012557496279336335,"rank":355,"remainingConfigurations":444},{"removed":"Datacurve","score":0.007362787095890558,"rank":357,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009342368787048924,"rank":357,"remainingConfigurations":444},{"removed":"Scale","score":0.011252450477565368,"rank":357,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.009345706460680558,"rank":357,"remainingConfigurations":444},{"removed":"Cognition","score":0.009182490985159652,"rank":357,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009888723879320395,"rank":356,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.009765846058576633,"rank":357,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.009706315691426071,"rank":341,"remainingConfigurations":431},{"removed":"Vals AI","score":0.009080808079785882,"rank":355,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.009450262081840357,"rank":357,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.009134263179199086,"rank":357,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.009437149682209189,"rank":357,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009454575985417091,"rank":357,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.009533976221193336,"rank":357,"remainingConfigurations":444},{"removed":"All provider reports","score":0.009194041183984251,"rank":357,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009550094777232643,"rank":357,"remainingConfigurations":444},{"removed":"briefcase","score":0.009601298312886818,"rank":356,"remainingConfigurations":444},{"removed":"aime","score":0.010708245983347667,"rank":350,"remainingConfigurations":444},{"removed":"apex-agents","score":0.009628923638639141,"rank":357,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00892800586451537,"rank":360,"remainingConfigurations":444},{"removed":"automationbench","score":0.009651493141588193,"rank":356,"remainingConfigurations":444},{"removed":"critpt","score":0.009186308701524704,"rank":358,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009468339124101657,"rank":357,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.009873637233473844,"rank":356,"remainingConfigurations":444},{"removed":"gdpval","score":0.009997443969554667,"rank":354,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00868174198872391,"rank":362,"remainingConfigurations":444},{"removed":"gpqa","score":0.009226969602845171,"rank":356,"remainingConfigurations":444},{"removed":"harvey","score":0.009345759835449573,"rank":357,"remainingConfigurations":444},{"removed":"hle","score":0.010849347670297904,"rank":357,"remainingConfigurations":444},{"removed":"ifbench","score":0.008664783991638614,"rank":358,"remainingConfigurations":444},{"removed":"itbench","score":0.00937774511875024,"rank":357,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009989668458587146,"rank":352,"remainingConfigurations":444},{"removed":"math500","score":0.010091489949378498,"rank":354,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00917384150519863,"rank":361,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00996430384203855,"rank":357,"remainingConfigurations":444},{"removed":"omniscience","score":0.007347026640872465,"rank":364,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009677924269150656,"rank":355,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.009612642037720722,"rank":357,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.009387675689127944,"rank":359,"remainingConfigurations":444},{"removed":"arc-agi","score":0.012066315610641235,"rank":355,"remainingConfigurations":444},{"removed":"deepswe","score":0.0073680412420654194,"rank":357,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.009457122091409502,"rank":357,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009286157699601711,"rank":356,"remainingConfigurations":444},{"removed":"frontiercode","score":0.009182490985159652,"rank":357,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.009312109695071341,"rank":357,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009336974077227507,"rank":357,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009449501858099599,"rank":357,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.009411365085800214,"rank":357,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009466606115663691,"rank":357,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.009332259577421185,"rank":357,"remainingConfigurations":444},{"removed":"livebench-language","score":0.009621819910003897,"rank":357,"remainingConfigurations":444},{"removed":"livebench-data","score":0.009453310712534779,"rank":357,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0092394800463521,"rank":357,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00938222931184399,"rank":357,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009697026763702246,"rank":357,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.009765846058576633,"rank":357,"remainingConfigurations":444},{"removed":"frontiermath","score":0.009470512450399588,"rank":357,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008811957392237625,"rank":354,"remainingConfigurations":444},{"removed":"simpleqa","score":0.009995367816539138,"rank":357,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.009414872682346977,"rank":357,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.00941339259705775,"rank":357,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00941672533683134,"rank":357,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009432128626630867,"rank":357,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009384597703758062,"rank":357,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009424209828918364,"rank":357,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-30b-a3b-instruct--effort-non-reasoning":{"score":0.009336794889896659,"rank":358,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.012420317110120782,"rank":356,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0072698554243192754,"rank":358,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009222688007133929,"rank":358,"remainingConfigurations":444},{"removed":"Scale","score":0.011103354977208326,"rank":358,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00922868940282867,"rank":358,"remainingConfigurations":444},{"removed":"Cognition","score":0.009078367065369214,"rank":358,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009760958851389912,"rank":357,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.009628837695609628,"rank":358,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.009500835155883267,"rank":342,"remainingConfigurations":431},{"removed":"Vals AI","score":0.008959257998649788,"rank":357,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00933255027990842,"rank":358,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.009021092022943409,"rank":358,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00931960536384674,"rank":358,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009336794889896659,"rank":358,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00941537342328018,"rank":358,"remainingConfigurations":444},{"removed":"All provider reports","score":0.009080309081521368,"rank":358,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009429683417118405,"rank":358,"remainingConfigurations":444},{"removed":"briefcase","score":0.009283650732884986,"rank":358,"remainingConfigurations":444},{"removed":"aime","score":0.008202147195602262,"rank":361,"remainingConfigurations":444},{"removed":"apex-agents","score":0.009499563344488723,"rank":358,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00920873149793854,"rank":359,"remainingConfigurations":444},{"removed":"automationbench","score":0.009293068685916254,"rank":358,"remainingConfigurations":444},{"removed":"critpt","score":0.009106679668537024,"rank":360,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009348584702120284,"rank":358,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.009583061624334798,"rank":358,"remainingConfigurations":444},{"removed":"gdpval","score":0.009387251937746149,"rank":359,"remainingConfigurations":444},{"removed":"gmmlu","score":0.009467078684097898,"rank":356,"remainingConfigurations":444},{"removed":"gpqa","score":0.00879307599538874,"rank":359,"remainingConfigurations":444},{"removed":"harvey","score":0.009229212688267345,"rank":358,"remainingConfigurations":444},{"removed":"hle","score":0.01029261152505128,"rank":359,"remainingConfigurations":444},{"removed":"ifbench","score":0.00974534035081273,"rank":351,"remainingConfigurations":444},{"removed":"itbench","score":0.009257671056508274,"rank":358,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009430742770415014,"rank":356,"remainingConfigurations":444},{"removed":"math500","score":0.009430399902600849,"rank":358,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.009791089295564237,"rank":356,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009676767681316782,"rank":359,"remainingConfigurations":444},{"removed":"omniscience","score":0.008287473124801941,"rank":356,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009989858675973167,"rank":354,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00949361611990559,"rank":358,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.009533374584211678,"rank":357,"remainingConfigurations":444},{"removed":"arc-agi","score":0.011929996527491089,"rank":356,"remainingConfigurations":444},{"removed":"deepswe","score":0.007274986035488931,"rank":358,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.009339285011563602,"rank":358,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009166854198884114,"rank":358,"remainingConfigurations":444},{"removed":"frontiercode","score":0.009078367065369214,"rank":358,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.009196022731919025,"rank":358,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009220780057605201,"rank":358,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009331727962617378,"rank":358,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00929357180453905,"rank":358,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009348853123178113,"rank":358,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.009215493527178218,"rank":358,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00950156892880933,"rank":358,"remainingConfigurations":444},{"removed":"livebench-data","score":0.009335822587853414,"rank":358,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.009124631948468876,"rank":358,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.009265264019441565,"rank":358,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009576537365232217,"rank":358,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.009628837695609628,"rank":358,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00935724828985426,"rank":358,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008673983917154258,"rank":357,"remainingConfigurations":444},{"removed":"simpleqa","score":0.009870893469586648,"rank":358,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.009297580583478505,"rank":358,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.009296086876975208,"rank":358,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.009299512756905631,"rank":358,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009314480409400347,"rank":358,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009267647642626433,"rank":358,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009306808937733077,"rank":358,"remainingConfigurations":444}],"sharedOrderConflicts":0},"step3-vl-10b--effort-reasoning":{"score":0.009218784265193703,"rank":359,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.012274413983464431,"rank":357,"remainingConfigurations":444},{"removed":"Datacurve","score":0.007180114977041946,"rank":359,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.009110143644431051,"rank":359,"remainingConfigurations":444},{"removed":"Scale","score":0.010965589769843525,"rank":359,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.009112628688714715,"rank":359,"remainingConfigurations":444},{"removed":"Cognition","score":0.00896492501454571,"rank":359,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009639214874709074,"rank":358,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00951142578138195,"rank":359,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.009343160112165532,"rank":345,"remainingConfigurations":431},{"removed":"Vals AI","score":0.008847385287103734,"rank":358,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.009214587552756994,"rank":359,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008906841266472369,"rank":359,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.009201788246812852,"rank":359,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009218784265193703,"rank":359,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00929648302219907,"rank":359,"remainingConfigurations":444},{"removed":"All provider reports","score":0.008965390705513285,"rank":359,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009314604718622303,"rank":359,"remainingConfigurations":444},{"removed":"briefcase","score":0.009164769519926742,"rank":359,"remainingConfigurations":444},{"removed":"aime","score":0.009116223027059618,"rank":355,"remainingConfigurations":444},{"removed":"apex-agents","score":0.009379653341631504,"rank":359,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010960800342473973,"rank":345,"remainingConfigurations":444},{"removed":"automationbench","score":0.009177406014564021,"rank":359,"remainingConfigurations":444},{"removed":"critpt","score":0.00913212754102493,"rank":359,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009233284024578141,"rank":359,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.009459429130886389,"rank":359,"remainingConfigurations":444},{"removed":"gdpval","score":0.009258536704884817,"rank":360,"remainingConfigurations":444},{"removed":"gmmlu","score":0.009345607244375052,"rank":357,"remainingConfigurations":444},{"removed":"gpqa","score":0.008532725452083952,"rank":363,"remainingConfigurations":444},{"removed":"harvey","score":0.009113238303160645,"rank":359,"remainingConfigurations":444},{"removed":"hle","score":0.008773981131245785,"rank":367,"remainingConfigurations":444},{"removed":"ifbench","score":0.007293648228285144,"rank":364,"remainingConfigurations":444},{"removed":"itbench","score":0.009143041441262316,"rank":359,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00924401127165005,"rank":359,"remainingConfigurations":444},{"removed":"math500","score":0.009273089438797314,"rank":359,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00960871982358368,"rank":358,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009024445035244924,"rank":364,"remainingConfigurations":444},{"removed":"omniscience","score":0.009015638397832697,"rank":355,"remainingConfigurations":444},{"removed":"tau-bench","score":0.010558245158584873,"rank":347,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00937505229582894,"rank":359,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.009675513072880124,"rank":356,"remainingConfigurations":444},{"removed":"arc-agi","score":0.011786899173014892,"rank":357,"remainingConfigurations":444},{"removed":"deepswe","score":0.007185173647781634,"rank":359,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.00922124278036855,"rank":359,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.009052811507254626,"rank":359,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00896492501454571,"rank":359,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0090801073179893,"rank":359,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.009104566257181765,"rank":359,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009213764435873418,"rank":359,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.009176104744514076,"rank":359,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009230668423453535,"rank":359,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.009098919091252499,"rank":359,"remainingConfigurations":444},{"removed":"livebench-language","score":0.009381553113345925,"rank":359,"remainingConfigurations":444},{"removed":"livebench-data","score":0.009217905500721107,"rank":359,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.009009239656942593,"rank":359,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.009148123288945919,"rank":359,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009455576394547001,"rank":359,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00951142578138195,"rank":359,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00923814097261205,"rank":359,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00856543073604363,"rank":358,"remainingConfigurations":444},{"removed":"simpleqa","score":0.009745006802548131,"rank":359,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.009180078067367677,"rank":359,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.009178597077920339,"rank":359,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.009181939001095625,"rank":359,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.009196756980908353,"rank":359,"remainingConfigurations":444},{"removed":"vibe-code","score":0.009150506181621389,"rank":359,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.009189170834748238,"rank":359,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-30b-a3b--effort-reasoning":{"score":0.009015404601291918,"rank":360,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01200477818132195,"rank":358,"remainingConfigurations":444},{"removed":"Datacurve","score":0.007021400804623062,"rank":360,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00890673722704906,"rank":360,"remainingConfigurations":444},{"removed":"Scale","score":0.010721663042680714,"rank":360,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.008910466587618756,"rank":360,"remainingConfigurations":444},{"removed":"Cognition","score":0.008767716481758005,"rank":360,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009427623203136677,"rank":359,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.009298588625086255,"rank":360,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.009204024634033038,"rank":346,"remainingConfigurations":431},{"removed":"Vals AI","score":0.008650937829107301,"rank":359,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.009011299949502368,"rank":360,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008710427995615649,"rank":360,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.008998807149407215,"rank":360,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.009015404601291918,"rank":360,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00909138539638397,"rank":360,"remainingConfigurations":444},{"removed":"All provider reports","score":0.008767702983480513,"rank":360,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.009105006805318562,"rank":360,"remainingConfigurations":444},{"removed":"briefcase","score":0.008964289944385449,"rank":360,"remainingConfigurations":444},{"removed":"aime","score":0.007998986945040136,"rank":363,"remainingConfigurations":444},{"removed":"apex-agents","score":0.00917431988963404,"rank":360,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.010058952747408756,"rank":355,"remainingConfigurations":444},{"removed":"automationbench","score":0.008971239060167658,"rank":360,"remainingConfigurations":444},{"removed":"critpt","score":0.008682262441088577,"rank":361,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.009028741258739164,"rank":360,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.009247648186427612,"rank":360,"remainingConfigurations":444},{"removed":"gdpval","score":0.00904914357246999,"rank":361,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00913535167975314,"rank":359,"remainingConfigurations":444},{"removed":"gpqa","score":0.009109093897599252,"rank":357,"remainingConfigurations":444},{"removed":"harvey","score":0.008912191676229453,"rank":360,"remainingConfigurations":444},{"removed":"hle","score":0.009962553179203542,"rank":360,"remainingConfigurations":444},{"removed":"ifbench","score":0.008375405910566692,"rank":361,"remainingConfigurations":444},{"removed":"itbench","score":0.008938703439571217,"rank":360,"remainingConfigurations":444},{"removed":"livecodebench","score":0.009014826850535396,"rank":360,"remainingConfigurations":444},{"removed":"math500","score":0.008619213157051163,"rank":361,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.009208325902132187,"rank":360,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009898272708681852,"rank":358,"remainingConfigurations":444},{"removed":"omniscience","score":0.007768071103425876,"rank":359,"remainingConfigurations":444},{"removed":"tau-bench","score":0.008893048210476455,"rank":361,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.009169817649713478,"rank":360,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.009780141311676496,"rank":355,"remainingConfigurations":444},{"removed":"arc-agi","score":0.011527580471790318,"rank":358,"remainingConfigurations":444},{"removed":"deepswe","score":0.007026344323216453,"rank":360,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.009017810482492315,"rank":360,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.008850913910293128,"rank":360,"remainingConfigurations":444},{"removed":"frontiercode","score":0.008767716481758005,"rank":360,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.008879656975029319,"rank":360,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.008903552978274644,"rank":360,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.009010520660646584,"rank":360,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.008973646499207668,"rank":360,"remainingConfigurations":444},{"removed":"livebench-math","score":0.009027044662243952,"rank":360,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.008898093827425653,"rank":360,"remainingConfigurations":444},{"removed":"livebench-language","score":0.009174585456671545,"rank":360,"remainingConfigurations":444},{"removed":"livebench-data","score":0.009014569104911484,"rank":360,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.008810408565936395,"rank":360,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00894625928965311,"rank":360,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009247155853870197,"rank":360,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.009298588625086255,"rank":360,"remainingConfigurations":444},{"removed":"frontiermath","score":0.009033856420597388,"rank":360,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008371286714630511,"rank":360,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00953166275684234,"rank":360,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00897751455227916,"rank":360,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.008976067564687646,"rank":360,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.008979397352847291,"rank":360,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.008993825693273448,"rank":360,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00894857217690329,"rank":360,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.008986434845277608,"rank":360,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-4o--effort-non-reasoning":{"score":0.008802001554885135,"rank":361,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01174855254255261,"rank":359,"remainingConfigurations":444},{"removed":"Datacurve","score":0.006859423324615762,"rank":361,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.008701606750242893,"rank":361,"remainingConfigurations":444},{"removed":"Scale","score":0.01047153380296846,"rank":361,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.008701082832418114,"rank":361,"remainingConfigurations":444},{"removed":"Cognition","score":0.008582040127168162,"rank":361,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009212332723074783,"rank":360,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.009073273273469972,"rank":361,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.008933468491935385,"rank":347,"remainingConfigurations":431},{"removed":"Vals AI","score":0.008451570910715663,"rank":360,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00879796803607831,"rank":361,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008503702745684646,"rank":361,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.008785677146022517,"rank":361,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.008802001554885135,"rank":361,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.008876759471657674,"rank":361,"remainingConfigurations":444},{"removed":"All provider reports","score":0.008560031680625227,"rank":361,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.008889965967491274,"rank":361,"remainingConfigurations":444},{"removed":"briefcase","score":0.008735727889367927,"rank":361,"remainingConfigurations":444},{"removed":"aime","score":0.008744931023113365,"rank":358,"remainingConfigurations":444},{"removed":"apex-agents","score":0.008957035999612296,"rank":361,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00867801756949516,"rank":361,"remainingConfigurations":444},{"removed":"automationbench","score":0.008753438215165468,"rank":361,"remainingConfigurations":444},{"removed":"critpt","score":0.009195888993848598,"rank":357,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.008814604730394667,"rank":361,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.009032322182964283,"rank":361,"remainingConfigurations":444},{"removed":"gdpval","score":0.009403512032283678,"rank":358,"remainingConfigurations":444},{"removed":"gmmlu","score":0.008893816018740288,"rank":360,"remainingConfigurations":444},{"removed":"gpqa","score":0.008828795070552531,"rank":358,"remainingConfigurations":444},{"removed":"harvey","score":0.00870376546409909,"rank":361,"remainingConfigurations":444},{"removed":"hle","score":0.009924372063571446,"rank":361,"remainingConfigurations":444},{"removed":"ifbench","score":0.008381578231905516,"rank":360,"remainingConfigurations":444},{"removed":"itbench","score":0.008721779410815292,"rank":361,"remainingConfigurations":444},{"removed":"livecodebench","score":0.008862710926890397,"rank":361,"remainingConfigurations":444},{"removed":"math500","score":0.008937711194838154,"rank":360,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.009232999415382847,"rank":359,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00938589187977241,"rank":362,"remainingConfigurations":444},{"removed":"omniscience","score":0.007969973476695364,"rank":357,"remainingConfigurations":444},{"removed":"tau-bench","score":0.008373948310874388,"rank":364,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.008961771797886054,"rank":361,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0075566703093486965,"rank":366,"remainingConfigurations":444},{"removed":"arc-agi","score":0.01123741559816161,"rank":359,"remainingConfigurations":444},{"removed":"deepswe","score":0.006864209916281315,"rank":361,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.008804350880849651,"rank":361,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.008646398133411263,"rank":361,"remainingConfigurations":444},{"removed":"frontiercode","score":0.008582040127168162,"rank":361,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.008669961250268943,"rank":361,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.008693045862715826,"rank":361,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.008797226945658768,"rank":361,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.008761189383634167,"rank":361,"remainingConfigurations":444},{"removed":"livebench-math","score":0.008813212794537064,"rank":361,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.008687484411000054,"rank":361,"remainingConfigurations":444},{"removed":"livebench-language","score":0.008957647599961522,"rank":361,"remainingConfigurations":444},{"removed":"livebench-data","score":0.008801215551873428,"rank":361,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00860162442730223,"rank":361,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.008734433989787222,"rank":361,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.009028482316742003,"rank":361,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.009073273273469972,"rank":361,"remainingConfigurations":444},{"removed":"frontiermath","score":0.008833541005075225,"rank":361,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008169033896729178,"rank":361,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00930349710158968,"rank":361,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.008765073617031256,"rank":361,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.008763569757558345,"rank":361,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.008766816907677569,"rank":361,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.008780895991179026,"rank":361,"remainingConfigurations":444},{"removed":"vibe-code","score":0.008736678430737242,"rank":361,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.008773725379665297,"rank":361,"remainingConfigurations":444}],"sharedOrderConflicts":1},"qwen3-30b-a3b-instruct-2507--effort-non-reasoning":{"score":0.008662455538272848,"rank":362,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.011505925125087848,"rank":361,"remainingConfigurations":444},{"removed":"Datacurve","score":0.006743108632232494,"rank":362,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.008555600635098965,"rank":362,"remainingConfigurations":444},{"removed":"Scale","score":0.010304777248614576,"rank":362,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.008561548620447298,"rank":362,"remainingConfigurations":444},{"removed":"Cognition","score":0.00842263264788931,"rank":362,"remainingConfigurations":444},{"removed":"LiveBench","score":0.009057371539836859,"rank":361,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.008933424325767795,"rank":362,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.008818506267990071,"rank":349,"remainingConfigurations":431},{"removed":"Vals AI","score":0.008312809325603937,"rank":361,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00865851319952488,"rank":362,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008369314563874753,"rank":362,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.008646510371668843,"rank":362,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.008662455538272848,"rank":362,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00873532563828375,"rank":362,"remainingConfigurations":444},{"removed":"All provider reports","score":0.008424222663764516,"rank":362,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.008749017602081391,"rank":362,"remainingConfigurations":444},{"removed":"briefcase","score":0.00860630541345685,"rank":362,"remainingConfigurations":444},{"removed":"aime","score":0.007976310666507105,"rank":364,"remainingConfigurations":444},{"removed":"apex-agents","score":0.008813895851905512,"rank":362,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.008658871469586554,"rank":362,"remainingConfigurations":444},{"removed":"automationbench","score":0.008613872559258265,"rank":362,"remainingConfigurations":444},{"removed":"critpt","score":0.008337449805753383,"rank":362,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.008672844390412307,"rank":362,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.008879789052004145,"rank":362,"remainingConfigurations":444},{"removed":"gdpval","score":0.008702921737179325,"rank":362,"remainingConfigurations":444},{"removed":"gmmlu","score":0.009283811017215688,"rank":358,"remainingConfigurations":444},{"removed":"gpqa","score":0.008544607639874847,"rank":362,"remainingConfigurations":444},{"removed":"harvey","score":0.008563080385334784,"rank":362,"remainingConfigurations":444},{"removed":"hle","score":0.009385975197738716,"rank":364,"remainingConfigurations":444},{"removed":"ifbench","score":0.008913321565302558,"rank":356,"remainingConfigurations":444},{"removed":"itbench","score":0.008589784300950755,"rank":362,"remainingConfigurations":444},{"removed":"livecodebench","score":0.008451641544857528,"rank":362,"remainingConfigurations":444},{"removed":"math500","score":0.007766591115377869,"rank":364,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.008780366114804603,"rank":363,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009518695562911524,"rank":360,"remainingConfigurations":444},{"removed":"omniscience","score":0.007708864934444393,"rank":362,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009427369906719437,"rank":358,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00880816784370417,"rank":362,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.008780391991819052,"rank":361,"remainingConfigurations":444},{"removed":"arc-agi","score":0.011053413190776044,"rank":361,"remainingConfigurations":444},{"removed":"deepswe","score":0.006747881765326917,"rank":362,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.008664771770048077,"rank":362,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.008504341400222385,"rank":362,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00842263264788931,"rank":362,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.008531491572613854,"rank":362,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.00855471847809479,"rank":362,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.008657759944002726,"rank":362,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.008622402686293284,"rank":362,"remainingConfigurations":444},{"removed":"livebench-math","score":0.008673678005963513,"rank":362,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.008549699582193824,"rank":362,"remainingConfigurations":444},{"removed":"livebench-language","score":0.008815530749069656,"rank":362,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00866157200383682,"rank":362,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.008465368975897435,"rank":362,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.008595997369081733,"rank":362,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.00888523032546975,"rank":362,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.008933424325767795,"rank":362,"remainingConfigurations":444},{"removed":"frontiermath","score":0.008681154554163973,"rank":362,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.008045545538892418,"rank":362,"remainingConfigurations":444},{"removed":"simpleqa","score":0.009159549853701092,"rank":362,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00862600974361971,"rank":362,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.008624642268939086,"rank":362,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.008627808663331035,"rank":362,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.008641733747495876,"rank":362,"remainingConfigurations":444},{"removed":"vibe-code","score":0.008598226837051694,"rank":362,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0086345785469085,"rank":362,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning":{"score":0.00840186920783392,"rank":363,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.011189732798937972,"rank":362,"remainingConfigurations":444},{"removed":"Datacurve","score":0.006542921456248007,"rank":363,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.008302249048375138,"rank":363,"remainingConfigurations":444},{"removed":"Scale","score":0.00999591921165925,"rank":363,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.008304165729508711,"rank":363,"remainingConfigurations":444},{"removed":"Cognition","score":0.008172704222765604,"rank":363,"remainingConfigurations":444},{"removed":"LiveBench","score":0.008787314201872844,"rank":362,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.008667405053977088,"rank":363,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.008571322051559324,"rank":350,"remainingConfigurations":431},{"removed":"Vals AI","score":0.00806215852550624,"rank":362,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.008398038260806092,"rank":363,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008117287731158954,"rank":363,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.008386370962420111,"rank":363,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.00840186920783392,"rank":363,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00847280330276415,"rank":363,"remainingConfigurations":444},{"removed":"All provider reports","score":0.00817074912644815,"rank":363,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.008485165683611582,"rank":363,"remainingConfigurations":444},{"removed":"briefcase","score":0.008348803349012343,"rank":363,"remainingConfigurations":444},{"removed":"aime","score":0.007192714496633174,"rank":367,"remainingConfigurations":444},{"removed":"apex-agents","score":0.008550217897129708,"rank":363,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.007976673922181633,"rank":365,"remainingConfigurations":444},{"removed":"automationbench","score":0.0083559506319169,"rank":363,"remainingConfigurations":444},{"removed":"critpt","score":0.008064957014853685,"rank":363,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.008413867930659546,"rank":363,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.008618176529808287,"rank":363,"remainingConfigurations":444},{"removed":"gdpval","score":0.00842304309362638,"rank":363,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0085102032850278,"rank":363,"remainingConfigurations":444},{"removed":"gpqa","score":0.008744763279556339,"rank":360,"remainingConfigurations":444},{"removed":"harvey","score":0.008305749015606568,"rank":363,"remainingConfigurations":444},{"removed":"hle","score":0.009393655300075581,"rank":363,"remainingConfigurations":444},{"removed":"ifbench","score":0.008864307983623457,"rank":357,"remainingConfigurations":444},{"removed":"itbench","score":0.00833032483595843,"rank":363,"remainingConfigurations":444},{"removed":"livecodebench","score":0.007435744164078872,"rank":367,"remainingConfigurations":444},{"removed":"math500","score":0.008523145326209368,"rank":362,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.008920764085169291,"rank":362,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009434574353780025,"rank":361,"remainingConfigurations":444},{"removed":"omniscience","score":0.007572642478142822,"rank":363,"remainingConfigurations":444},{"removed":"tau-bench","score":0.008632708513866895,"rank":363,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.008546067760616003,"rank":363,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.008710311155106535,"rank":362,"remainingConfigurations":444},{"removed":"arc-agi","score":0.010741382311789768,"rank":362,"remainingConfigurations":444},{"removed":"deepswe","score":0.006547522852613958,"rank":363,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.008404112393278654,"rank":363,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.008248929587459855,"rank":363,"remainingConfigurations":444},{"removed":"frontiercode","score":0.008172704222765604,"rank":363,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.008275300353264426,"rank":363,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.008297615486050812,"rank":363,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.008397317058403908,"rank":363,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.008362900368442243,"rank":363,"remainingConfigurations":444},{"removed":"livebench-math","score":0.008412725630943077,"rank":363,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.008292405135714753,"rank":363,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00855039839870402,"rank":363,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00840109382752102,"rank":363,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.008210596880573805,"rank":363,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.008337349350034051,"rank":363,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.008618144600548508,"rank":363,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.008667405053977088,"rank":363,"remainingConfigurations":444},{"removed":"frontiermath","score":0.008419468938906835,"rank":363,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.007800351267115709,"rank":363,"remainingConfigurations":444},{"removed":"simpleqa","score":0.008883298384288004,"rank":363,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.008366523446440559,"rank":363,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.008365159941307208,"rank":363,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0083682799867614,"rank":363,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.008381715982321122,"rank":363,"remainingConfigurations":444},{"removed":"vibe-code","score":0.008339504772323985,"rank":363,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.008374842406631937,"rank":363,"remainingConfigurations":444}],"sharedOrderConflicts":0},"ernie-4.5-300b-a47b-pt--effort-non-reasoning":{"score":0.008284296032939531,"rank":364,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.011036824925723268,"rank":363,"remainingConfigurations":444},{"removed":"Datacurve","score":0.006449489158121993,"rank":364,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.008185574252996076,"rank":364,"remainingConfigurations":444},{"removed":"Scale","score":0.009859995235554855,"rank":364,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00818822222037587,"rank":364,"remainingConfigurations":444},{"removed":"Cognition","score":0.008057772154592446,"rank":364,"remainingConfigurations":444},{"removed":"LiveBench","score":0.008662640989244274,"rank":363,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.008549720562031056,"rank":364,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.008434576876401262,"rank":351,"remainingConfigurations":431},{"removed":"Vals AI","score":0.007950850384117778,"rank":363,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.008280524759130556,"rank":364,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.008003777483727216,"rank":364,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.008269048336875352,"rank":364,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.008284296032939531,"rank":364,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.008354036607873755,"rank":364,"remainingConfigurations":444},{"removed":"All provider reports","score":0.008056338337011248,"rank":364,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.008370363680808594,"rank":364,"remainingConfigurations":444},{"removed":"briefcase","score":0.008258347173062652,"rank":364,"remainingConfigurations":444},{"removed":"aime","score":0.00832583305534414,"rank":360,"remainingConfigurations":444},{"removed":"apex-agents","score":0.008434098345248003,"rank":364,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.008164095097662786,"rank":364,"remainingConfigurations":444},{"removed":"automationbench","score":0.008267398671867498,"rank":364,"remainingConfigurations":444},{"removed":"critpt","score":0.007928847014849269,"rank":364,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.008304552715434156,"rank":364,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.008520465240025386,"rank":364,"remainingConfigurations":444},{"removed":"gdpval","score":0.008351141178482633,"rank":364,"remainingConfigurations":444},{"removed":"gmmlu","score":0.008410247439056046,"rank":364,"remainingConfigurations":444},{"removed":"gpqa","score":0.006752030892357771,"rank":372,"remainingConfigurations":444},{"removed":"harvey","score":0.008190206701717552,"rank":364,"remainingConfigurations":444},{"removed":"hle","score":0.010681144158914841,"rank":358,"remainingConfigurations":444},{"removed":"ifbench","score":0.00790228286964752,"rank":362,"remainingConfigurations":444},{"removed":"itbench","score":0.008217980646141735,"rank":364,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00836728212207549,"rank":363,"remainingConfigurations":444},{"removed":"math500","score":0.008357867222554386,"rank":363,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.008335265693150651,"rank":364,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.009122730852613897,"rank":363,"remainingConfigurations":444},{"removed":"omniscience","score":0.006479762315777484,"rank":368,"remainingConfigurations":444},{"removed":"tau-bench","score":0.009425408193470495,"rank":359,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.008425001120399117,"rank":364,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.008380920846016928,"rank":363,"remainingConfigurations":444},{"removed":"arc-agi","score":0.010601391647686241,"rank":363,"remainingConfigurations":444},{"removed":"deepswe","score":0.006454051804595489,"rank":364,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.008286510861715477,"rank":364,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.008132831320829476,"rank":364,"remainingConfigurations":444},{"removed":"frontiercode","score":0.008057772154592446,"rank":364,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.008159154896716007,"rank":364,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.008181254026821468,"rank":364,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.008279822283430263,"rank":364,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.008245958324148008,"rank":364,"remainingConfigurations":444},{"removed":"livebench-math","score":0.008295041329601772,"rank":364,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00817634146766655,"rank":364,"remainingConfigurations":444},{"removed":"livebench-language","score":0.008430790007166296,"rank":364,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00828350269651915,"rank":364,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.008095682898102648,"rank":364,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.008220674849719563,"rank":364,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.008497524058168617,"rank":364,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.008549720562031056,"rank":364,"remainingConfigurations":444},{"removed":"frontiermath","score":0.008302660545242027,"rank":364,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.007695734479695502,"rank":364,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00876046427077243,"rank":364,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.008249418429513945,"rank":364,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.008248103887125366,"rank":364,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.008251147873306816,"rank":364,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.008264451033862403,"rank":364,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00822281812458237,"rank":364,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.008257631231714021,"rank":364,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-14b--effort-reasoning":{"score":0.007780433535420968,"rank":365,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.010352638686214003,"rank":364,"remainingConfigurations":444},{"removed":"Datacurve","score":0.006059024157073104,"rank":365,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00768983856995269,"rank":365,"remainingConfigurations":444},{"removed":"Scale","score":0.009264249590038317,"rank":365,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.007690967759814993,"rank":365,"remainingConfigurations":444},{"removed":"Cognition","score":0.007561003852132152,"rank":365,"remainingConfigurations":444},{"removed":"LiveBench","score":0.008142779628122215,"rank":364,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.008032695229660382,"rank":365,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.007972586846559887,"rank":352,"remainingConfigurations":431},{"removed":"Vals AI","score":0.007477274514687284,"rank":364,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.007776866941162163,"rank":365,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.007515876073654928,"rank":365,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.007766046045678061,"rank":365,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.007780433535420968,"rank":365,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00784597780577113,"rank":365,"remainingConfigurations":444},{"removed":"All provider reports","score":0.007565203506372257,"rank":365,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00786261350600372,"rank":365,"remainingConfigurations":444},{"removed":"briefcase","score":0.007897527924401576,"rank":365,"remainingConfigurations":444},{"removed":"aime","score":0.0074601948334815935,"rank":366,"remainingConfigurations":444},{"removed":"apex-agents","score":0.00792316590512533,"rank":365,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.008375808874484669,"rank":363,"remainingConfigurations":444},{"removed":"automationbench","score":0.008094533614978748,"rank":365,"remainingConfigurations":444},{"removed":"critpt","score":0.007411858885398075,"rank":365,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0077955817275964625,"rank":365,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.007785618509620021,"rank":366,"remainingConfigurations":444},{"removed":"gdpval","score":0.008032443982476172,"rank":365,"remainingConfigurations":444},{"removed":"gmmlu","score":0.007864719653035443,"rank":365,"remainingConfigurations":444},{"removed":"gpqa","score":0.007822042927407949,"rank":365,"remainingConfigurations":444},{"removed":"harvey","score":0.00769206982501432,"rank":365,"remainingConfigurations":444},{"removed":"hle","score":0.009119287552962771,"rank":365,"remainingConfigurations":444},{"removed":"ifbench","score":0.00717534762827064,"rank":365,"remainingConfigurations":444},{"removed":"itbench","score":0.007716324286769567,"rank":365,"remainingConfigurations":444},{"removed":"livecodebench","score":0.007546818769767251,"rank":366,"remainingConfigurations":444},{"removed":"math500","score":0.007349721554441059,"rank":367,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.007970767233414448,"rank":366,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.008560298090572441,"rank":366,"remainingConfigurations":444},{"removed":"omniscience","score":0.006908551794723825,"rank":366,"remainingConfigurations":444},{"removed":"tau-bench","score":0.007223205677751321,"rank":367,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.007913375571430917,"rank":365,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.007837566831612729,"rank":365,"remainingConfigurations":444},{"removed":"arc-agi","score":0.009943422410966053,"rank":364,"remainingConfigurations":444},{"removed":"deepswe","score":0.0060633381955878494,"rank":365,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.007782533683114949,"rank":365,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.007641813224832982,"rank":365,"remainingConfigurations":444},{"removed":"frontiercode","score":0.007561003852132152,"rank":365,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.007663244804330251,"rank":365,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.007683686430090343,"rank":365,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00777627838128852,"rank":365,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.007744908804717974,"rank":365,"remainingConfigurations":444},{"removed":"livebench-math","score":0.007790356955123351,"rank":365,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0076792203279981396,"rank":365,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00791848794542906,"rank":365,"remainingConfigurations":444},{"removed":"livebench-data","score":0.007779637859273161,"rank":365,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.007602856877318823,"rank":365,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.007720624812095172,"rank":365,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.007980794285796467,"rank":365,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.008032695229660382,"rank":365,"remainingConfigurations":444},{"removed":"frontiermath","score":0.007793912649256564,"rank":365,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.007238682572702454,"rank":365,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00822733409088868,"rank":365,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.007747667295634559,"rank":365,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0077464374526018285,"rank":365,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.007749193071349479,"rank":365,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.007761870763085032,"rank":365,"remainingConfigurations":444},{"removed":"vibe-code","score":0.007722634277612279,"rank":365,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0077553827484998375,"rank":365,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-8b-thinking--effort-reasoning":{"score":0.00760858638067614,"rank":366,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.010137933670451023,"rank":365,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005922227004254475,"rank":366,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.007516441486892307,"rank":366,"remainingConfigurations":444},{"removed":"Scale","score":0.009057352262083188,"rank":366,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.007520562242559898,"rank":366,"remainingConfigurations":444},{"removed":"Cognition","score":0.007400676070943676,"rank":366,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00795815451112422,"rank":365,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.007852017696298366,"rank":366,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.007748883133306058,"rank":353,"remainingConfigurations":431},{"removed":"Vals AI","score":0.007303327626720177,"rank":365,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00760511630994157,"rank":366,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00735055627667868,"rank":366,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0075945425261435455,"rank":366,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.00760858638067614,"rank":366,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.007672726205598925,"rank":366,"remainingConfigurations":444},{"removed":"All provider reports","score":0.007398869676282618,"rank":366,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.007687777914176259,"rank":366,"remainingConfigurations":444},{"removed":"briefcase","score":0.0075648544117284,"rank":366,"remainingConfigurations":444},{"removed":"aime","score":0.008121124016275152,"rank":362,"remainingConfigurations":444},{"removed":"apex-agents","score":0.007743449487198367,"rank":366,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.007319336806670987,"rank":367,"remainingConfigurations":444},{"removed":"automationbench","score":0.007574741023548694,"rank":366,"remainingConfigurations":444},{"removed":"critpt","score":0.006186766731476184,"rank":368,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.007621578897401706,"rank":366,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.007812985661998348,"rank":365,"remainingConfigurations":444},{"removed":"gdpval","score":0.007648776187304453,"rank":366,"remainingConfigurations":444},{"removed":"gmmlu","score":0.007726545797774323,"rank":366,"remainingConfigurations":444},{"removed":"gpqa","score":0.00774554863188186,"rank":366,"remainingConfigurations":444},{"removed":"harvey","score":0.0075228667176575,"rank":366,"remainingConfigurations":444},{"removed":"hle","score":0.009456154508548576,"rank":362,"remainingConfigurations":444},{"removed":"ifbench","score":0.007019599733384383,"rank":367,"remainingConfigurations":444},{"removed":"itbench","score":0.007545499367401856,"rank":366,"remainingConfigurations":444},{"removed":"livecodebench","score":0.008184010752789486,"rank":364,"remainingConfigurations":444},{"removed":"math500","score":0.007687897539359462,"rank":365,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00806061839745245,"rank":365,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00816596475514632,"rank":367,"remainingConfigurations":444},{"removed":"omniscience","score":0.00583127660400255,"rank":372,"remainingConfigurations":444},{"removed":"tau-bench","score":0.007638993802240288,"rank":365,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.007739072339485346,"rank":366,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.007979054807486504,"rank":364,"remainingConfigurations":444},{"removed":"arc-agi","score":0.009735247977263951,"rank":365,"remainingConfigurations":444},{"removed":"deepswe","score":0.0059264155433667405,"rank":366,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.007610622699109614,"rank":366,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.007469984811535937,"rank":366,"remainingConfigurations":444},{"removed":"frontiercode","score":0.007400676070943676,"rank":366,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.007493529425732462,"rank":366,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0075138547857426866,"rank":366,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0076044779087354915,"rank":366,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.007573371676203196,"rank":366,"remainingConfigurations":444},{"removed":"livebench-math","score":0.007618452090825148,"rank":366,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.007509316261213802,"rank":366,"remainingConfigurations":444},{"removed":"livebench-language","score":0.007743329718099073,"rank":366,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0076078609644511025,"rank":366,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.007435118182432636,"rank":366,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0075500709212042655,"rank":366,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.007804712698846334,"rank":366,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.007852017696298366,"rank":366,"remainingConfigurations":444},{"removed":"frontiermath","score":0.007625439581716482,"rank":366,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0070665506187123665,"rank":366,"remainingConfigurations":444},{"removed":"simpleqa","score":0.008046046297160745,"rank":366,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.007576518936752941,"rank":366,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.007575301177581008,"rank":366,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.007578102822900863,"rank":366,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.007590325341403217,"rank":366,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0075520472627445155,"rank":366,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.007584065706057548,"rank":366,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-e4b-it--effort-non-reasoning":{"score":0.007583993335564365,"rank":367,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.01012042802979679,"rank":366,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005906610749634435,"rank":367,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.007496305651291811,"rank":367,"remainingConfigurations":444},{"removed":"Scale","score":0.009029606731864854,"rank":367,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.007495830987850986,"rank":367,"remainingConfigurations":444},{"removed":"Cognition","score":0.00738786566227433,"rank":367,"remainingConfigurations":444},{"removed":"LiveBench","score":0.007934918115783887,"rank":366,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00782284470158237,"rank":367,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.007708678744488054,"rank":354,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0072790310060643236,"rank":366,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0075805265355868325,"rank":367,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.007326640633311139,"rank":367,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.007569969354747907,"rank":367,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.007583993335564365,"rank":367,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.007648166181661183,"rank":367,"remainingConfigurations":444},{"removed":"All provider reports","score":0.007374995093943161,"rank":367,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.007661723588010312,"rank":367,"remainingConfigurations":444},{"removed":"briefcase","score":0.007537569659486116,"rank":367,"remainingConfigurations":444},{"removed":"aime","score":0.0075294808066573805,"rank":365,"remainingConfigurations":444},{"removed":"apex-agents","score":0.007719342717481138,"rank":367,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0076221514951789774,"rank":366,"remainingConfigurations":444},{"removed":"automationbench","score":0.007547248346709037,"rank":367,"remainingConfigurations":444},{"removed":"critpt","score":0.005690490282372896,"rank":374,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.007597246037773564,"rank":367,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.007784583755291493,"rank":367,"remainingConfigurations":444},{"removed":"gdpval","score":0.007615169311107536,"rank":367,"remainingConfigurations":444},{"removed":"gmmlu","score":0.007675894303117399,"rank":367,"remainingConfigurations":444},{"removed":"gpqa","score":0.008121854617007745,"rank":364,"remainingConfigurations":444},{"removed":"harvey","score":0.007498337592540798,"rank":367,"remainingConfigurations":444},{"removed":"hle","score":0.008859765694532685,"rank":366,"remainingConfigurations":444},{"removed":"ifbench","score":0.006756425664942605,"rank":370,"remainingConfigurations":444},{"removed":"itbench","score":0.007519997193379934,"rank":367,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0076409654856343075,"rank":365,"remainingConfigurations":444},{"removed":"math500","score":0.007682101487961115,"rank":366,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.007955207300796572,"rank":367,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.008630338618421529,"rank":365,"remainingConfigurations":444},{"removed":"omniscience","score":0.00782235232640867,"rank":358,"remainingConfigurations":444},{"removed":"tau-bench","score":0.007371029356064966,"rank":366,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.007718288484821788,"rank":367,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.007217771823976764,"rank":367,"remainingConfigurations":444},{"removed":"arc-agi","score":0.009702353472374964,"rank":366,"remainingConfigurations":444},{"removed":"deepswe","score":0.005910763522237988,"rank":367,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.007586020666567645,"rank":367,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.007447364600942333,"rank":367,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00738786566227433,"rank":367,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.00746968558140525,"rank":367,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.007489883734505169,"rank":367,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.007579883173244501,"rank":367,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.007548792091995149,"rank":367,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00759377842016657,"rank":367,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.007484973744493387,"rank":367,"remainingConfigurations":444},{"removed":"livebench-language","score":0.007718318364216929,"rank":367,"remainingConfigurations":444},{"removed":"livebench-data","score":0.007583359699227111,"rank":367,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.007411052233919818,"rank":367,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.007525636360770418,"rank":367,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.007779590403958348,"rank":367,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00782284470158237,"rank":367,"remainingConfigurations":444},{"removed":"frontiermath","score":0.007605742822192071,"rank":367,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.007039133192349108,"rank":367,"remainingConfigurations":444},{"removed":"simpleqa","score":0.008018616951918333,"rank":367,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.007552055636209765,"rank":367,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.007550810431626691,"rank":367,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.007553605542836632,"rank":367,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.007565771269860761,"rank":367,"remainingConfigurations":444},{"removed":"vibe-code","score":0.007527615096106703,"rank":367,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.007559557036050065,"rank":367,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gemma-4-e4b-it--effort-reasoning":{"score":0.006871027693573418,"rank":368,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.009149864613652615,"rank":367,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0053525596342292245,"rank":368,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0067951901798517615,"rank":368,"remainingConfigurations":444},{"removed":"Scale","score":0.008183467634711896,"rank":368,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.006794105197555165,"rank":368,"remainingConfigurations":444},{"removed":"Cognition","score":0.0066798200440696355,"rank":368,"remainingConfigurations":444},{"removed":"LiveBench","score":0.007198181095000353,"rank":367,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.007102729624159052,"rank":368,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0070260122485495844,"rank":356,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006610671711962126,"rank":367,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0068678628385765265,"rank":368,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.006636867906551173,"rank":368,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006858254519277188,"rank":368,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006871027693573418,"rank":368,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006929120731739408,"rank":368,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006680551821907961,"rank":368,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006948606205247904,"rank":368,"remainingConfigurations":444},{"removed":"briefcase","score":0.006992661014809602,"rank":368,"remainingConfigurations":444},{"removed":"aime","score":0.006796046252375784,"rank":369,"remainingConfigurations":444},{"removed":"apex-agents","score":0.007004662942131048,"rank":368,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006632738513489962,"rank":369,"remainingConfigurations":444},{"removed":"automationbench","score":0.006868351395759872,"rank":369,"remainingConfigurations":444},{"removed":"critpt","score":0.00526643145490431,"rank":377,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006890189045242264,"rank":368,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006993456754157269,"rank":369,"remainingConfigurations":444},{"removed":"gdpval","score":0.007169999170811558,"rank":369,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006944783772656354,"rank":368,"remainingConfigurations":444},{"removed":"gpqa","score":0.006995954312952437,"rank":370,"remainingConfigurations":444},{"removed":"harvey","score":0.006795356662657101,"rank":368,"remainingConfigurations":444},{"removed":"hle","score":0.008603580484345733,"rank":368,"remainingConfigurations":444},{"removed":"ifbench","score":0.005795216807963715,"rank":376,"remainingConfigurations":444},{"removed":"itbench","score":0.00682132511078718,"rank":368,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006900364089516953,"rank":369,"remainingConfigurations":444},{"removed":"math500","score":0.006941737041920334,"rank":368,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.007186565279521255,"rank":369,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0077276762690857955,"rank":370,"remainingConfigurations":444},{"removed":"omniscience","score":0.006866881676838352,"rank":367,"remainingConfigurations":444},{"removed":"tau-bench","score":0.006967404420991569,"rank":369,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006992746953144929,"rank":368,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006632831887244082,"rank":370,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008778599495632285,"rank":367,"remainingConfigurations":444},{"removed":"deepswe","score":0.0053563635023043295,"rank":368,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0068728849143628356,"rank":368,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006750476968523325,"rank":368,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0066798200440696355,"rank":368,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.006767526675937306,"rank":368,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006785562597121473,"rank":368,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00686735542120901,"rank":368,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006839655891229872,"rank":368,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006879739035763798,"rank":368,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0067814429327273384,"rank":368,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006993239818734378,"rank":368,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0068703933329543505,"rank":368,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006713869350242521,"rank":368,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006818086801853138,"rank":368,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.007048391774882191,"rank":368,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.007102729624159052,"rank":368,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006884835218328922,"rank":368,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.006401350437516194,"rank":368,"remainingConfigurations":444},{"removed":"simpleqa","score":0.007265520956215403,"rank":368,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00684207852784257,"rank":368,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006840946393604607,"rank":368,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.006843376374486236,"rank":368,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006854590460172145,"rank":368,"remainingConfigurations":444},{"removed":"vibe-code","score":0.006819876601730004,"rank":368,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006848868916241515,"rank":368,"remainingConfigurations":444}],"sharedOrderConflicts":1},"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning":{"score":0.006861746077449139,"rank":369,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.009130568719213064,"rank":368,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0053430873922893736,"rank":369,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00678328178205963,"rank":369,"remainingConfigurations":444},{"removed":"Scale","score":0.008172846361750617,"rank":369,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.006784944390096397,"rank":369,"remainingConfigurations":444},{"removed":"Cognition","score":0.006669956648001264,"rank":369,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0071867682399620195,"rank":368,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0070919438620942075,"rank":369,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0070464774030453,"rank":355,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006602401474985108,"rank":368,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.006858591915066416,"rank":369,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.006628108548242264,"rank":369,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006849013872782144,"rank":369,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006861746077449139,"rank":369,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006919637708903264,"rank":369,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006671644796153301,"rank":369,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006938226751829267,"rank":369,"remainingConfigurations":444},{"removed":"briefcase","score":0.0069479622792841715,"rank":369,"remainingConfigurations":444},{"removed":"aime","score":0.0067804368989519935,"rank":370,"remainingConfigurations":444},{"removed":"apex-agents","score":0.00699314559199427,"rank":369,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006862957448394006,"rank":368,"remainingConfigurations":444},{"removed":"automationbench","score":0.006900148424616015,"rank":368,"remainingConfigurations":444},{"removed":"critpt","score":0.00653127100597168,"rank":366,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006879281136096487,"rank":369,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0072171876937985255,"rank":368,"remainingConfigurations":444},{"removed":"gdpval","score":0.007200822375164812,"rank":368,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00693131336880921,"rank":369,"remainingConfigurations":444},{"removed":"gpqa","score":0.007342984080362898,"rank":367,"remainingConfigurations":444},{"removed":"harvey","score":0.006785204809692772,"rank":369,"remainingConfigurations":444},{"removed":"hle","score":0.007796393296220532,"rank":373,"remainingConfigurations":444},{"removed":"ifbench","score":0.0048811591823589425,"rank":386,"remainingConfigurations":444},{"removed":"itbench","score":0.006810285860534418,"rank":369,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006885977456421158,"rank":370,"remainingConfigurations":444},{"removed":"math500","score":0.006921373041181946,"rank":369,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.007171413858975323,"rank":370,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.007514871502388629,"rank":371,"remainingConfigurations":444},{"removed":"omniscience","score":0.006951258457819313,"rank":365,"remainingConfigurations":444},{"removed":"tau-bench","score":0.006460895189924198,"rank":370,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006981237701450663,"rank":369,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006730274190151177,"rank":369,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008765147398376371,"rank":368,"remainingConfigurations":444},{"removed":"deepswe","score":0.005346898103333663,"rank":369,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.00686360062978807,"rank":369,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006740852648248218,"rank":369,"remainingConfigurations":444},{"removed":"frontiercode","score":0.006669956648001264,"rank":369,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0067581088777472105,"rank":369,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006776179321225165,"rank":369,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006858077241822272,"rank":369,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0068304260114357565,"rank":369,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006870484038773678,"rank":369,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0067722411355956,"rank":369,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006983771492771019,"rank":369,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006861119138656494,"rank":369,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006704832488688338,"rank":369,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006808873116380745,"rank":369,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.007038852646601825,"rank":369,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0070919438620942075,"rank":369,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0068747380633361575,"rank":369,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.006391014830920149,"rank":369,"remainingConfigurations":444},{"removed":"simpleqa","score":0.007256268117180877,"rank":369,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.006832823038318403,"rank":369,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006831711890784027,"rank":369,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0068341191231775025,"rank":369,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006845344123727754,"rank":369,"remainingConfigurations":444},{"removed":"vibe-code","score":0.006810685188945045,"rank":369,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006839606010595012,"rank":369,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5.4-nano--effort-non-reasoning":{"score":0.006676398720630945,"rank":370,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00899823448638494,"rank":369,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005199967623225206,"rank":370,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00660310698117093,"rank":370,"remainingConfigurations":444},{"removed":"Scale","score":0.007953721085587924,"rank":370,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.006600468319803963,"rank":370,"remainingConfigurations":444},{"removed":"Cognition","score":0.006511526758907526,"rank":370,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006988988106918525,"rank":369,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006906936483352467,"rank":370,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0068359997896702855,"rank":357,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006411016467726263,"rank":369,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.006673326485035697,"rank":370,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00644906161265455,"rank":370,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00666402705869396,"rank":370,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006676398720630945,"rank":370,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006732890541403143,"rank":370,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006491588597604708,"rank":370,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00674786613299434,"rank":370,"remainingConfigurations":444},{"removed":"briefcase","score":0.006649529906560986,"rank":370,"remainingConfigurations":444},{"removed":"aime","score":0.0066096844651091224,"rank":373,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006810016391864675,"rank":370,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0064594825715244145,"rank":371,"remainingConfigurations":444},{"removed":"automationbench","score":0.006653951118599563,"rank":370,"remainingConfigurations":444},{"removed":"critpt","score":0.006283005481431465,"rank":367,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006701516110228209,"rank":370,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00686154436529812,"rank":370,"remainingConfigurations":444},{"removed":"gdpval","score":0.006685263225047932,"rank":370,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006741099083518119,"rank":371,"remainingConfigurations":444},{"removed":"gpqa","score":0.0070126259845666285,"rank":369,"remainingConfigurations":444},{"removed":"harvey","score":0.006602261590175486,"rank":370,"remainingConfigurations":444},{"removed":"hle","score":0.008453703066318624,"rank":370,"remainingConfigurations":444},{"removed":"ifbench","score":0.0068913412058444,"rank":368,"remainingConfigurations":444},{"removed":"itbench","score":0.0065064924882858146,"rank":372,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006721692052316173,"rank":372,"remainingConfigurations":444},{"removed":"math500","score":0.006741363273502142,"rank":370,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0069895947863916974,"rank":371,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00811476492250448,"rank":368,"remainingConfigurations":444},{"removed":"omniscience","score":0.005923028036450808,"rank":370,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005824751287839052,"rank":375,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006796641363596483,"rank":370,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.005338157332524593,"rank":381,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00861432247888565,"rank":369,"remainingConfigurations":444},{"removed":"deepswe","score":0.005203647114482839,"rank":370,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006678184815713052,"rank":370,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006557123298990927,"rank":370,"remainingConfigurations":444},{"removed":"frontiercode","score":0.006511526758907526,"rank":370,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.006575771910195834,"rank":370,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006593496966072098,"rank":370,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006672785517666297,"rank":370,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006645371617262253,"rank":370,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0066850627090690555,"rank":370,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.006588986496810314,"rank":370,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006794769196980809,"rank":370,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00667591843867268,"rank":370,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006523899312099541,"rank":370,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00662494706064617,"rank":370,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006848986330575866,"rank":370,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006906936483352467,"rank":370,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006691458579363815,"rank":370,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.006213393021308714,"rank":370,"remainingConfigurations":444},{"removed":"simpleqa","score":0.007059933004985332,"rank":370,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.006648271525818364,"rank":370,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006647110505523489,"rank":370,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0066495673133296525,"rank":370,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006660347568489951,"rank":370,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0066267272891831945,"rank":370,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006654836378223308,"rank":370,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-small-4--effort-non-reasoning":{"score":0.006625396816002979,"rank":371,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00886331788910673,"rank":370,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005159876423524417,"rank":371,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.006548984871957209,"rank":371,"remainingConfigurations":444},{"removed":"Scale","score":0.007893589673092597,"rank":371,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0065486045690635345,"rank":371,"remainingConfigurations":444},{"removed":"Cognition","score":0.006458387537511458,"rank":371,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006933796938826088,"rank":370,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006838153001042294,"rank":371,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.00675952127661169,"rank":358,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006360414078244777,"rank":370,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.006622363881214455,"rank":371,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.006400221185619416,"rank":371,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006613133264421849,"rank":371,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006625396816002979,"rank":371,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006681498203987085,"rank":371,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006442486508943215,"rank":371,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0066962773004423095,"rank":371,"remainingConfigurations":444},{"removed":"briefcase","score":0.006595869353578192,"rank":371,"remainingConfigurations":444},{"removed":"aime","score":0.0065335736766589615,"rank":375,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006745455646872533,"rank":371,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006427204952051507,"rank":372,"remainingConfigurations":444},{"removed":"automationbench","score":0.0066022209380076635,"rank":371,"remainingConfigurations":444},{"removed":"critpt","score":0.004859409629149288,"rank":383,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006641296758450502,"rank":371,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006805081810438822,"rank":371,"remainingConfigurations":444},{"removed":"gdpval","score":0.006664445126749682,"rank":371,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006716873475734907,"rank":372,"remainingConfigurations":444},{"removed":"gpqa","score":0.006867054315635936,"rank":371,"remainingConfigurations":444},{"removed":"harvey","score":0.00655103118844784,"rank":371,"remainingConfigurations":444},{"removed":"hle","score":0.008591174751648093,"rank":369,"remainingConfigurations":444},{"removed":"ifbench","score":0.006827371055780372,"rank":369,"remainingConfigurations":444},{"removed":"itbench","score":0.006571221772630811,"rank":370,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0066382700132951965,"rank":373,"remainingConfigurations":444},{"removed":"math500","score":0.006669696885715168,"rank":371,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006908832074560947,"rank":374,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.007792086785435681,"rank":369,"remainingConfigurations":444},{"removed":"omniscience","score":0.005422622633193747,"rank":375,"remainingConfigurations":444},{"removed":"tau-bench","score":0.007137439334040024,"rank":368,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006744391222107484,"rank":371,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.005998902862568871,"rank":376,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008494606014692098,"rank":370,"remainingConfigurations":444},{"removed":"deepswe","score":0.005163508897366023,"rank":371,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006627170838388132,"rank":371,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006505778882773217,"rank":371,"remainingConfigurations":444},{"removed":"frontiercode","score":0.006458387537511458,"rank":371,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.006525383747413829,"rank":371,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006543112786822953,"rank":371,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006621815920977059,"rank":371,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006594645906891037,"rank":371,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006633969312096329,"rank":371,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.006538695115062124,"rank":371,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00674296151902045,"rank":371,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006624865282513859,"rank":371,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006474043479056874,"rank":371,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006574311964449345,"rank":371,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0067966326747811836,"rank":371,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006838153001042294,"rank":371,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0066460145368517284,"rank":371,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.006149720377329683,"rank":371,"remainingConfigurations":444},{"removed":"simpleqa","score":0.007006205690690874,"rank":371,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.006597440061187142,"rank":371,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006596351053131842,"rank":371,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00659880520202762,"rank":371,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006609436944791898,"rank":371,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00657605110452002,"rank":371,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006604009511644561,"rank":371,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-2-lite--effort-non-reasoning":{"score":0.006562344869589378,"rank":372,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.008751585272908015,"rank":371,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005107763848855811,"rank":372,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.006488107131109737,"rank":372,"remainingConfigurations":444},{"removed":"Scale","score":0.00781868894085777,"rank":372,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.006485194987956212,"rank":372,"remainingConfigurations":444},{"removed":"Cognition","score":0.006395937003713521,"rank":372,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006865084610622681,"rank":371,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006767167627519007,"rank":372,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.006749216097931766,"rank":359,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006297094264683439,"rank":371,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0065593423846959965,"rank":372,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0063393867061867296,"rank":372,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006550211794725373,"rank":372,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006562344869589378,"rank":372,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006617812694722794,"rank":372,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006381168902503763,"rank":372,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006628676993726122,"rank":372,"remainingConfigurations":444},{"removed":"briefcase","score":0.006527483725751386,"rank":372,"remainingConfigurations":444},{"removed":"aime","score":0.006806717434243231,"rank":368,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006682770668854335,"rank":372,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00663097747623018,"rank":370,"remainingConfigurations":444},{"removed":"automationbench","score":0.006544238286263285,"rank":372,"remainingConfigurations":444},{"removed":"critpt","score":0.006145100987810904,"rank":369,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006572106535963071,"rank":372,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00674323363962214,"rank":372,"remainingConfigurations":444},{"removed":"gdpval","score":0.006592143599940776,"rank":372,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0060408025017839985,"rank":376,"remainingConfigurations":444},{"removed":"gpqa","score":0.006553390155019381,"rank":375,"remainingConfigurations":444},{"removed":"harvey","score":0.006487453724149053,"rank":372,"remainingConfigurations":444},{"removed":"hle","score":0.008224045094426726,"rank":371,"remainingConfigurations":444},{"removed":"ifbench","score":0.006009832057710221,"rank":373,"remainingConfigurations":444},{"removed":"itbench","score":0.006507764554182698,"rank":371,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0069733939194077605,"rank":368,"remainingConfigurations":444},{"removed":"math500","score":0.006633702761335346,"rank":372,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006919703626562309,"rank":372,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.007408100748613853,"rank":373,"remainingConfigurations":444},{"removed":"omniscience","score":0.005839214303986685,"rank":371,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005567836726776645,"rank":377,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006675760210941912,"rank":372,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006409969170565449,"rank":372,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008391673484359099,"rank":371,"remainingConfigurations":444},{"removed":"deepswe","score":0.005111368144947424,"rank":372,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0065641033730568865,"rank":372,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006442534274401064,"rank":372,"remainingConfigurations":444},{"removed":"frontiercode","score":0.006395937003713521,"rank":372,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0064628577014781315,"rank":372,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006480716778863868,"rank":372,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0065587820179392395,"rank":372,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006531845757149876,"rank":372,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006570868736421708,"rank":372,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0064764798863033435,"rank":372,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006678761501667566,"rank":372,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006561735368050884,"rank":372,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006412439284854827,"rank":372,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006511772413221811,"rank":372,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006731978368565699,"rank":372,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006767167627519007,"rank":372,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006577637634284385,"rank":372,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00609035879673443,"rank":372,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006940072600105649,"rank":372,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0065346308806083775,"rank":372,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006533560606570731,"rank":372,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0065360176569453365,"rank":372,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.00654652467976512,"rank":372,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0065134601847461225,"rank":372,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006541139985049822,"rank":372,"remainingConfigurations":444}],"sharedOrderConflicts":0},"labs-devstral-small-2512--effort-non-reasoning":{"score":0.00647401590584536,"rank":373,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.008632955755209226,"rank":372,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005038003931507024,"rank":373,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.006397426558207172,"rank":373,"remainingConfigurations":444},{"removed":"Scale","score":0.007731164646056505,"rank":373,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0063992732679775954,"rank":373,"remainingConfigurations":444},{"removed":"Cognition","score":0.006292533295582314,"rank":373,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006777100724662682,"rank":372,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00669410611363746,"rank":373,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.006680023976289316,"rank":360,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006225501349298684,"rank":372,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.006471047541196016,"rank":373,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0062535965805198155,"rank":373,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00646202206597778,"rank":373,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.00647401590584536,"rank":373,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00652859237515697,"rank":373,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006294654969277552,"rank":373,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006543612592251828,"rank":373,"remainingConfigurations":444},{"removed":"briefcase","score":0.00587726848022323,"rank":376,"remainingConfigurations":444},{"removed":"aime","score":0.00664203719951605,"rank":372,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006597648545384527,"rank":373,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006303417277426539,"rank":374,"remainingConfigurations":444},{"removed":"automationbench","score":0.005919128181175237,"rank":376,"remainingConfigurations":444},{"removed":"critpt","score":0.006087306284408972,"rank":370,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006487242940517102,"rank":373,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006585834463345827,"rank":374,"remainingConfigurations":444},{"removed":"gdpval","score":0.005928525962426927,"rank":378,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006892734991642739,"rank":370,"remainingConfigurations":444},{"removed":"gpqa","score":0.006636052357929484,"rank":373,"remainingConfigurations":444},{"removed":"harvey","score":0.006401311917117567,"rank":373,"remainingConfigurations":444},{"removed":"hle","score":0.007973721959731745,"rank":372,"remainingConfigurations":444},{"removed":"ifbench","score":0.00662943027134857,"rank":371,"remainingConfigurations":444},{"removed":"itbench","score":0.006424152852817711,"rank":373,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006849745827561285,"rank":371,"remainingConfigurations":444},{"removed":"math500","score":0.006547699142047061,"rank":374,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00743146859772982,"rank":368,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.007423554740972516,"rank":372,"remainingConfigurations":444},{"removed":"omniscience","score":0.005606089720430943,"rank":374,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0059069306468987615,"rank":374,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006583452261465045,"rank":373,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00594127144718996,"rank":378,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008292423453224328,"rank":372,"remainingConfigurations":444},{"removed":"deepswe","score":0.00504159715704192,"rank":373,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006475764497800257,"rank":373,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006357817711023072,"rank":373,"remainingConfigurations":444},{"removed":"frontiercode","score":0.006292533295582314,"rank":373,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.00637596927729113,"rank":373,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006393228424335646,"rank":373,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006470555191997224,"rank":373,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006444500639611998,"rank":373,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0064823317055676824,"rank":373,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.006389561375823208,"rank":373,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0065891388691880605,"rank":373,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006473304049741903,"rank":373,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006325939613378227,"rank":373,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006424132453977156,"rank":373,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006641204929593379,"rank":373,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00669410611363746,"rank":373,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006485496617921415,"rank":373,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0060264324858740476,"rank":373,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006847223090050561,"rank":373,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.006446669795029232,"rank":373,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0064456447418233045,"rank":373,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0064479709136424515,"rank":373,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006458500423376913,"rank":373,"remainingConfigurations":444},{"removed":"vibe-code","score":0.006425809247519866,"rank":373,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006453101839138446,"rank":373,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-nano-9b-v2--effort-reasoning":{"score":0.0064347702317688075,"rank":374,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.008598349327537017,"rank":373,"remainingConfigurations":444},{"removed":"Datacurve","score":0.005009521466992443,"rank":374,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0063591515069912966,"rank":374,"remainingConfigurations":444},{"removed":"Scale","score":0.0076646704182246625,"rank":374,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0063597767295645626,"rank":374,"remainingConfigurations":444},{"removed":"Cognition","score":0.00626497281185989,"rank":374,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006732897658882783,"rank":373,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006651314003435215,"rank":374,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0065307646754206,"rank":361,"remainingConfigurations":431},{"removed":"Vals AI","score":0.006176595130088617,"rank":373,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0064318275091403004,"rank":374,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.006216117576429289,"rank":374,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006422881948832664,"rank":374,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0064347702317688075,"rank":374,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006489152587817654,"rank":374,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006257090952760086,"rank":374,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006501230617861734,"rank":374,"remainingConfigurations":444},{"removed":"briefcase","score":0.006396063265040233,"rank":373,"remainingConfigurations":444},{"removed":"aime","score":0.005450993953918636,"rank":380,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006550010238648429,"rank":374,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006378275368713227,"rank":373,"remainingConfigurations":444},{"removed":"automationbench","score":0.006402295609657691,"rank":373,"remainingConfigurations":444},{"removed":"critpt","score":0.005976980590942593,"rank":371,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.00644606415012727,"rank":374,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006601426930417128,"rank":373,"remainingConfigurations":444},{"removed":"gdpval","score":0.0064585171666477715,"rank":373,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006527032254444638,"rank":373,"remainingConfigurations":444},{"removed":"gpqa","score":0.006604662163522289,"rank":374,"remainingConfigurations":444},{"removed":"harvey","score":0.006361673306640399,"rank":374,"remainingConfigurations":444},{"removed":"hle","score":0.007311026854598625,"rank":375,"remainingConfigurations":444},{"removed":"ifbench","score":0.007048351583829532,"rank":366,"remainingConfigurations":444},{"removed":"itbench","score":0.0063821390814561675,"rank":374,"remainingConfigurations":444},{"removed":"livecodebench","score":0.005152883399185632,"rank":383,"remainingConfigurations":444},{"removed":"math500","score":0.006531944018607534,"rank":375,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006917147266809034,"rank":373,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.007057655951988719,"rank":374,"remainingConfigurations":444},{"removed":"omniscience","score":0.0059615760657643875,"rank":369,"remainingConfigurations":444},{"removed":"tau-bench","score":0.006403306916533925,"rank":371,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006546470311065752,"rank":374,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.007032219281811886,"rank":368,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008251839307520714,"rank":373,"remainingConfigurations":444},{"removed":"deepswe","score":0.005013058284118276,"rank":374,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006436494877490856,"rank":374,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006317314035697237,"rank":374,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00626497281185989,"rank":374,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.006337478061177522,"rank":374,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006354725254390268,"rank":374,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006431303813690389,"rank":374,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006404914731622868,"rank":374,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006443131094057871,"rank":374,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.006350518333273946,"rank":374,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006548968097460971,"rank":374,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006434244780534801,"rank":374,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.006287733808358005,"rank":374,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.006385139387708465,"rank":374,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0066011383766710376,"rank":374,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006651314003435215,"rank":374,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00644944334419533,"rank":374,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0059728452810652866,"rank":374,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006805845366954917,"rank":374,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0064075885561620145,"rank":374,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006406546211781143,"rank":374,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.006408944714860334,"rank":374,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006419263010067171,"rank":374,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00638682607121216,"rank":374,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006413988472836887,"rank":374,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-medium-2505--effort-non-reasoning":{"score":0.006251341017192766,"rank":375,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.008336303902325436,"rank":374,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004864655274833905,"rank":375,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0061754520419879215,"rank":375,"remainingConfigurations":444},{"removed":"Scale","score":0.007445887641275587,"rank":375,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.006179054709285246,"rank":375,"remainingConfigurations":444},{"removed":"Cognition","score":0.00608302202798269,"rank":375,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006540813424840908,"rank":374,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0064527301485392645,"rank":375,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.006367827448634549,"rank":362,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0060020624416740566,"rank":374,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.006248484080752952,"rank":375,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0060388726511248795,"rank":375,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.006239787460262578,"rank":375,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.006251341017192766,"rank":375,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006304099672668044,"rank":375,"remainingConfigurations":444},{"removed":"All provider reports","score":0.006078606213680129,"rank":375,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006317527446738617,"rank":375,"remainingConfigurations":444},{"removed":"briefcase","score":0.0062148036049089325,"rank":374,"remainingConfigurations":444},{"removed":"aime","score":0.006539618813242093,"rank":374,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006363928790741178,"rank":375,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.006025275427867151,"rank":376,"remainingConfigurations":444},{"removed":"automationbench","score":0.006222767990725711,"rank":374,"remainingConfigurations":444},{"removed":"critpt","score":0.005802278266926374,"rank":372,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006263020043764454,"rank":375,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006418723251902766,"rank":375,"remainingConfigurations":444},{"removed":"gdpval","score":0.006284722757584187,"rank":374,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006353543108740684,"rank":374,"remainingConfigurations":444},{"removed":"gpqa","score":0.006274239455365357,"rank":376,"remainingConfigurations":444},{"removed":"harvey","score":0.006180961937237078,"rank":375,"remainingConfigurations":444},{"removed":"hle","score":0.007535609907661839,"rank":374,"remainingConfigurations":444},{"removed":"ifbench","score":0.005783326686219698,"rank":377,"remainingConfigurations":444},{"removed":"itbench","score":0.006200874642860922,"rank":375,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006403829848062189,"rank":375,"remainingConfigurations":444},{"removed":"math500","score":0.006342258897956163,"rank":376,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006383004680602526,"rank":376,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.006847814540876812,"rank":375,"remainingConfigurations":444},{"removed":"omniscience","score":0.004970331374749504,"rank":378,"remainingConfigurations":444},{"removed":"tau-bench","score":0.006074553750178302,"rank":373,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006359043815049588,"rank":375,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006442592916994464,"rank":371,"remainingConfigurations":444},{"removed":"arc-agi","score":0.008004063903932539,"rank":374,"remainingConfigurations":444},{"removed":"deepswe","score":0.004868101795205627,"rank":375,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006253018143389674,"rank":375,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.006137102032076437,"rank":375,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00608302202798269,"rank":375,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.00615656983487362,"rank":375,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.006173388179504309,"rank":375,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.006247982562835829,"rank":375,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.006222417819734879,"rank":375,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006259482605193052,"rank":375,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0061695050173372415,"rank":375,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006362341713686621,"rank":375,"remainingConfigurations":444},{"removed":"livebench-data","score":0.006250776102883834,"rank":375,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00610845743355461,"rank":375,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00620312521620238,"rank":375,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006412962790787576,"rank":375,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0064527301485392645,"rank":375,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006265470097802986,"rank":375,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005804137602149963,"rank":375,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0066126655473815596,"rank":375,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.006224919082868268,"rank":375,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.006223918585259699,"rank":375,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.006226234485459513,"rank":375,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.006236283874673977,"rank":375,"remainingConfigurations":444},{"removed":"vibe-code","score":0.006204763562396759,"rank":375,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.006231139986617025,"rank":375,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.7-flash--effort-non-reasoning":{"score":0.005998644741066458,"rank":376,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0023315044326186825,"rank":198,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.008107904210976744,"rank":375,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004707912055787876,"rank":376,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005941928155022741,"rank":376,"remainingConfigurations":444},{"removed":"Scale","score":0.007142534142199117,"rank":376,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005948481788991367,"rank":376,"remainingConfigurations":444},{"removed":"Cognition","score":0.005940711342629904,"rank":376,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006250023403433873,"rank":375,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006201429206272341,"rank":376,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.009442086701919908,"rank":343,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005784246649164152,"rank":375,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005996060496762544,"rank":376,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005798689283519215,"rank":376,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005988520204727979,"rank":376,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005998644741066458,"rank":376,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.006047890602202126,"rank":376,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005836574119135029,"rank":376,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.006060163958516825,"rank":376,"remainingConfigurations":444},{"removed":"briefcase","score":0.005980714882211479,"rank":375,"remainingConfigurations":444},{"removed":"aime","score":0.0052617960924212295,"rank":381,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006103526765175521,"rank":376,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00622786395617856,"rank":375,"remainingConfigurations":444},{"removed":"automationbench","score":0.005988029698943523,"rank":375,"remainingConfigurations":444},{"removed":"critpt","score":0.0057384978534906405,"rank":373,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.006012797709584366,"rank":376,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006148461107948931,"rank":376,"remainingConfigurations":444},{"removed":"gdpval","score":0.0060246913267006375,"rank":375,"remainingConfigurations":444},{"removed":"gmmlu","score":0.006112295387191061,"rank":375,"remainingConfigurations":444},{"removed":"gpqa","score":0.007168122780820737,"rank":368,"remainingConfigurations":444},{"removed":"harvey","score":0.005927078226466979,"rank":376,"remainingConfigurations":444},{"removed":"hle","score":0.0068526174258296815,"rank":378,"remainingConfigurations":444},{"removed":"ifbench","score":0.005146824960590314,"rank":384,"remainingConfigurations":444},{"removed":"itbench","score":0.0059549897176290265,"rank":376,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00613025100709751,"rank":377,"remainingConfigurations":444},{"removed":"math500","score":0.00607281208771343,"rank":378,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006370800866524741,"rank":377,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.006616470996782118,"rank":376,"remainingConfigurations":444},{"removed":"omniscience","score":0.005806370669009054,"rank":373,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004323964902472308,"rank":388,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0060920465634986725,"rank":376,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006347581098256411,"rank":373,"remainingConfigurations":444},{"removed":"arc-agi","score":0.007777054562757725,"rank":375,"remainingConfigurations":444},{"removed":"deepswe","score":0.004711467791781761,"rank":376,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.006000226007315125,"rank":376,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005890957814307013,"rank":376,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005940711342629904,"rank":376,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005912849746168118,"rank":376,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005922826887990128,"rank":376,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005995596019172641,"rank":376,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00597062084239841,"rank":376,"remainingConfigurations":444},{"removed":"livebench-math","score":0.006009634595078948,"rank":376,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005915553586276697,"rank":376,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006104225983892935,"rank":376,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005999362749230141,"rank":376,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005863377794857811,"rank":376,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005952002252787207,"rank":376,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006152965179194845,"rank":376,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006201429206272341,"rank":376,"remainingConfigurations":444},{"removed":"frontiermath","score":0.006018404141041769,"rank":376,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0053400708101486415,"rank":378,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006400241564718782,"rank":376,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005972944227906573,"rank":376,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005973063318527174,"rank":376,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005973931376126499,"rank":376,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005984728480642329,"rank":376,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005954847692618409,"rank":376,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005978709941401798,"rank":376,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-premier--effort-non-reasoning":{"score":0.005911832885137268,"rank":377,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007881596120878338,"rank":376,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004599708900405566,"rank":377,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0058406504855109944,"rank":377,"remainingConfigurations":444},{"removed":"Scale","score":0.007045681712596622,"rank":377,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005843042898305403,"rank":377,"remainingConfigurations":444},{"removed":"Cognition","score":0.005752529033187996,"rank":377,"remainingConfigurations":444},{"removed":"LiveBench","score":0.006185398255175941,"rank":376,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00610195546397961,"rank":377,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0060297560421098085,"rank":363,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005675633866183226,"rank":376,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005909129795085787,"rank":377,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005710825888619177,"rank":377,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005900912457727104,"rank":377,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005911832885137268,"rank":377,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005961715291176971,"rank":377,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005748395639560036,"rank":377,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005974525799427691,"rank":377,"remainingConfigurations":444},{"removed":"briefcase","score":0.005873562701967691,"rank":377,"remainingConfigurations":444},{"removed":"aime","score":0.006706706677300343,"rank":371,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006019186288398492,"rank":377,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005575490874260639,"rank":382,"remainingConfigurations":444},{"removed":"automationbench","score":0.005878337479636793,"rank":378,"remainingConfigurations":444},{"removed":"critpt","score":0.005464184977550622,"rank":375,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005923178402396395,"rank":377,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006059023273819439,"rank":378,"remainingConfigurations":444},{"removed":"gdpval","score":0.005931060838697083,"rank":377,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005605498526902091,"rank":382,"remainingConfigurations":444},{"removed":"gpqa","score":0.005996075425930757,"rank":379,"remainingConfigurations":444},{"removed":"harvey","score":0.005845263141469051,"rank":377,"remainingConfigurations":444},{"removed":"hle","score":0.007027582741907858,"rank":377,"remainingConfigurations":444},{"removed":"ifbench","score":0.0057093011065896095,"rank":379,"remainingConfigurations":444},{"removed":"itbench","score":0.005863758564166235,"rank":377,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006419976034154445,"rank":374,"remainingConfigurations":444},{"removed":"math500","score":0.00659916208565359,"rank":373,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006343973573999066,"rank":378,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0064910836639379054,"rank":378,"remainingConfigurations":444},{"removed":"omniscience","score":0.0043810537149599925,"rank":383,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005227204010548383,"rank":381,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006013399346119751,"rank":377,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.005722044134282882,"rank":379,"remainingConfigurations":444},{"removed":"arc-agi","score":0.007568617114371758,"rank":376,"remainingConfigurations":444},{"removed":"deepswe","score":0.004602972282243671,"rank":377,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0059134206262901135,"rank":377,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005803622581077617,"rank":377,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005752529033187996,"rank":377,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005822068545864609,"rank":377,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005838084886236995,"rank":377,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005908653037196481,"rank":377,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.005884477622057755,"rank":377,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005919546800128163,"rank":377,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005834360294049344,"rank":377,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006016866157073545,"rank":377,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005911306656716822,"rank":377,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005776627567729026,"rank":377,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005866203962276107,"rank":377,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.006064805696284329,"rank":377,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00610195546397961,"rank":377,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005925136888385664,"rank":377,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0054880155380433995,"rank":376,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006253941577233801,"rank":377,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005886824065310538,"rank":377,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005885882323436244,"rank":377,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005888070174487754,"rank":377,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.00589758460344603,"rank":377,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005867758180094869,"rank":377,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005892708296113654,"rank":377,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-coder-30b-a3b-instruct--effort-non-reasoning":{"score":0.005901401795297451,"rank":378,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007878207495010817,"rank":377,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004592470661433663,"rank":378,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005831671677355367,"rank":378,"remainingConfigurations":444},{"removed":"Scale","score":0.007032925865934223,"rank":378,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0058331159606907395,"rank":378,"remainingConfigurations":444},{"removed":"Cognition","score":0.005743488784758906,"rank":378,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00617489907658425,"rank":377,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.006092760944879277,"rank":378,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.006017714986990525,"rank":364,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005666425990783354,"rank":377,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005898703693165245,"rank":378,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0057007480186888485,"rank":378,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005890501367911447,"rank":378,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005901401795297451,"rank":378,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0059512080458421586,"rank":378,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005738263647942096,"rank":378,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005963832335608135,"rank":378,"remainingConfigurations":444},{"removed":"briefcase","score":0.005872110655477186,"rank":378,"remainingConfigurations":444},{"removed":"aime","score":0.006213192552446172,"rank":376,"remainingConfigurations":444},{"removed":"apex-agents","score":0.006007875446758021,"rank":378,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005598545471267972,"rank":379,"remainingConfigurations":444},{"removed":"automationbench","score":0.00588052769783231,"rank":377,"remainingConfigurations":444},{"removed":"critpt","score":0.005433193899751291,"rank":376,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005912937575268072,"rank":378,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.006062259340123308,"rank":377,"remainingConfigurations":444},{"removed":"gdpval","score":0.0059415398169573655,"rank":376,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005997139492250882,"rank":377,"remainingConfigurations":444},{"removed":"gpqa","score":0.0060758654934992004,"rank":377,"remainingConfigurations":444},{"removed":"harvey","score":0.005834290844631565,"rank":378,"remainingConfigurations":444},{"removed":"hle","score":0.0071744258003157415,"rank":376,"remainingConfigurations":444},{"removed":"ifbench","score":0.005933976720480588,"rank":375,"remainingConfigurations":444},{"removed":"itbench","score":0.005854244349359203,"rank":378,"remainingConfigurations":444},{"removed":"livecodebench","score":0.005956214629554883,"rank":378,"remainingConfigurations":444},{"removed":"math500","score":0.0060942759110274095,"rank":377,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006503693622712646,"rank":375,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00649838656239064,"rank":377,"remainingConfigurations":444},{"removed":"omniscience","score":0.004845126397589772,"rank":380,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005288351244517944,"rank":380,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.006002289968627801,"rank":378,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.005284153065202712,"rank":382,"remainingConfigurations":444},{"removed":"arc-agi","score":0.007564423984418099,"rank":377,"remainingConfigurations":444},{"removed":"deepswe","score":0.004595727488332322,"rank":378,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.005902986405483676,"rank":378,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005793423720321535,"rank":378,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005743488784758906,"rank":378,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0058119020411800835,"rank":378,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005827800010383571,"rank":378,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005898234984539165,"rank":378,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00587409872189761,"rank":378,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005909102951107181,"rank":378,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005824047835940198,"rank":378,"remainingConfigurations":444},{"removed":"livebench-language","score":0.006006253972209337,"rank":378,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005900903083625381,"rank":378,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005766431042303383,"rank":378,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005855842831234627,"rank":378,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0060541077095023705,"rank":378,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.006092760944879277,"rank":378,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005914913136537911,"rank":378,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005478296446431943,"rank":377,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006243084467217007,"rank":378,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00587643837945979,"rank":378,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005875498569431849,"rank":378,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005877681393145179,"rank":378,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005887178493003363,"rank":378,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005857402576894702,"rank":378,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005882316737439753,"rank":378,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-nano-9b-v2--effort-non-reasoning":{"score":0.0057049442913313,"rank":379,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007633362304939228,"rank":378,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00444106666627562,"rank":379,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005638154771442749,"rank":379,"remainingConfigurations":444},{"removed":"Scale","score":0.006798526595730939,"rank":379,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005638550113146716,"rank":379,"remainingConfigurations":444},{"removed":"Cognition","score":0.005556440777671864,"rank":379,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0059703700320821685,"rank":378,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.005896496945847783,"rank":379,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.005796516828703539,"rank":365,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0054768361677141565,"rank":378,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005702332310358548,"rank":379,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005510853423735436,"rank":379,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005694395045469789,"rank":379,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0057049442913313,"rank":379,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0057531901703070445,"rank":379,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005547198278518784,"rank":379,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005764703934223551,"rank":379,"remainingConfigurations":444},{"removed":"briefcase","score":0.00567317924964517,"rank":379,"remainingConfigurations":444},{"removed":"aime","score":0.0049580270718760895,"rank":384,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005807914368279579,"rank":379,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005589827637863625,"rank":380,"remainingConfigurations":444},{"removed":"automationbench","score":0.005677399901710729,"rank":379,"remainingConfigurations":444},{"removed":"critpt","score":0.005222830459687129,"rank":378,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.00571606573629381,"rank":379,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.005855213963284158,"rank":379,"remainingConfigurations":444},{"removed":"gdpval","score":0.005724095957559042,"rank":379,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005781757131531299,"rank":378,"remainingConfigurations":444},{"removed":"gpqa","score":0.005830124885753681,"rank":380,"remainingConfigurations":444},{"removed":"harvey","score":0.005640362241450303,"rank":379,"remainingConfigurations":444},{"removed":"hle","score":0.006581413877566907,"rank":379,"remainingConfigurations":444},{"removed":"ifbench","score":0.006200076010494753,"rank":372,"remainingConfigurations":444},{"removed":"itbench","score":0.005659020281671202,"rank":379,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004604898183792997,"rank":387,"remainingConfigurations":444},{"removed":"math500","score":0.005788961273693434,"rank":379,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.006109886048389174,"rank":379,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.006270219442065063,"rank":379,"remainingConfigurations":444},{"removed":"omniscience","score":0.0053188409540065795,"rank":376,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005529738192803768,"rank":378,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005804514996886066,"rank":379,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006280195360790615,"rank":374,"remainingConfigurations":444},{"removed":"arc-agi","score":0.007324550822291116,"rank":378,"remainingConfigurations":444},{"removed":"deepswe","score":0.004444204915045589,"rank":379,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.005706475221327073,"rank":379,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005600725637267669,"rank":379,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005556440777671864,"rank":379,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005618584089660375,"rank":379,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0056339282277367364,"rank":379,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005701877059503438,"rank":379,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00567847233599236,"rank":379,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005712372350504612,"rank":379,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0056301174150693994,"rank":379,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005806334709775189,"rank":379,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00570449363391579,"rank":379,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005574405901430601,"rank":379,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005660874154748741,"rank":379,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.00585268029383476,"rank":379,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.005896496945847783,"rank":379,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005718553575080095,"rank":379,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005295205366808264,"rank":379,"remainingConfigurations":444},{"removed":"simpleqa","score":0.006034694635472483,"rank":379,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005680809978128445,"rank":379,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005679884369627561,"rank":379,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005682017510349711,"rank":379,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005691169266057751,"rank":379,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00566237706499353,"rank":379,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005686493321821105,"rank":379,"remainingConfigurations":444}],"sharedOrderConflicts":0},"exaone-4.0-32b--effort-non-reasoning":{"score":0.00563398181515098,"rank":380,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007528743314322757,"rank":379,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004385792067574522,"rank":380,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005567423469078719,"rank":380,"remainingConfigurations":444},{"removed":"Scale","score":0.006714022080319272,"rank":380,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005568527445907294,"rank":380,"remainingConfigurations":444},{"removed":"Cognition","score":0.0054875186753301055,"rank":380,"remainingConfigurations":444},{"removed":"LiveBench","score":0.005895718558692888,"rank":379,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0058206873506704065,"rank":380,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.005752124682938719,"rank":366,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005408656741674292,"rank":379,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005631403461706691,"rank":380,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005442315147072164,"rank":380,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005623570301660447,"rank":380,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.00563398181515098,"rank":380,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005681607315334291,"rank":380,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005478195897996971,"rank":380,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00569320489114199,"rank":380,"remainingConfigurations":444},{"removed":"briefcase","score":0.0056131266100584234,"rank":380,"remainingConfigurations":444},{"removed":"aime","score":0.005495728257118475,"rank":379,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005736282696209116,"rank":380,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005576209450561802,"rank":381,"remainingConfigurations":444},{"removed":"automationbench","score":0.00561776916534425,"rank":380,"remainingConfigurations":444},{"removed":"critpt","score":0.00512162032560632,"rank":379,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005645292289406534,"rank":380,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.005791701970627279,"rank":380,"remainingConfigurations":444},{"removed":"gdpval","score":0.005672332568973599,"rank":380,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0057100930595835745,"rank":380,"remainingConfigurations":444},{"removed":"gpqa","score":0.005411658264353404,"rank":382,"remainingConfigurations":444},{"removed":"harvey","score":0.005570140435077194,"rank":380,"remainingConfigurations":444},{"removed":"hle","score":0.006200849217353289,"rank":381,"remainingConfigurations":444},{"removed":"ifbench","score":0.0055367511019087,"rank":381,"remainingConfigurations":444},{"removed":"itbench","score":0.0055888991418854275,"rank":380,"remainingConfigurations":444},{"removed":"livecodebench","score":0.005450910640562987,"rank":382,"remainingConfigurations":444},{"removed":"math500","score":0.00526317282798101,"rank":382,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005572896263525262,"rank":381,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0062042608020337975,"rank":380,"remainingConfigurations":444},{"removed":"omniscience","score":0.0051580834707852284,"rank":377,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0060927479499439585,"rank":372,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005732046245278744,"rank":380,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.006067689015379022,"rank":375,"remainingConfigurations":444},{"removed":"arc-agi","score":0.007224906708252796,"rank":379,"remainingConfigurations":444},{"removed":"deepswe","score":0.004388893489168791,"rank":380,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0056354936789399105,"rank":380,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005530741808490514,"rank":380,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0054875186753301055,"rank":380,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005548671763499827,"rank":380,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005563839710117123,"rank":380,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0056309572499817885,"rank":380,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.005607835720008476,"rank":380,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005641331865890554,"rank":380,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005560072663615616,"rank":380,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005734117402796664,"rank":380,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005633525664412167,"rank":380,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005505061095137711,"rank":380,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005590459486656002,"rank":380,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005779889095277582,"rank":380,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0058206873506704065,"rank":380,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005648015001358704,"rank":380,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005228906242625336,"rank":380,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005960218785449098,"rank":380,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005610140575996622,"rank":380,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0056092293902624095,"rank":380,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005611340592653242,"rank":380,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005620374776777345,"rank":380,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005591939591375351,"rank":380,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005615757520170295,"rank":380,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-distill-llama-70b--effort-reasoning":{"score":0.005553260598386876,"rank":381,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007412153517596072,"rank":380,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004321345552978008,"rank":381,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005486511622418251,"rank":381,"remainingConfigurations":444},{"removed":"Scale","score":0.006617025811069478,"rank":381,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005489041874766323,"rank":381,"remainingConfigurations":444},{"removed":"Cognition","score":0.005405283128911433,"rank":381,"remainingConfigurations":444},{"removed":"LiveBench","score":0.005811147244521902,"rank":380,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.005733975171390411,"rank":381,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.005658146048290797,"rank":367,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0053325114100926385,"rank":380,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005550720196533045,"rank":381,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005364332086706665,"rank":381,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005542998815973738,"rank":381,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005553260598386876,"rank":381,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005600145958865335,"rank":381,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005399645644311428,"rank":381,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005612518795081109,"rank":381,"remainingConfigurations":444},{"removed":"briefcase","score":0.005518834820874295,"rank":381,"remainingConfigurations":444},{"removed":"aime","score":0.005080128940268883,"rank":382,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005653827417190064,"rank":381,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005733400431327154,"rank":378,"remainingConfigurations":444},{"removed":"automationbench","score":0.0055264936063048236,"rank":381,"remainingConfigurations":444},{"removed":"critpt","score":0.005080104585121684,"rank":380,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005564749840214437,"rank":381,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00569829290663226,"rank":381,"remainingConfigurations":444},{"removed":"gdpval","score":0.005584186161829519,"rank":381,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005636639353561924,"rank":381,"remainingConfigurations":444},{"removed":"gpqa","score":0.00603914182278487,"rank":378,"remainingConfigurations":444},{"removed":"harvey","score":0.005490825774166962,"rank":381,"remainingConfigurations":444},{"removed":"hle","score":0.00607354373867824,"rank":383,"remainingConfigurations":444},{"removed":"ifbench","score":0.005948010822033588,"rank":374,"remainingConfigurations":444},{"removed":"itbench","score":0.005508433648637528,"rank":381,"remainingConfigurations":444},{"removed":"livecodebench","score":0.006332354140216434,"rank":376,"remainingConfigurations":444},{"removed":"math500","score":0.005195925390284268,"rank":383,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005139071233080858,"rank":385,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.006117461852405387,"rank":381,"remainingConfigurations":444},{"removed":"omniscience","score":0.004185574570109586,"rank":385,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005466935911122999,"rank":379,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005649037826801335,"rank":381,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.005986537910569866,"rank":377,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0071165086287040625,"rank":380,"remainingConfigurations":444},{"removed":"deepswe","score":0.004324411076501344,"rank":381,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.005554752561052894,"rank":381,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005451617946161779,"rank":381,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005405283128911433,"rank":381,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005468995562173811,"rank":381,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005483975682714638,"rank":381,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005550283263923828,"rank":381,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0055275678847302905,"rank":381,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00556051473998511,"rank":381,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005480407477526319,"rank":381,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005651994097751808,"rank":381,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005552799743936042,"rank":381,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0054261692711129,"rank":381,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005510357018358583,"rank":381,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005697069457118033,"rank":381,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.005733975171390411,"rank":381,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005566071776743405,"rank":381,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005154735069438788,"rank":381,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005875151284247972,"rank":381,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005529753533765211,"rank":381,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005528868325861414,"rank":381,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005530925445938921,"rank":381,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005539863734022799,"rank":381,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00551182858346129,"rank":381,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005535289201256726,"rank":381,"remainingConfigurations":444}],"sharedOrderConflicts":0},"ministral-3-14b--effort-non-reasoning":{"score":0.005420280321491684,"rank":382,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0072295650950873515,"rank":381,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004217700405876767,"rank":382,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.005356577585839153,"rank":382,"remainingConfigurations":444},{"removed":"Scale","score":0.006472270970881412,"rank":382,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.005358006109495632,"rank":382,"remainingConfigurations":444},{"removed":"Cognition","score":0.005270777354895481,"rank":382,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0056760667058943235,"rank":381,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.005602570734315765,"rank":382,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0055756160130679975,"rank":369,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005210711793437968,"rank":381,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.005417791465859113,"rank":382,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005235443694495654,"rank":382,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005410228256079998,"rank":382,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005420280321491684,"rank":382,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005466028673878068,"rank":382,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005269858401554083,"rank":382,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005477440953217359,"rank":382,"remainingConfigurations":444},{"removed":"briefcase","score":0.005181488808977015,"rank":383,"remainingConfigurations":444},{"removed":"aime","score":0.0055928783681008926,"rank":378,"remainingConfigurations":444},{"removed":"apex-agents","score":0.00552195241614493,"rank":382,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00525638317296447,"rank":383,"remainingConfigurations":444},{"removed":"automationbench","score":0.005268677966368288,"rank":383,"remainingConfigurations":444},{"removed":"critpt","score":0.005007942185837821,"rank":381,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005430402549276919,"rank":382,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.005372617987238649,"rank":383,"remainingConfigurations":444},{"removed":"gdpval","score":0.005246354593174997,"rank":383,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005752273464930152,"rank":379,"remainingConfigurations":444},{"removed":"gpqa","score":0.005435038488735423,"rank":381,"remainingConfigurations":444},{"removed":"harvey","score":0.005358700275583658,"rank":382,"remainingConfigurations":444},{"removed":"hle","score":0.006128826180600558,"rank":382,"remainingConfigurations":444},{"removed":"ifbench","score":0.005383250015972101,"rank":383,"remainingConfigurations":444},{"removed":"itbench","score":0.005377211751613688,"rank":382,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00563700016518119,"rank":381,"remainingConfigurations":444},{"removed":"math500","score":0.005486652112056855,"rank":380,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0060041901504789665,"rank":380,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0060275048826627,"rank":382,"remainingConfigurations":444},{"removed":"omniscience","score":0.004845977833752899,"rank":379,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004971009957365252,"rank":383,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005512472119294114,"rank":382,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00526649521219029,"rank":384,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00694303552289801,"rank":381,"remainingConfigurations":444},{"removed":"deepswe","score":0.004220709404307761,"rank":382,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.005421745808023293,"rank":382,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005322715899121932,"rank":382,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005270777354895481,"rank":382,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005338054852623417,"rank":382,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005352566151275436,"rank":382,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005417389230426552,"rank":382,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.005395613667436981,"rank":382,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00542726900225523,"rank":382,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005349369639657175,"rank":382,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005516846075950571,"rank":382,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005419720182043721,"rank":382,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00529607236047147,"rank":382,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005378418046625107,"rank":382,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005560597423519519,"rank":382,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.005602570734315765,"rank":382,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005430220222307648,"rank":382,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.005043765268588952,"rank":382,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005733815136760762,"rank":382,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0053973371560345025,"rank":382,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005396474607164813,"rank":382,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005398437074930595,"rank":382,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005407247414154291,"rank":382,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005379834550509351,"rank":382,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.005402734837492557,"rank":382,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-235b-a22b--effort-non-reasoning":{"score":0.005391843638312011,"rank":383,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.007208580335861023,"rank":382,"remainingConfigurations":444},{"removed":"Datacurve","score":0.004197428034135351,"rank":383,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0053283450341415255,"rank":383,"remainingConfigurations":444},{"removed":"Scale","score":0.0064268873277056535,"rank":383,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00532931980973194,"rank":383,"remainingConfigurations":444},{"removed":"Cognition","score":0.00525188961982045,"rank":383,"remainingConfigurations":444},{"removed":"LiveBench","score":0.005643105257490125,"rank":382,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.005570259459558909,"rank":383,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.005578249677345996,"rank":368,"remainingConfigurations":431},{"removed":"Vals AI","score":0.005176892822725046,"rank":382,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0053893747366343435,"rank":383,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.005208334832476386,"rank":383,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005381874566783465,"rank":383,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005391843638312011,"rank":383,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005437435690759963,"rank":383,"remainingConfigurations":444},{"removed":"All provider reports","score":0.005242680247255031,"rank":383,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005449592003239274,"rank":383,"remainingConfigurations":444},{"removed":"briefcase","score":0.005371768899477831,"rank":382,"remainingConfigurations":444},{"removed":"aime","score":0.0058333299373989796,"rank":377,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005490236046287435,"rank":383,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005824718324538029,"rank":377,"remainingConfigurations":444},{"removed":"automationbench","score":0.005377038965312217,"rank":382,"remainingConfigurations":444},{"removed":"critpt","score":0.004910815828700104,"rank":382,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005405101867796661,"rank":383,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0055429817997201605,"rank":382,"remainingConfigurations":444},{"removed":"gdpval","score":0.005429901505465788,"rank":382,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005478888220317872,"rank":383,"remainingConfigurations":444},{"removed":"gpqa","score":0.005249873069113081,"rank":383,"remainingConfigurations":444},{"removed":"harvey","score":0.005331387194336387,"rank":383,"remainingConfigurations":444},{"removed":"hle","score":0.006370599583836686,"rank":380,"remainingConfigurations":444},{"removed":"ifbench","score":0.005104558608060225,"rank":385,"remainingConfigurations":444},{"removed":"itbench","score":0.005349221925762833,"rank":383,"remainingConfigurations":444},{"removed":"livecodebench","score":0.005716901772985832,"rank":380,"remainingConfigurations":444},{"removed":"math500","score":0.005478626476671896,"rank":381,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005344565050342431,"rank":383,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.005946954016271451,"rank":383,"remainingConfigurations":444},{"removed":"omniscience","score":0.0041245384415460815,"rank":386,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0050343785694055366,"rank":382,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005487644065132006,"rank":383,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0052768611076790236,"rank":383,"remainingConfigurations":444},{"removed":"arc-agi","score":0.006917285338274837,"rank":382,"remainingConfigurations":444},{"removed":"deepswe","score":0.004200396600363954,"rank":383,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.00539329132949646,"rank":383,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005293115148338871,"rank":383,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00525188961982045,"rank":383,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005310166524990351,"rank":383,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005324695369848433,"rank":383,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005388950562570122,"rank":383,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0053668367148932555,"rank":383,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005398882340606114,"rank":383,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00532106145584436,"rank":383,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005487722727244037,"rank":383,"remainingConfigurations":444},{"removed":"livebench-data","score":0.005391419774073646,"rank":383,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0052684065090649575,"rank":383,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005350167432196254,"rank":383,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005531558616850532,"rank":383,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.005570259459558909,"rank":383,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005404927678945983,"rank":383,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0050042695738207795,"rank":383,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005704246910508928,"rank":383,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005369016245782837,"rank":383,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005368145579083751,"rank":383,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005370163973869747,"rank":383,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005378814779741392,"rank":383,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00535159006209815,"rank":383,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0053743934750163,"rank":383,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-0528-qwen3-8b--effort-reasoning":{"score":0.005153068986739508,"rank":384,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.006881493221215201,"rank":383,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0040097386412568025,"rank":384,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0050913900167836625,"rank":384,"remainingConfigurations":444},{"removed":"Scale","score":0.0061416340486331635,"rank":384,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0050935303757287985,"rank":384,"remainingConfigurations":444},{"removed":"Cognition","score":0.005016450022502325,"rank":384,"remainingConfigurations":444},{"removed":"LiveBench","score":0.005392947142420213,"rank":383,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.005321476430799002,"rank":384,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0052447073144833815,"rank":370,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004948648937774475,"rank":383,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0051507100981396286,"rank":384,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00497763623489122,"rank":384,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.005143542054173739,"rank":384,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.005153068986739508,"rank":384,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.005196594002860471,"rank":384,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0050104167509198985,"rank":384,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005207822217651107,"rank":384,"remainingConfigurations":444},{"removed":"briefcase","score":0.005128504643985275,"rank":384,"remainingConfigurations":444},{"removed":"aime","score":0.004421936631819626,"rank":387,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005245921346783939,"rank":384,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005203375470783037,"rank":384,"remainingConfigurations":444},{"removed":"automationbench","score":0.0051332583791702125,"rank":384,"remainingConfigurations":444},{"removed":"critpt","score":0.004669325786557636,"rank":384,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.005163641089665795,"rank":384,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.005295068618799372,"rank":384,"remainingConfigurations":444},{"removed":"gdpval","score":0.005185692520826028,"rank":384,"remainingConfigurations":444},{"removed":"gmmlu","score":0.005232421799356894,"rank":384,"remainingConfigurations":444},{"removed":"gpqa","score":0.00500027045613768,"rank":384,"remainingConfigurations":444},{"removed":"harvey","score":0.005094657653628287,"rank":384,"remainingConfigurations":444},{"removed":"hle","score":0.005450357168322404,"rank":387,"remainingConfigurations":444},{"removed":"ifbench","score":0.005751602041247927,"rank":378,"remainingConfigurations":444},{"removed":"itbench","score":0.005111737800443887,"rank":384,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004776414665960438,"rank":386,"remainingConfigurations":444},{"removed":"math500","score":0.004843715464406946,"rank":384,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005435958643855875,"rank":382,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0056890373407756,"rank":384,"remainingConfigurations":444},{"removed":"omniscience","score":0.004617003229697638,"rank":381,"remainingConfigurations":444},{"removed":"tau-bench","score":0.005573404560821741,"rank":376,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005241566133674818,"rank":384,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0055238300443358175,"rank":380,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0066065466571096215,"rank":383,"remainingConfigurations":444},{"removed":"deepswe","score":0.004012584160333423,"rank":384,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.005154454320658467,"rank":384,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.005058715557780854,"rank":384,"remainingConfigurations":444},{"removed":"frontiercode","score":0.005016450022502325,"rank":384,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.005074829560516565,"rank":384,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.005088750555189023,"rank":384,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.005150309049448063,"rank":384,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.005129228336952843,"rank":384,"remainingConfigurations":444},{"removed":"livebench-math","score":0.005159808316341473,"rank":384,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.005085399049574925,"rank":384,"remainingConfigurations":444},{"removed":"livebench-language","score":0.005244758646882918,"rank":384,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00515265041549005,"rank":384,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.005035048022149108,"rank":384,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.005113222754262786,"rank":384,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005286633343301462,"rank":384,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.005321476430799002,"rank":384,"remainingConfigurations":444},{"removed":"frontiermath","score":0.005165069205016369,"rank":384,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004782853794965451,"rank":384,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005452160777026263,"rank":384,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.005131238514842175,"rank":384,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.005130416256857993,"rank":384,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.005132328331709505,"rank":384,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.005140624102800819,"rank":384,"remainingConfigurations":444},{"removed":"vibe-code","score":0.005114592439183892,"rank":384,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.00513637960946184,"rank":384,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-distill-qwen-32b--effort-reasoning":{"score":0.0049561084800737966,"rank":385,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0066348899551835734,"rank":384,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0038577602334426086,"rank":385,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004897276925499713,"rank":385,"remainingConfigurations":444},{"removed":"Scale","score":0.005908023238993899,"rank":385,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00489874981982486,"rank":385,"remainingConfigurations":444},{"removed":"Cognition","score":0.0048274646244371305,"rank":385,"remainingConfigurations":444},{"removed":"LiveBench","score":0.005186581742950033,"rank":384,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0051212247219579515,"rank":385,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.005073220751889372,"rank":371,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004759004480695823,"rank":384,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004953839428233773,"rank":385,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004787328804771215,"rank":385,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004946947003171861,"rank":385,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0049561084800737966,"rank":385,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004997994664249591,"rank":385,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004818880635728694,"rank":385,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.005008084164364523,"rank":385,"remainingConfigurations":444},{"removed":"briefcase","score":0.004926753786179821,"rank":385,"remainingConfigurations":444},{"removed":"aime","score":0.003987140407394022,"rank":396,"remainingConfigurations":444},{"removed":"apex-agents","score":0.005045377149990999,"rank":385,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005182362510859024,"rank":385,"remainingConfigurations":444},{"removed":"automationbench","score":0.0049328940006773065,"rank":385,"remainingConfigurations":444},{"removed":"critpt","score":0.0045788071859506115,"rank":385,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0049649012823271685,"rank":385,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.005085737061495122,"rank":385,"remainingConfigurations":444},{"removed":"gdpval","score":0.004983954026828748,"rank":385,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0050299068067557315,"rank":385,"remainingConfigurations":444},{"removed":"gpqa","score":0.004689262348137455,"rank":387,"remainingConfigurations":444},{"removed":"harvey","score":0.004899625687601014,"rank":385,"remainingConfigurations":444},{"removed":"hle","score":0.005673144299280657,"rank":385,"remainingConfigurations":444},{"removed":"ifbench","score":0.005672781129132356,"rank":380,"remainingConfigurations":444},{"removed":"itbench","score":0.004915828976748254,"rank":385,"remainingConfigurations":444},{"removed":"livecodebench","score":0.005821975722941872,"rank":379,"remainingConfigurations":444},{"removed":"math500","score":0.004327193361065592,"rank":392,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005214074774579844,"rank":384,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.005455169436222828,"rank":385,"remainingConfigurations":444},{"removed":"omniscience","score":0.004285176233763325,"rank":384,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004751836309572385,"rank":385,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.005041112770190954,"rank":385,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00497587297854505,"rank":386,"remainingConfigurations":444},{"removed":"arc-agi","score":0.006368462353224272,"rank":384,"remainingConfigurations":444},{"removed":"deepswe","score":0.0038604939374870164,"rank":385,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0049574406475724276,"rank":385,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004864976529367338,"rank":385,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0048274646244371305,"rank":385,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004880960166345071,"rank":385,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004894341324631318,"rank":385,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004953457771948353,"rank":385,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004933143990563938,"rank":385,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004962605182363428,"rank":385,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004890979139229703,"rank":385,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0050443077481394415,"rank":385,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004955712381505093,"rank":385,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004842564540502901,"rank":385,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004917770641575235,"rank":385,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.005084635190296361,"rank":385,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0051212247219579515,"rank":385,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004967773888065692,"rank":385,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004598761988006484,"rank":385,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005244239703507566,"rank":385,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0049350997608475335,"rank":385,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004934308171301119,"rank":385,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004936167488739527,"rank":385,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004944121304646916,"rank":385,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004919079933170283,"rank":385,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004940053831705205,"rank":385,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-distill-qwen-14b--effort-reasoning":{"score":0.0047417726352610426,"rank":386,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.006349992075704209,"rank":385,"remainingConfigurations":444},{"removed":"Datacurve","score":0.003690859280735465,"rank":386,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00468560475531427,"rank":386,"remainingConfigurations":444},{"removed":"Scale","score":0.005653256684566115,"rank":386,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004686918270548081,"rank":386,"remainingConfigurations":444},{"removed":"Cognition","score":0.0046190876720160175,"rank":386,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0049625535313078855,"rank":385,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004900333510890343,"rank":386,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004849269528968809,"rank":373,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004553395953701239,"rank":385,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00473960095208536,"rank":386,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0045802340601385294,"rank":386,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004733005078533401,"rank":386,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0047417726352610426,"rank":386,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004781855937000419,"rank":386,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0046104267258665335,"rank":386,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004791671804348901,"rank":386,"remainingConfigurations":444},{"removed":"briefcase","score":0.004712434246275129,"rank":386,"remainingConfigurations":444},{"removed":"aime","score":0.004014550443208807,"rank":395,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004827355119341764,"rank":386,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004888600285557596,"rank":387,"remainingConfigurations":444},{"removed":"automationbench","score":0.004717387179760172,"rank":386,"remainingConfigurations":444},{"removed":"critpt","score":0.004374135186460085,"rank":386,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004750434215169641,"rank":386,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004863548066366433,"rank":386,"remainingConfigurations":444},{"removed":"gdpval","score":0.004765720966704746,"rank":386,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004810474002357208,"rank":386,"remainingConfigurations":444},{"removed":"gpqa","score":0.004973742736946239,"rank":385,"remainingConfigurations":444},{"removed":"harvey","score":0.00468777854100011,"rank":386,"remainingConfigurations":444},{"removed":"hle","score":0.005721858980033017,"rank":384,"remainingConfigurations":444},{"removed":"ifbench","score":0.005439803771242366,"rank":382,"remainingConfigurations":444},{"removed":"itbench","score":0.004703368284075333,"rank":386,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004885180912299796,"rank":384,"remainingConfigurations":444},{"removed":"math500","score":0.003962683177020737,"rank":399,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004896213804301886,"rank":389,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.005224371326572909,"rank":388,"remainingConfigurations":444},{"removed":"omniscience","score":0.004097790956265053,"rank":387,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004541906067629108,"rank":386,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004823207117319645,"rank":386,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004759835376196133,"rank":387,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00609474086273104,"rank":385,"remainingConfigurations":444},{"removed":"deepswe","score":0.003693475352245948,"rank":386,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004743047639304815,"rank":386,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004654574689655364,"rank":386,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0046190876720160175,"rank":386,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004669851111783098,"rank":386,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0046826640406606,"rank":386,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004739237903576035,"rank":386,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00471980104641994,"rank":386,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0047479922830114185,"rank":386,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004679426949848518,"rank":386,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00482619309446843,"rank":386,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004741398107300756,"rank":386,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004633095485989476,"rank":386,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00470507574017159,"rank":386,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004864799369652481,"rank":386,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004900333510890343,"rank":386,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004753000530560151,"rank":386,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004399705910473153,"rank":386,"remainingConfigurations":444},{"removed":"simpleqa","score":0.005017644797486879,"rank":386,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004721663954319423,"rank":386,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004720906208180604,"rank":386,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004722686299616728,"rank":386,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004730297477268121,"rank":386,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00470633073472672,"rank":386,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004726405769698923,"rank":386,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-omni-30b-a3b-instruct--effort-non-reasoning":{"score":0.004677913660575805,"rank":387,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0062532307047474525,"rank":386,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0036397131701083256,"rank":387,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0046226279773466635,"rank":387,"remainingConfigurations":444},{"removed":"Scale","score":0.005577058152765036,"rank":387,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004624114795877439,"rank":387,"remainingConfigurations":444},{"removed":"Cognition","score":0.004554549562804588,"rank":387,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00489669760758148,"rank":386,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004831761133801069,"rank":387,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004764201906006758,"rank":375,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0044929127155689365,"rank":386,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0046757697854614725,"rank":387,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0045184887282236985,"rank":387,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004669250595094951,"rank":387,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004677913660575805,"rank":387,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004717466048591412,"rank":387,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004548269211610039,"rank":387,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0047281606036719435,"rank":387,"remainingConfigurations":444},{"removed":"briefcase","score":0.004655557474365197,"rank":387,"remainingConfigurations":444},{"removed":"aime","score":0.004204570006010418,"rank":392,"remainingConfigurations":444},{"removed":"apex-agents","score":0.00476277497155198,"rank":387,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.005014177833814783,"rank":386,"remainingConfigurations":444},{"removed":"automationbench","score":0.0046613019877062905,"rank":387,"remainingConfigurations":444},{"removed":"critpt","score":0.004199245720704511,"rank":387,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0046881431457543,"rank":387,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0048095452042600005,"rank":387,"remainingConfigurations":444},{"removed":"gdpval","score":0.004708170615362749,"rank":387,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00475365296390637,"rank":387,"remainingConfigurations":444},{"removed":"gpqa","score":0.004445066522909285,"rank":392,"remainingConfigurations":444},{"removed":"harvey","score":0.004625077964449697,"rank":387,"remainingConfigurations":444},{"removed":"hle","score":0.005224158280444482,"rank":390,"remainingConfigurations":444},{"removed":"ifbench","score":0.004778996774662764,"rank":388,"remainingConfigurations":444},{"removed":"itbench","score":0.004640878654071337,"rank":387,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004516392999672649,"rank":390,"remainingConfigurations":444},{"removed":"math500","score":0.0047413228665211474,"rank":385,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004953912989582136,"rank":388,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004907826055728175,"rank":391,"remainingConfigurations":444},{"removed":"omniscience","score":0.004023938547524745,"rank":389,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004760043943638163,"rank":384,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004758745774935489,"rank":387,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004992463568911054,"rank":385,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0060017470763335246,"rank":386,"remainingConfigurations":444},{"removed":"deepswe","score":0.0036422947424182314,"rank":387,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004679171777534335,"rank":387,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0045923778043509885,"rank":387,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004554549562804588,"rank":387,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004606847921343865,"rank":387,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004619494581030306,"rank":387,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00467540744791536,"rank":387,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004656260759889694,"rank":387,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004684029168344307,"rank":387,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004616436266695959,"rank":387,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004761230582799745,"rank":387,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00467753023803187,"rank":387,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0045706725813694634,"rank":387,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004641707789871968,"rank":387,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.00479928938959183,"rank":387,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004831761133801069,"rank":387,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004688876109052206,"rank":387,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0043420245396245585,"rank":387,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004949378667762649,"rank":387,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004658081318319465,"rank":387,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004657326944235333,"rank":387,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004659072284196822,"rank":387,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004666597246338021,"rank":387,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004642949520571471,"rank":387,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004662751556107126,"rank":387,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.6v--effort-non-reasoning":{"score":0.0046495427945504675,"rank":388,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.006216629776348562,"rank":387,"remainingConfigurations":444},{"removed":"Datacurve","score":0.003619124396440963,"rank":388,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004595572346029063,"rank":388,"remainingConfigurations":444},{"removed":"Scale","score":0.0055449098892378845,"rank":388,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004595680396781493,"rank":388,"remainingConfigurations":444},{"removed":"Cognition","score":0.004529790904180934,"rank":388,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004867103574180875,"rank":387,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004800438558753236,"rank":388,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004784226184712426,"rank":374,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004464454543496611,"rank":387,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004647410142364876,"rank":388,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004491065101297825,"rank":388,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00464092995382035,"rank":388,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0046495427945504675,"rank":388,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004688904288895822,"rank":388,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004520707415405444,"rank":388,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004698744667470507,"rank":388,"remainingConfigurations":444},{"removed":"briefcase","score":0.004625283449434493,"rank":388,"remainingConfigurations":444},{"removed":"aime","score":0.004871419996645311,"rank":385,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004735137495325711,"rank":388,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004616448786511021,"rank":390,"remainingConfigurations":444},{"removed":"automationbench","score":0.004628937857609804,"rank":388,"remainingConfigurations":444},{"removed":"critpt","score":0.004185839016268565,"rank":388,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004660743340706853,"rank":388,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004774762689787396,"rank":388,"remainingConfigurations":444},{"removed":"gdpval","score":0.004676344620143445,"rank":388,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004614501992805478,"rank":390,"remainingConfigurations":444},{"removed":"gpqa","score":0.0046626174225798955,"rank":388,"remainingConfigurations":444},{"removed":"harvey","score":0.004597552579242123,"rank":388,"remainingConfigurations":444},{"removed":"hle","score":0.005641925879933928,"rank":386,"remainingConfigurations":444},{"removed":"ifbench","score":0.0048508954400539855,"rank":387,"remainingConfigurations":444},{"removed":"itbench","score":0.004612270443186819,"rank":388,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004539743584934071,"rank":388,"remainingConfigurations":444},{"removed":"math500","score":0.004715290051510352,"rank":386,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004656834125380001,"rank":393,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.005395082071947045,"rank":386,"remainingConfigurations":444},{"removed":"omniscience","score":0.003643362097689028,"rank":394,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004170360183988014,"rank":390,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004731175900037728,"rank":388,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0047471819893529724,"rank":388,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005963514974012581,"rank":387,"remainingConfigurations":444},{"removed":"deepswe","score":0.003621684223086445,"rank":388,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004650792542406252,"rank":388,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004564492375892549,"rank":388,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004529790904180934,"rank":388,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004578998969852667,"rank":388,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004591633410236642,"rank":388,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004647044025150708,"rank":388,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004627955239274142,"rank":388,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004655615614839963,"rank":388,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004588419861986696,"rank":388,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004732343363430446,"rank":388,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004649171049956124,"rank":388,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004542946928241333,"rank":388,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004613554767442113,"rank":388,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004770221939779399,"rank":388,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004800438558753236,"rank":388,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0046608629746436965,"rank":388,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004315270963323201,"rank":388,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004919029128655025,"rank":388,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004629831498757044,"rank":388,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004629073087571277,"rank":388,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004630824622001138,"rank":388,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004638281256449707,"rank":388,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0046147781498692645,"rank":388,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004634472514462887,"rank":388,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-8b--effort-reasoning":{"score":0.004590905380866439,"rank":389,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.006136579983470833,"rank":388,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0035748668394498446,"rank":389,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0045380246752676585,"rank":389,"remainingConfigurations":444},{"removed":"Scale","score":0.0054739882928536675,"rank":389,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00453892377252321,"rank":389,"remainingConfigurations":444},{"removed":"Cognition","score":0.0044689249076648825,"rank":390,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004809879518226186,"rank":388,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00475091055398887,"rank":389,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004721909748179281,"rank":376,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004416829313754089,"rank":388,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0045887928788323215,"rank":389,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004434092438218601,"rank":389,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004582388673035633,"rank":389,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004590905380866439,"rank":389,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004629712093949609,"rank":389,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004463290514719605,"rank":389,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004641682141523286,"rank":389,"remainingConfigurations":444},{"removed":"briefcase","score":0.0045730942640750645,"rank":389,"remainingConfigurations":444},{"removed":"aime","score":0.004959802364726112,"rank":383,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004678116963085874,"rank":389,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0048323141281572295,"rank":388,"remainingConfigurations":444},{"removed":"automationbench","score":0.00455454306847861,"rank":389,"remainingConfigurations":444},{"removed":"critpt","score":0.004152466972788084,"rank":389,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004603193033424346,"rank":389,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004406538778838435,"rank":393,"remainingConfigurations":444},{"removed":"gdpval","score":0.004675344671030993,"rank":389,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004660305664016021,"rank":389,"remainingConfigurations":444},{"removed":"gpqa","score":0.004481017059027148,"rank":391,"remainingConfigurations":444},{"removed":"harvey","score":0.004539906983300496,"rank":389,"remainingConfigurations":444},{"removed":"hle","score":0.005406784492894344,"rank":388,"remainingConfigurations":444},{"removed":"ifbench","score":0.004384508271800271,"rank":392,"remainingConfigurations":444},{"removed":"itbench","score":0.004555762482021367,"rank":389,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004528613360767245,"rank":389,"remainingConfigurations":444},{"removed":"math500","score":0.004584374823541026,"rank":388,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004728311470474272,"rank":391,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.005058825748484809,"rank":389,"remainingConfigurations":444},{"removed":"omniscience","score":0.004026806092594341,"rank":388,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004271959143463262,"rank":389,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004671180731399807,"rank":389,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0045740450949078235,"rank":391,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00588985470891881,"rank":388,"remainingConfigurations":444},{"removed":"deepswe","score":0.0035774150698461888,"rank":389,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004592147987010488,"rank":389,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004508301136574488,"rank":389,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0044689249076648825,"rank":390,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004521376995177248,"rank":389,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0045336396279596165,"rank":389,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00458846706964745,"rank":389,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004570055009601053,"rank":389,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00459683647080492,"rank":389,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004530672925426506,"rank":389,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004672820991615027,"rank":389,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004590507179483386,"rank":389,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004485536698112379,"rank":389,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004555369425180987,"rank":389,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0047099960731017895,"rank":389,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00475091055398887,"rank":389,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004599831207375184,"rank":389,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004271294533728726,"rank":389,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004857339994057125,"rank":389,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004571445621679116,"rank":389,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0045707100386382015,"rank":389,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004572377891471424,"rank":389,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004579840105392498,"rank":389,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004556584756643637,"rank":389,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004576029063215664,"rank":389,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-14b--effort-non-reasoning":{"score":0.004545119150285334,"rank":390,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.006116571015477467,"rank":193,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0061169834288029926,"rank":389,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0035602257634339113,"rank":390,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00449704800377984,"rank":390,"remainingConfigurations":444},{"removed":"Scale","score":0.005414044711409788,"rank":390,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004504407347511924,"rank":390,"remainingConfigurations":444},{"removed":"Cognition","score":0.004480547264320715,"rank":389,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004743174244394265,"rank":389,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004686209898871954,"rank":390,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0038179034816730913,"rank":386,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004382028992460005,"rank":389,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004543121764696743,"rank":390,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004392390306447439,"rank":390,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0045372221482523215,"rank":390,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004545119150285334,"rank":390,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004582781580395611,"rank":390,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004421174626160924,"rank":390,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004591290319157286,"rank":390,"remainingConfigurations":444},{"removed":"briefcase","score":0.00451430828108091,"rank":390,"remainingConfigurations":444},{"removed":"aime","score":0.003966271742582209,"rank":397,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004624726884817754,"rank":390,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004725922944662113,"rank":389,"remainingConfigurations":444},{"removed":"automationbench","score":0.004517667355444036,"rank":390,"remainingConfigurations":444},{"removed":"critpt","score":0.0040702989432910746,"rank":390,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004554545602909954,"rank":390,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004647134432206368,"rank":389,"remainingConfigurations":444},{"removed":"gdpval","score":0.004545950413024738,"rank":391,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004605930921110199,"rank":391,"remainingConfigurations":444},{"removed":"gpqa","score":0.004497769731183872,"rank":390,"remainingConfigurations":444},{"removed":"harvey","score":0.004491448039287382,"rank":390,"remainingConfigurations":444},{"removed":"hle","score":0.005198939947354936,"rank":391,"remainingConfigurations":444},{"removed":"ifbench","score":0.004687512987199185,"rank":389,"remainingConfigurations":444},{"removed":"itbench","score":0.004510120765973906,"rank":390,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00483570951303452,"rank":385,"remainingConfigurations":444},{"removed":"math500","score":0.004610318509715094,"rank":387,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004997272458657381,"rank":387,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004978047638725555,"rank":390,"remainingConfigurations":444},{"removed":"omniscience","score":0.004004389475529883,"rank":390,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0040081069200001325,"rank":393,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004617808255900695,"rank":390,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004433415230153385,"rank":392,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005868103415520311,"rank":389,"remainingConfigurations":444},{"removed":"deepswe","score":0.003562870209298743,"rank":390,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004546326722705282,"rank":390,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00446251053083905,"rank":390,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004480547264320715,"rank":389,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004478754140171514,"rank":390,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004487524647786263,"rank":390,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00454278517155098,"rank":390,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004523939155482163,"rank":390,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004552765041735677,"rank":390,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0044829599156245604,"rank":390,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004625554294071002,"rank":390,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004545399865260122,"rank":390,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004441927559612374,"rank":390,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004509746240301826,"rank":390,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0046626250369345345,"rank":390,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004686209898871954,"rank":390,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004568047703937531,"rank":390,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00409603299170971,"rank":392,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004846862548474448,"rank":390,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004525659296982581,"rank":390,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004525507909133377,"rank":390,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004526490209409797,"rank":390,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004534405936569878,"rank":390,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004511627482574803,"rank":390,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004530096093720243,"rank":390,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemini-2.5-flash-lite--effort-non-reasoning":{"score":0.004460570198113241,"rank":391,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005978754232643249,"rank":391,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0034725910623341805,"rank":391,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004408446953274706,"rank":391,"remainingConfigurations":444},{"removed":"Scale","score":0.005319777588705224,"rank":391,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004409191002526717,"rank":391,"remainingConfigurations":444},{"removed":"Cognition","score":0.004346985794563283,"rank":391,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004669743536089396,"rank":390,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0046125609965143284,"rank":391,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004573471321041499,"rank":377,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004283816669668803,"rank":390,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004458524396500096,"rank":391,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004308505470086771,"rank":391,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004452309220855494,"rank":391,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004460570198113241,"rank":391,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004498336187796599,"rank":391,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004336949004988921,"rank":391,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004507960072796874,"rank":391,"remainingConfigurations":444},{"removed":"briefcase","score":0.0044389927365102505,"rank":391,"remainingConfigurations":444},{"removed":"aime","score":0.004407517371076568,"rank":388,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004542362370792532,"rank":391,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004194932422959283,"rank":393,"remainingConfigurations":444},{"removed":"automationbench","score":0.004444848542136813,"rank":391,"remainingConfigurations":444},{"removed":"critpt","score":0.00398374377876991,"rank":391,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004471289120577155,"rank":391,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0045825829163755796,"rank":390,"remainingConfigurations":444},{"removed":"gdpval","score":0.004493599140935902,"rank":392,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00453599043555901,"rank":392,"remainingConfigurations":444},{"removed":"gpqa","score":0.0046025480208096645,"rank":389,"remainingConfigurations":444},{"removed":"harvey","score":0.004410408916119052,"rank":391,"remainingConfigurations":444},{"removed":"hle","score":0.0053626320568028844,"rank":389,"remainingConfigurations":444},{"removed":"ifbench","score":0.004491929746053049,"rank":391,"remainingConfigurations":444},{"removed":"itbench","score":0.004425166079295,"rank":391,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0044268996207066065,"rank":393,"remainingConfigurations":444},{"removed":"math500","score":0.004293635495976482,"rank":394,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004732093934103984,"rank":390,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004738713957750182,"rank":393,"remainingConfigurations":444},{"removed":"omniscience","score":0.0037062775691828705,"rank":393,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004433998372086035,"rank":387,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004538437267065439,"rank":391,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004607516329697144,"rank":389,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005734711896230075,"rank":391,"remainingConfigurations":444},{"removed":"deepswe","score":0.0034750479313248005,"rank":391,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004461769443815566,"rank":391,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004378866174745906,"rank":391,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004346985794563283,"rank":391,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004392931585332675,"rank":391,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004405003646020968,"rank":391,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0044581815665377675,"rank":391,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004439875825050474,"rank":391,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004466407274026102,"rank":391,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004401891908001331,"rank":391,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004540034016415312,"rank":391,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004460226130539698,"rank":391,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004358274316719139,"rank":391,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004426027349949781,"rank":391,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004576387600556515,"rank":391,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0046125609965143284,"rank":391,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0044717399356746694,"rank":391,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.004139629427222301,"rank":390,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004719695568596244,"rank":391,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004441651615191694,"rank":391,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004440926766562354,"rank":391,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004442607690130746,"rank":391,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.00444976179878608,"rank":391,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004427206692172046,"rank":391,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004446109208569269,"rank":391,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-2b--effort-non-reasoning":{"score":0.004434241330172628,"rank":392,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.006007107132526644,"rank":390,"remainingConfigurations":444},{"removed":"Datacurve","score":0.003457503693970075,"rank":392,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004386131153707008,"rank":392,"remainingConfigurations":444},{"removed":"Scale","score":0.005291271361125868,"rank":392,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004384066400389632,"rank":392,"remainingConfigurations":444},{"removed":"Cognition","score":0.004336627209470141,"rank":392,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004646337491530667,"rank":391,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004592466155956032,"rank":392,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004492084783749633,"rank":378,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0042622127558096775,"rank":391,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004432203345626353,"rank":392,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004282951334433034,"rank":392,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004426012127204699,"rank":392,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004434241330172628,"rank":392,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004471847581142288,"rank":392,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004311267705846026,"rank":392,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004484153609007196,"rank":392,"remainingConfigurations":444},{"removed":"briefcase","score":0.004404442968118734,"rank":392,"remainingConfigurations":444},{"removed":"aime","score":0.00437656298235427,"rank":389,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004518779346550099,"rank":392,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004503501998273744,"rank":391,"remainingConfigurations":444},{"removed":"automationbench","score":0.004408632872461644,"rank":392,"remainingConfigurations":444},{"removed":"critpt","score":0.003922032217709073,"rank":393,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004447669526973727,"rank":392,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0045475632905825954,"rank":391,"remainingConfigurations":444},{"removed":"gdpval","score":0.00463332520876452,"rank":390,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004493347432298268,"rank":393,"remainingConfigurations":444},{"removed":"gpqa","score":0.0047973366962570235,"rank":386,"remainingConfigurations":444},{"removed":"harvey","score":0.00438551087221905,"rank":392,"remainingConfigurations":444},{"removed":"hle","score":0.004768603299069562,"rank":396,"remainingConfigurations":444},{"removed":"ifbench","score":0.004638440902450929,"rank":390,"remainingConfigurations":444},{"removed":"itbench","score":0.004402311012367081,"rank":392,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004471556068289681,"rank":392,"remainingConfigurations":444},{"removed":"math500","score":0.004483913380508779,"rank":389,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004658445413917303,"rank":392,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0052496223038015115,"rank":387,"remainingConfigurations":444},{"removed":"omniscience","score":0.004383889000206617,"rank":382,"remainingConfigurations":444},{"removed":"tau-bench","score":0.002861299971881913,"rank":410,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0045157201226259675,"rank":392,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004594817806823215,"rank":390,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005749854186179484,"rank":390,"remainingConfigurations":444},{"removed":"deepswe","score":0.003459947083480588,"rank":392,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004435434519246052,"rank":392,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004354349401682898,"rank":392,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004336627209470141,"rank":392,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004367191211095609,"rank":392,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004379104195254206,"rank":392,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0044318658331562386,"rank":392,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0044137370746417885,"rank":392,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004440006587852559,"rank":392,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004375920649605343,"rank":392,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004513284390480765,"rank":392,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004433924253014141,"rank":392,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004332506738511499,"rank":392,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004399888369063987,"rank":392,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004549394688982936,"rank":392,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004592466155956032,"rank":392,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004446020553162933,"rank":392,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00411767726072422,"rank":391,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004690903292890268,"rank":392,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00441544724471082,"rank":392,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004414719697202372,"rank":392,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004416363971933234,"rank":392,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.00442350810939194,"rank":392,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00440107491758513,"rank":392,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004419865028455538,"rank":392,"remainingConfigurations":444}],"sharedOrderConflicts":1},"qwen3-4b-instruct-2507--effort-non-reasoning":{"score":0.004401824476429298,"rank":393,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005880587346962909,"rank":392,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0034242954037250624,"rank":393,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004350086812754243,"rank":393,"remainingConfigurations":444},{"removed":"Scale","score":0.005248973600826544,"rank":393,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0043508167543474955,"rank":393,"remainingConfigurations":444},{"removed":"Cognition","score":0.004285449811557914,"rank":393,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004607470078996124,"rank":392,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004546212118816684,"rank":393,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004489332640811171,"rank":379,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004227406966661771,"rank":392,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.004399806401582184,"rank":393,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004251761396437251,"rank":393,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004393676395932936,"rank":393,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004401824476429298,"rank":393,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004439032211864924,"rank":393,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004279777539827778,"rank":393,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004448809392634809,"rank":393,"remainingConfigurations":444},{"removed":"briefcase","score":0.0043684895490533815,"rank":393,"remainingConfigurations":444},{"removed":"aime","score":0.00392815632818961,"rank":398,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004481577425673152,"rank":393,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004452789920052873,"rank":392,"remainingConfigurations":444},{"removed":"automationbench","score":0.004371671414490875,"rank":393,"remainingConfigurations":444},{"removed":"critpt","score":0.003932008162573704,"rank":392,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0044112364579668275,"rank":393,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004511547381102348,"rank":392,"remainingConfigurations":444},{"removed":"gdpval","score":0.0044182224008393915,"rank":393,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004664463578985027,"rank":388,"remainingConfigurations":444},{"removed":"gpqa","score":0.0044361248582672,"rank":393,"remainingConfigurations":444},{"removed":"harvey","score":0.0043520750534294,"rank":393,"remainingConfigurations":444},{"removed":"hle","score":0.004995227358161976,"rank":394,"remainingConfigurations":444},{"removed":"ifbench","score":0.004207637221422223,"rank":393,"remainingConfigurations":444},{"removed":"itbench","score":0.004366753821767061,"rank":393,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004414778843342416,"rank":394,"remainingConfigurations":444},{"removed":"math500","score":0.004458287113796551,"rank":390,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.005040015276854772,"rank":386,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004847670016325631,"rank":392,"remainingConfigurations":444},{"removed":"omniscience","score":0.003980208406552343,"rank":391,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004041840150373789,"rank":391,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00447760994388705,"rank":393,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004346949206049131,"rank":393,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005645318854006417,"rank":392,"remainingConfigurations":444},{"removed":"deepswe","score":0.003426727400636097,"rank":393,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0044030094219360515,"rank":393,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00432123055308467,"rank":393,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004285449811557914,"rank":393,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004334860221370134,"rank":393,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004346835985623922,"rank":393,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004399463528341156,"rank":393,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004381451112322477,"rank":393,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004407588517369022,"rank":393,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004343925438618391,"rank":393,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004480261169168062,"rank":393,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004401468537220995,"rank":393,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004300864029538523,"rank":393,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0043677362049608605,"rank":393,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004516113811429109,"rank":393,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004546212118816684,"rank":393,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004412043186843545,"rank":393,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0040852513895823775,"rank":393,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004657554988069861,"rank":393,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004383149041484021,"rank":393,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004382442799896914,"rank":393,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004384082285801847,"rank":393,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004391171430337979,"rank":393,"remainingConfigurations":444},{"removed":"vibe-code","score":0.004368908471056553,"rank":393,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0043875440745894225,"rank":393,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-small-2506--effort-non-reasoning":{"score":0.004160710637181107,"rank":394,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0055556213061102415,"rank":393,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0032378256160238545,"rank":394,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004111817498330344,"rank":394,"remainingConfigurations":444},{"removed":"Scale","score":0.004966474258028786,"rank":394,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004113424189044178,"rank":394,"remainingConfigurations":444},{"removed":"Cognition","score":0.004049294170328102,"rank":394,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004358935198898714,"rank":393,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004301786628811525,"rank":394,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004272985959471897,"rank":380,"remainingConfigurations":431},{"removed":"Vals AI","score":0.004001477456456218,"rank":393,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0041587979379001,"rank":394,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.004018599417059169,"rank":394,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004152989510866244,"rank":394,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004160710637181107,"rank":394,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004195874281356821,"rank":394,"remainingConfigurations":444},{"removed":"All provider reports","score":0.004045053989798999,"rank":394,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004205612153464773,"rank":394,"remainingConfigurations":444},{"removed":"briefcase","score":0.0041161563801476436,"rank":394,"remainingConfigurations":444},{"removed":"aime","score":0.004252276684860067,"rank":390,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004239117614339322,"rank":394,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004054222251913041,"rank":395,"remainingConfigurations":444},{"removed":"automationbench","score":0.004115774729563888,"rank":394,"remainingConfigurations":444},{"removed":"critpt","score":0.00374195274781869,"rank":394,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004169691430213402,"rank":394,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004334999047890863,"rank":394,"remainingConfigurations":444},{"removed":"gdpval","score":0.004244784876174461,"rank":394,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0041974877013979455,"rank":394,"remainingConfigurations":444},{"removed":"gpqa","score":0.004218358619547869,"rank":395,"remainingConfigurations":444},{"removed":"harvey","score":0.004113898107764553,"rank":394,"remainingConfigurations":444},{"removed":"hle","score":0.004723876242992738,"rank":397,"remainingConfigurations":444},{"removed":"ifbench","score":0.0039600778759056226,"rank":396,"remainingConfigurations":444},{"removed":"itbench","score":0.004128406692406099,"rank":394,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00448744096644673,"rank":391,"remainingConfigurations":444},{"removed":"math500","score":0.004205226592925121,"rank":395,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0045970961299752235,"rank":394,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0046050369445691484,"rank":394,"remainingConfigurations":444},{"removed":"omniscience","score":0.0035545714295948205,"rank":395,"remainingConfigurations":444},{"removed":"tau-bench","score":0.003732425307186795,"rank":394,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004232152980267982,"rank":394,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.003966081201364341,"rank":396,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005333815368470266,"rank":393,"remainingConfigurations":444},{"removed":"deepswe","score":0.003240136049348037,"rank":394,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004161836590135356,"rank":394,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0040853726215481405,"rank":394,"remainingConfigurations":444},{"removed":"frontiercode","score":0.004049294170328102,"rank":394,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004097463221626195,"rank":394,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004108668401816877,"rank":394,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004158499108977491,"rank":394,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0041418293632664,"rank":394,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004166111377702747,"rank":394,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00410607602714888,"rank":394,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004234989885628303,"rank":394,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004160315953025909,"rank":394,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.004065164774006129,"rank":394,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004128487108889109,"rank":394,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004268733236457346,"rank":394,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004301786628811525,"rank":394,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00416899291955686,"rank":394,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0038689543476393244,"rank":394,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004402714767403418,"rank":394,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004143051866001176,"rank":394,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004142389296072064,"rank":394,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00414391168878943,"rank":394,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004150665335077277,"rank":394,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0041295868393368155,"rank":394,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004147208528382852,"rank":394,"remainingConfigurations":444}],"sharedOrderConflicts":0},"llama-4-scout--effort-non-reasoning":{"score":0.004086444650076497,"rank":395,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005452942410809709,"rank":394,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0031800416267010515,"rank":395,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.004038463765258013,"rank":395,"remainingConfigurations":444},{"removed":"Scale","score":0.0048747178144825124,"rank":395,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.004040031069352933,"rank":395,"remainingConfigurations":444},{"removed":"Cognition","score":0.003977180451004532,"rank":395,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004281263633309396,"rank":394,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0042221378059779215,"rank":395,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004189073607577242,"rank":381,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003930193129390889,"rank":394,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00408456590199572,"rank":395,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00394685442601559,"rank":395,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0040788608093772355,"rank":395,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004086444650076497,"rank":395,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004120983533197976,"rank":395,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003972838872666693,"rank":395,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0041306067911517875,"rank":395,"remainingConfigurations":444},{"removed":"briefcase","score":0.0040408005676487654,"rank":395,"remainingConfigurations":444},{"removed":"aime","score":0.0045021609128587615,"rank":386,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004162953750774458,"rank":395,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.003887976059169868,"rank":398,"remainingConfigurations":444},{"removed":"automationbench","score":0.004115691902071094,"rank":395,"remainingConfigurations":444},{"removed":"critpt","score":0.0036683397020137666,"rank":395,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004095062201215228,"rank":395,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004255875486863565,"rank":395,"remainingConfigurations":444},{"removed":"gdpval","score":0.004139633728168729,"rank":395,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004044063920938705,"rank":397,"remainingConfigurations":444},{"removed":"gpqa","score":0.003980365101127184,"rank":398,"remainingConfigurations":444},{"removed":"harvey","score":0.00404049350984536,"rank":395,"remainingConfigurations":444},{"removed":"hle","score":0.004799422134832115,"rank":395,"remainingConfigurations":444},{"removed":"ifbench","score":0.0036517516413408246,"rank":400,"remainingConfigurations":444},{"removed":"itbench","score":0.004054490840373163,"rank":395,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004323115595942982,"rank":395,"remainingConfigurations":444},{"removed":"math500","score":0.004328567728284833,"rank":391,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004088920949508978,"rank":399,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004385908349476838,"rank":397,"remainingConfigurations":444},{"removed":"omniscience","score":0.0034574207075516593,"rank":398,"remainingConfigurations":444},{"removed":"tau-bench","score":0.004028475069784184,"rank":392,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004156649927310314,"rank":395,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00407439062514987,"rank":395,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005235143034093433,"rank":394,"remainingConfigurations":444},{"removed":"deepswe","score":0.0031823108763762813,"rank":395,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.004087550582198217,"rank":395,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.004012438023080725,"rank":395,"remainingConfigurations":444},{"removed":"frontiercode","score":0.003977180451004532,"rank":395,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.004024320492621022,"rank":395,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.004035327459688678,"rank":395,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004084272907269373,"rank":395,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.004067904431852509,"rank":395,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00409175055322429,"rank":395,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.004032774174689187,"rank":395,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004159407626097525,"rank":395,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004086059082118201,"rank":395,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.003992591875205969,"rank":395,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004054791015263462,"rank":395,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004192557266707179,"rank":395,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0042221378059779215,"rank":395,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004094604624457093,"rank":395,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003797494867054581,"rank":395,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004324195081866691,"rank":395,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004069098519612883,"rank":395,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004068447582680462,"rank":395,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004069943520702858,"rank":395,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004076576388967491,"rank":395,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0040558718794649895,"rank":395,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.00407318163273632,"rank":395,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-8b-instruct--effort-non-reasoning":{"score":0.004041700701005101,"rank":396,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005407618592176997,"rank":395,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0031445984912366258,"rank":396,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003994240693174768,"rank":396,"remainingConfigurations":444},{"removed":"Scale","score":0.004820416922237365,"rank":396,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003995359947001905,"rank":396,"remainingConfigurations":444},{"removed":"Cognition","score":0.003936185323865846,"rank":396,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004231585887999461,"rank":395,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004175736748770115,"rank":396,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004120129864947997,"rank":382,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0038825951805431676,"rank":395,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00403984649267324,"rank":396,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0039038120306199298,"rank":396,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.004034210687362332,"rank":396,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.004041700701005101,"rank":396,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.004075895500958202,"rank":396,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003929556416059411,"rank":396,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.004086216470445025,"rank":396,"remainingConfigurations":444},{"removed":"briefcase","score":0.004014711342941935,"rank":396,"remainingConfigurations":444},{"removed":"aime","score":0.00411141534046689,"rank":394,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004115902351248155,"rank":396,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0039827292550384885,"rank":397,"remainingConfigurations":444},{"removed":"automationbench","score":0.004019633599227934,"rank":396,"remainingConfigurations":444},{"removed":"critpt","score":0.0035682906738087185,"rank":396,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.004051880416729062,"rank":396,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004147564083425121,"rank":396,"remainingConfigurations":444},{"removed":"gdpval","score":0.004062031861561487,"rank":396,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004103787720759787,"rank":396,"remainingConfigurations":444},{"removed":"gpqa","score":0.0042787872177985666,"rank":394,"remainingConfigurations":444},{"removed":"harvey","score":0.0039967541789581095,"rank":396,"remainingConfigurations":444},{"removed":"hle","score":0.005045873777404876,"rank":393,"remainingConfigurations":444},{"removed":"ifbench","score":0.0039601049413184215,"rank":395,"remainingConfigurations":444},{"removed":"itbench","score":0.004010138610408515,"rank":396,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004173598688531183,"rank":396,"remainingConfigurations":444},{"removed":"math500","score":0.004096771077254905,"rank":396,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0044601018269153,"rank":396,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004493306488886045,"rank":396,"remainingConfigurations":444},{"removed":"omniscience","score":0.0028524337153722347,"rank":407,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0036005682875188023,"rank":399,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00411241334142749,"rank":396,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.004169792794332864,"rank":394,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005189405520411794,"rank":395,"remainingConfigurations":444},{"removed":"deepswe","score":0.003146830343724101,"rank":396,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0040427888605061866,"rank":396,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003967745601931604,"rank":396,"remainingConfigurations":444},{"removed":"frontiercode","score":0.003936185323865846,"rank":396,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.003980247087876408,"rank":396,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003991196033041558,"rank":396,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.004039539098571159,"rank":396,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0040229985814077985,"rank":396,"remainingConfigurations":444},{"removed":"livebench-math","score":0.004046994772167652,"rank":396,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0039884996749571635,"rank":396,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004113775090167586,"rank":396,"remainingConfigurations":444},{"removed":"livebench-data","score":0.004041381603424247,"rank":396,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.003948934550720377,"rank":396,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.004010375707200215,"rank":396,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.00414671781692745,"rank":396,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004175736748770115,"rank":396,"remainingConfigurations":444},{"removed":"frontiermath","score":0.004051341938235603,"rank":396,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003750990604542216,"rank":396,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004276767960995332,"rank":396,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.004024543605346286,"rank":396,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.004023891082007027,"rank":396,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.004025402932725123,"rank":396,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.004031906771245789,"rank":396,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0040114539867918235,"rank":396,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.004028584298603302,"rank":396,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-30b-a3b--effort-non-reasoning":{"score":0.003960874242405142,"rank":397,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.004240569200256979,"rank":196,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0053363140667770925,"rank":397,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0031037024614101612,"rank":397,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003918940240276529,"rank":397,"remainingConfigurations":444},{"removed":"Scale","score":0.0047202041612328886,"rank":397,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003925758011926909,"rank":397,"remainingConfigurations":444},{"removed":"Cognition","score":0.0039045893427849462,"rank":397,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004135512613031885,"rank":396,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.004085202169790864,"rank":397,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0036237408490343154,"rank":389,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003820738900678876,"rank":396,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003959127466329816,"rank":397,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003827532586061107,"rank":397,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.003953960758682577,"rank":397,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003960874242405142,"rank":397,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003993754938233143,"rank":397,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0038526376821433543,"rank":397,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0040013948905645354,"rank":397,"remainingConfigurations":444},{"removed":"briefcase","score":0.003934568653171257,"rank":397,"remainingConfigurations":444},{"removed":"aime","score":0.003922439506859149,"rank":399,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004030589230815829,"rank":397,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.004120017814696473,"rank":394,"remainingConfigurations":444},{"removed":"automationbench","score":0.0039387857402240645,"rank":397,"remainingConfigurations":444},{"removed":"critpt","score":0.0035213142791490413,"rank":397,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.00396939935924253,"rank":397,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.004051395214120515,"rank":397,"remainingConfigurations":444},{"removed":"gdpval","score":0.00396441336901028,"rank":398,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0040221376017105836,"rank":398,"remainingConfigurations":444},{"removed":"gpqa","score":0.0038929491607546177,"rank":399,"remainingConfigurations":444},{"removed":"harvey","score":0.0039143176181257585,"rank":397,"remainingConfigurations":444},{"removed":"hle","score":0.004354581512336737,"rank":400,"remainingConfigurations":444},{"removed":"ifbench","score":0.003893527751637978,"rank":398,"remainingConfigurations":444},{"removed":"itbench","score":0.0039305908928384875,"rank":397,"remainingConfigurations":444},{"removed":"livecodebench","score":0.004086033289228956,"rank":398,"remainingConfigurations":444},{"removed":"math500","score":0.00402621797462004,"rank":397,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004167715277377762,"rank":397,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0043477249125415994,"rank":400,"remainingConfigurations":444},{"removed":"omniscience","score":0.0035318691301888775,"rank":396,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0036833226243547985,"rank":397,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004024721265573495,"rank":397,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00375635425256274,"rank":400,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00511768480133488,"rank":396,"remainingConfigurations":444},{"removed":"deepswe","score":0.0031060026485526505,"rank":397,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003961928345560557,"rank":397,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0038887868190215016,"rank":397,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0039045893427849462,"rank":397,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0039029646468120693,"rank":397,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003910693192812794,"rank":397,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.003958838924572415,"rank":397,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.003942424398348884,"rank":397,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00396745693392811,"rank":397,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003906754045899807,"rank":397,"remainingConfigurations":444},{"removed":"livebench-language","score":0.004031076718587154,"rank":397,"remainingConfigurations":444},{"removed":"livebench-data","score":0.003961094938582784,"rank":397,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.003870795769693219,"rank":397,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003930018161750657,"rank":397,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004063436070807236,"rank":397,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.004085202169790864,"rank":397,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003984416543084345,"rank":397,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003577867358906268,"rank":399,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004226065213644447,"rank":397,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0039439054377795124,"rank":397,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.003943742386102914,"rank":397,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003944640686815833,"rank":397,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003951507097223119,"rank":397,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0039316274677114816,"rank":397,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.003947783519888388,"rank":397,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-2b--effort-reasoning":{"score":0.003941657235449699,"rank":398,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005339390977047268,"rank":396,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0030723670780637372,"rank":398,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0038990446572268567,"rank":398,"remainingConfigurations":444},{"removed":"Scale","score":0.00470542973261468,"rank":398,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003897284768900959,"rank":398,"remainingConfigurations":444},{"removed":"Cognition","score":0.003855085109950376,"rank":398,"remainingConfigurations":444},{"removed":"LiveBench","score":0.004130086136675571,"rank":397,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0040791464423342114,"rank":398,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004008322667154811,"rank":384,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0037890478170847126,"rank":397,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003939844416346749,"rank":398,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0038070674337684044,"rank":398,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.003934338710546791,"rank":398,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003941657235449699,"rank":398,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003975096785377281,"rank":398,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0038322442362377605,"rank":398,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003986759908464085,"rank":398,"remainingConfigurations":444},{"removed":"briefcase","score":0.003918929555696296,"rank":398,"remainingConfigurations":444},{"removed":"aime","score":0.0038855425965133535,"rank":400,"remainingConfigurations":444},{"removed":"apex-agents","score":0.004016815337956698,"rank":398,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.003761122417555354,"rank":399,"remainingConfigurations":444},{"removed":"automationbench","score":0.003922839620931678,"rank":398,"remainingConfigurations":444},{"removed":"critpt","score":0.0034219389469380634,"rank":399,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003954573416289267,"rank":398,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00404558697884354,"rank":398,"remainingConfigurations":444},{"removed":"gdpval","score":0.003965512324773084,"rank":397,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0039994141222939,"rank":399,"remainingConfigurations":444},{"removed":"gpqa","score":0.0041806039595971055,"rank":396,"remainingConfigurations":444},{"removed":"harvey","score":0.003898622486353315,"rank":398,"remainingConfigurations":444},{"removed":"hle","score":0.00516744523594716,"rank":392,"remainingConfigurations":444},{"removed":"ifbench","score":0.003971265552601002,"rank":394,"remainingConfigurations":444},{"removed":"itbench","score":0.003914023710426232,"rank":398,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003973247701049268,"rank":399,"remainingConfigurations":444},{"removed":"math500","score":0.003984027796698464,"rank":398,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004141706717252573,"rank":398,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004597930599690109,"rank":395,"remainingConfigurations":444},{"removed":"omniscience","score":0.0038364245233435935,"rank":392,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0026533211784688267,"rank":412,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.004014663724479363,"rank":398,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.003951104155221614,"rank":397,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005111310082179321,"rank":397,"remainingConfigurations":444},{"removed":"deepswe","score":0.003074539872037752,"rank":398,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.00394271874199167,"rank":398,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00387055755032611,"rank":398,"remainingConfigurations":444},{"removed":"frontiercode","score":0.003855085109950376,"rank":398,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.003882023022486999,"rank":398,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.00389263455409772,"rank":398,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.003939548387777826,"rank":398,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.003923442532733415,"rank":398,"remainingConfigurations":444},{"removed":"livebench-math","score":0.003946790653180793,"rank":398,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0038897534028049245,"rank":398,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0040119855355421645,"rank":398,"remainingConfigurations":444},{"removed":"livebench-data","score":0.00394138191020505,"rank":398,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.003851141859756968,"rank":398,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003911088738662417,"rank":398,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004044129262291266,"rank":398,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0040791464423342114,"rank":398,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003952678372003345,"rank":398,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00366023819355857,"rank":397,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004170211325940876,"rank":398,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003924933661578017,"rank":398,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.003924286619248643,"rank":398,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003925752229601706,"rank":398,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0039321035975229054,"rank":398,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00391214674714683,"rank":398,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0039288655743891085,"rank":398,"remainingConfigurations":444}],"sharedOrderConflicts":1},"ministral-3-8b--effort-non-reasoning":{"score":0.003906508394625741,"rank":399,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.005214577306902721,"rank":398,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0030398268920161114,"rank":399,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003861113732068023,"rank":399,"remainingConfigurations":444},{"removed":"Scale","score":0.00466048680960673,"rank":399,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003862123788357093,"rank":399,"remainingConfigurations":444},{"removed":"Cognition","score":0.0038017793331463472,"rank":399,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0040933365002832935,"rank":398,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00404115988513707,"rank":399,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.004022456386511341,"rank":383,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0037580449040046974,"rank":398,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003904710974531151,"rank":399,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0037729918318443662,"rank":399,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0038992533183050946,"rank":399,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003906508394625741,"rank":399,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003939536647462857,"rank":399,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0037978358024220106,"rank":399,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003948824162082329,"rank":399,"remainingConfigurations":444},{"removed":"briefcase","score":0.003717677682442738,"rank":400,"remainingConfigurations":444},{"removed":"aime","score":0.003847784558058708,"rank":401,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003980860807419609,"rank":399,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.003722574601321539,"rank":401,"remainingConfigurations":444},{"removed":"automationbench","score":0.0037682942754822192,"rank":400,"remainingConfigurations":444},{"removed":"critpt","score":0.0034888367252103075,"rank":398,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003915231595056812,"rank":399,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003960331922966204,"rank":399,"remainingConfigurations":444},{"removed":"gdpval","score":0.0037461994134230293,"rank":400,"remainingConfigurations":444},{"removed":"gmmlu","score":0.004130975921564926,"rank":395,"remainingConfigurations":444},{"removed":"gpqa","score":0.0040108688724478985,"rank":397,"remainingConfigurations":444},{"removed":"harvey","score":0.003862592840183762,"rank":399,"remainingConfigurations":444},{"removed":"hle","score":0.004444202060988628,"rank":399,"remainingConfigurations":444},{"removed":"ifbench","score":0.0039237093548763835,"rank":397,"remainingConfigurations":444},{"removed":"itbench","score":0.0038764216759699936,"rank":399,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0041073323003402214,"rank":397,"remainingConfigurations":444},{"removed":"math500","score":0.003961487380569689,"rank":400,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004464453930675727,"rank":395,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0043545639745816616,"rank":398,"remainingConfigurations":444},{"removed":"omniscience","score":0.003449508064552716,"rank":399,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0036476886674758706,"rank":398,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003973652224435013,"rank":399,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.003779780815559603,"rank":399,"remainingConfigurations":444},{"removed":"arc-agi","score":0.005006248806936519,"rank":398,"remainingConfigurations":444},{"removed":"deepswe","score":0.0030419964434125336,"rank":399,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003907566114192432,"rank":399,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003835902866857016,"rank":399,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0038017793331463472,"rank":399,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0038471228859078763,"rank":399,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003857629689952798,"rank":399,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0039044311741042426,"rank":399,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.003888802281241275,"rank":399,"remainingConfigurations":444},{"removed":"livebench-math","score":0.003911574665439598,"rank":399,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0038551886573964193,"rank":399,"remainingConfigurations":444},{"removed":"livebench-language","score":0.003976291335079134,"rank":399,"remainingConfigurations":444},{"removed":"livebench-data","score":0.003906143276847006,"rank":399,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0038167486879900677,"rank":399,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0038762353836685436,"rank":399,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.004007991093239681,"rank":399,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00404115988513707,"rank":399,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003914107520139778,"rank":399,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0036343194927428387,"rank":398,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0041336932568006276,"rank":399,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0038899227222641253,"rank":399,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.003889297096108869,"rank":399,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0038907266800571427,"rank":399,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0038970709054087587,"rank":399,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003877270064622867,"rank":399,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0038938259611486317,"rank":399,"remainingConfigurations":444}],"sharedOrderConflicts":0},"glm-4.5v--effort-non-reasoning":{"score":0.0037929905474901326,"rank":400,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0050855280271078504,"rank":399,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002953059554169754,"rank":400,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003749150676547267,"rank":400,"remainingConfigurations":444},{"removed":"Scale","score":0.004526557346496541,"rank":400,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0037494126009801234,"rank":400,"remainingConfigurations":444},{"removed":"Cognition","score":0.003698615713943794,"rank":400,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0039719409798788935,"rank":399,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.003919737949692681,"rank":400,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0039008499079896254,"rank":385,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003643257945321408,"rank":399,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003791248527263084,"rank":400,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003663526211045122,"rank":400,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0037859575397678866,"rank":400,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0037929905474901326,"rank":400,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0038251353402054965,"rank":400,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003687732274663663,"rank":400,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0038345758832876386,"rank":400,"remainingConfigurations":444},{"removed":"briefcase","score":0.0037733036268479125,"rank":399,"remainingConfigurations":444},{"removed":"aime","score":0.004195389182011309,"rank":393,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0038637640509232812,"rank":400,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00402940654133586,"rank":396,"remainingConfigurations":444},{"removed":"automationbench","score":0.003775636600932634,"rank":399,"remainingConfigurations":444},{"removed":"critpt","score":0.003326957511010059,"rank":400,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0038039758211522675,"rank":400,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0038938334929780895,"rank":400,"remainingConfigurations":444},{"removed":"gdpval","score":0.0038179574000870935,"rank":399,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0038520990754028835,"rank":400,"remainingConfigurations":444},{"removed":"gpqa","score":0.0036867374878210494,"rank":403,"remainingConfigurations":444},{"removed":"harvey","score":0.0037510447799795972,"rank":400,"remainingConfigurations":444},{"removed":"hle","score":0.004610843974275529,"rank":398,"remainingConfigurations":444},{"removed":"ifbench","score":0.0038688469367824407,"rank":399,"remainingConfigurations":444},{"removed":"itbench","score":0.003763843785935836,"rank":400,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0038074210559340175,"rank":400,"remainingConfigurations":444},{"removed":"math500","score":0.0038389533693743206,"rank":401,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0036899260624840995,"rank":405,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004350974700729686,"rank":399,"remainingConfigurations":444},{"removed":"omniscience","score":0.0028294374726347544,"rank":408,"remainingConfigurations":444},{"removed":"tau-bench","score":0.003693503267082896,"rank":396,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003861568407922724,"rank":400,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.003527770639675562,"rank":403,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004876205031351625,"rank":399,"remainingConfigurations":444},{"removed":"deepswe","score":0.0029551493821859142,"rank":400,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0037940114226712647,"rank":400,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0037235770223193487,"rank":400,"remainingConfigurations":444},{"removed":"frontiercode","score":0.003698615713943794,"rank":400,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0037354393384881088,"rank":400,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0037457254079059647,"rank":400,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0037909612578065598,"rank":400,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0037753908949983636,"rank":400,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0037979562626150876,"rank":400,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003743020052143241,"rank":400,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0038606526098878464,"rank":400,"remainingConfigurations":444},{"removed":"livebench-data","score":0.003792709513819694,"rank":400,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0037058897204081003,"rank":400,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003763574000941189,"rank":400,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.003891625327368168,"rank":400,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.003919737949692681,"rank":400,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003802985636966107,"rank":400,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.00352031707082184,"rank":400,"remainingConfigurations":444},{"removed":"simpleqa","score":0.004013549982001278,"rank":400,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003776883619527384,"rank":400,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0037762632674102747,"rank":400,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0037776975139344206,"rank":400,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003783782676688579,"rank":400,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0037645816182111775,"rank":400,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.003780678563169281,"rank":400,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-vl-4b-thinking--effort-reasoning":{"score":0.003669250867942845,"rank":401,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004912057067400238,"rank":400,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0028548048705384337,"rank":401,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0036263407285716657,"rank":401,"remainingConfigurations":444},{"removed":"Scale","score":0.004377221414056889,"rank":401,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0036272764795533576,"rank":401,"remainingConfigurations":444},{"removed":"Cognition","score":0.0035740850439815656,"rank":401,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00384212757004663,"rank":400,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0037915832106893005,"rank":401,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0037391330947707815,"rank":387,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003525257321441296,"rank":400,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0036675665240504807,"rank":401,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0035439914169327,"rank":401,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0036624483820840935,"rank":401,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003669250867942845,"rank":401,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0037003059806820816,"rank":401,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003567370898290795,"rank":401,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003709538389930269,"rank":401,"remainingConfigurations":444},{"removed":"briefcase","score":0.0036461736532936886,"rank":401,"remainingConfigurations":444},{"removed":"aime","score":0.003759531981039515,"rank":402,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003736736897663895,"rank":401,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0034861691236294334,"rank":405,"remainingConfigurations":444},{"removed":"automationbench","score":0.0036524770306926944,"rank":401,"remainingConfigurations":444},{"removed":"critpt","score":0.0031970263916505297,"rank":401,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003678514267907143,"rank":401,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003769067439490362,"rank":401,"remainingConfigurations":444},{"removed":"gdpval","score":0.0036902860105315974,"rank":401,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0037340376843522185,"rank":401,"remainingConfigurations":444},{"removed":"gpqa","score":0.003728752211885175,"rank":401,"remainingConfigurations":444},{"removed":"harvey","score":0.0036281059357203813,"rank":401,"remainingConfigurations":444},{"removed":"hle","score":0.004044251467247076,"rank":401,"remainingConfigurations":444},{"removed":"ifbench","score":0.0033264404407605526,"rank":403,"remainingConfigurations":444},{"removed":"itbench","score":0.003640857590610025,"rank":401,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003805920082944026,"rank":401,"remainingConfigurations":444},{"removed":"math500","score":0.0037319163890728022,"rank":402,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0039112607211584825,"rank":402,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003912811513377885,"rank":404,"remainingConfigurations":444},{"removed":"omniscience","score":0.0032114694919848784,"rank":401,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0036955766565732752,"rank":395,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0037331798238090367,"rank":401,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0038550274194129514,"rank":398,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0047134098004188675,"rank":400,"remainingConfigurations":444},{"removed":"deepswe","score":0.002856831833356671,"rank":401,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0036702393625296314,"rank":401,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0036020845713152848,"rank":401,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0035740850439815656,"rank":401,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.003613434088709729,"rank":401,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.00362338450617458,"rank":401,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0036672904680495103,"rank":401,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0036522769633017672,"rank":401,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00367406275328545,"rank":401,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0036209070457807156,"rank":401,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00373473068154651,"rank":401,"remainingConfigurations":444},{"removed":"livebench-data","score":0.003668967738161609,"rank":401,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00358497477338014,"rank":401,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0036407894989245854,"rank":401,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0037646696202265294,"rank":401,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0037915832106893005,"rank":401,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0036781074678249735,"rank":401,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0034050642865155398,"rank":401,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0038829458184577253,"rank":401,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003653663095760821,"rank":401,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0036530703768782695,"rank":401,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003654444881004894,"rank":401,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003660350682781121,"rank":401,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003641771390776429,"rank":401,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0036573344062985577,"rank":401,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-e2b-it--effort-reasoning":{"score":0.003579104872670886,"rank":402,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0048147488476525295,"rank":402,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0027894731311706683,"rank":402,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003538571667498776,"rank":402,"remainingConfigurations":444},{"removed":"Scale","score":0.004272518108626584,"rank":402,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0035393510983706554,"rank":402,"remainingConfigurations":444},{"removed":"Cognition","score":0.0034958620877345897,"rank":403,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0037511495735965904,"rank":401,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0037010949193956367,"rank":402,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0036404770285774686,"rank":388,"remainingConfigurations":431},{"removed":"Vals AI","score":0.00344243921113155,"rank":401,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0035774574173376406,"rank":402,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003456793595683492,"rank":402,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00357245587975929,"rank":402,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003579104872670886,"rank":402,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003609459084539274,"rank":402,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0034796411588633807,"rank":402,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003619866673153466,"rank":402,"remainingConfigurations":444},{"removed":"briefcase","score":0.0035518329529322244,"rank":402,"remainingConfigurations":444},{"removed":"aime","score":0.00355030776116437,"rank":405,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0036472327369649255,"rank":402,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0035011185919452026,"rank":404,"remainingConfigurations":444},{"removed":"automationbench","score":0.0035573043982229783,"rank":402,"remainingConfigurations":444},{"removed":"critpt","score":0.0030583992320379525,"rank":405,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003590427692658939,"rank":402,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003670072856084289,"rank":402,"remainingConfigurations":444},{"removed":"gdpval","score":0.0036708311344400726,"rank":402,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0036264559763297295,"rank":402,"remainingConfigurations":444},{"removed":"gpqa","score":0.0038181591242917572,"rank":400,"remainingConfigurations":444},{"removed":"harvey","score":0.0035403230214517637,"rank":402,"remainingConfigurations":444},{"removed":"hle","score":0.003841348175233959,"rank":403,"remainingConfigurations":444},{"removed":"ifbench","score":0.0030399016004249344,"rank":407,"remainingConfigurations":444},{"removed":"itbench","score":0.0035536244398345633,"rank":402,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0036221194591953554,"rank":402,"remainingConfigurations":444},{"removed":"math500","score":0.003644709201786559,"rank":403,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003786855538776403,"rank":404,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004010695750066473,"rank":402,"remainingConfigurations":444},{"removed":"omniscience","score":0.0034959796136386748,"rank":397,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0033927605729220174,"rank":401,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0036454963565203924,"rank":402,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.00369392060118365,"rank":402,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004610565494373908,"rank":402,"remainingConfigurations":444},{"removed":"deepswe","score":0.002791449497244723,"rank":402,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0035800700702669597,"rank":402,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00351457933439747,"rank":402,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0034958620877345897,"rank":403,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.003524945336429129,"rank":402,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003534561523014011,"rank":402,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0035771952051940827,"rank":402,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.003562627374691005,"rank":402,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0035837666166917744,"rank":402,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003531947387274493,"rank":402,"remainingConfigurations":444},{"removed":"livebench-language","score":0.003643021745444575,"rank":402,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0035788574381827604,"rank":402,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.003496849334775001,"rank":402,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0035513275439728012,"rank":402,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.003672215644359995,"rank":402,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0037010949193956367,"rank":402,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003589293223527691,"rank":402,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003323451441557202,"rank":402,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0037868934180545094,"rank":402,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003563908053920612,"rank":402,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0035633233168209304,"rank":402,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0035646476943128062,"rank":402,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0035704284715863746,"rank":402,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003552292254336529,"rank":402,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0035674810860926477,"rank":402,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-5-nano--effort-minimal":{"score":0.003495490351731011,"rank":403,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0021402630950877444,"rank":200,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00484947926973175,"rank":401,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002736842966810956,"rank":403,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003479813882502965,"rank":403,"remainingConfigurations":444},{"removed":"Scale","score":0.004171120573950999,"rank":403,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003458438001221868,"rank":403,"remainingConfigurations":444},{"removed":"Cognition","score":0.0035287961644140334,"rank":402,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0036595389016238562,"rank":402,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0036099119848360685,"rank":403,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0034368969079964806,"rank":393,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0033462129967539813,"rank":402,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003493917444718301,"rank":403,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003379081666958095,"rank":403,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0034893000833414287,"rank":403,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003495490351731011,"rank":403,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0035256915417134246,"rank":403,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0034022118091619345,"rank":403,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0035293561076164466,"rank":403,"remainingConfigurations":444},{"removed":"briefcase","score":0.0034740030574893113,"rank":403,"remainingConfigurations":444},{"removed":"aime","score":0.003499406049586219,"rank":406,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0035531737127702,"rank":403,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0033941537299994468,"rank":406,"remainingConfigurations":444},{"removed":"automationbench","score":0.0034770708615282937,"rank":403,"remainingConfigurations":444},{"removed":"critpt","score":0.0031752477747509305,"rank":402,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0035018449264532115,"rank":403,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003570766070136603,"rank":403,"remainingConfigurations":444},{"removed":"gdpval","score":0.003508215848929778,"rank":403,"remainingConfigurations":444},{"removed":"gmmlu","score":0.003537413696814188,"rank":404,"remainingConfigurations":444},{"removed":"gpqa","score":0.003622389871544456,"rank":404,"remainingConfigurations":444},{"removed":"harvey","score":0.003452834934267481,"rank":403,"remainingConfigurations":444},{"removed":"hle","score":0.004041573370595658,"rank":402,"remainingConfigurations":444},{"removed":"ifbench","score":0.0033868795879544293,"rank":402,"remainingConfigurations":444},{"removed":"itbench","score":0.003470888641059848,"rank":403,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0032654603808510495,"rank":406,"remainingConfigurations":444},{"removed":"math500","score":0.003540135790064187,"rank":404,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.004055433040753745,"rank":400,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.004041322626020439,"rank":401,"remainingConfigurations":444},{"removed":"omniscience","score":0.003094070748455857,"rank":403,"remainingConfigurations":444},{"removed":"tau-bench","score":0.003245175726277918,"rank":403,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0035480048696274447,"rank":403,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.003287999239522449,"rank":407,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004643856976596691,"rank":401,"remainingConfigurations":444},{"removed":"deepswe","score":0.002738570292910544,"rank":403,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003496393795196982,"rank":403,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003432528707476445,"rank":403,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0035287961644140334,"rank":402,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0034428790029531775,"rank":403,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003452980250953419,"rank":403,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0034937288495986486,"rank":403,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0034788986350834487,"rank":403,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0035002676695907926,"rank":403,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0034497588276593306,"rank":403,"remainingConfigurations":444},{"removed":"livebench-language","score":0.003557053505824824,"rank":403,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0034943154333004814,"rank":403,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0034153187245406654,"rank":403,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003468844880392219,"rank":403,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0035868930926897763,"rank":403,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0036099119848360685,"rank":403,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0035148324597143094,"rank":403,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003164131837261469,"rank":404,"remainingConfigurations":444},{"removed":"simpleqa","score":0.003696196342607812,"rank":403,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003480408308617579,"rank":403,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.003479249369444319,"rank":403,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003482701694242712,"rank":403,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0034859315202103356,"rank":403,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0034685235366606177,"rank":403,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.003484633853116635,"rank":403,"remainingConfigurations":444}],"sharedOrderConflicts":0},"exaone-4.0-1.2b--effort-reasoning":{"score":0.0034161072242841367,"rank":404,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004594469348607639,"rank":403,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002659261936271994,"rank":404,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003376677820271409,"rank":404,"remainingConfigurations":444},{"removed":"Scale","score":0.004077284812891298,"rank":404,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.003376716162392371,"rank":404,"remainingConfigurations":444},{"removed":"Cognition","score":0.0033318816952813287,"rank":405,"remainingConfigurations":444},{"removed":"LiveBench","score":0.003577452241779793,"rank":403,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0035331750312554058,"rank":404,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0034507326454368513,"rank":391,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003281548490195785,"rank":403,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.003414537619202124,"rank":404,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003299441329659631,"rank":404,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.003409773401136729,"rank":404,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0034161072242841367,"rank":404,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0034450547045725994,"rank":404,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003321239002050716,"rank":404,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0034533224671040607,"rank":404,"remainingConfigurations":444},{"removed":"briefcase","score":0.003401188457513117,"rank":404,"remainingConfigurations":444},{"removed":"aime","score":0.002917228463831748,"rank":411,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003479549216722485,"rank":404,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.003626812712374581,"rank":402,"remainingConfigurations":444},{"removed":"automationbench","score":0.0034027699242239182,"rank":404,"remainingConfigurations":444},{"removed":"critpt","score":0.0029268602004412256,"rank":406,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0034248421118735204,"rank":404,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003509476073483036,"rank":404,"remainingConfigurations":444},{"removed":"gdpval","score":0.0034380028403624917,"rank":404,"remainingConfigurations":444},{"removed":"gmmlu","score":0.003472037128980729,"rank":405,"remainingConfigurations":444},{"removed":"gpqa","score":0.0034061796046323685,"rank":406,"remainingConfigurations":444},{"removed":"harvey","score":0.003378012802333312,"rank":404,"remainingConfigurations":444},{"removed":"hle","score":0.0034002348946524995,"rank":411,"remainingConfigurations":444},{"removed":"ifbench","score":0.0036376324576873867,"rank":401,"remainingConfigurations":444},{"removed":"itbench","score":0.0033898545887118387,"rank":404,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0028819730076673038,"rank":411,"remainingConfigurations":444},{"removed":"math500","score":0.003468984447513403,"rank":405,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003999724096650817,"rank":401,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003766833746743671,"rank":405,"remainingConfigurations":444},{"removed":"omniscience","score":0.003193217072464232,"rank":402,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0034073577941829748,"rank":400,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003476987749312563,"rank":404,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0037433872001575875,"rank":401,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004405816669203874,"rank":403,"remainingConfigurations":444},{"removed":"deepswe","score":0.002661146516954095,"rank":404,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0034170274964955504,"rank":404,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0033535730697572363,"rank":404,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0033318816952813287,"rank":405,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0033642243603559884,"rank":404,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003373499674883037,"rank":404,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0034142820094417072,"rank":404,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0034002651341804736,"rank":404,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0034205864487210466,"rank":404,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003371051927637651,"rank":404,"remainingConfigurations":444},{"removed":"livebench-language","score":0.003477091555069738,"rank":404,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0034158669576473885,"rank":404,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0033376062905217142,"rank":404,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003389589079945753,"rank":404,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0035050168022690256,"rank":404,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0035331750312554058,"rank":404,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003425663282054913,"rank":404,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0031704905159009346,"rank":403,"remainingConfigurations":444},{"removed":"simpleqa","score":0.003615120887617583,"rank":404,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0034015885535001017,"rank":404,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0034010323547596106,"rank":404,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003402320913563022,"rank":404,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003407809285764977,"rank":404,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003390504435630727,"rank":404,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.003405008933591295,"rank":404,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-4-e2b-it--effort-non-reasoning":{"score":0.003397569727275427,"rank":405,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00457009017353288,"rank":405,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0026467540346071616,"rank":406,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00335887491142531,"rank":405,"remainingConfigurations":444},{"removed":"Scale","score":0.0040567307528464385,"rank":405,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0033589446456575097,"rank":405,"remainingConfigurations":444},{"removed":"Cognition","score":0.003321838193710222,"rank":406,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0035595013324604802,"rank":404,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.003513694193938852,"rank":405,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0034507165876618844,"rank":392,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0032651276139006986,"rank":404,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0033960068525897996,"rank":405,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003281483348957887,"rank":405,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0033912597233692813,"rank":405,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003397569727275427,"rank":405,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0034264037145683643,"rank":405,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0033031926181409693,"rank":405,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0034357050405312596,"rank":405,"remainingConfigurations":444},{"removed":"briefcase","score":0.003380479302734621,"rank":405,"remainingConfigurations":444},{"removed":"aime","score":0.0033670251912840433,"rank":408,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0034616669425397047,"rank":405,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0033034983588954344,"rank":407,"remainingConfigurations":444},{"removed":"automationbench","score":0.0033825765047818084,"rank":405,"remainingConfigurations":444},{"removed":"critpt","score":0.0028310326614431236,"rank":408,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0034078597486076924,"rank":405,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003489395147083733,"rank":405,"remainingConfigurations":444},{"removed":"gdpval","score":0.003416029599640821,"rank":406,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0034434227741798238,"rank":407,"remainingConfigurations":444},{"removed":"gpqa","score":0.003712627734789794,"rank":402,"remainingConfigurations":444},{"removed":"harvey","score":0.003360263145925772,"rank":405,"remainingConfigurations":444},{"removed":"hle","score":0.0035977335224759138,"rank":408,"remainingConfigurations":444},{"removed":"ifbench","score":0.0030440003761619525,"rank":406,"remainingConfigurations":444},{"removed":"itbench","score":0.003372976168022221,"rank":405,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003438298535347635,"rank":404,"remainingConfigurations":444},{"removed":"math500","score":0.003463205386001779,"rank":406,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0035947489364944597,"rank":407,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0039826916473358915,"rank":403,"remainingConfigurations":444},{"removed":"omniscience","score":0.003245451152716747,"rank":400,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0031105737580809137,"rank":406,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003460055273177866,"rank":405,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0034674965554969237,"rank":404,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004373711161145063,"rank":405,"remainingConfigurations":444},{"removed":"deepswe","score":0.0026486262493891975,"rank":406,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003398484723782085,"rank":405,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003335867770478653,"rank":405,"remainingConfigurations":444},{"removed":"frontiercode","score":0.003321838193710222,"rank":406,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0033460652368413734,"rank":405,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003355278957047202,"rank":405,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0033957506366033377,"rank":405,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0033818223024703995,"rank":405,"remainingConfigurations":444},{"removed":"livebench-math","score":0.003402009271319046,"rank":405,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003352764245080043,"rank":405,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0034582374483710693,"rank":405,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0033973360534078237,"rank":405,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0033194828932921836,"rank":405,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0033711929233775505,"rank":405,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0034860059200454156,"rank":405,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.003513694193938852,"rank":405,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0034088877198355377,"rank":405,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0031548378164885133,"rank":405,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0035949783300398015,"rank":406,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003383136980012962,"rank":405,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0033825766443679943,"rank":405,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003383853951959203,"rank":405,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003389316015798884,"rank":405,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003372104159471074,"rank":405,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.00338653245421975,"rank":405,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-4b--effort-reasoning":{"score":0.003391309614391691,"rank":406,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004550438886663747,"rank":406,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002639195336394038,"rank":407,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003351813415038708,"rank":406,"remainingConfigurations":444},{"removed":"Scale","score":0.0040468502131757655,"rank":406,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0033519775739095713,"rank":406,"remainingConfigurations":444},{"removed":"Cognition","score":0.0033060580777040664,"rank":407,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0035504422987193613,"rank":405,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.003507877887759987,"rank":406,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0034832574075592086,"rank":390,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0032571382289691146,"rank":406,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00338975286195492,"rank":406,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0032755005127431893,"rank":406,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0033850256586133005,"rank":406,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003391309614391691,"rank":406,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0034200231791381673,"rank":406,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003297122458976237,"rank":406,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003427830574309782,"rank":406,"remainingConfigurations":444},{"removed":"briefcase","score":0.0033724078713884124,"rank":406,"remainingConfigurations":444},{"removed":"aime","score":0.0036294485232731305,"rank":404,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0034537792846202494,"rank":406,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.003725846157118653,"rank":400,"remainingConfigurations":444},{"removed":"automationbench","score":0.003376820251243867,"rank":406,"remainingConfigurations":444},{"removed":"critpt","score":0.0031044745197203838,"rank":403,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0033988611156629636,"rank":406,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0034820886458761025,"rank":406,"remainingConfigurations":444},{"removed":"gdpval","score":0.0034249017193838903,"rank":405,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0034501254372435435,"rank":406,"remainingConfigurations":444},{"removed":"gpqa","score":0.0033412310725477756,"rank":407,"remainingConfigurations":444},{"removed":"harvey","score":0.003352893148977081,"rank":406,"remainingConfigurations":444},{"removed":"hle","score":0.003779483022191389,"rank":405,"remainingConfigurations":444},{"removed":"ifbench","score":0.0032539105840821126,"rank":405,"remainingConfigurations":444},{"removed":"itbench","score":0.003364694449693666,"rank":406,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0031539422607740728,"rank":409,"remainingConfigurations":444},{"removed":"math500","score":0.00303294383777962,"rank":411,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00361114106799558,"rank":406,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0037547995005468514,"rank":406,"remainingConfigurations":444},{"removed":"omniscience","score":0.002942995187594694,"rank":405,"remainingConfigurations":444},{"removed":"tau-bench","score":0.00332105489320402,"rank":402,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0034502152640547862,"rank":406,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0034165885946174906,"rank":405,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004365402427923995,"rank":406,"remainingConfigurations":444},{"removed":"deepswe","score":0.0026410682019971116,"rank":407,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0033922232282490214,"rank":406,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0033290122998881027,"rank":406,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0033060580777040664,"rank":407,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.003339773530647825,"rank":406,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003348996149159802,"rank":406,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0033894995552162343,"rank":406,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.003375574940166774,"rank":406,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0033957671483554504,"rank":406,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.003346580171023695,"rank":406,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0034518495029220338,"rank":406,"remainingConfigurations":444},{"removed":"livebench-data","score":0.003391061469021503,"rank":406,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0033133839580486613,"rank":406,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003364986908046753,"rank":406,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0034795642757439594,"rank":406,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.003507877887759987,"rank":406,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003399514591713854,"rank":407,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003146763179116324,"rank":406,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0035891083926669425,"rank":407,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.003376892248146838,"rank":406,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0033763442434210124,"rank":406,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0033776231364598,"rank":406,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003383073193550929,"rank":406,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003365895724608424,"rank":406,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0033802899049443455,"rank":406,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-32b--effort-non-reasoning":{"score":0.0033804165075937806,"rank":407,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.00450874961641735,"rank":195,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004570276525282948,"rank":404,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002652648843866484,"rank":405,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003345052585229199,"rank":407,"remainingConfigurations":444},{"removed":"Scale","score":0.004029997019802643,"rank":407,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0033516188024580013,"rank":407,"remainingConfigurations":444},{"removed":"Cognition","score":0.0033375256115418615,"rank":404,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0035302333369905264,"rank":406,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0034893520409479354,"rank":407,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002745930233822738,"rank":402,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003263726418487473,"rank":405,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0033789258324073055,"rank":407,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003266543532481866,"rank":407,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0033745214687079263,"rank":407,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0033804165075937806,"rank":407,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003408490590333031,"rank":407,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003287986098457553,"rank":407,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0034147983940397957,"rank":407,"remainingConfigurations":444},{"removed":"briefcase","score":0.003357845299513196,"rank":407,"remainingConfigurations":444},{"removed":"aime","score":0.004229834736236156,"rank":391,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003439992750460368,"rank":407,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0035176847921137427,"rank":403,"remainingConfigurations":444},{"removed":"automationbench","score":0.0033607255554789005,"rank":407,"remainingConfigurations":444},{"removed":"critpt","score":0.003078877064434483,"rank":404,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0033873088824149266,"rank":407,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003455731108895832,"rank":407,"remainingConfigurations":444},{"removed":"gdpval","score":0.003383238850971594,"rank":407,"remainingConfigurations":444},{"removed":"gmmlu","score":0.003429540373685982,"rank":408,"remainingConfigurations":444},{"removed":"gpqa","score":0.0024715846715979233,"rank":419,"remainingConfigurations":444},{"removed":"harvey","score":0.0033405247149575767,"rank":407,"remainingConfigurations":444},{"removed":"hle","score":0.003801230170550445,"rank":404,"remainingConfigurations":444},{"removed":"ifbench","score":0.003310112641014299,"rank":404,"remainingConfigurations":444},{"removed":"itbench","score":0.003354490787131395,"rank":407,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003567545121182888,"rank":403,"remainingConfigurations":444},{"removed":"math500","score":0.0033519019468625302,"rank":408,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003419583103386826,"rank":410,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0037067480220319853,"rank":407,"remainingConfigurations":444},{"removed":"omniscience","score":0.002970590610846778,"rank":404,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0031495239282674117,"rank":404,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003434873502758515,"rank":407,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0033728290748143304,"rank":406,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004380576123431889,"rank":404,"remainingConfigurations":444},{"removed":"deepswe","score":0.002654615489754933,"rank":405,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003381316369873188,"rank":407,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003318702312080555,"rank":407,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0033375256115418615,"rank":404,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0033311755997830067,"rank":407,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003337598821939214,"rank":407,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0033786847237578022,"rank":407,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0033646459431560995,"rank":407,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0033860718299454796,"rank":407,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0033341204649971323,"rank":407,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0034403809005607473,"rank":407,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0033806235707410435,"rank":407,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0033034754313910866,"rank":407,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0033540464396593192,"rank":407,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.003468062282553598,"rank":407,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0034893520409479354,"rank":407,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0034054667294725308,"rank":406,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003054245853559316,"rank":408,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0036120327988847325,"rank":405,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0033659131413477515,"rank":407,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.003365781326735431,"rank":407,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.003366549730845089,"rank":407,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003372407448425416,"rank":407,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0033554303241504903,"rank":407,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.003369229463423069,"rank":407,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning":{"score":0.0033153111862093128,"rank":408,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004447531949474146,"rank":407,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00258092846380519,"rank":408,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.003277230791360573,"rank":408,"remainingConfigurations":444},{"removed":"Scale","score":0.00395775931599263,"rank":408,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0032772399253694177,"rank":408,"remainingConfigurations":444},{"removed":"Cognition","score":0.0032327943490175616,"rank":408,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00347239268166113,"rank":407,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.003428159647447129,"rank":408,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.003402437044587417,"rank":394,"remainingConfigurations":431},{"removed":"Vals AI","score":0.003185529473227417,"rank":407,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0033137871698472646,"rank":408,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.003202057944288454,"rank":408,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0033091628529507405,"rank":408,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0033153111862093128,"rank":408,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003343397214836398,"rank":408,"remainingConfigurations":444},{"removed":"All provider reports","score":0.003223203595561292,"rank":408,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003351643462721345,"rank":408,"remainingConfigurations":444},{"removed":"briefcase","score":0.0032880649189869766,"rank":408,"remainingConfigurations":444},{"removed":"aime","score":0.0036970740764500757,"rank":403,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003377159615584713,"rank":408,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0032870801846570045,"rank":408,"remainingConfigurations":444},{"removed":"automationbench","score":0.003288810834172295,"rank":408,"remainingConfigurations":444},{"removed":"critpt","score":0.00288223963714019,"rank":407,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003323928444233407,"rank":408,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0033925741361186834,"rank":408,"remainingConfigurations":444},{"removed":"gdpval","score":0.0033816832666566537,"rank":408,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0036161797850192503,"rank":403,"remainingConfigurations":444},{"removed":"gpqa","score":0.003516581982277946,"rank":405,"remainingConfigurations":444},{"removed":"harvey","score":0.00327850826112207,"rank":408,"remainingConfigurations":444},{"removed":"hle","score":0.003640871232073638,"rank":407,"remainingConfigurations":444},{"removed":"ifbench","score":0.0029660007653290812,"rank":410,"remainingConfigurations":444},{"removed":"itbench","score":0.003289860625977268,"rank":408,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0032638543336632204,"rank":407,"remainingConfigurations":444},{"removed":"math500","score":0.0033601452828059355,"rank":407,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003865510471139548,"rank":403,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003652989343679161,"rank":408,"remainingConfigurations":444},{"removed":"omniscience","score":0.002925589213133398,"rank":406,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0029968769067647873,"rank":407,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0033738703517712377,"rank":408,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0028800927724366775,"rank":412,"remainingConfigurations":444},{"removed":"arc-agi","score":0.004265058949611053,"rank":407,"remainingConfigurations":444},{"removed":"deepswe","score":0.002582759182183788,"rank":408,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003316204933360748,"rank":408,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.003254724041389989,"rank":408,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0032327943490175616,"rank":408,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0032649209185700353,"rank":408,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.003273961085941263,"rank":408,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.003313537289464234,"rank":408,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0032999589130952964,"rank":408,"remainingConfigurations":444},{"removed":"livebench-math","score":0.003319657631906729,"rank":408,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0032715836002031613,"rank":408,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0033745123517969103,"rank":408,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0033150663068052724,"rank":408,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00323910880513301,"rank":408,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.003289574464069324,"rank":408,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0034016157746343347,"rank":408,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.003428159647447129,"rank":408,"remainingConfigurations":444},{"removed":"frontiermath","score":0.003323728619416551,"rank":408,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.003076912656671935,"rank":407,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0035084345065056117,"rank":408,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0033012176902623377,"rank":408,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0033006783467019085,"rank":408,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0033019261759682024,"rank":408,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.003307258195315016,"rank":408,"remainingConfigurations":444},{"removed":"vibe-code","score":0.003290460390671641,"rank":408,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0033045345293668395,"rank":408,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-pro--effort-non-reasoning":{"score":0.003004172979329693,"rank":409,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.004024589187673541,"rank":408,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0023372402859559746,"rank":409,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.002969159175579375,"rank":409,"remainingConfigurations":444},{"removed":"Scale","score":0.003585722293104788,"rank":409,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0029698891196907307,"rank":409,"remainingConfigurations":444},{"removed":"Cognition","score":0.002927091661505263,"rank":409,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0031463672125962125,"rank":408,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0031046925872988008,"rank":409,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0030619380758900006,"rank":395,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0028869489634723616,"rank":408,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0030027927654891727,"rank":409,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.002901512140695273,"rank":409,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0029986011642594602,"rank":409,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.003004172979329693,"rank":409,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0030296101937225656,"rank":409,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002920661330882618,"rank":409,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.003038118587825827,"rank":409,"remainingConfigurations":444},{"removed":"briefcase","score":0.00298084614387858,"rank":409,"remainingConfigurations":444},{"removed":"aime","score":0.003389462243971769,"rank":407,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003060065093101237,"rank":409,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.002836641883672108,"rank":412,"remainingConfigurations":444},{"removed":"automationbench","score":0.002984025577880497,"rank":409,"remainingConfigurations":444},{"removed":"critpt","score":0.0025709761680574993,"rank":410,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0030125725634147123,"rank":409,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0030774565475692717,"rank":409,"remainingConfigurations":444},{"removed":"gdpval","score":0.0030125108499254234,"rank":410,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0030474614323305776,"rank":409,"remainingConfigurations":444},{"removed":"gpqa","score":0.0029993638350906105,"rank":411,"remainingConfigurations":444},{"removed":"harvey","score":0.0029710918207302463,"rank":409,"remainingConfigurations":444},{"removed":"hle","score":0.0035870737071629845,"rank":409,"remainingConfigurations":444},{"removed":"ifbench","score":0.0026339265186456615,"rank":415,"remainingConfigurations":444},{"removed":"itbench","score":0.0029812497487901146,"rank":409,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003320680001667293,"rank":405,"remainingConfigurations":444},{"removed":"math500","score":0.003267330004484679,"rank":409,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0031914562619802076,"rank":413,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003338716200896531,"rank":410,"remainingConfigurations":444},{"removed":"omniscience","score":0.002284545966082138,"rank":417,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0029946964736707483,"rank":408,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.003057254758529732,"rank":409,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002805164470838574,"rank":414,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0038616231711805457,"rank":408,"remainingConfigurations":444},{"removed":"deepswe","score":0.0023389016487576422,"rank":409,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.003004983277014081,"rank":409,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0029491020148161434,"rank":409,"remainingConfigurations":444},{"removed":"frontiercode","score":0.002927091661505263,"rank":409,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.002958427858756913,"rank":409,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0029665899456587604,"rank":409,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.003002572621708735,"rank":409,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.00299029113843084,"rank":409,"remainingConfigurations":444},{"removed":"livebench-math","score":0.003008125062772304,"rank":409,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002964521711153689,"rank":409,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0030578527363497917,"rank":409,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0030039497561410444,"rank":409,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0029350902020034825,"rank":409,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0029808373146037134,"rank":409,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0030824083785305225,"rank":409,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0031046925872988008,"rank":409,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0030115831806099527,"rank":409,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002787308185237014,"rank":409,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0031798033440552345,"rank":409,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002991392348876074,"rank":409,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0029909088554578196,"rank":409,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0029920352384113897,"rank":409,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0029968744947971096,"rank":409,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0029816464685610516,"rank":409,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0029944027009791937,"rank":409,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-4.1-nano--effort-non-reasoning":{"score":0.002994888009199505,"rank":410,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00400956911373937,"rank":409,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0023303449281186837,"rank":410,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0029600627272605806,"rank":410,"remainingConfigurations":444},{"removed":"Scale","score":0.0035744555620280797,"rank":410,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.002960957508635571,"rank":410,"remainingConfigurations":444},{"removed":"Cognition","score":0.0029175833857767474,"rank":410,"remainingConfigurations":444},{"removed":"LiveBench","score":0.003137610203008123,"rank":409,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0030950436820465347,"rank":410,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.00305422625954176,"rank":396,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002879529893698576,"rank":409,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0029935111711913796,"rank":410,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0028924986830011477,"rank":410,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0029893313033596443,"rank":410,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002994888009199505,"rank":410,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.003020236444195053,"rank":410,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0029115766144264207,"rank":410,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0030289116999324905,"rank":410,"remainingConfigurations":444},{"removed":"briefcase","score":0.002969212779223352,"rank":410,"remainingConfigurations":444},{"removed":"aime","score":0.003030039580696939,"rank":409,"remainingConfigurations":444},{"removed":"apex-agents","score":0.003050981617634415,"rank":410,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00284700734759168,"rank":411,"remainingConfigurations":444},{"removed":"automationbench","score":0.0029735915765725647,"rank":410,"remainingConfigurations":444},{"removed":"critpt","score":0.0025696762504940677,"rank":411,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.003003430393120291,"rank":410,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0030675923144408393,"rank":410,"remainingConfigurations":444},{"removed":"gdpval","score":0.003034849237222034,"rank":409,"remainingConfigurations":444},{"removed":"gmmlu","score":0.003037492504879906,"rank":410,"remainingConfigurations":444},{"removed":"gpqa","score":0.0029674468544154606,"rank":412,"remainingConfigurations":444},{"removed":"harvey","score":0.0029618024611875356,"rank":410,"remainingConfigurations":444},{"removed":"hle","score":0.003494436880350116,"rank":410,"remainingConfigurations":444},{"removed":"ifbench","score":0.0028668983065244426,"rank":411,"remainingConfigurations":444},{"removed":"itbench","score":0.002972572020703368,"rank":410,"remainingConfigurations":444},{"removed":"livecodebench","score":0.003025889797215622,"rank":410,"remainingConfigurations":444},{"removed":"math500","score":0.003070892090322984,"rank":410,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0033167342658948426,"rank":411,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0034273629121983804,"rank":409,"remainingConfigurations":444},{"removed":"omniscience","score":0.002512788800112702,"rank":411,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0028789717165153355,"rank":409,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00304776922544629,"rank":410,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0029503357669846777,"rank":411,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0038476383860222905,"rank":409,"remainingConfigurations":444},{"removed":"deepswe","score":0.0023320039933372523,"rank":410,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0029956970137305704,"rank":410,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0029402270905108246,"rank":410,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0029175833857767474,"rank":410,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0029493128946299807,"rank":410,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0029574067334197343,"rank":410,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002993297091108272,"rank":410,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.002981159237150312,"rank":410,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0029988183394916673,"rank":410,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002955381969101582,"rank":410,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0030484231494027447,"rank":410,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0029946590582940677,"rank":410,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.002926001923117772,"rank":410,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0029716251052126726,"rank":410,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.003072869655614428,"rank":410,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0030950436820465347,"rank":410,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0030017769537933185,"rank":410,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0027791835550746292,"rank":410,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00316994421740484,"rank":410,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002982146186036701,"rank":410,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0029816683020311287,"rank":410,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0029827804098808606,"rank":410,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.002987620584039957,"rank":410,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0029724328949740676,"rank":410,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002985147643231684,"rank":410,"remainingConfigurations":444}],"sharedOrderConflicts":0},"kimi-linear-48b-a3b-instruct--effort-non-reasoning":{"score":0.0029380181666419634,"rank":411,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.003942174815114823,"rank":410,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0022863201289619246,"rank":411,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0029040270252885113,"rank":411,"remainingConfigurations":444},{"removed":"Scale","score":0.003507391042473783,"rank":411,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.002904105227606099,"rank":411,"remainingConfigurations":444},{"removed":"Cognition","score":0.0028637585864024497,"rank":411,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0030762146285714504,"rank":410,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0030382508686251984,"rank":411,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002999685406666678,"rank":397,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002822233172315412,"rank":410,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0029366687370089265,"rank":411,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0028376184805379563,"rank":411,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0029325725644419056,"rank":411,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0029380181666419634,"rank":411,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002962899363498441,"rank":411,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002856353568627566,"rank":411,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0029699479131512357,"rank":411,"remainingConfigurations":444},{"removed":"briefcase","score":0.002921029141050808,"rank":411,"remainingConfigurations":444},{"removed":"aime","score":0.002656436790936844,"rank":416,"remainingConfigurations":444},{"removed":"apex-agents","score":0.002992262441997658,"rank":411,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0026078590287701643,"rank":415,"remainingConfigurations":444},{"removed":"automationbench","score":0.002923380825117046,"rank":411,"remainingConfigurations":444},{"removed":"critpt","score":0.0026819612766114157,"rank":409,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0029448724773994133,"rank":411,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.003014610035907721,"rank":411,"remainingConfigurations":444},{"removed":"gdpval","score":0.002954378162161349,"rank":411,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0029909141142860384,"rank":411,"remainingConfigurations":444},{"removed":"gpqa","score":0.0031031290767361518,"rank":409,"remainingConfigurations":444},{"removed":"harvey","score":0.0029047702207614552,"rank":411,"remainingConfigurations":444},{"removed":"hle","score":0.003711003977905357,"rank":406,"remainingConfigurations":444},{"removed":"ifbench","score":0.003014476334062568,"rank":408,"remainingConfigurations":444},{"removed":"itbench","score":0.0029150375105926763,"rank":411,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0027205538306066175,"rank":415,"remainingConfigurations":444},{"removed":"math500","score":0.0029835334344726207,"rank":412,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0034977750470117455,"rank":408,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0032393845519191338,"rank":412,"remainingConfigurations":444},{"removed":"omniscience","score":0.0025533905317957056,"rank":410,"remainingConfigurations":444},{"removed":"tau-bench","score":0.003148409921769596,"rank":405,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002988980572718802,"rank":411,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002384833831057607,"rank":419,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0037825250682621213,"rank":410,"remainingConfigurations":444},{"removed":"deepswe","score":0.0022879439432417956,"rank":411,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.002938810246174336,"rank":411,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.002884015468086082,"rank":411,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0028637585864024497,"rank":411,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.002893347256386746,"rank":411,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0029013460594098654,"rank":411,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002936451287023035,"rank":411,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0029243965940357382,"rank":411,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0029418877291475126,"rank":411,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002899222647522059,"rank":411,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0029905109297169337,"rank":411,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0029378085932647117,"rank":411,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.002870453071397721,"rank":411,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.002915191588597698,"rank":411,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0030145513342095223,"rank":411,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0030382508686251984,"rank":411,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002945275574249471,"rank":411,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002725737086417426,"rank":411,"remainingConfigurations":444},{"removed":"simpleqa","score":0.003109698741991931,"rank":411,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0029255158843239128,"rank":411,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0029250418342222392,"rank":411,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0029261507293710585,"rank":411,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0029308746558023087,"rank":411,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0029159825046758537,"rank":411,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0029284629223112536,"rank":411,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3-27b-it--effort-non-reasoning":{"score":0.002878275810312836,"rank":412,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0038521126869291086,"rank":411,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002239808951789218,"rank":412,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00284495920495639,"rank":412,"remainingConfigurations":444},{"removed":"Scale","score":0.0034368837382323125,"rank":412,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0028457710462811495,"rank":412,"remainingConfigurations":444},{"removed":"Cognition","score":0.0028033142726293803,"rank":412,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0030166091248480967,"rank":411,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0029750644049056797,"rank":412,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0029488525736456887,"rank":398,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0027694308685277703,"rank":411,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0028769508714700915,"rank":412,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.002779796701737074,"rank":412,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0028729301525981794,"rank":412,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002878275810312836,"rank":412,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0029026367996595162,"rank":412,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0027981252900741507,"rank":412,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0029100232412796463,"rank":412,"remainingConfigurations":444},{"removed":"briefcase","score":0.0028562595997725817,"rank":412,"remainingConfigurations":444},{"removed":"aime","score":0.0029751397974435985,"rank":410,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0029324139060508125,"rank":412,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0028715963523247867,"rank":410,"remainingConfigurations":444},{"removed":"automationbench","score":0.002871176048986178,"rank":412,"remainingConfigurations":444},{"removed":"critpt","score":0.002485850978690089,"rank":412,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0028850859383871066,"rank":412,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0029372444188520627,"rank":412,"remainingConfigurations":444},{"removed":"gdpval","score":0.0029520771816016513,"rank":412,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00270495712500355,"rank":417,"remainingConfigurations":444},{"removed":"gpqa","score":0.0029484460994901665,"rank":414,"remainingConfigurations":444},{"removed":"harvey","score":0.0028460928406177353,"rank":412,"remainingConfigurations":444},{"removed":"hle","score":0.0031767707743080575,"rank":412,"remainingConfigurations":444},{"removed":"ifbench","score":0.002761477870068718,"rank":414,"remainingConfigurations":444},{"removed":"itbench","score":0.0028562257708694273,"rank":412,"remainingConfigurations":444},{"removed":"livecodebench","score":0.00325006297925399,"rank":408,"remainingConfigurations":444},{"removed":"math500","score":0.002799494536654365,"rank":415,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003151086058603898,"rank":414,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003109827333919221,"rank":413,"remainingConfigurations":444},{"removed":"omniscience","score":0.002477132708915047,"rank":412,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0028271397690777926,"rank":411,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002928118828818452,"rank":412,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0027551164675077866,"rank":415,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0036971915621596655,"rank":411,"remainingConfigurations":444},{"removed":"deepswe","score":0.002241406763283819,"rank":412,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0028790550440481997,"rank":412,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0028259150729437583,"rank":412,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0028033142726293803,"rank":412,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.002834453071601928,"rank":412,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.002842231595378076,"rank":412,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0028767482086938397,"rank":412,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0028652209386041474,"rank":412,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0028820379389435506,"rank":412,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0028403330322055247,"rank":412,"remainingConfigurations":444},{"removed":"livebench-language","score":0.002929765823228772,"rank":412,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002878034232213648,"rank":412,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0028120375336563256,"rank":412,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0028559190113566523,"rank":412,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0029532285662460596,"rank":412,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0029750644049056797,"rank":412,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0028844708271368214,"rank":412,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002672657392048987,"rank":412,"remainingConfigurations":444},{"removed":"simpleqa","score":0.003046541058699968,"rank":412,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0028660280322640127,"rank":412,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0028655679811523255,"rank":412,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0028666320492206003,"rank":412,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0028712960735426617,"rank":412,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00285668980535244,"rank":412,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002868911851060385,"rank":412,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-1.7b--effort-reasoning":{"score":0.0027877271433720493,"rank":413,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0037523282515451724,"rank":413,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002170160010711739,"rank":413,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.002755605671943636,"rank":413,"remainingConfigurations":444},{"removed":"Scale","score":0.003328612461241873,"rank":413,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0027557443891485785,"rank":413,"remainingConfigurations":444},{"removed":"Cognition","score":0.002719571350595968,"rank":413,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0029199513820588907,"rank":412,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.002887913333735674,"rank":413,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002841683836461303,"rank":399,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0026785234534410815,"rank":412,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0027864453717364288,"rank":413,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.00269243060281072,"rank":413,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.002782556365992508,"rank":413,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0027877271433720493,"rank":413,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002811355575380651,"rank":413,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002710221481595138,"rank":413,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0028186403941423063,"rank":413,"remainingConfigurations":444},{"removed":"briefcase","score":0.002777376478073428,"rank":413,"remainingConfigurations":444},{"removed":"aime","score":0.002498946241440542,"rank":418,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0028399542729441885,"rank":413,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0028974236285802552,"rank":409,"remainingConfigurations":444},{"removed":"automationbench","score":0.002779704681567945,"rank":413,"remainingConfigurations":444},{"removed":"critpt","score":0.0023397405535298967,"rank":414,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.002795571470828581,"rank":413,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002865748890332325,"rank":413,"remainingConfigurations":444},{"removed":"gdpval","score":0.002804750848784803,"rank":414,"remainingConfigurations":444},{"removed":"gmmlu","score":0.002834522441049758,"rank":412,"remainingConfigurations":444},{"removed":"gpqa","score":0.0029495772578546943,"rank":413,"remainingConfigurations":444},{"removed":"harvey","score":0.002756796678007208,"rank":413,"remainingConfigurations":444},{"removed":"hle","score":0.0029592732393470874,"rank":417,"remainingConfigurations":444},{"removed":"ifbench","score":0.0028456525255506084,"rank":412,"remainingConfigurations":444},{"removed":"itbench","score":0.0027668103451641887,"rank":413,"remainingConfigurations":444},{"removed":"livecodebench","score":0.002843847197516309,"rank":412,"remainingConfigurations":444},{"removed":"math500","score":0.002633365777123094,"rank":419,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0032257919700379076,"rank":412,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0030762998847775835,"rank":414,"remainingConfigurations":444},{"removed":"omniscience","score":0.002470053490711822,"rank":413,"remainingConfigurations":444},{"removed":"tau-bench","score":0.002441962039642582,"rank":415,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0028376100676068203,"rank":413,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0029879594282032507,"rank":409,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0035981213437743056,"rank":413,"remainingConfigurations":444},{"removed":"deepswe","score":0.002171699797893149,"rank":413,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0027884789607708835,"rank":413,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.002736603509712557,"rank":413,"remainingConfigurations":444},{"removed":"frontiercode","score":0.002719571350595968,"rank":413,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0027453435662423745,"rank":413,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0027529350492358252,"rank":413,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002786241524466878,"rank":413,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.002774809833397927,"rank":413,"remainingConfigurations":444},{"removed":"livebench-math","score":0.002791393835135157,"rank":413,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0027509004443554406,"rank":413,"remainingConfigurations":444},{"removed":"livebench-language","score":0.002837553001214294,"rank":413,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0027875362924534397,"rank":413,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.002723594523509393,"rank":413,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0027660588861421176,"rank":413,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002860378532963025,"rank":413,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.002887913333735674,"rank":413,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002795501660064765,"rank":413,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002586885256219486,"rank":413,"remainingConfigurations":444},{"removed":"simpleqa","score":0.002950604369103507,"rank":413,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0027758629154296505,"rank":413,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0027754105343082407,"rank":413,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0027764638594199183,"rank":413,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0027809451712183116,"rank":413,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002766809418439457,"rank":413,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002778658583621904,"rank":413,"remainingConfigurations":444}],"sharedOrderConflicts":0},"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning":{"score":0.0027572101642861324,"rank":414,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0037083425825783552,"rank":415,"remainingConfigurations":444},{"removed":"Datacurve","score":0.002147031090777303,"rank":414,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0027256216461316513,"rank":414,"remainingConfigurations":444},{"removed":"Scale","score":0.003292616033006516,"rank":414,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0027258142650576976,"rank":414,"remainingConfigurations":444},{"removed":"Cognition","score":0.00269095865266107,"rank":414,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0028884289237559404,"rank":413,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.002852368166060576,"rank":414,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0028094361600671867,"rank":400,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0026495033833996685,"rank":413,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0027559418994983573,"rank":414,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0026629391665504362,"rank":414,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.002752092248356724,"rank":414,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0027572101642861324,"rank":414,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002780595644198724,"rank":414,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002680546125694126,"rank":414,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0027879362512552024,"rank":414,"remainingConfigurations":444},{"removed":"briefcase","score":0.002741887851377868,"rank":414,"remainingConfigurations":444},{"removed":"aime","score":0.0027109084532485847,"rank":413,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0028091522126201724,"rank":414,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.002575492511503821,"rank":416,"remainingConfigurations":444},{"removed":"automationbench","score":0.002745101264855597,"rank":414,"remainingConfigurations":444},{"removed":"critpt","score":0.002309378847737714,"rank":415,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0027652734278794376,"rank":414,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0028310464055028486,"rank":414,"remainingConfigurations":444},{"removed":"gdpval","score":0.002775297852946057,"rank":415,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0028016996627478526,"rank":413,"remainingConfigurations":444},{"removed":"gpqa","score":0.002809366264673602,"rank":415,"remainingConfigurations":444},{"removed":"harvey","score":0.002726791702766556,"rank":414,"remainingConfigurations":444},{"removed":"hle","score":0.003057172498067784,"rank":414,"remainingConfigurations":444},{"removed":"ifbench","score":0.0028287790086715305,"rank":413,"remainingConfigurations":444},{"removed":"itbench","score":0.002736724565565925,"rank":414,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0027112411860426918,"rank":417,"remainingConfigurations":444},{"removed":"math500","score":0.002808674983780721,"rank":414,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.003042700434964018,"rank":416,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003025315368077077,"rank":415,"remainingConfigurations":444},{"removed":"omniscience","score":0.00236336565306937,"rank":414,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0026036157887118906,"rank":413,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002807015189901066,"rank":414,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002966204719105934,"rank":410,"remainingConfigurations":444},{"removed":"arc-agi","score":0.003554216268639111,"rank":415,"remainingConfigurations":444},{"removed":"deepswe","score":0.0021485528433486784,"rank":414,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.002757953602370678,"rank":414,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.002706716455046465,"rank":414,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00269095865266107,"rank":414,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0027153304551512975,"rank":414,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0027228307800379148,"rank":414,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0027557393742810694,"rank":414,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0027444287439759418,"rank":414,"remainingConfigurations":444},{"removed":"livebench-math","score":0.002760832349633553,"rank":414,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002720792161761828,"rank":414,"remainingConfigurations":444},{"removed":"livebench-language","score":0.002806494742386992,"rank":414,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002757017930789808,"rank":414,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0026937725795451225,"rank":414,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.002735778896641445,"rank":414,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002829072979409692,"rank":414,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.002852368166060576,"rank":414,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002765038432238322,"rank":414,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002558973811120725,"rank":414,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0029181755573018473,"rank":414,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002745476850258558,"rank":414,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.002745025859939085,"rank":414,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0027460715740273128,"rank":414,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0027504992573612764,"rank":414,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0027365180279459445,"rank":414,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0027482417322389264,"rank":414,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-0.8b--effort-non-reasoning":{"score":0.0027373310240663795,"rank":415,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.003724204223745494,"rank":414,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0021347608832480505,"rank":415,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0027081321577014914,"rank":415,"remainingConfigurations":444},{"removed":"Scale","score":0.00327138896032874,"rank":415,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.00270705261319982,"rank":415,"remainingConfigurations":444},{"removed":"Cognition","score":0.002682036041130046,"rank":415,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002869874007988356,"rank":414,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0028337716609707145,"rank":415,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0027972899983552658,"rank":401,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0026332461656210023,"rank":414,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.002736070040969755,"rank":415,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0026436839615303974,"rank":415,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0027322428091503697,"rank":415,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0027373310240663795,"rank":415,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002760571640784021,"rank":415,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002661178345015797,"rank":415,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.002770318438389348,"rank":415,"remainingConfigurations":444},{"removed":"briefcase","score":0.0027297487085741565,"rank":415,"remainingConfigurations":444},{"removed":"aime","score":0.002701051910750648,"rank":414,"remainingConfigurations":444},{"removed":"apex-agents","score":0.002790531050859772,"rank":415,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0027323197317395396,"rank":413,"remainingConfigurations":444},{"removed":"automationbench","score":0.0027313977605407723,"rank":415,"remainingConfigurations":444},{"removed":"critpt","score":0.002225430573920198,"rank":417,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.002748210371470853,"rank":415,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0028169292282257297,"rank":415,"remainingConfigurations":444},{"removed":"gdpval","score":0.0028219046415590733,"rank":413,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0027792896709833096,"rank":414,"remainingConfigurations":444},{"removed":"gpqa","score":0.003180408215080952,"rank":408,"remainingConfigurations":444},{"removed":"harvey","score":0.0027080594857764044,"rank":415,"remainingConfigurations":444},{"removed":"hle","score":0.002662193097978996,"rank":420,"remainingConfigurations":444},{"removed":"ifbench","score":0.002995341636789417,"rank":409,"remainingConfigurations":444},{"removed":"itbench","score":0.0027197161977594846,"rank":415,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0027693108439150447,"rank":414,"remainingConfigurations":444},{"removed":"math500","score":0.0027695313539453596,"rank":416,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0028882963165886726,"rank":418,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.003325991624217355,"rank":411,"remainingConfigurations":444},{"removed":"omniscience","score":0.0026785877404534642,"rank":409,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0016976413160104727,"rank":425,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0027892678628611265,"rank":415,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0030305566005453884,"rank":408,"remainingConfigurations":444},{"removed":"arc-agi","score":0.003562136770311144,"rank":414,"remainingConfigurations":444},{"removed":"deepswe","score":0.0021362733118909373,"rank":415,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.002738069665275641,"rank":415,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0026878273601644805,"rank":415,"remainingConfigurations":444},{"removed":"frontiercode","score":0.002682036041130046,"rank":415,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.00269587872073694,"rank":415,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.002703279101959519,"rank":415,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0027358712204942873,"rank":415,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0027247121503565885,"rank":415,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0027409111700472184,"rank":415,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002701179983935639,"rank":415,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00278628309295106,"rank":415,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002737151163688594,"rank":415,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0026743323534776237,"rank":415,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0027160484135723417,"rank":415,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002808681887980585,"rank":415,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0028337716609707145,"rank":415,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002746125464900308,"rank":415,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0025420529789360866,"rank":415,"remainingConfigurations":444},{"removed":"simpleqa","score":0.002896784251312077,"rank":415,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0027256877406195475,"rank":415,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0027252380683373215,"rank":415,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0027262623967990764,"rank":415,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.002730674854493312,"rank":415,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0027167890116511946,"rank":415,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0027284265523669026,"rank":415,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-4--effort-non-reasoning":{"score":0.0026657433284480946,"rank":416,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.003599650580192296,"rank":416,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0020770687992282357,"rank":416,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.002635156311275835,"rank":416,"remainingConfigurations":444},{"removed":"Scale","score":0.003183547598732291,"rank":416,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.002635864333211083,"rank":416,"remainingConfigurations":444},{"removed":"Cognition","score":0.0026031358037154778,"rank":416,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002793446776226742,"rank":415,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0027556903765105605,"rank":416,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0027062764870039876,"rank":403,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002563299265316106,"rank":415,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.002664517197007521,"rank":416,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0025745787611840183,"rank":416,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0026607986923735546,"rank":416,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0026657433284480946,"rank":416,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00268833445962164,"rank":416,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0025915877666136,"rank":416,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.002696953357549032,"rank":416,"remainingConfigurations":444},{"removed":"briefcase","score":0.0026730557734891795,"rank":416,"remainingConfigurations":444},{"removed":"aime","score":0.0025855528378443747,"rank":417,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0027166718905864656,"rank":416,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0026369714262591258,"rank":414,"remainingConfigurations":444},{"removed":"automationbench","score":0.002673637069774451,"rank":416,"remainingConfigurations":444},{"removed":"critpt","score":0.002449193804832228,"rank":413,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.00267696172000413,"rank":416,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002753987255132553,"rank":416,"remainingConfigurations":444},{"removed":"gdpval","score":0.0025409292289685125,"rank":417,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0027153843290517368,"rank":416,"remainingConfigurations":444},{"removed":"gpqa","score":0.003018685379998823,"rank":410,"remainingConfigurations":444},{"removed":"harvey","score":0.0026370522890802072,"rank":416,"remainingConfigurations":444},{"removed":"hle","score":0.0029622398914976697,"rank":416,"remainingConfigurations":444},{"removed":"ifbench","score":0.002291796019098963,"rank":419,"remainingConfigurations":444},{"removed":"itbench","score":0.0026483849476311855,"rank":416,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0026722226122322403,"rank":418,"remainingConfigurations":444},{"removed":"math500","score":0.004298942672847849,"rank":393,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0034211692581810984,"rank":409,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0029495659508910563,"rank":417,"remainingConfigurations":444},{"removed":"omniscience","score":0.0012179241942165198,"rank":435,"remainingConfigurations":444},{"removed":"tau-bench","score":0.002527602392623711,"rank":414,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002715893673502622,"rank":416,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002704401726311897,"rank":416,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0034496909960429235,"rank":416,"remainingConfigurations":444},{"removed":"deepswe","score":0.0020785446049802047,"rank":416,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0026664629415741365,"rank":416,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0026171139182494998,"rank":416,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0026031358037154778,"rank":416,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0026252986497545885,"rank":416,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0026325103363797724,"rank":416,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0026643274957265906,"rank":416,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.002653441246561042,"rank":416,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0026692506977132034,"rank":416,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002630518962637338,"rank":416,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0027134129007323794,"rank":416,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0026655623057667225,"rank":416,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0026043977674484,"rank":416,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0026450169410679792,"rank":416,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0027352256097320136,"rank":416,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0027556903765105605,"rank":416,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0026725658514718045,"rank":416,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0024790725987689642,"rank":416,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00282193603010295,"rank":416,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0026543962823114896,"rank":416,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.002653966785162025,"rank":416,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.002654963364767622,"rank":416,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0026592630000264253,"rank":416,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0026457401877513042,"rank":416,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0026570678127765582,"rank":416,"remainingConfigurations":444}],"sharedOrderConflicts":2},"qwen3-vl-4b-instruct--effort-non-reasoning":{"score":0.002621675159914403,"rank":417,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0035159977241018283,"rank":417,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0020398980897746895,"rank":417,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0025914303909531002,"rank":417,"remainingConfigurations":444},{"removed":"Scale","score":0.0031296744643174723,"rank":417,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0025919681650964552,"rank":417,"remainingConfigurations":444},{"removed":"Cognition","score":0.0025551746209044645,"rank":417,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002746331758919067,"rank":416,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.002710635365745629,"rank":417,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002673696633079195,"rank":405,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0025199557548666496,"rank":416,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0026204697167832793,"rank":417,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.002532022471166509,"rank":417,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0026168095750509443,"rank":417,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002621675159914403,"rank":417,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0026438865969507564,"rank":417,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0025487419972672247,"rank":417,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0026513026089237603,"rank":417,"remainingConfigurations":444},{"removed":"briefcase","score":0.0026038574465517867,"rank":417,"remainingConfigurations":444},{"removed":"aime","score":0.0023381935296165374,"rank":422,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0026707450908218244,"rank":417,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.002532977061148474,"rank":417,"remainingConfigurations":444},{"removed":"automationbench","score":0.0026062951850756837,"rank":417,"remainingConfigurations":444},{"removed":"critpt","score":0.0021880515725269376,"rank":419,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0026294891075802945,"rank":417,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0026898385257247645,"rank":418,"remainingConfigurations":444},{"removed":"gdpval","score":0.0026322800086317024,"rank":416,"remainingConfigurations":444},{"removed":"gmmlu","score":0.002665001791202768,"rank":418,"remainingConfigurations":444},{"removed":"gpqa","score":0.00275374451693661,"rank":416,"remainingConfigurations":444},{"removed":"harvey","score":0.002592588131829077,"rank":417,"remainingConfigurations":444},{"removed":"hle","score":0.00308083453452752,"rank":413,"remainingConfigurations":444},{"removed":"ifbench","score":0.002509192644743108,"rank":417,"remainingConfigurations":444},{"removed":"itbench","score":0.0026020386731449682,"rank":417,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0027152574482768982,"rank":416,"remainingConfigurations":444},{"removed":"math500","score":0.0026695079583756976,"rank":417,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0029536365034778388,"rank":417,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002912238021308465,"rank":418,"remainingConfigurations":444},{"removed":"omniscience","score":0.0022852030785563836,"rank":416,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0023504632409440777,"rank":418,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002667849858604141,"rank":417,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0028303540696823803,"rank":413,"remainingConfigurations":444},{"removed":"arc-agi","score":0.00337276801540932,"rank":417,"remainingConfigurations":444},{"removed":"deepswe","score":0.0020413480966249464,"rank":417,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0026223826622652573,"rank":417,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.002573637447818696,"rank":417,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0025551746209044645,"rank":417,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0025817496339384225,"rank":417,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0025888744852787305,"rank":417,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002620278529197493,"rank":417,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.002609564117237832,"rank":417,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0026251253666473517,"rank":417,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0025870412988953026,"rank":417,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00266855515803613,"rank":417,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0026214863724719835,"rank":417,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.002561342744808309,"rank":417,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00260129312754928,"rank":417,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002690010763909411,"rank":417,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.002710635365745629,"rank":417,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0026282664369449474,"rank":417,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0024323983582915103,"rank":418,"remainingConfigurations":444},{"removed":"simpleqa","score":0.002774987089218046,"rank":417,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002610514039208709,"rank":417,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0026100901442257626,"rank":417,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.002611075851755946,"rank":417,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0026152984648001366,"rank":417,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002602001006518173,"rank":417,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0026131431066852644,"rank":417,"remainingConfigurations":444}],"sharedOrderConflicts":0},"ministral-3-3b--effort-non-reasoning":{"score":0.002616765674525333,"rank":418,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0035055591871811687,"rank":418,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0020366714234717463,"rank":418,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0025867580212545296,"rank":418,"remainingConfigurations":444},{"removed":"Scale","score":0.0031278390649776746,"rank":418,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0025875478253558314,"rank":418,"remainingConfigurations":444},{"removed":"Cognition","score":0.002548902275869873,"rank":418,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0027438079920460655,"rank":417,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00270789309184051,"rank":418,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0026955486428036266,"rank":404,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002519607238835452,"rank":417,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0026155597048393687,"rank":418,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.002527161235361562,"rank":418,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.002611900426660117,"rank":418,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002616765674525333,"rank":418,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002638921356466267,"rank":418,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0025438261609962228,"rank":418,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.002646012060514156,"rank":418,"remainingConfigurations":444},{"removed":"briefcase","score":0.0025476558499549734,"rank":418,"remainingConfigurations":444},{"removed":"aime","score":0.002657453405765784,"rank":415,"remainingConfigurations":444},{"removed":"apex-agents","score":0.002667131651800868,"rank":418,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0025018901125974983,"rank":418,"remainingConfigurations":444},{"removed":"automationbench","score":0.0024480266407568368,"rank":418,"remainingConfigurations":444},{"removed":"critpt","score":0.0022334697309113103,"rank":416,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0026236509933467507,"rank":418,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002695155862834857,"rank":417,"remainingConfigurations":444},{"removed":"gdpval","score":0.0025064038800693164,"rank":418,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0027646964482657185,"rank":415,"remainingConfigurations":444},{"removed":"gpqa","score":0.0027361778651095875,"rank":417,"remainingConfigurations":444},{"removed":"harvey","score":0.0025877592565999802,"rank":418,"remainingConfigurations":444},{"removed":"hle","score":0.002649151339227083,"rank":421,"remainingConfigurations":444},{"removed":"ifbench","score":0.002631341587248937,"rank":416,"remainingConfigurations":444},{"removed":"itbench","score":0.0025973055240185363,"rank":418,"remainingConfigurations":444},{"removed":"livecodebench","score":0.002807756789656999,"rank":413,"remainingConfigurations":444},{"removed":"math500","score":0.002661040363161461,"rank":418,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0030656276159523994,"rank":415,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002981506217590059,"rank":416,"remainingConfigurations":444},{"removed":"omniscience","score":0.0023442297643016126,"rank":415,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0023676501283409024,"rank":417,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002662271135655143,"rank":418,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0026257076439438806,"rank":417,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0033642706353567467,"rank":418,"remainingConfigurations":444},{"removed":"deepswe","score":0.002038125522907878,"rank":418,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.002617475003458465,"rank":418,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0025693056274672843,"rank":418,"remainingConfigurations":444},{"removed":"frontiercode","score":0.002548902275869873,"rank":418,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0025769365965305664,"rank":418,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0025839842819805926,"rank":418,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002615377840905211,"rank":418,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0026049805480046263,"rank":418,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0026201780234833944,"rank":418,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002582264546764555,"rank":418,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0026636146954259875,"rank":418,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002616544358567959,"rank":418,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0025565041801447765,"rank":418,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0025964287653827997,"rank":418,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0026849457373214537,"rank":418,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00270789309184051,"rank":418,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0026221991194500635,"rank":418,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0024333106693124763,"rank":417,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0027697496658491473,"rank":418,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00260562694483338,"rank":418,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0026052060988835993,"rank":418,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0026061720932622837,"rank":418,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.002610418587625773,"rank":418,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002597130365332903,"rank":418,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002608248948764736,"rank":418,"remainingConfigurations":444}],"sharedOrderConflicts":0},"pixtral-large-2411--effort-non-reasoning":{"score":0.0024281387844967126,"rank":419,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.003263363654297875,"rank":419,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0018898874119489654,"rank":419,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00240016982279802,"rank":419,"remainingConfigurations":444},{"removed":"Scale","score":0.002900074487212376,"rank":419,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.002400464812083479,"rank":419,"remainingConfigurations":444},{"removed":"Cognition","score":0.002367942950197343,"rank":419,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002542932181607922,"rank":418,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0025114334128348583,"rank":419,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002462659179784914,"rank":406,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002332936268121573,"rank":418,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.002427022693490705,"rank":419,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0023450938395978573,"rank":419,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0024236351465445616,"rank":419,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0024281387844967126,"rank":419,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002448716051405521,"rank":419,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0023605872381133506,"rank":419,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.002455183620153511,"rank":419,"remainingConfigurations":444},{"removed":"briefcase","score":0.0024162525759656027,"rank":419,"remainingConfigurations":444},{"removed":"aime","score":0.0029042655310294353,"rank":412,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0024735599568460062,"rank":419,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.002387820564845333,"rank":420,"remainingConfigurations":444},{"removed":"automationbench","score":0.0024181583955705044,"rank":419,"remainingConfigurations":444},{"removed":"critpt","score":0.0021898824990987686,"rank":418,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0024346802713970327,"rank":419,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002493336278727809,"rank":419,"remainingConfigurations":444},{"removed":"gdpval","score":0.0024420191935306187,"rank":419,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0024651444260242127,"rank":419,"remainingConfigurations":444},{"removed":"gpqa","score":0.002348525934914183,"rank":420,"remainingConfigurations":444},{"removed":"harvey","score":0.0024008683554740304,"rank":419,"remainingConfigurations":444},{"removed":"hle","score":0.0029656991250861867,"rank":415,"remainingConfigurations":444},{"removed":"ifbench","score":0.002111788734580873,"rank":422,"remainingConfigurations":444},{"removed":"itbench","score":0.0024095476414483616,"rank":419,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0026423718449330984,"rank":420,"remainingConfigurations":444},{"removed":"math500","score":0.0028756847340452667,"rank":413,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002431621869067876,"rank":422,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00250727376610272,"rank":422,"remainingConfigurations":444},{"removed":"omniscience","score":0.0020868605477509564,"rank":418,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0018220747225552128,"rank":423,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0024706440652488347,"rank":419,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0024339368866785464,"rank":418,"remainingConfigurations":444},{"removed":"arc-agi","score":0.003129833132142206,"rank":419,"remainingConfigurations":444},{"removed":"deepswe","score":0.0018912299959499936,"rank":419,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0024287938563772966,"rank":419,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0023834424600505753,"rank":419,"remainingConfigurations":444},{"removed":"frontiercode","score":0.002367942950197343,"rank":419,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0023912187259615444,"rank":419,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.002397830893845128,"rank":419,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0024268471643962178,"rank":419,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0024168728257179385,"rank":419,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0024313446596894526,"rank":419,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002396038502759405,"rank":419,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0024715644012951008,"rank":419,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002427963927551365,"rank":419,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0023722481554879654,"rank":419,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.002409255568111631,"rank":419,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002491456945916803,"rank":419,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0025114334128348583,"rank":419,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0024344769809056263,"rank":419,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0022522891596778354,"rank":419,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0025704905362242737,"rank":419,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0024177955611561085,"rank":419,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0024174031739922467,"rank":419,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00241832352409815,"rank":419,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0024222257265032964,"rank":419,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002409908576329315,"rank":419,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002420234106276519,"rank":419,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gemma-3-12b-it--effort-non-reasoning":{"score":0.0023710239789564097,"rank":420,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0031760761189245372,"rank":420,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00184529341941292,"rank":420,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0023438032944483544,"rank":420,"remainingConfigurations":444},{"removed":"Scale","score":0.002831985104829935,"rank":420,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0023444555782885473,"rank":420,"remainingConfigurations":444},{"removed":"Cognition","score":0.0023101450929398065,"rank":420,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0024856905678662757,"rank":419,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0024510021395480926,"rank":420,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002430610873840476,"rank":407,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002282252795505146,"rank":419,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0023699318155785995,"rank":420,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0022898387400194,"rank":420,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0023666184194808255,"rank":420,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0023710239789564097,"rank":420,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002391102850984626,"rank":420,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0023049452485828232,"rank":420,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.002397529696483387,"rank":420,"remainingConfigurations":444},{"removed":"briefcase","score":0.0023510108590425248,"rank":420,"remainingConfigurations":444},{"removed":"aime","score":0.002448015197064391,"rank":419,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0024159207396940306,"rank":420,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0023325242206358333,"rank":422,"remainingConfigurations":444},{"removed":"automationbench","score":0.0023520795035828802,"rank":420,"remainingConfigurations":444},{"removed":"critpt","score":0.0020039621713471897,"rank":420,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.002377067414942182,"rank":420,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0023227583385406693,"rank":422,"remainingConfigurations":444},{"removed":"gdpval","score":0.002426764097886624,"rank":420,"remainingConfigurations":444},{"removed":"gmmlu","score":0.002347747438365112,"rank":421,"remainingConfigurations":444},{"removed":"gpqa","score":0.0024744199443177514,"rank":418,"remainingConfigurations":444},{"removed":"harvey","score":0.0023446725626702987,"rank":420,"remainingConfigurations":444},{"removed":"hle","score":0.0026088838599717134,"rank":422,"remainingConfigurations":444},{"removed":"ifbench","score":0.002079379460018508,"rank":424,"remainingConfigurations":444},{"removed":"itbench","score":0.002353149793307694,"rank":420,"remainingConfigurations":444},{"removed":"livecodebench","score":0.002651659195147073,"rank":419,"remainingConfigurations":444},{"removed":"math500","score":0.0023222669116088027,"rank":422,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0026342172782656786,"rank":419,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002707593471945546,"rank":419,"remainingConfigurations":444},{"removed":"omniscience","score":0.002065442909035382,"rank":419,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0022994906646072854,"rank":419,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0024122902761105776,"rank":420,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002350404856909597,"rank":420,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0030478586519505093,"rank":420,"remainingConfigurations":444},{"removed":"deepswe","score":0.0018466100929813867,"rank":420,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0023716662128625845,"rank":420,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.002327845070919008,"rank":420,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0023101450929398065,"rank":420,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0023349115395771454,"rank":420,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.002341318239756644,"rank":420,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002369766888017603,"rank":420,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0023602990343323392,"rank":420,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0023741298886706566,"rank":420,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0023397234455197176,"rank":420,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0024134778387489724,"rank":420,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0023708333590532465,"rank":420,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0023164102433865905,"rank":420,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00235258618793603,"rank":420,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002432839227541139,"rank":420,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0024510021395480926,"rank":420,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0023762725074644876,"rank":420,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002201422709533978,"rank":420,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0025099497303091964,"rank":420,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002360924456617638,"rank":420,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0023605449606529474,"rank":420,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0023614239731164833,"rank":420,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.002365265604922317,"rank":420,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002353224527024613,"rank":420,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0023633025446684894,"rank":420,"remainingConfigurations":444}],"sharedOrderConflicts":0},"phi-4--effort-non-reasoning":{"score":0.0023281797286033605,"rank":421,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0031228173217581357,"rank":421,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0018115599382673008,"rank":421,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.002301353418044184,"rank":421,"remainingConfigurations":444},{"removed":"Scale","score":0.0027798657762419985,"rank":421,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0023017211519582932,"rank":421,"remainingConfigurations":444},{"removed":"Cognition","score":0.0022694589052989216,"rank":422,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002438842427719042,"rank":420,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.002407312887723206,"rank":421,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002372942784779401,"rank":408,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002237977559014695,"rank":420,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0023271091590503,"rank":421,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0022485409999348813,"rank":421,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0023238613833127617,"rank":421,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0023281797286033605,"rank":421,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0023479018523275084,"rank":421,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0022633886192170226,"rank":421,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0023545049874521295,"rank":421,"remainingConfigurations":444},{"removed":"briefcase","score":0.002312900358163421,"rank":421,"remainingConfigurations":444},{"removed":"aime","score":0.0024209945195395187,"rank":420,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0023717590753312154,"rank":421,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00239715852494427,"rank":419,"remainingConfigurations":444},{"removed":"automationbench","score":0.0023138446721853024,"rank":421,"remainingConfigurations":444},{"removed":"critpt","score":0.0019164731522901338,"rank":422,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0023351764310337556,"rank":421,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0023862236598799435,"rank":420,"remainingConfigurations":444},{"removed":"gdpval","score":0.0023371916388511675,"rank":421,"remainingConfigurations":444},{"removed":"gmmlu","score":0.002363198664597958,"rank":420,"remainingConfigurations":444},{"removed":"gpqa","score":0.0021626775573100553,"rank":423,"remainingConfigurations":444},{"removed":"harvey","score":0.0023023308085092726,"rank":421,"remainingConfigurations":444},{"removed":"hle","score":0.0026644741589600973,"rank":419,"remainingConfigurations":444},{"removed":"ifbench","score":0.0023810023327996096,"rank":418,"remainingConfigurations":444},{"removed":"itbench","score":0.002310728100199383,"rank":421,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0025639823895627486,"rank":421,"remainingConfigurations":444},{"removed":"math500","score":0.0024137782278389986,"rank":420,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002302993784487165,"rank":423,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0025676302783992186,"rank":420,"remainingConfigurations":444},{"removed":"omniscience","score":0.0018794602356998799,"rank":423,"remainingConfigurations":444},{"removed":"tau-bench","score":0.002388451324103941,"rank":416,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0023691046512579277,"rank":421,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0022271124067528318,"rank":423,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0029960581322708946,"rank":421,"remainingConfigurations":444},{"removed":"deepswe","score":0.0018128490934488232,"rank":421,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0023288084465192343,"rank":421,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0022854598866425915,"rank":421,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0022694589052989216,"rank":422,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.00229271032748246,"rank":421,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0022990441108833213,"rank":421,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.002326941917619223,"rank":421,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0023174335078857424,"rank":421,"remainingConfigurations":444},{"removed":"livebench-math","score":0.002331253185402067,"rank":421,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.002297387853534116,"rank":421,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0023698326264763717,"rank":421,"remainingConfigurations":444},{"removed":"livebench-data","score":0.002328020924435065,"rank":421,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.002274576702474635,"rank":421,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0023100664024719862,"rank":421,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0023889042054299663,"rank":421,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.002407312887723206,"rank":421,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002334161727561527,"rank":421,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0021596133532912902,"rank":421,"remainingConfigurations":444},{"removed":"simpleqa","score":0.002464766023986057,"rank":421,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002318260620802364,"rank":421,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.002317887529117157,"rank":421,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.002318760140476052,"rank":421,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0023225146951008926,"rank":421,"remainingConfigurations":444},{"removed":"vibe-code","score":0.002310700034299211,"rank":421,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002320596998756458,"rank":421,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-8b--effort-non-reasoning":{"score":0.0023013799488494336,"rank":422,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.002053198745465282,"rank":201,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.003112580073377024,"rank":422,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0018066190044721297,"rank":422,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.002276969453179624,"rank":422,"remainingConfigurations":444},{"removed":"Scale","score":0.0027465697627820185,"rank":422,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.002282092035687664,"rank":422,"remainingConfigurations":444},{"removed":"Cognition","score":0.0022695447615147715,"rank":421,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002406958800267246,"rank":421,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0023763513669958192,"rank":422,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0022467080207507944,"rank":409,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0022247209324501374,"rank":421,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0023003542044522825,"rank":422,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.002223483402806038,"rank":422,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0022973064248586815,"rank":422,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0023013799488494336,"rank":422,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0023205896422832726,"rank":422,"remainingConfigurations":444},{"removed":"All provider reports","score":0.002238106085989388,"rank":422,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00232598204956519,"rank":422,"remainingConfigurations":444},{"removed":"briefcase","score":0.0022853993336838293,"rank":422,"remainingConfigurations":444},{"removed":"aime","score":0.002403092330855945,"rank":421,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0023430015116187486,"rank":422,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.002354581356288165,"rank":421,"remainingConfigurations":444},{"removed":"automationbench","score":0.0022869808381584234,"rank":422,"remainingConfigurations":444},{"removed":"critpt","score":0.001949043500863653,"rank":421,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.002307500758274877,"rank":422,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0023543732249453144,"rank":421,"remainingConfigurations":444},{"removed":"gdpval","score":0.002303462804533737,"rank":422,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0023384324013434724,"rank":422,"remainingConfigurations":444},{"removed":"gpqa","score":0.00199094698736335,"rank":425,"remainingConfigurations":444},{"removed":"harvey","score":0.00227479639022574,"rank":422,"remainingConfigurations":444},{"removed":"hle","score":0.002695203921424043,"rank":418,"remainingConfigurations":444},{"removed":"ifbench","score":0.0022613046903371113,"rank":420,"remainingConfigurations":444},{"removed":"itbench","score":0.0022842875238784782,"rank":422,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0024867011855810145,"rank":422,"remainingConfigurations":444},{"removed":"math500","score":0.002340333344003893,"rank":421,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002497854906143349,"rank":421,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002530172874113116,"rank":421,"remainingConfigurations":444},{"removed":"omniscience","score":0.002004270757225654,"rank":420,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0020229687499903515,"rank":420,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0023394749679952844,"rank":422,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.002282480663339162,"rank":422,"remainingConfigurations":444},{"removed":"arc-agi","score":0.002981701188783723,"rank":422,"remainingConfigurations":444},{"removed":"deepswe","score":0.0018079483653863214,"rank":422,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0023019953992950283,"rank":422,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0022593324186461973,"rank":422,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0022695447615147715,"rank":421,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0022676578574630656,"rank":422,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.002272253169652278,"rank":422,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0023001938112613353,"rank":422,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0022906813205554447,"rank":422,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0023050586192294984,"rank":422,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0022700340716127914,"rank":422,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0023423497535207598,"rank":422,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0023014641829871355,"rank":422,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0022487833237343257,"rank":422,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.002283403418692455,"rank":422,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0023612404540335513,"rank":422,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0023763513669958192,"rank":422,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0023232483751221135,"rank":422,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.002096477628491348,"rank":422,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0024609152493609474,"rank":422,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0022915051290204936,"rank":422,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0022913540105069245,"rank":422,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0022919513812825255,"rank":422,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.002295883884277592,"rank":422,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0022842835463528183,"rank":422,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0022937776736438663,"rank":422,"remainingConfigurations":444}],"sharedOrderConflicts":0},"exaone-4.0-1.2b--effort-non-reasoning":{"score":0.002147826546760522,"rank":423,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0028893567139110054,"rank":423,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0016725011104880203,"rank":423,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0021233474948722563,"rank":423,"remainingConfigurations":444},{"removed":"Scale","score":0.0025662192164198467,"rank":423,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0021233947989866614,"rank":423,"remainingConfigurations":444},{"removed":"Cognition","score":0.00209751807869202,"rank":423,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0022504669557453344,"rank":422,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0022235526221408074,"rank":423,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.002185203688849694,"rank":410,"remainingConfigurations":431},{"removed":"Vals AI","score":0.002064540533035808,"rank":422,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.002146837858026139,"rank":423,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0020743218034966642,"rank":423,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.002143838938340757,"rank":423,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002147826546760522,"rank":423,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0021660457175430147,"rank":423,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0020880381922254022,"rank":423,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0021722628843980924,"rank":423,"remainingConfigurations":444},{"removed":"briefcase","score":0.0021380584573820888,"rank":423,"remainingConfigurations":444},{"removed":"aime","score":0.0020797875485928695,"rank":426,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0021886729027440436,"rank":423,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0022167507953842606,"rank":423,"remainingConfigurations":444},{"removed":"automationbench","score":0.0021396313463885245,"rank":423,"remainingConfigurations":444},{"removed":"critpt","score":0.0017194280480747292,"rank":424,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0021547400902726765,"rank":423,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0022065291115132006,"rank":423,"remainingConfigurations":444},{"removed":"gdpval","score":0.002160505839464714,"rank":423,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0021854450487676677,"rank":423,"remainingConfigurations":444},{"removed":"gpqa","score":0.0021899803610255213,"rank":422,"remainingConfigurations":444},{"removed":"harvey","score":0.002124257392060252,"rank":423,"remainingConfigurations":444},{"removed":"hle","score":0.0020108662625667626,"rank":428,"remainingConfigurations":444},{"removed":"ifbench","score":0.0021834516301319673,"rank":421,"remainingConfigurations":444},{"removed":"itbench","score":0.0021322974509630685,"rank":423,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0021402340245094647,"rank":424,"remainingConfigurations":444},{"removed":"math500","score":0.0021937563961958533,"rank":423,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002550056801903766,"rank":420,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0023669726803923485,"rank":423,"remainingConfigurations":444},{"removed":"omniscience","score":0.0019694144105423888,"rank":421,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0019627081366013458,"rank":421,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002186833667731491,"rank":423,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0022958901485674527,"rank":421,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0027691154917353004,"rank":423,"remainingConfigurations":444},{"removed":"deepswe","score":0.0016736884876569042,"rank":423,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0021484063907729945,"rank":423,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00210848608938247,"rank":423,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00209751807869202,"rank":423,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0021151706619447637,"rank":423,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0021210208768722297,"rank":423,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0021466831212980197,"rank":423,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0021378850423797537,"rank":423,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0021506557922338345,"rank":423,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0021194090534119307,"rank":423,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0021862640639195292,"rank":423,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0021476863583003883,"rank":423,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00209835460367534,"rank":423,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0021311083938503773,"rank":423,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0022038819288474217,"rank":423,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0022235526221408074,"rank":423,"remainingConfigurations":444},{"removed":"frontiermath","score":0.002154649921727667,"rank":423,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.001993530402555264,"rank":423,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0022736113826209935,"rank":423,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.002138674477692586,"rank":423,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0021383248607224556,"rank":423,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0021391379599982356,"rank":423,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0021425925200452174,"rank":423,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00213169018697124,"rank":423,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.002140830862981303,"rank":423,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-4o-mini--effort-non-reasoning":{"score":0.002005890117289301,"rank":424,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0026979872708486727,"rank":424,"remainingConfigurations":444},{"removed":"Datacurve","score":0.001562594304460076,"rank":424,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0019829981728844348,"rank":424,"remainingConfigurations":444},{"removed":"Scale","score":0.002396662033808487,"rank":424,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0019840859077060943,"rank":424,"remainingConfigurations":444},{"removed":"Cognition","score":0.001957623486407094,"rank":424,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0021028478597546977,"rank":423,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0020751637096667005,"rank":424,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.00204646205633296,"rank":411,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0019301276035528104,"rank":423,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0020049665807988283,"rank":424,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.001937208911181984,"rank":424,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.002002166468293629,"rank":424,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.002005890117289301,"rank":424,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.002022884413788718,"rank":424,"remainingConfigurations":444},{"removed":"All provider reports","score":0.001949999606859098,"rank":424,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0020298297260801863,"rank":424,"remainingConfigurations":444},{"removed":"briefcase","score":0.001994750380879301,"rank":424,"remainingConfigurations":444},{"removed":"aime","score":0.0021210249807523387,"rank":425,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0020446942030282293,"rank":424,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0019521688222598878,"rank":424,"remainingConfigurations":444},{"removed":"automationbench","score":0.0019966180782720997,"rank":424,"remainingConfigurations":444},{"removed":"critpt","score":0.0018165720385686765,"rank":423,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.002013977868926795,"rank":424,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002058966404047411,"rank":424,"remainingConfigurations":444},{"removed":"gdpval","score":0.0019065185325165674,"rank":426,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0020366742124352764,"rank":424,"remainingConfigurations":444},{"removed":"gpqa","score":0.0020271876846132985,"rank":424,"remainingConfigurations":444},{"removed":"harvey","score":0.001984032541545343,"rank":424,"remainingConfigurations":444},{"removed":"hle","score":0.002157197438109397,"rank":426,"remainingConfigurations":444},{"removed":"ifbench","score":0.00190584202709198,"rank":426,"remainingConfigurations":444},{"removed":"itbench","score":0.0019922419526817955,"rank":424,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0021503877905566147,"rank":423,"remainingConfigurations":444},{"removed":"math500","score":0.00208099517166481,"rank":427,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0021654455776291518,"rank":424,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002243783733167396,"rank":425,"remainingConfigurations":444},{"removed":"omniscience","score":0.00174296299999724,"rank":424,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0018826838125426276,"rank":422,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0020420558191987957,"rank":424,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0019334003839312375,"rank":426,"remainingConfigurations":444},{"removed":"arc-agi","score":0.002586107626472383,"rank":424,"remainingConfigurations":444},{"removed":"deepswe","score":0.0015637075592438681,"rank":424,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.002006432613304399,"rank":424,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.001969271867619103,"rank":424,"remainingConfigurations":444},{"removed":"frontiercode","score":0.001957623486407094,"rank":424,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.001975405317394,"rank":424,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.001980816837057977,"rank":424,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0020048277685940272,"rank":424,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.001996690869266541,"rank":424,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00200853413346895,"rank":424,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.001979359204007184,"rank":424,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0020418115207678305,"rank":424,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0020057478157336044,"rank":424,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.00195966888129537,"rank":424,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.001990275827093434,"rank":424,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.002058237030192552,"rank":424,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0020751637096667005,"rank":424,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0020110638748827873,"rank":424,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0018610271832097864,"rank":424,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0021237514738669653,"rank":424,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0019973391815886325,"rank":424,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0019970181105694543,"rank":424,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0019977667796433566,"rank":424,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0020010085096123977,"rank":424,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0019908200142082426,"rank":424,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0019993538532942197,"rank":424,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3.5-0.8b--effort-reasoning":{"score":0.001970950374810006,"rank":425,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0026869381466434316,"rank":425,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0015380076641339443,"rank":425,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0019487916618812224,"rank":425,"remainingConfigurations":444},{"removed":"Scale","score":0.0023576593223115826,"rank":425,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0019496015639121238,"rank":425,"remainingConfigurations":444},{"removed":"Cognition","score":0.00193448983012907,"rank":425,"remainingConfigurations":444},{"removed":"LiveBench","score":0.002067526316847684,"rank":424,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0020429808957962477,"rank":425,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0020118005320843286,"rank":412,"remainingConfigurations":431},{"removed":"Vals AI","score":0.001897451420461974,"rank":424,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0019700415600572853,"rank":425,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0019034412569485855,"rank":425,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001967284395216443,"rank":425,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.001970950374810006,"rank":425,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0019876916812449964,"rank":425,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0019160418285040885,"rank":425,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00199574501056367,"rank":425,"remainingConfigurations":444},{"removed":"briefcase","score":0.001968095252733537,"rank":425,"remainingConfigurations":444},{"removed":"aime","score":0.0019424960829820996,"rank":427,"remainingConfigurations":444},{"removed":"apex-agents","score":0.002010097998978175,"rank":425,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.001876989193889549,"rank":425,"remainingConfigurations":444},{"removed":"automationbench","score":0.001969356258332963,"rank":425,"remainingConfigurations":444},{"removed":"critpt","score":0.0014957143881869559,"rank":429,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0019799749056557815,"rank":425,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.002030710673100755,"rank":425,"remainingConfigurations":444},{"removed":"gdpval","score":0.0020042852004768254,"rank":424,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0020026182198302207,"rank":425,"remainingConfigurations":444},{"removed":"gpqa","score":0.002269245981395805,"rank":421,"remainingConfigurations":444},{"removed":"harvey","score":0.0019503460730598491,"rank":425,"remainingConfigurations":444},{"removed":"hle","score":0.0024805575063246766,"rank":423,"remainingConfigurations":444},{"removed":"ifbench","score":0.0020952920064274236,"rank":423,"remainingConfigurations":444},{"removed":"itbench","score":0.001959237293315317,"rank":425,"remainingConfigurations":444},{"removed":"livecodebench","score":0.001992939787957041,"rank":426,"remainingConfigurations":444},{"removed":"math500","score":0.001992349755780326,"rank":428,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002081740908622379,"rank":427,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.00234350611844266,"rank":424,"remainingConfigurations":444},{"removed":"omniscience","score":0.0018904911967764155,"rank":422,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0011509788485215683,"rank":436,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.002009271225596128,"rank":425,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0021513894720934135,"rank":424,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0025680385742040276,"rank":425,"remainingConfigurations":444},{"removed":"deepswe","score":0.0015390986466160747,"rank":425,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.001971482882700728,"rank":425,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0019352573554876475,"rank":425,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00193448983012907,"rank":425,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0019411084145280041,"rank":425,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0019464431649674518,"rank":425,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0019699015056736918,"rank":425,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.001961893043741137,"rank":425,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0019735360834370183,"rank":425,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0019448711164096806,"rank":425,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0020062480156790453,"rank":425,"remainingConfigurations":444},{"removed":"livebench-data","score":0.001970826131640108,"rank":425,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0019255264629629157,"rank":425,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.001955601574174472,"rank":425,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0020224107522386074,"rank":425,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0020429808957962477,"rank":425,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0019780975734986486,"rank":425,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.001830941736223333,"rank":425,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0020861526970015905,"rank":425,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0019625532422969656,"rank":425,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0019622296299954827,"rank":425,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.001962969979206515,"rank":425,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0019661479718154538,"rank":425,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00195613774765284,"rank":425,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.001964529085206972,"rank":425,"remainingConfigurations":444}],"sharedOrderConflicts":0},"amazon-nova-lite--effort-non-reasoning":{"score":0.0019429591255626245,"rank":426,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.002608850656391484,"rank":426,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0015119220843124613,"rank":426,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.001920780891982823,"rank":426,"remainingConfigurations":444},{"removed":"Scale","score":0.00232060801588742,"rank":426,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0019212799723997943,"rank":426,"remainingConfigurations":444},{"removed":"Cognition","score":0.001894563624893447,"rank":426,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0020361227966743975,"rank":425,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0020091624049850274,"rank":426,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.001981169871306579,"rank":413,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0018684522481337725,"rank":425,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0019420649535676945,"rank":426,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0018764467345281715,"rank":426,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001939352991239206,"rank":426,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0019429591255626245,"rank":426,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0019594262700173937,"rank":426,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0018888427479102135,"rank":426,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.001965819514911404,"rank":426,"remainingConfigurations":444},{"removed":"briefcase","score":0.0019287879544194148,"rank":426,"remainingConfigurations":444},{"removed":"aime","score":0.0021288005751392,"rank":424,"remainingConfigurations":444},{"removed":"apex-agents","score":0.001979938502143502,"rank":426,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0018398023136163514,"rank":426,"remainingConfigurations":444},{"removed":"automationbench","score":0.0019291702432696833,"rank":426,"remainingConfigurations":444},{"removed":"critpt","score":0.0015705797221008423,"rank":427,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.001949502515995915,"rank":426,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.001990133710002807,"rank":426,"remainingConfigurations":444},{"removed":"gdpval","score":0.001947054208132651,"rank":425,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001969946376693173,"rank":426,"remainingConfigurations":444},{"removed":"gpqa","score":0.0019371588736910867,"rank":426,"remainingConfigurations":444},{"removed":"harvey","score":0.001921801302710035,"rank":426,"remainingConfigurations":444},{"removed":"hle","score":0.00207337001689966,"rank":427,"remainingConfigurations":444},{"removed":"ifbench","score":0.0016997424139008762,"rank":430,"remainingConfigurations":444},{"removed":"itbench","score":0.0019289921206256415,"rank":426,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0021236444985127134,"rank":425,"remainingConfigurations":444},{"removed":"math500","score":0.0020937268933345003,"rank":426,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0021424954241665967,"rank":425,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0021921602116666584,"rank":426,"remainingConfigurations":444},{"removed":"omniscience","score":0.001669448651971294,"rank":425,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0018195074757746687,"rank":424,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.001977774416468766,"rank":426,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.001999311129541164,"rank":425,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0025020829852466175,"rank":426,"remainingConfigurations":444},{"removed":"deepswe","score":0.0015129985179907948,"rank":426,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.001943484139383506,"rank":426,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0019073776635842128,"rank":426,"remainingConfigurations":444},{"removed":"frontiercode","score":0.001894563624893447,"rank":426,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0019133519255662781,"rank":426,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.001918623042160265,"rank":426,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0019419274009777564,"rank":426,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0019340013102991146,"rank":426,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0019455236824507474,"rank":426,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0019172482346858863,"rank":426,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00197775067549298,"rank":426,"remainingConfigurations":444},{"removed":"livebench-data","score":0.001942822307099191,"rank":426,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0018981898013029936,"rank":426,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0019278324515378004,"rank":426,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.001993675674766974,"rank":426,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0020091624049850274,"rank":426,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0019479513481156054,"rank":426,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0018024412037702376,"rank":426,"remainingConfigurations":444},{"removed":"simpleqa","score":0.002057098382195596,"rank":426,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0019346759697878733,"rank":426,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0019343621688753879,"rank":426,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0019350926672396073,"rank":426,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0019382262531183337,"rank":426,"remainingConfigurations":444},{"removed":"vibe-code","score":0.00192836000831145,"rank":426,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.001936627018036155,"rank":426,"remainingConfigurations":444}],"sharedOrderConflicts":0},"mistral-large-2407--effort-non-reasoning":{"score":0.0018865972019153838,"rank":427,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0025372387833298266,"rank":427,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0014684974710158815,"rank":427,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0018650615842182678,"rank":427,"remainingConfigurations":444},{"removed":"Scale","score":0.0022541556171760163,"rank":427,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0018651023130509213,"rank":427,"remainingConfigurations":444},{"removed":"Cognition","score":0.0018403086245390627,"rank":427,"remainingConfigurations":444},{"removed":"LiveBench","score":0.00197618863952352,"rank":426,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.001952213425943761,"rank":427,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0019200376339031785,"rank":414,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0018133178801170516,"rank":426,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0018857293470948778,"rank":427,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0018220202233487932,"rank":427,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0018830973674286114,"rank":427,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0018865972019153838,"rank":427,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0019025878048879279,"rank":427,"remainingConfigurations":444},{"removed":"All provider reports","score":0.001834059581598102,"rank":427,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0019079754413363324,"rank":427,"remainingConfigurations":444},{"removed":"briefcase","score":0.001875966969887663,"rank":427,"remainingConfigurations":444},{"removed":"aime","score":0.002231743511781395,"rank":423,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0019221349271668223,"rank":427,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0018379557184799462,"rank":427,"remainingConfigurations":444},{"removed":"automationbench","score":0.0018769272880003515,"rank":427,"remainingConfigurations":444},{"removed":"critpt","score":0.0016835210907821766,"rank":425,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0018921178169444127,"rank":427,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0019349884251379458,"rank":427,"remainingConfigurations":444},{"removed":"gdpval","score":0.0018954867610439503,"rank":427,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001915473895512173,"rank":427,"remainingConfigurations":444},{"removed":"gpqa","score":0.0018174127265589998,"rank":428,"remainingConfigurations":444},{"removed":"harvey","score":0.001865482152022641,"rank":427,"remainingConfigurations":444},{"removed":"hle","score":0.002243912439385612,"rank":424,"remainingConfigurations":444},{"removed":"ifbench","score":0.0017486703328371952,"rank":427,"remainingConfigurations":444},{"removed":"itbench","score":0.0018723760254866363,"rank":427,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0019522781650166045,"rank":427,"remainingConfigurations":444},{"removed":"math500","score":0.0021655451052475525,"rank":424,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0019258869134797863,"rank":428,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.002074230497255279,"rank":427,"remainingConfigurations":444},{"removed":"omniscience","score":0.0016170739796958437,"rank":426,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0014083522236829373,"rank":432,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0019197072693396434,"rank":427,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0018888905577991372,"rank":427,"remainingConfigurations":444},{"removed":"arc-agi","score":0.002433582417160698,"rank":427,"remainingConfigurations":444},{"removed":"deepswe","score":0.001469542210719125,"rank":427,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0018871068244804585,"rank":427,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0018518980131809846,"rank":427,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0018403086245390627,"rank":427,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0018578855473911568,"rank":427,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.001863025533493573,"rank":427,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0018855954284324736,"rank":427,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.001877869360768616,"rank":427,"remainingConfigurations":444},{"removed":"livebench-math","score":0.001889094768197543,"rank":427,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0018616138379587831,"rank":427,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0019203738327275071,"rank":427,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0018864725696501668,"rank":427,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0018431284999031645,"rank":427,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0018719058291349231,"rank":427,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0019358538349413818,"rank":427,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.001952213425943761,"rank":427,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0018915880922249384,"rank":427,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0017497226224107763,"rank":427,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0019975428975244464,"rank":427,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0018785514410119726,"rank":427,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0018782488510751883,"rank":427,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0018789606818906807,"rank":427,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0018819989752588467,"rank":427,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0018724196602572058,"rank":427,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.001880447710559073,"rank":427,"remainingConfigurations":444}],"sharedOrderConflicts":1},"deepseek-r1-distill-llama-8b--effort-reasoning":{"score":0.0017753539845267487,"rank":428,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0023890680052321006,"rank":428,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0013818463853766665,"rank":428,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0017551118469367407,"rank":428,"remainingConfigurations":444},{"removed":"Scale","score":0.002120910602692687,"rank":428,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.001754991876425968,"rank":428,"remainingConfigurations":444},{"removed":"Cognition","score":0.0017320694578533042,"rank":428,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0018595597308171206,"rank":427,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.001837737243022163,"rank":428,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0018060241162176844,"rank":415,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0017060219383706506,"rank":427,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.00177453716618926,"rank":428,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0017145744957656162,"rank":428,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001772060136093749,"rank":428,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0017753539845267487,"rank":428,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.001790404123294475,"rank":428,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0017259057434660474,"rank":428,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0017950997361173334,"rank":428,"remainingConfigurations":444},{"removed":"briefcase","score":0.0017661009109690056,"rank":428,"remainingConfigurations":444},{"removed":"aime","score":0.0012573656872376063,"rank":436,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0018085811037364876,"rank":428,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0018183329191169412,"rank":428,"remainingConfigurations":444},{"removed":"automationbench","score":0.0017662484750502003,"rank":428,"remainingConfigurations":444},{"removed":"critpt","score":0.001589028389329297,"rank":426,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.001780283366361906,"rank":428,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.001820647092789397,"rank":428,"remainingConfigurations":444},{"removed":"gdpval","score":0.001784666182734997,"rank":429,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0018072939979555775,"rank":428,"remainingConfigurations":444},{"removed":"gpqa","score":0.0019027379848299145,"rank":427,"remainingConfigurations":444},{"removed":"harvey","score":0.0017554017479064754,"rank":428,"remainingConfigurations":444},{"removed":"hle","score":0.0019639221352169066,"rank":429,"remainingConfigurations":444},{"removed":"ifbench","score":0.001956410760328207,"rank":425,"remainingConfigurations":444},{"removed":"itbench","score":0.0017619915629466434,"rank":428,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0019392828719281031,"rank":428,"remainingConfigurations":444},{"removed":"math500","score":0.0015903413374661153,"rank":431,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.002095673796688022,"rank":426,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0019636444808531304,"rank":428,"remainingConfigurations":444},{"removed":"omniscience","score":0.0015218038970120891,"rank":427,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0016848268994558624,"rank":426,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0018064413139830832,"rank":428,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0017859051400205505,"rank":428,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0022914268702794506,"rank":428,"remainingConfigurations":444},{"removed":"deepswe","score":0.0013828292995026348,"rank":428,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.001775833619040725,"rank":428,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.001742656491518426,"rank":428,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0017320694578533042,"rank":428,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0017483214039032155,"rank":428,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0017531602707639195,"rank":428,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0017744119912299478,"rank":428,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0017671308612277525,"rank":428,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0017777058392415643,"rank":428,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.001751836823803465,"rank":428,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0018071442855613791,"rank":428,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0017752375061057789,"rank":428,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0017344403153212572,"rank":428,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0017615255602635453,"rank":428,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0018217186650049866,"rank":428,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.001837737243022163,"rank":428,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0017801878094296055,"rank":428,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0016465472795568316,"rank":428,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0018798603868381582,"rank":428,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0017677805139268696,"rank":428,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0017674957937504523,"rank":428,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0017681673472649193,"rank":428,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0017710248194804299,"rank":428,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0017620088243115613,"rank":428,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0017695659284738478,"rank":428,"remainingConfigurations":444}],"sharedOrderConflicts":1},"gpt-4-turbo--effort-non-reasoning":{"score":0.0017635734513382552,"rank":429,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.002377305056140454,"rank":429,"remainingConfigurations":444},{"removed":"Datacurve","score":0.001372769602298929,"rank":429,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0017434400268926964,"rank":429,"remainingConfigurations":444},{"removed":"Scale","score":0.002106892683986427,"rank":429,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0017434683519325367,"rank":429,"remainingConfigurations":444},{"removed":"Cognition","score":0.001722681618966021,"rank":429,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0018474270400337944,"rank":428,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0018238665567601794,"rank":429,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0017887079765472908,"rank":416,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0016950178767058562,"rank":428,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0017627619759152467,"rank":429,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0017032082381112958,"rank":429,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001760302401102468,"rank":429,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0017635734513382552,"rank":429,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0017785275170608638,"rank":429,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0017144686555270515,"rank":429,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0017832057175450177,"rank":429,"remainingConfigurations":444},{"removed":"briefcase","score":0.0017545407540613782,"rank":429,"remainingConfigurations":444},{"removed":"aime","score":0.0017289838759806195,"rank":429,"remainingConfigurations":444},{"removed":"apex-agents","score":0.001796805216313478,"rank":429,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0017310898987426208,"rank":429,"remainingConfigurations":444},{"removed":"automationbench","score":0.0017558711315158433,"rank":429,"remainingConfigurations":444},{"removed":"critpt","score":0.0015555926261330826,"rank":428,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0017683110525620533,"rank":429,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.001809463830107913,"rank":429,"remainingConfigurations":444},{"removed":"gdpval","score":0.0017877173343449277,"rank":428,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0017925437100610095,"rank":429,"remainingConfigurations":444},{"removed":"gpqa","score":0.001772162364142386,"rank":429,"remainingConfigurations":444},{"removed":"harvey","score":0.001743916781156021,"rank":429,"remainingConfigurations":444},{"removed":"hle","score":0.0021757923650004072,"rank":425,"remainingConfigurations":444},{"removed":"ifbench","score":0.0017207503204638372,"rank":429,"remainingConfigurations":444},{"removed":"itbench","score":0.001750368560763469,"rank":429,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0016791823452704342,"rank":431,"remainingConfigurations":444},{"removed":"math500","score":0.002146031037432719,"rank":425,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0015463763546748786,"rank":435,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0019549775915327517,"rank":429,"remainingConfigurations":444},{"removed":"omniscience","score":0.001492616232421227,"rank":429,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0016610536711976203,"rank":428,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.001794981773235899,"rank":429,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0017555966132733935,"rank":429,"remainingConfigurations":444},{"removed":"arc-agi","score":0.002278003761097025,"rank":429,"remainingConfigurations":444},{"removed":"deepswe","score":0.0013737457626009503,"rank":429,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.001764049896107872,"rank":429,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0017310933520022708,"rank":429,"remainingConfigurations":444},{"removed":"frontiercode","score":0.001722681618966021,"rank":429,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0017367013659496727,"rank":429,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0017415077911731856,"rank":429,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0017626384663794465,"rank":429,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.001755398541936702,"rank":429,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0017659130997653629,"rank":429,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0017402025987456086,"rank":429,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0017951521492775401,"rank":429,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0017634605464341702,"rank":429,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0017229327364328458,"rank":429,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0017498350801712793,"rank":429,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0018096349081349495,"rank":429,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0018238665567601794,"rank":429,"remainingConfigurations":444},{"removed":"frontiermath","score":0.001768745699621594,"rank":429,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0016354618245739052,"rank":429,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0018676666788115194,"rank":429,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.001756049940470813,"rank":429,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0017557675943737246,"rank":429,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0017564347678720926,"rank":429,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0017592722521491955,"rank":429,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0017503159543858814,"rank":429,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0017578232959189087,"rank":429,"remainingConfigurations":444}],"sharedOrderConflicts":1},"tiny-aya-global--effort-non-reasoning":{"score":0.0016142283528126947,"rank":430,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00217618717046509,"rank":430,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0012577619543568984,"rank":430,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0015960799089413198,"rank":430,"remainingConfigurations":444},{"removed":"Scale","score":0.0019293084856636207,"rank":430,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0015964318730285962,"rank":430,"remainingConfigurations":444},{"removed":"Cognition","score":0.0015763783514448177,"rank":430,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0016922569474417835,"rank":429,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.001673228424139247,"rank":430,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0016490202148479545,"rank":417,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0015536702442689378,"rank":429,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0016134847043397886,"rank":430,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0015589291943704407,"rank":430,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0016112298766592283,"rank":430,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0016142283528126947,"rank":430,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0016279187917706492,"rank":430,"remainingConfigurations":444},{"removed":"All provider reports","score":0.001569233833329321,"rank":430,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0016339791811683646,"rank":430,"remainingConfigurations":444},{"removed":"briefcase","score":0.0016078365571877602,"rank":430,"remainingConfigurations":444},{"removed":"aime","score":0.0015877476105049136,"rank":430,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0016454219916082547,"rank":430,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0016624107970235039,"rank":430,"remainingConfigurations":444},{"removed":"automationbench","score":0.0016069282039069448,"rank":430,"remainingConfigurations":444},{"removed":"critpt","score":0.0011500253227800892,"rank":432,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.001621191145435863,"rank":430,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0016578915085922376,"rank":430,"remainingConfigurations":444},{"removed":"gdpval","score":0.0016233327561447255,"rank":430,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0017071675503656022,"rank":430,"remainingConfigurations":444},{"removed":"gpqa","score":0.0017398013600363187,"rank":430,"remainingConfigurations":444},{"removed":"harvey","score":0.0015970146852979275,"rank":430,"remainingConfigurations":444},{"removed":"hle","score":0.0013333462809021,"rank":434,"remainingConfigurations":444},{"removed":"ifbench","score":0.0017438485082478547,"rank":428,"remainingConfigurations":444},{"removed":"itbench","score":0.0016031040136883102,"rank":430,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0016357574709919057,"rank":433,"remainingConfigurations":444},{"removed":"math500","score":0.001635807327732045,"rank":430,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0017103616315415106,"rank":431,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0017792247413494335,"rank":430,"remainingConfigurations":444},{"removed":"omniscience","score":0.0015069141977412078,"rank":428,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0016790729890455204,"rank":427,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0016435919375639826,"rank":430,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0017510677994855483,"rank":430,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0020856400849027746,"rank":430,"remainingConfigurations":444},{"removed":"deepswe","score":0.0012586570019206148,"rank":430,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0016146647162870004,"rank":430,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0015847340391278945,"rank":430,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0015763783514448177,"rank":430,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0015897075797527275,"rank":430,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0015941143377738185,"rank":430,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0016133679667604893,"rank":430,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0016068128623037085,"rank":430,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0016163590609549609,"rank":430,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0015928429243330872,"rank":430,"remainingConfigurations":444},{"removed":"livebench-language","score":0.001643150107550107,"rank":430,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0016141244032682669,"rank":430,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.001577010993557721,"rank":430,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0016016507869847138,"rank":430,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0016564015784969628,"rank":430,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.001673228424139247,"rank":430,"remainingConfigurations":444},{"removed":"frontiermath","score":0.001618391671365996,"rank":430,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0014980976223080082,"rank":430,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0017089077853476647,"rank":430,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0016073428546875797,"rank":430,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0016070817843841087,"rank":430,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0016076875336186287,"rank":430,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0016102928386088307,"rank":430,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0016020919018492872,"rank":430,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0016089631741947876,"rank":430,"remainingConfigurations":444}],"sharedOrderConflicts":1},"amazon-nova-micro--effort-non-reasoning":{"score":0.0015845504258562145,"rank":431,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0021291115348423912,"rank":432,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0012331898765856422,"rank":431,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0015665943955935054,"rank":431,"remainingConfigurations":444},{"removed":"Scale","score":0.0018930769537039156,"rank":431,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0015667554631919143,"rank":431,"remainingConfigurations":444},{"removed":"Cognition","score":0.0015454750912542354,"rank":431,"remainingConfigurations":444},{"removed":"LiveBench","score":0.001660506281427849,"rank":430,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0016393517044846415,"rank":431,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.001615207557770084,"rank":418,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0015239483023951183,"rank":430,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0015838209885545601,"rank":431,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0015302819710892495,"rank":431,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001581609127163452,"rank":431,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0015845504258562145,"rank":431,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0015979830497198661,"rank":431,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0015403937478113787,"rank":431,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0016029861003251436,"rank":431,"remainingConfigurations":444},{"removed":"briefcase","score":0.0015749061841445016,"rank":431,"remainingConfigurations":444},{"removed":"aime","score":0.0017413354231817885,"rank":428,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0016146996913279498,"rank":431,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0014775775695026541,"rank":433,"remainingConfigurations":444},{"removed":"automationbench","score":0.0015755648910613432,"rank":431,"remainingConfigurations":444},{"removed":"critpt","score":0.0012358351204422716,"rank":431,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0015900456908262116,"rank":431,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0016250526865600624,"rank":431,"remainingConfigurations":444},{"removed":"gdpval","score":0.001592095338037197,"rank":431,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001611348914041578,"rank":431,"remainingConfigurations":444},{"removed":"gpqa","score":0.001613434493539443,"rank":431,"remainingConfigurations":444},{"removed":"harvey","score":0.0015671629010796286,"rank":431,"remainingConfigurations":444},{"removed":"hle","score":0.0015757706179393577,"rank":431,"remainingConfigurations":444},{"removed":"ifbench","score":0.0014941941366815369,"rank":432,"remainingConfigurations":444},{"removed":"itbench","score":0.0015730888158325075,"rank":431,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0017379729517555907,"rank":429,"remainingConfigurations":444},{"removed":"math500","score":0.0017925569592405009,"rank":429,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0017974782549013797,"rank":429,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0017428978466914012,"rank":431,"remainingConfigurations":444},{"removed":"omniscience","score":0.0013337410357282921,"rank":431,"remainingConfigurations":444},{"removed":"tau-bench","score":0.001508139644694008,"rank":429,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.001612695699280262,"rank":431,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0015719318504684849,"rank":431,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0020420992541370555,"rank":431,"remainingConfigurations":444},{"removed":"deepswe","score":0.0012340681612334657,"rank":431,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0015849788270927256,"rank":431,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0015554658303423641,"rank":431,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0015454750912542354,"rank":431,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0015604011744737407,"rank":431,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.001564711428723937,"rank":431,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0015837096470178401,"rank":431,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0015772531661685195,"rank":431,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0015866483238914616,"rank":431,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0015635530031039898,"rank":431,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0016129397328315009,"rank":431,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0015844481948201615,"rank":431,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.001548018606048294,"rank":431,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0015722025530262322,"rank":431,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0016259471985299026,"rank":431,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0016393517044846415,"rank":431,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0015888034007119425,"rank":431,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.001469641006828508,"rank":431,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0016778387563588586,"rank":431,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0015777893653459057,"rank":431,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0015775355047025527,"rank":431,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0015781304863902808,"rank":431,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.001580687410966148,"rank":431,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0015726369213782882,"rank":431,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0015793818462126808,"rank":431,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-4b--effort-non-reasoning":{"score":0.0015585405064157765,"rank":432,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.001068377473278154,"rank":202,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0021326233510382438,"rank":431,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0012273086788969405,"rank":432,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.001542171359824437,"rank":432,"remainingConfigurations":444},{"removed":"Scale","score":0.0018614611294338736,"rank":432,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.001545136220141189,"rank":432,"remainingConfigurations":444},{"removed":"Cognition","score":0.0015453767902935476,"rank":432,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0016305348978165055,"rank":431,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0016102292253702443,"rank":432,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.001596837403667591,"rank":419,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0015068259242317767,"rank":431,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.001557845989746707,"rank":432,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0015057003349419331,"rank":432,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0015557708148659,"rank":432,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0015585405064157765,"rank":432,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.001571574016087733,"rank":432,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0015156155188092062,"rank":432,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0015752671400863594,"rank":432,"remainingConfigurations":444},{"removed":"briefcase","score":0.0015477618431430278,"rank":432,"remainingConfigurations":444},{"removed":"aime","score":0.0014200264142485875,"rank":434,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0015872055062351403,"rank":432,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0015402105338839624,"rank":431,"remainingConfigurations":444},{"removed":"automationbench","score":0.001548299371530098,"rank":432,"remainingConfigurations":444},{"removed":"critpt","score":0.001388618235707871,"rank":430,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.001562730230021062,"rank":432,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.001592391072225843,"rank":432,"remainingConfigurations":444},{"removed":"gdpval","score":0.0015695335398513447,"rank":432,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0015860466164579505,"rank":432,"remainingConfigurations":444},{"removed":"gpqa","score":0.00161189123744602,"rank":432,"remainingConfigurations":444},{"removed":"harvey","score":0.0015405937603551268,"rank":432,"remainingConfigurations":444},{"removed":"hle","score":0.0017900697256317255,"rank":430,"remainingConfigurations":444},{"removed":"ifbench","score":0.0015204058840957468,"rank":431,"remainingConfigurations":444},{"removed":"itbench","score":0.0015472967600742603,"rank":432,"remainingConfigurations":444},{"removed":"livecodebench","score":0.001685614034984819,"rank":430,"remainingConfigurations":444},{"removed":"math500","score":0.0014156271148168178,"rank":435,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0017042764243527493,"rank":432,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0017180639217280493,"rank":432,"remainingConfigurations":444},{"removed":"omniscience","score":0.001355959486994433,"rank":430,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0014481288612947865,"rank":430,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0015847857030892858,"rank":432,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.001559352522262598,"rank":432,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0020414717913760376,"rank":432,"remainingConfigurations":444},{"removed":"deepswe","score":0.0012282079669309646,"rank":432,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0015589577246364983,"rank":432,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0015297874056758663,"rank":432,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0015453767902935476,"rank":432,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.001535646585661964,"rank":432,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0015388306370503722,"rank":432,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.001557738381519904,"rank":432,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0015512911558555854,"rank":432,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0015610197992445157,"rank":432,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0015372734396054018,"rank":432,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0015863202836866703,"rank":432,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0015585741292494456,"rank":432,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0015228944565772223,"rank":432,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0015463233161040447,"rank":432,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0015992007160761823,"rank":432,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0016102292253702443,"rank":432,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0015805594116252118,"rank":432,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0014192162662497044,"rank":432,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0016707503229028235,"rank":432,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.001551846528444147,"rank":432,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.001551729065131193,"rank":432,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0015521622832289086,"rank":432,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.001554796426943471,"rank":432,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0015469309837312145,"rank":432,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0015533944806442165,"rank":432,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-0.6b--effort-reasoning":{"score":0.0014852116653943197,"rank":433,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0020050016652706183,"rank":433,"remainingConfigurations":444},{"removed":"Datacurve","score":0.001156837820215592,"rank":433,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.001468441298566041,"rank":433,"remainingConfigurations":444},{"removed":"Scale","score":0.001775447935201374,"rank":433,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0014685154798936234,"rank":433,"remainingConfigurations":444},{"removed":"Cognition","score":0.0014511089190857817,"rank":433,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0015566470133399016,"rank":432,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0015390336006423121,"rank":433,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0014928274772064397,"rank":421,"remainingConfigurations":431},{"removed":"Vals AI","score":0.001428251698858773,"rank":432,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.001484527585840535,"rank":433,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0014343341751403913,"rank":433,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0014824536513526043,"rank":433,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0014852116653943197,"rank":433,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00149781288880526,"rank":433,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0014438207451516049,"rank":433,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0015025569013852557,"rank":433,"remainingConfigurations":444},{"removed":"briefcase","score":0.0014804631363742303,"rank":433,"remainingConfigurations":444},{"removed":"aime","score":0.0014678782374410405,"rank":433,"remainingConfigurations":444},{"removed":"apex-agents","score":0.001513842036449693,"rank":433,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0014869098605463634,"rank":432,"remainingConfigurations":444},{"removed":"automationbench","score":0.001479852302968078,"rank":433,"remainingConfigurations":444},{"removed":"critpt","score":0.0011473089588115203,"rank":433,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0014905990644151644,"rank":433,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0015254918095862578,"rank":433,"remainingConfigurations":444},{"removed":"gdpval","score":0.0014946112785856709,"rank":433,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0015124486222091733,"rank":433,"remainingConfigurations":444},{"removed":"gpqa","score":0.001575927616710674,"rank":433,"remainingConfigurations":444},{"removed":"harvey","score":0.001469070659758331,"rank":433,"remainingConfigurations":444},{"removed":"hle","score":0.0013463659383682275,"rank":433,"remainingConfigurations":444},{"removed":"ifbench","score":0.0014732631180776855,"rank":433,"remainingConfigurations":444},{"removed":"itbench","score":0.0014749054779669788,"rank":433,"remainingConfigurations":444},{"removed":"livecodebench","score":0.001666722296687095,"rank":432,"remainingConfigurations":444},{"removed":"math500","score":0.0015325373049193552,"rank":432,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0017798137830904671,"rank":430,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0016390469944093146,"rank":434,"remainingConfigurations":444},{"removed":"omniscience","score":0.0013172338028189078,"rank":432,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0013009901986055347,"rank":434,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.001512403541547679,"rank":433,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0015522108737327943,"rank":433,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0019212683499900427,"rank":433,"remainingConfigurations":444},{"removed":"deepswe","score":0.0011576602995268294,"rank":433,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.001485613072101959,"rank":433,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0014579752137842438,"rank":433,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0014511089190857817,"rank":433,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0014626212762501069,"rank":433,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0014666674024095827,"rank":433,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.001484423140359858,"rank":433,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0014783491288254318,"rank":433,"remainingConfigurations":444},{"removed":"livebench-math","score":0.001487176591183608,"rank":433,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0014655244246667522,"rank":433,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0015118239827427266,"rank":433,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0014851189295410877,"rank":433,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0014509629427145228,"rank":433,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0014736348288774505,"rank":433,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0015240276078091763,"rank":433,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0015390336006423121,"rank":433,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0014900184310023973,"rank":433,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.001378227007290877,"rank":433,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0015725992495299376,"rank":433,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0014788738157627424,"rank":433,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0014786336858635032,"rank":433,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0014791955345346893,"rank":433,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0014815870647849037,"rank":433,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0014740404763708456,"rank":433,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0014803671031866858,"rank":433,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3n-e4b-it--effort-non-reasoning":{"score":0.0014720076001073458,"rank":434,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.001978540512576378,"rank":434,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0011458853933162027,"rank":434,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.001455439666445744,"rank":434,"remainingConfigurations":444},{"removed":"Scale","score":0.0017589509551332993,"rank":434,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0014557683525093692,"rank":434,"remainingConfigurations":444},{"removed":"Cognition","score":0.0014359237536697694,"rank":434,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0015432068251696237,"rank":433,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0015227608470517195,"rank":434,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0015017862682507562,"rank":420,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0014165079912566896,"rank":433,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0014713296183919838,"rank":434,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0014215705457253684,"rank":434,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0014692733952678535,"rank":434,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0014720076001073458,"rank":434,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.001484486879879111,"rank":434,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0014309628359124103,"rank":434,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0014896772335261388,"rank":434,"remainingConfigurations":444},{"removed":"briefcase","score":0.0014608437942099615,"rank":434,"remainingConfigurations":444},{"removed":"aime","score":0.0015000833855628962,"rank":431,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0015003397969238798,"rank":434,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.001475147526470537,"rank":434,"remainingConfigurations":444},{"removed":"automationbench","score":0.0014602115149771801,"rank":434,"remainingConfigurations":444},{"removed":"critpt","score":0.0011420244087765167,"rank":434,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.001477486185100826,"rank":434,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0015064735545962952,"rank":434,"remainingConfigurations":444},{"removed":"gdpval","score":0.0014732352380845079,"rank":434,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0014927040247466564,"rank":434,"remainingConfigurations":444},{"removed":"gpqa","score":0.0015410746117131603,"rank":434,"remainingConfigurations":444},{"removed":"harvey","score":0.001456080397687725,"rank":434,"remainingConfigurations":444},{"removed":"hle","score":0.0014972546261657236,"rank":432,"remainingConfigurations":444},{"removed":"ifbench","score":0.0014123629111368054,"rank":434,"remainingConfigurations":444},{"removed":"itbench","score":0.001461617982626546,"rank":434,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0015920324818945164,"rank":435,"remainingConfigurations":444},{"removed":"math500","score":0.0014928476047391824,"rank":433,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0016838237177740072,"rank":433,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0016682301178182297,"rank":433,"remainingConfigurations":444},{"removed":"omniscience","score":0.0012819376152355553,"rank":433,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0014194414538856112,"rank":431,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0014984928525633252,"rank":434,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0014262689211283503,"rank":434,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0018973241163852735,"rank":434,"remainingConfigurations":444},{"removed":"deepswe","score":0.0011467018969751816,"rank":434,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0014724058795359245,"rank":434,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.001445040632009022,"rank":434,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0014359237536697694,"rank":434,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0014495817552652142,"rank":434,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.001453568870502386,"rank":434,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.001471227593134742,"rank":434,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0014652797635826178,"rank":434,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0014739540886034698,"rank":434,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0014525051803390126,"rank":434,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0014983908852731073,"rank":434,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0014719092829378925,"rank":434,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.001438059582722231,"rank":434,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0014605350926052965,"rank":434,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0015104696425987142,"rank":434,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0015227608470517195,"rank":434,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0014758718758811126,"rank":434,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0013654041040389554,"rank":434,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0015586833680408315,"rank":434,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0014657253613618746,"rank":434,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0014654899408632022,"rank":434,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.00146604147438559,"rank":434,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0014684192478003953,"rank":434,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0014609379662651031,"rank":434,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0014672053634427935,"rank":434,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3-4b-it--effort-non-reasoning":{"score":0.0014206741978264048,"rank":435,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.001909285537694038,"rank":435,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0011056841985456311,"rank":435,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0014047011210111479,"rank":435,"remainingConfigurations":444},{"removed":"Scale","score":0.0016978244750583662,"rank":435,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0014048543971652639,"rank":435,"remainingConfigurations":444},{"removed":"Cognition","score":0.0013855510583749909,"rank":435,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0014893062104185879,"rank":434,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0014695960341280466,"rank":435,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0014539408909088447,"rank":422,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0013669828624375165,"rank":434,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0014200197584369372,"rank":435,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0013719906262449975,"rank":435,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0014180350079219018,"rank":435,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0014206741978264048,"rank":435,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0014327177921444742,"rank":435,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0013810545098326846,"rank":435,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0014376294982646667,"rank":435,"remainingConfigurations":444},{"removed":"briefcase","score":0.001408346896035785,"rank":435,"remainingConfigurations":444},{"removed":"aime","score":0.0014779893175365353,"rank":432,"remainingConfigurations":444},{"removed":"apex-agents","score":0.001448084859161563,"rank":435,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0013601948455348861,"rank":435,"remainingConfigurations":444},{"removed":"automationbench","score":0.001406280119045491,"rank":435,"remainingConfigurations":444},{"removed":"critpt","score":0.0011072743538151498,"rank":435,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0014258469680978846,"rank":435,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.001451159503879966,"rank":435,"remainingConfigurations":444},{"removed":"gdpval","score":0.0014210528758137836,"rank":435,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0014826087185957112,"rank":435,"remainingConfigurations":444},{"removed":"gpqa","score":0.001487252244096321,"rank":435,"remainingConfigurations":444},{"removed":"harvey","score":0.0014053044625659782,"rank":435,"remainingConfigurations":444},{"removed":"hle","score":0.0013221953046230446,"rank":435,"remainingConfigurations":444},{"removed":"ifbench","score":0.0013472321353091453,"rank":435,"remainingConfigurations":444},{"removed":"itbench","score":0.0014106854187562658,"rank":435,"remainingConfigurations":444},{"removed":"livecodebench","score":0.001598821548830102,"rank":434,"remainingConfigurations":444},{"removed":"math500","score":0.0014567682149691224,"rank":434,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0016600905356251878,"rank":434,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0016005508723093299,"rank":435,"remainingConfigurations":444},{"removed":"omniscience","score":0.0012400271092043755,"rank":434,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0013622419740081332,"rank":433,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0014461864678149575,"rank":435,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0014251210688041053,"rank":435,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0018312997375988479,"rank":435,"remainingConfigurations":444},{"removed":"deepswe","score":0.0011064722603088316,"rank":435,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0014210586755843864,"rank":435,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0013946390203279507,"rank":435,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0013855510583749909,"rank":435,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0013990173543600097,"rank":435,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0014028744026615136,"rank":435,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0014199207808566214,"rank":435,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0014141843461827185,"rank":435,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0014225524887915553,"rank":435,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.001401852053549632,"rank":435,"remainingConfigurations":444},{"removed":"livebench-language","score":0.001446140194850117,"rank":435,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0014205765839081775,"rank":435,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0013879066213228987,"rank":435,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0014096015290332633,"rank":435,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0014577991882974391,"rank":435,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0014695960341280466,"rank":435,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0014243063013862215,"rank":435,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0013178895519389989,"rank":435,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0015043240945681352,"rank":435,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.001414610210165793,"rank":435,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0014143829246811796,"rank":435,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.001414915553436403,"rank":435,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0014172104801681781,"rank":435,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0014099895197248597,"rank":435,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0014160383879005109,"rank":435,"remainingConfigurations":444}],"sharedOrderConflicts":0},"phi-4-mini-instruct--effort-non-reasoning":{"score":0.0012232503321692077,"rank":436,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0016454023404647588,"rank":436,"remainingConfigurations":444},{"removed":"Datacurve","score":0.000952407303027696,"rank":436,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0012095761575252222,"rank":436,"remainingConfigurations":444},{"removed":"Scale","score":0.0014620814794468065,"rank":436,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0012098375616273521,"rank":436,"remainingConfigurations":444},{"removed":"Cognition","score":0.0011936341896326443,"rank":436,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0012827382153779798,"rank":435,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0012657578341328428,"rank":436,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0012486064717778164,"rank":424,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0011777100331650297,"rank":435,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.001222686684338928,"rank":436,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0011813213724772818,"rank":436,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0012209779720327467,"rank":436,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0012232503321692077,"rank":436,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0012336226479590976,"rank":436,"remainingConfigurations":444},{"removed":"All provider reports","score":0.00118912790252252,"rank":436,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.001238217568557953,"rank":436,"remainingConfigurations":444},{"removed":"briefcase","score":0.0012154424040585936,"rank":436,"remainingConfigurations":444},{"removed":"aime","score":0.0013069301461678458,"rank":435,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0012470361068052736,"rank":436,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0010979055289408338,"rank":437,"remainingConfigurations":444},{"removed":"automationbench","score":0.001214842907790026,"rank":436,"remainingConfigurations":444},{"removed":"critpt","score":0.0009177892672898912,"rank":438,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0012281647542006827,"rank":436,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0012530993416386713,"rank":436,"remainingConfigurations":444},{"removed":"gdpval","score":0.001236985343601974,"rank":436,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001240986891467942,"rank":437,"remainingConfigurations":444},{"removed":"gpqa","score":0.0012422092724324618,"rank":436,"remainingConfigurations":444},{"removed":"harvey","score":0.0012101700187694276,"rank":436,"remainingConfigurations":444},{"removed":"hle","score":0.0012196344034920007,"rank":436,"remainingConfigurations":444},{"removed":"ifbench","score":0.0012303878450734293,"rank":436,"remainingConfigurations":444},{"removed":"itbench","score":0.0012148608866039301,"rank":436,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0013511082516546615,"rank":436,"remainingConfigurations":444},{"removed":"math500","score":0.0013640195073535953,"rank":436,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0014009710706777946,"rank":436,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0013483828784402673,"rank":436,"remainingConfigurations":444},{"removed":"omniscience","score":0.0010239115772197641,"rank":437,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0011686868237139722,"rank":435,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.001245400048540182,"rank":436,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0012399623251915233,"rank":436,"remainingConfigurations":444},{"removed":"arc-agi","score":0.001577742240219733,"rank":436,"remainingConfigurations":444},{"removed":"deepswe","score":0.0009530863196244435,"rank":436,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0012235814443705589,"rank":436,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0012008488534271595,"rank":436,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0011936341896326443,"rank":436,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0012046218878870518,"rank":436,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0012079339538777106,"rank":436,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0012226026154155765,"rank":436,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.001217666633026439,"rank":436,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0012248695446284482,"rank":436,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0012070301101952026,"rank":436,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0012451859510499484,"rank":436,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0012231725396372889,"rank":436,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0011950262158116442,"rank":436,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.001213710520501369,"rank":436,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.001255231632022823,"rank":436,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0012657578341328428,"rank":436,"remainingConfigurations":444},{"removed":"frontiermath","score":0.001226525521034897,"rank":436,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0011346824802486329,"rank":436,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0012953980459091167,"rank":436,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0012180274132761397,"rank":436,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0012178316707832976,"rank":436,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0012182893623939306,"rank":436,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0012202669486532137,"rank":436,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0012140473074851892,"rank":436,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0012192572931547438,"rank":436,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-1.7b--effort-non-reasoning":{"score":0.0012011723518672367,"rank":437,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0006750612315699371,"rank":203,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0016315753070019862,"rank":437,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0009458168336690375,"rank":437,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.001188500542132566,"rank":437,"remainingConfigurations":444},{"removed":"Scale","score":0.0014355981533833372,"rank":437,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.001192133716690347,"rank":437,"remainingConfigurations":444},{"removed":"Cognition","score":0.001185984248321197,"rank":437,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0012585484997559091,"rank":436,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.00124166348513374,"rank":437,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0013300187237291693,"rank":423,"remainingConfigurations":431},{"removed":"Vals AI","score":0.001164760146681108,"rank":436,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.001200632577414371,"rank":437,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0011603518755660472,"rank":437,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0011990227635833542,"rank":437,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0012011723518672367,"rank":437,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0012112393243144135,"rank":437,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0011679962487246458,"rank":437,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0012146163679574145,"rank":437,"remainingConfigurations":444},{"removed":"briefcase","score":0.001194072784942942,"rank":437,"remainingConfigurations":444},{"removed":"aime","score":0.0011496422213899164,"rank":437,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0012234468840017186,"rank":437,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0012042465443817523,"rank":436,"remainingConfigurations":444},{"removed":"automationbench","score":0.0011939775873375095,"rank":437,"remainingConfigurations":444},{"removed":"critpt","score":0.0009585405877712703,"rank":436,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0012049178713377038,"rank":437,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0012294327151584294,"rank":437,"remainingConfigurations":444},{"removed":"gdpval","score":0.0012036225011506346,"rank":437,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0012572985159085546,"rank":436,"remainingConfigurations":444},{"removed":"gpqa","score":0.0012243041106669713,"rank":437,"remainingConfigurations":444},{"removed":"harvey","score":0.0011875825349430215,"rank":437,"remainingConfigurations":444},{"removed":"hle","score":0.0011492555813876143,"rank":437,"remainingConfigurations":444},{"removed":"ifbench","score":0.001204717518787055,"rank":437,"remainingConfigurations":444},{"removed":"itbench","score":0.0011925347231595555,"rank":437,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0013068269260416562,"rank":437,"remainingConfigurations":444},{"removed":"math500","score":0.0012472213858134395,"rank":438,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0013702360708569093,"rank":437,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.001321550377936436,"rank":437,"remainingConfigurations":444},{"removed":"omniscience","score":0.0010608996513209895,"rank":436,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0010417735638958607,"rank":437,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0012215509326845779,"rank":437,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0012352468915443654,"rank":437,"remainingConfigurations":444},{"removed":"arc-agi","score":0.001560948831909204,"rank":437,"remainingConfigurations":444},{"removed":"deepswe","score":0.0009465088998266868,"rank":437,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0012014948047242653,"rank":437,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0011791731815707365,"rank":437,"remainingConfigurations":444},{"removed":"frontiercode","score":0.001185984248321197,"rank":437,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0011836103614800309,"rank":437,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0011859870106222313,"rank":437,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0012005508354327665,"rank":437,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0011956107741264543,"rank":437,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0012030298528203618,"rank":437,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.001184865456828847,"rank":437,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0012226229156179296,"rank":437,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0012011937754355568,"rank":437,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.001173622612005823,"rank":437,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0011917753072191804,"rank":437,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0012325116712745964,"rank":437,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.00124166348513374,"rank":437,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0012183048420448522,"rank":437,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.001104684012700163,"rank":437,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0012887073394155168,"rank":437,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.001196014194247342,"rank":437,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.001195911706007412,"rank":437,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0011962541728993785,"rank":437,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0011982836932027865,"rank":437,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0011922102432969362,"rank":437,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0011972068978897772,"rank":437,"remainingConfigurations":444}],"sharedOrderConflicts":0},"phi-4-multimodal-instruct--effort-non-reasoning":{"score":0.0010686021181837448,"rank":438,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0014460310180062245,"rank":438,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0008329853708125061,"rank":438,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0010566961804114488,"rank":438,"remainingConfigurations":444},{"removed":"Scale","score":0.001277965589258045,"rank":438,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0010568595783765563,"rank":438,"remainingConfigurations":444},{"removed":"Cognition","score":0.0010451361029337259,"rank":438,"remainingConfigurations":444},{"removed":"LiveBench","score":0.001120260531255609,"rank":437,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.001107322425825511,"rank":438,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.001078872379470737,"rank":425,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0010279063127422588,"rank":437,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.001068109733616553,"rank":438,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0010319742522067244,"rank":438,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.001066617094476175,"rank":438,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0010686021181837448,"rank":438,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0010776725844390664,"rank":438,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0010388027535088637,"rank":438,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0010811285629113109,"rank":438,"remainingConfigurations":444},{"removed":"briefcase","score":0.0010661016973366713,"rank":438,"remainingConfigurations":444},{"removed":"aime","score":0.001043351408839572,"rank":438,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0010894142371305048,"rank":438,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0010491932733757113,"rank":438,"remainingConfigurations":444},{"removed":"automationbench","score":0.001065527886612814,"rank":438,"remainingConfigurations":444},{"removed":"critpt","score":0.0009454209494554117,"rank":437,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0010724634837056093,"rank":438,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0010983108326986927,"rank":438,"remainingConfigurations":444},{"removed":"gdpval","score":0.0010752677813510123,"rank":438,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001088085095040854,"rank":438,"remainingConfigurations":444},{"removed":"gpqa","score":0.0010735133152347182,"rank":438,"remainingConfigurations":444},{"removed":"harvey","score":0.0010570039758923692,"rank":438,"remainingConfigurations":444},{"removed":"hle","score":0.000767151153761078,"rank":441,"remainingConfigurations":444},{"removed":"ifbench","score":0.00103284539977359,"rank":438,"remainingConfigurations":444},{"removed":"itbench","score":0.0010612252008649228,"rank":438,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0012080597588778887,"rank":438,"remainingConfigurations":444},{"removed":"math500","score":0.0012776381454732155,"rank":437,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0012554123249815723,"rank":438,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.001237682887072907,"rank":438,"remainingConfigurations":444},{"removed":"omniscience","score":0.0009145919778943329,"rank":438,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0009998234875106661,"rank":438,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0010882375943286181,"rank":438,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0010738678224722238,"rank":438,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0013843457057641474,"rank":438,"remainingConfigurations":444},{"removed":"deepswe","score":0.0008335778150616342,"rank":438,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0010688911129411362,"rank":438,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.001048959971378263,"rank":438,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0010451361029337259,"rank":438,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0010523592700114094,"rank":438,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0010552657464296146,"rank":438,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0010680360568055523,"rank":438,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0010636659391463135,"rank":438,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0010700207169971703,"rank":438,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0010544215873616656,"rank":438,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0010877637983668555,"rank":438,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0010685351533910976,"rank":438,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0010439432263621045,"rank":438,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.001060265982747544,"rank":438,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0010965536153526702,"rank":438,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.001107322425825511,"rank":438,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0010718540721988102,"rank":438,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.000991356673714611,"rank":438,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0011317455393376377,"rank":438,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0010640376944238087,"rank":438,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.001063865646363791,"rank":438,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0010642708935821614,"rank":438,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0010659911161544854,"rank":438,"remainingConfigurations":444},{"removed":"vibe-code","score":0.001060558043101687,"rank":438,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0010651135520290539,"rank":438,"remainingConfigurations":444}],"sharedOrderConflicts":0},"qwen3-0.6b--effort-non-reasoning":{"score":0.0009988612617428054,"rank":439,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.001353532038046166,"rank":439,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00077844590603714,"rank":439,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.000987743689346609,"rank":439,"remainingConfigurations":444},{"removed":"Scale","score":0.0011948463562407123,"rank":439,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0009878140109707498,"rank":439,"remainingConfigurations":444},{"removed":"Cognition","score":0.0009769618833495237,"rank":439,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0010473464165810492,"rank":438,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.001036556278245747,"rank":439,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0010070459772937742,"rank":426,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0009611467818938791,"rank":438,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0009984008984515588,"rank":439,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0009646174530329342,"rank":439,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.000997005605478104,"rank":439,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0009988612617428054,"rank":439,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0010073391430243937,"rank":439,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0009709994839047605,"rank":439,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0010109543393789615,"rank":439,"remainingConfigurations":444},{"removed":"briefcase","score":0.000998317771774313,"rank":439,"remainingConfigurations":444},{"removed":"aime","score":0.0010050349014783836,"rank":439,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0010185084848249393,"rank":439,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0009767070320453376,"rank":439,"remainingConfigurations":444},{"removed":"automationbench","score":0.0009981469954781824,"rank":439,"remainingConfigurations":444},{"removed":"critpt","score":0.0007212526698810875,"rank":439,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0010030876711824206,"rank":439,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0010288410108126138,"rank":439,"remainingConfigurations":444},{"removed":"gdpval","score":0.0010083362128404992,"rank":439,"remainingConfigurations":444},{"removed":"gmmlu","score":0.001019363031355893,"rank":439,"remainingConfigurations":444},{"removed":"gpqa","score":0.0010415497608397294,"rank":439,"remainingConfigurations":444},{"removed":"harvey","score":0.0009881913203383917,"rank":439,"remainingConfigurations":444},{"removed":"hle","score":0.0008837968981107,"rank":439,"remainingConfigurations":444},{"removed":"ifbench","score":0.0009804117741280451,"rank":439,"remainingConfigurations":444},{"removed":"itbench","score":0.0009923570989438764,"rank":439,"remainingConfigurations":444},{"removed":"livecodebench","score":0.001104180087116398,"rank":439,"remainingConfigurations":444},{"removed":"math500","score":0.0011711977743064678,"rank":439,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0011780804924199115,"rank":439,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0011053422557811357,"rank":439,"remainingConfigurations":444},{"removed":"omniscience","score":0.0008807717771287704,"rank":439,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0009179033588124535,"rank":439,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0010174726568599752,"rank":439,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0010293463004097437,"rank":439,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0012963492596635743,"rank":439,"remainingConfigurations":444},{"removed":"deepswe","score":0.0007789997985984224,"rank":439,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0009991314419673706,"rank":439,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0009805518609795486,"rank":439,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0009769618833495237,"rank":439,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0009836769198577333,"rank":439,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.000986395245430538,"rank":439,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.000998331702022542,"rank":439,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0009942587054834501,"rank":439,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0010001856919948265,"rank":439,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0009856038894631434,"rank":439,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0010167758394649558,"rank":439,"remainingConfigurations":444},{"removed":"livebench-data","score":0.000998801148095815,"rank":439,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0009758074052421739,"rank":439,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0009910671630684687,"rank":439,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0010249939548642982,"rank":439,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.001036556278245747,"rank":439,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0010023835735049338,"rank":439,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0009270870641170046,"rank":439,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0010577956010570245,"rank":439,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0009945945427274224,"rank":439,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0009944333188375985,"rank":439,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0009948112562622857,"rank":439,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0009964207705468158,"rank":439,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0009913415020581845,"rank":439,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0009955997837294702,"rank":439,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3n-e2b-it--effort-non-reasoning":{"score":0.0009387125400343871,"rank":440,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.00126425892178815,"rank":440,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0007308846154152675,"rank":440,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0009283327415782403,"rank":440,"remainingConfigurations":444},{"removed":"Scale","score":0.001122236103332802,"rank":440,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.000928385897537931,"rank":440,"remainingConfigurations":444},{"removed":"Cognition","score":0.0009162751040278153,"rank":440,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0009842325763935588,"rank":439,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0009719993853552832,"rank":440,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0009574541082397625,"rank":427,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0009035437599026116,"rank":439,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0009382800099576909,"rank":440,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0009065291328573705,"rank":440,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.000936969003266671,"rank":440,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0009387125400343871,"rank":440,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0009466751286550391,"rank":440,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0009125228253815481,"rank":440,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0009501031659829235,"rank":440,"remainingConfigurations":444},{"removed":"briefcase","score":0.0009342600325441651,"rank":440,"remainingConfigurations":444},{"removed":"aime","score":0.0009449599719887131,"rank":440,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0009569954072381325,"rank":440,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0009141772214759047,"rank":440,"remainingConfigurations":444},{"removed":"automationbench","score":0.0009334099098006273,"rank":440,"remainingConfigurations":444},{"removed":"critpt","score":0.0006648137707360277,"rank":440,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0009426368611692701,"rank":440,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0009626360877007589,"rank":440,"remainingConfigurations":444},{"removed":"gdpval","score":0.0009419932118380749,"rank":440,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0009531922786882124,"rank":440,"remainingConfigurations":444},{"removed":"gpqa","score":0.0009808575263275559,"rank":440,"remainingConfigurations":444},{"removed":"harvey","score":0.0009286099588023677,"rank":440,"remainingConfigurations":444},{"removed":"hle","score":0.0009396749107519659,"rank":438,"remainingConfigurations":444},{"removed":"ifbench","score":0.0009155781833789078,"rank":440,"remainingConfigurations":444},{"removed":"itbench","score":0.0009323040054706025,"rank":440,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0010423408680792186,"rank":440,"remainingConfigurations":444},{"removed":"math500","score":0.001055152409097367,"rank":440,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.001086776819990809,"rank":440,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0010317677809973441,"rank":440,"remainingConfigurations":444},{"removed":"omniscience","score":0.0008042689613519208,"rank":440,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0009099948469677746,"rank":440,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0009556392259340915,"rank":440,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0009212996327416224,"rank":440,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0012121086591135384,"rank":440,"remainingConfigurations":444},{"removed":"deepswe","score":0.0007314055463910146,"rank":440,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0009389665851253429,"rank":440,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.000921479925935908,"rank":440,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0009162751040278153,"rank":440,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0009244105532697245,"rank":440,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.000926958361032326,"rank":440,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0009382153208245661,"rank":440,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0009344083007254873,"rank":440,"remainingConfigurations":444},{"removed":"livebench-math","score":0.000939958846436693,"rank":440,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0009262519519749724,"rank":440,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0009555515595968915,"rank":440,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0009386551363610476,"rank":440,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0009170450852147082,"rank":440,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0009313871070035716,"rank":440,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0009632715443739912,"rank":440,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0009719993853552832,"rank":440,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0009413720434978198,"rank":440,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0008706140648843856,"rank":440,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0009941785443603878,"rank":440,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0009347019209118085,"rank":440,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0009345516869685436,"rank":440,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0009349045480228404,"rank":440,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0009364202809771252,"rank":440,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0009316462046476165,"rank":440,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0009356465079241179,"rank":440,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3-1b-it--effort-non-reasoning":{"score":0.000891196263350803,"rank":441,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0012005039362819713,"rank":441,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0006937456569319512,"rank":441,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0008813698592716534,"rank":441,"remainingConfigurations":444},{"removed":"Scale","score":0.0010655834100826921,"rank":441,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.000881341077197499,"rank":441,"remainingConfigurations":444},{"removed":"Cognition","score":0.0008697517175668291,"rank":441,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0009344040773437461,"rank":440,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.000922737166553503,"rank":441,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0009073436942702131,"rank":428,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0008577762360963433,"rank":440,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0008907855595599616,"rank":441,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.000860638384929533,"rank":441,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0008895407229470067,"rank":441,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.000891196263350803,"rank":441,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0008987555173032882,"rank":441,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0008663281211047927,"rank":441,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0009020676429679727,"rank":441,"remainingConfigurations":444},{"removed":"briefcase","score":0.0008868573340963448,"rank":441,"remainingConfigurations":444},{"removed":"aime","score":0.0009427187021216057,"rank":441,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0009085467613677286,"rank":441,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0008649677217103972,"rank":441,"remainingConfigurations":444},{"removed":"automationbench","score":0.0008861794619644918,"rank":441,"remainingConfigurations":444},{"removed":"critpt","score":0.000632088902536289,"rank":441,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0008947779290912998,"rank":441,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0009141195277000171,"rank":441,"remainingConfigurations":444},{"removed":"gdpval","score":0.0008955008571384829,"rank":441,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0009295001392996366,"rank":441,"remainingConfigurations":444},{"removed":"gpqa","score":0.0009183531196540056,"rank":441,"remainingConfigurations":444},{"removed":"harvey","score":0.000881647255916206,"rank":441,"remainingConfigurations":444},{"removed":"hle","score":0.0007385318437049637,"rank":443,"remainingConfigurations":444},{"removed":"ifbench","score":0.0008897736413473363,"rank":441,"remainingConfigurations":444},{"removed":"itbench","score":0.0008850660951920421,"rank":441,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0010050765692379501,"rank":441,"remainingConfigurations":444},{"removed":"math500","score":0.0010514991033422503,"rank":441,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0010518206612268857,"rank":441,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0009831294454422759,"rank":441,"remainingConfigurations":444},{"removed":"omniscience","score":0.0007797887708496989,"rank":441,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0008160029032263259,"rank":441,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0009072748852102381,"rank":441,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0009039018724853169,"rank":441,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0011511552963678869,"rank":441,"remainingConfigurations":444},{"removed":"deepswe","score":0.0006942402501670027,"rank":441,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0008914375058698185,"rank":441,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0008748353003684399,"rank":441,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0008697517175668291,"rank":441,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0008776093521728742,"rank":441,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0008800321504032422,"rank":441,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0008907239186744772,"rank":441,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0008871126303504935,"rank":441,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0008923792358394989,"rank":441,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0008793664978537693,"rank":441,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0009071846681600624,"rank":441,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0008911404405716655,"rank":441,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0008706234883753286,"rank":441,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.000884241407098117,"rank":441,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0009145144853279939,"rank":441,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.000922737166553503,"rank":441,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0008936704942407651,"rank":441,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0008266456627829337,"rank":441,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0009438605027665396,"rank":441,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0008873882383347997,"rank":441,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0008872455769657425,"rank":441,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0008875805579132337,"rank":441,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0008890198765373539,"rank":441,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0008844870623426305,"rank":441,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0008882848596523498,"rank":441,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gemma-3-270m-it--effort-non-reasoning":{"score":0.0007474236046053468,"rank":442,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0010087070034677087,"rank":442,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0005822687383166273,"rank":442,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.000739233712080044,"rank":442,"remainingConfigurations":444},{"removed":"Scale","score":0.0008937898826294682,"rank":442,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0007393565368867846,"rank":442,"remainingConfigurations":444},{"removed":"Cognition","score":0.0007300504519449478,"rank":442,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0007840112684104537,"rank":441,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.000774964589183909,"rank":442,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.000762047768797347,"rank":429,"remainingConfigurations":431},{"removed":"Vals AI","score":0.000719957346046185,"rank":441,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0007470790404130572,"rank":442,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0007217886000010087,"rank":442,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00074603469598184,"rank":442,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0007474236046053468,"rank":442,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.000753765977031493,"rank":442,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0007265623857035977,"rank":442,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0007567939249571945,"rank":442,"remainingConfigurations":444},{"removed":"briefcase","score":0.0007458027878376367,"rank":442,"remainingConfigurations":444},{"removed":"aime","score":0.0007983188292662928,"rank":442,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0007622252789784497,"rank":442,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0007096709354013708,"rank":442,"remainingConfigurations":444},{"removed":"automationbench","score":0.0007453502385109499,"rank":442,"remainingConfigurations":444},{"removed":"critpt","score":0.0004753845329968491,"rank":443,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0007512826989551979,"rank":442,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0007688666923991422,"rank":442,"remainingConfigurations":444},{"removed":"gdpval","score":0.0007516351365165997,"rank":442,"remainingConfigurations":444},{"removed":"gmmlu","score":0.0007593677181523868,"rank":442,"remainingConfigurations":444},{"removed":"gpqa","score":0.0007808117492533019,"rank":442,"remainingConfigurations":444},{"removed":"harvey","score":0.0007395228583553728,"rank":442,"remainingConfigurations":444},{"removed":"hle","score":0.0007758572775969896,"rank":440,"remainingConfigurations":444},{"removed":"ifbench","score":0.0007645706867875435,"rank":442,"remainingConfigurations":444},{"removed":"itbench","score":0.0007425465302937415,"rank":442,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0008548961272895182,"rank":442,"remainingConfigurations":444},{"removed":"math500","score":0.0007594827300749117,"rank":443,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.000901929723226531,"rank":442,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0008220762823495762,"rank":442,"remainingConfigurations":444},{"removed":"omniscience","score":0.0006573118291377279,"rank":442,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0006765452886784291,"rank":442,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0007610661282216319,"rank":442,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0007519129766765535,"rank":442,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0009667436960205097,"rank":442,"remainingConfigurations":444},{"removed":"deepswe","score":0.000582683650022208,"rank":442,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0007476259321957784,"rank":442,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0007337087904846763,"rank":442,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0007300504519449478,"rank":442,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0007360477327644815,"rank":442,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.000738073399849647,"rank":442,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0007470276064859036,"rank":442,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0007440090908834889,"rank":442,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0007484153918173947,"rank":442,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0007374987953532316,"rank":442,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0007608363530602354,"rank":442,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0007473784625606229,"rank":442,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0007301645445222725,"rank":442,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0007415885558718759,"rank":442,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0007669870658372746,"rank":442,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.000774964589183909,"rank":442,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0007495536321751591,"rank":442,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.000693366725662838,"rank":442,"remainingConfigurations":444},{"removed":"simpleqa","score":0.0007915752943852329,"rank":442,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0007442292293959957,"rank":442,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0007441089931704411,"rank":442,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0007443908692830077,"rank":442,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0007455971335060163,"rank":442,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0007417946896908249,"rank":442,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0007449817218790721,"rank":442,"remainingConfigurations":444}],"sharedOrderConflicts":0},"deepseek-r1-distill-qwen-1.5b--effort-reasoning":{"score":0.0007009524206795097,"rank":443,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.0009483570713368609,"rank":443,"remainingConfigurations":444},{"removed":"Datacurve","score":0.0005462492450350453,"rank":443,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.0006932724883710839,"rank":443,"remainingConfigurations":444},{"removed":"Scale","score":0.0008383721915354391,"rank":443,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0006932193403728877,"rank":443,"remainingConfigurations":444},{"removed":"Cognition","score":0.0006850844410706513,"rank":443,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0007348639939364245,"rank":442,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0007270850789661879,"rank":443,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.0007126941750188082,"rank":430,"remainingConfigurations":431},{"removed":"Vals AI","score":0.0006746046744869168,"rank":442,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0007006293969221239,"rank":443,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0006769130749524326,"rank":443,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.0006996506140478982,"rank":443,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.0007009524206795097,"rank":443,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.0007069003041394501,"rank":443,"remainingConfigurations":444},{"removed":"All provider reports","score":0.0006813907077465082,"rank":443,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.0007093145241773399,"rank":443,"remainingConfigurations":444},{"removed":"briefcase","score":0.0006984267749875047,"rank":443,"remainingConfigurations":444},{"removed":"aime","score":0.0005368217612436243,"rank":443,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0007145187923065713,"rank":443,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.0005977723732073821,"rank":443,"remainingConfigurations":444},{"removed":"automationbench","score":0.0006985556565879514,"rank":443,"remainingConfigurations":444},{"removed":"critpt","score":0.000611100791235095,"rank":442,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0007036627325849027,"rank":443,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.0007200958928121784,"rank":443,"remainingConfigurations":444},{"removed":"gdpval","score":0.0007042781179924627,"rank":443,"remainingConfigurations":444},{"removed":"gmmlu","score":0.000715112564647878,"rank":443,"remainingConfigurations":444},{"removed":"gpqa","score":0.0007364233362147831,"rank":443,"remainingConfigurations":444},{"removed":"harvey","score":0.0006933241410957254,"rank":443,"remainingConfigurations":444},{"removed":"hle","score":0.0007481572864115487,"rank":442,"remainingConfigurations":444},{"removed":"ifbench","score":0.0007133204221523681,"rank":443,"remainingConfigurations":444},{"removed":"itbench","score":0.0006960957393227321,"rank":443,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0007910300345514497,"rank":443,"remainingConfigurations":444},{"removed":"math500","score":0.0007917655333308874,"rank":442,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.0008255753673170684,"rank":443,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0007743762695061048,"rank":443,"remainingConfigurations":444},{"removed":"omniscience","score":0.0006002570757906452,"rank":443,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0006595417562882639,"rank":443,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.0007135701535723196,"rank":443,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.000705028816782441,"rank":443,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0009087269789772018,"rank":443,"remainingConfigurations":444},{"removed":"deepswe","score":0.0005466384347062751,"rank":443,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.0007011421385245338,"rank":443,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.0006880714735311326,"rank":443,"remainingConfigurations":444},{"removed":"frontiercode","score":0.0006850844410706513,"rank":443,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0006902960173809073,"rank":443,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.0006922006110946787,"rank":443,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.0007005815341409148,"rank":443,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0006977302160491439,"rank":443,"remainingConfigurations":444},{"removed":"livebench-math","score":0.0007018852063931479,"rank":443,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.0006916404024297711,"rank":443,"remainingConfigurations":444},{"removed":"livebench-language","score":0.0007135306278510421,"rank":443,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0007009106334710182,"rank":443,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0006847668526617437,"rank":443,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.0006954795932983358,"rank":443,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0007193013465976464,"rank":443,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0007270850789661879,"rank":443,"remainingConfigurations":444},{"removed":"frontiermath","score":0.0007029955199278526,"rank":443,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0006500940707573573,"rank":443,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00074245650090893,"rank":443,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.0006979558515758712,"rank":443,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.000697843736601869,"rank":443,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0006981085511949164,"rank":443,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0006992389558622717,"rank":443,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0006956730555782676,"rank":443,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.0006986620055792333,"rank":443,"remainingConfigurations":444}],"sharedOrderConflicts":0},"gpt-3.5-turbo--effort-non-reasoning":{"score":0.00041802401763200433,"rank":444,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":203},{"removed":"ARC Prize","score":0.000570793169773167,"rank":444,"remainingConfigurations":444},{"removed":"Datacurve","score":0.00032594621245045753,"rank":444,"remainingConfigurations":444},{"removed":"LiveCodeBench","score":0.00041356237051783676,"rank":444,"remainingConfigurations":444},{"removed":"Scale","score":0.0005004081750005455,"rank":444,"remainingConfigurations":444},{"removed":"Terminal-Bench","score":0.0004134108906247268,"rank":444,"remainingConfigurations":444},{"removed":"Cognition","score":0.00040899923856408445,"rank":444,"remainingConfigurations":444},{"removed":"LiveBench","score":0.0004381868891740414,"rank":443,"remainingConfigurations":443},{"removed":"SWE-rebench","score":0.0004343911744280787,"rank":444,"remainingConfigurations":444},{"removed":"Epoch AI","score":0.00041814668022134295,"rank":431,"remainingConfigurations":431},{"removed":"Vals AI","score":0.000402173212975242,"rank":443,"remainingConfigurations":443},{"removed":"Provider reports · Anthropic","score":0.0004178313738798069,"rank":444,"remainingConfigurations":444},{"removed":"Provider reports · Moonshot AI","score":0.0004036829918705349,"rank":444,"remainingConfigurations":444},{"removed":"Provider reports · Meta","score":0.00041724785537909675,"rank":444,"remainingConfigurations":444},{"removed":"Provider reports · Mistral","score":0.00041802401763200433,"rank":444,"remainingConfigurations":444},{"removed":"Provider reports · OpenAI","score":0.00042157108821101454,"rank":444,"remainingConfigurations":444},{"removed":"All provider reports","score":0.00040635345024439133,"rank":444,"remainingConfigurations":444}],"familyRemovals":[{"removed":"analyst-agent","score":0.00042304706646953297,"rank":444,"remainingConfigurations":444},{"removed":"briefcase","score":0.00041737907448200455,"rank":444,"remainingConfigurations":444},{"removed":"aime","score":0.00040798933963022015,"rank":444,"remainingConfigurations":444},{"removed":"apex-agents","score":0.0004263651231472539,"rank":444,"remainingConfigurations":444},{"removed":"aa-lcr","score":0.00041308360545740043,"rank":444,"remainingConfigurations":444},{"removed":"automationbench","score":0.00041708278676149904,"rank":444,"remainingConfigurations":444},{"removed":"critpt","score":0.0003677293877730706,"rank":444,"remainingConfigurations":444},{"removed":"enterprise-ops","score":0.0004197486877391459,"rank":444,"remainingConfigurations":444},{"removed":"gdp-pdf","score":0.00042964157349775414,"rank":444,"remainingConfigurations":444},{"removed":"gdpval","score":0.00042013998843915245,"rank":444,"remainingConfigurations":444},{"removed":"gmmlu","score":0.00042847047390536614,"rank":444,"remainingConfigurations":444},{"removed":"gpqa","score":0.0003078982592270307,"rank":444,"remainingConfigurations":444},{"removed":"harvey","score":0.0004134304191425557,"rank":444,"remainingConfigurations":444},{"removed":"hle","score":0.00043932039880618007,"rank":444,"remainingConfigurations":444},{"removed":"ifbench","score":0.0004079125690363767,"rank":444,"remainingConfigurations":444},{"removed":"itbench","score":0.00041536306242236526,"rank":444,"remainingConfigurations":444},{"removed":"livecodebench","score":0.0004243823803030044,"rank":444,"remainingConfigurations":444},{"removed":"math500","score":0.0006772833744610409,"rank":444,"remainingConfigurations":444},{"removed":"mmlu-pro","score":0.00037258329541699757,"rank":444,"remainingConfigurations":444},{"removed":"mmmu-pro","score":0.0004604502624870334,"rank":444,"remainingConfigurations":444},{"removed":"omniscience","score":0.0003561932617062826,"rank":444,"remainingConfigurations":444},{"removed":"tau-bench","score":0.0003964429032895078,"rank":444,"remainingConfigurations":444},{"removed":"terminal-bench-science","score":0.00042558243951357325,"rank":444,"remainingConfigurations":444},{"removed":"terminal-bench","score":0.0004279505430205832,"rank":444,"remainingConfigurations":444},{"removed":"arc-agi","score":0.0005467444548813524,"rank":444,"remainingConfigurations":444},{"removed":"deepswe","score":0.0003261786451235395,"rank":444,"remainingConfigurations":444},{"removed":"swe-bench-pro","score":0.00041813720299465604,"rank":444,"remainingConfigurations":444},{"removed":"arc-agi-3","score":0.00041032638673437345,"rank":444,"remainingConfigurations":444},{"removed":"frontiercode","score":0.00040899923856408445,"rank":444,"remainingConfigurations":444},{"removed":"enigma-eval","score":0.0004116652431253198,"rank":444,"remainingConfigurations":444},{"removed":"swe-atlas-qna","score":0.000412799412582632,"rank":444,"remainingConfigurations":444},{"removed":"swe-atlas-refactoring","score":0.00041780314862745107,"rank":444,"remainingConfigurations":444},{"removed":"swe-atlas-test-writing","score":0.0004161033764841942,"rank":444,"remainingConfigurations":444},{"removed":"livebench-math","score":0.00041858244853842523,"rank":444,"remainingConfigurations":444},{"removed":"livebench-coding","score":0.00041246421398186497,"rank":444,"remainingConfigurations":444},{"removed":"livebench-language","score":0.00042552872885707137,"rank":444,"remainingConfigurations":444},{"removed":"livebench-data","score":0.0004180004300234713,"rank":444,"remainingConfigurations":444},{"removed":"multi-swe-bench","score":0.0004083676863700268,"rank":444,"remainingConfigurations":444},{"removed":"livebench-reasoning","score":0.00041475790798240386,"rank":444,"remainingConfigurations":444},{"removed":"livebench-instructions","score":0.0004289731229861647,"rank":444,"remainingConfigurations":444},{"removed":"swe-rebench","score":0.0004343911744280787,"rank":444,"remainingConfigurations":444},{"removed":"frontiermath","score":0.00041960812339832376,"rank":444,"remainingConfigurations":444},{"removed":"epoch-game-puzzles","score":0.0003879275740771903,"rank":444,"remainingConfigurations":444},{"removed":"simpleqa","score":0.00044290462472265077,"rank":444,"remainingConfigurations":444},{"removed":"vals-finance-agent","score":0.00041623576471907375,"rank":444,"remainingConfigurations":444},{"removed":"vals-code-migration","score":0.0004161696314124389,"rank":444,"remainingConfigurations":444},{"removed":"vals-legal-research","score":0.0004163266560677041,"rank":444,"remainingConfigurations":444},{"removed":"vals-excel-modeling","score":0.0004170018504724047,"rank":444,"remainingConfigurations":444},{"removed":"vibe-code","score":0.0004148743989203076,"rank":444,"remainingConfigurations":444},{"removed":"vals-tax-agent","score":0.00041665696377943956,"rank":444,"remainingConfigurations":444}],"sharedOrderConflicts":0}},"rankedConfigurations":444,"rankedModels":231,"topModels":[{"rank":1,"id":"gpt-6-astra--effort-xhigh","score":0.959334185153284},{"rank":2,"id":"claude-opus-5-5--effort-high","score":0.9227331396853704},{"rank":3,"id":"gemini-4-argon--effort-medium","score":0.9018697849083788},{"rank":4,"id":"claude-fable-5-1--effort-max","score":0.8990820461798595},{"rank":5,"id":"gpt-6.1-sol--effort-high","score":0.8591089426089601},{"rank":6,"id":"muse-wonder-full--effort-max","score":0.8500987270785633},{"rank":7,"id":"claude-opus-5--effort-medium","score":0.8319049535030567},{"rank":8,"id":"claude-fable-5--effort-high","score":0.7974003321637468},{"rank":9,"id":"gpt-5.6-sol--effort-xhigh","score":0.7927595850485814},{"rank":10,"id":"claude-sonnet-5-5--effort-max","score":0.7752346952613443},{"rank":11,"id":"gpt-5.5-pro--effort-xhigh","score":0.7645221009807254},{"rank":12,"id":"muse-spark-1.3--effort-xhigh","score":0.7427064995842336},{"rank":13,"id":"muse-wonder--effort-max","score":0.7321209992509411},{"rank":14,"id":"gemini-3.8-flash--effort-high","score":0.7184744919870086},{"rank":15,"id":"deepseek-v4.1-flash--effort-high","score":0.7015963097002348},{"rank":16,"id":"kimi-k3--effort-max","score":0.6647155773036123},{"rank":17,"id":"gpt-6-sol--effort-max","score":0.6623840158950337},{"rank":18,"id":"grok-4.6--effort-medium","score":0.6251983967534925},{"rank":19,"id":"grok-4.7--effort-xhigh","score":0.6181766255704918},{"rank":20,"id":"gemini-3.7-flash--effort-medium","score":0.6090790624154763},{"rank":21,"id":"qwen-3.8-max-0902--effort-reasoning","score":0.5901081449562977},{"rank":22,"id":"glm-5.3--effort-max","score":0.5818778215067574},{"rank":23,"id":"gpt-5.5--effort-xhigh","score":0.5686822678550768},{"rank":24,"id":"gpt-5.6-terra--effort-max","score":0.5669778610965056},{"rank":25,"id":"mimo-v2.6-pro--effort-reasoning","score":0.5451296693325177}],"independentFamiliesByArea":{"agentic":["analyst-agent","briefcase","apex-agents","automationbench","enterprise-ops","gdp-pdf","gdpval","harvey","itbench","tau-bench","terminal-bench-science","livebench-data","vals-finance-agent","vals-legal-research","vals-excel-modeling","vals-tax-agent"],"hard_reasoning":["aime","critpt","gpqa","hle","math500","arc-agi","arc-agi-3","enigma-eval","livebench-math","livebench-reasoning","frontiermath","epoch-game-puzzles"],"long_context":["aa-lcr"],"knowledge":["gmmlu","ifbench","mmlu-pro","omniscience","livebench-language","livebench-instructions","simpleqa"],"coding":["livecodebench","terminal-bench","deepswe","swe-bench-pro","frontiercode","swe-atlas-qna","swe-atlas-refactoring","swe-atlas-test-writing","livebench-coding","multi-swe-bench","swe-rebench","vals-code-migration","vibe-code"],"multimodal":["mmmu-pro"]},"directDominanceReversals":[{"higherRanked":"claude-fable-5--effort-high","lowerRanked":"gpt-6-sol--effort-max","sharedFamilies":3,"losses":2,"ties":1,"weightedIndependentHeadToHead":0.18376837683768377,"weightedAllHeadToHead":0.18376837683768377,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"gpt-5.5-pro--effort-xhigh","lowerRanked":"gpt-6-sol--effort-max","sharedFamilies":3,"losses":4,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"claude-opus-4-6--effort-max","lowerRanked":"gemini-3.1-pro--effort-high","sharedFamilies":4,"losses":5,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"mistral-large-4--effort-reasoning","lowerRanked":"gpt-5.2--effort-xhigh","sharedFamilies":4,"losses":4,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"o4-mini--effort-high","lowerRanked":"minimax-m2.5--effort-reasoning","sharedFamilies":8,"losses":8,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"o4-mini--effort-high","lowerRanked":"minimax-m2.7--effort-reasoning","sharedFamilies":8,"losses":7,"ties":1,"weightedIndependentHeadToHead":0.05823312380108494,"weightedAllHeadToHead":0.05823312380108494,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"gpt-5-nano--effort-high","lowerRanked":"gpt-oss-120b--effort-high","sharedFamilies":12,"losses":12,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"diffusiongemma-26b-a4b--effort-reasoning","lowerRanked":"gpt-oss-120b--effort-high","sharedFamilies":8,"losses":8,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"glm-4.5v--effort-reasoning","lowerRanked":"gpt-4o--effort-non-reasoning","sharedFamilies":3,"losses":2,"ties":1,"weightedIndependentHeadToHead":0.12437681021793838,"weightedAllHeadToHead":0.12437681021793838,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"qwen3.5-0.8b--effort-non-reasoning","lowerRanked":"gpt-4--effort-non-reasoning","sharedFamilies":4,"losses":4,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"gpt-4--effort-non-reasoning","lowerRanked":"pixtral-large-2411--effort-non-reasoning","sharedFamilies":4,"losses":4,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"mistral-large-2407--effort-non-reasoning","lowerRanked":"gpt-4-turbo--effort-non-reasoning","sharedFamilies":4,"losses":4,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"deepseek-r1-distill-llama-8b--effort-reasoning","lowerRanked":"tiny-aya-global--effort-non-reasoning","sharedFamilies":3,"losses":2,"ties":1,"weightedIndependentHeadToHead":0.15568170566685371,"weightedAllHeadToHead":0.15568170566685371,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"}],"effortOrderChecks":{"scope":"Within-model settings whose aggregate order opposes the majority of shared independent evaluation units across at least three families. Counts are descriptive, not independent trials or a replacement ranking. Unequal coverage and opponent schedules require review; more effort is not constrained to win.","reversals":[{"higherRanked":"gpt-6-astra--effort-xhigh","lowerRanked":"gpt-6-astra--effort-max","higherScore":0.959334185153284,"lowerScore":0.906830004646622,"sharedUnits":21,"sharedFamilies":17,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI","Terminal-Bench"],"higherWins":6,"lowerWins":14,"ties":1,"higherOnlyUnits":2,"lowerOnlyUnits":42},{"higherRanked":"claude-opus-5-5--effort-high","lowerRanked":"claude-opus-5-5--effort-max","higherScore":0.9227331396853704,"lowerScore":0.9192642183499763,"sharedUnits":14,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":3,"lowerWins":11,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":5},{"higherRanked":"claude-opus-5-5--effort-high","lowerRanked":"claude-opus-5-5--effort-xhigh","higherScore":0.9227331396853704,"lowerScore":0.8737406978750922,"sharedUnits":14,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":4,"lowerWins":10,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":0},{"higherRanked":"gpt-6-astra--effort-high","lowerRanked":"gpt-6-astra--effort-max","higherScore":0.9184835607694163,"lowerScore":0.906830004646622,"sharedUnits":21,"sharedFamilies":17,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI","Terminal-Bench"],"higherWins":3,"lowerWins":15,"ties":3,"higherOnlyUnits":0,"lowerOnlyUnits":42},{"higherRanked":"gemini-4-argon--effort-medium","lowerRanked":"gemini-4-argon--effort-low","higherScore":0.9018697849083788,"lowerScore":0.7328455654459817,"sharedUnits":5,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition"],"higherWins":2,"lowerWins":3,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":0},{"higherRanked":"claude-opus-5-5--effort-medium","lowerRanked":"claude-opus-5-5--effort-xhigh","higherScore":0.8968900120893727,"lowerScore":0.8737406978750922,"sharedUnits":14,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":2,"lowerWins":12,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":0},{"higherRanked":"gemini-4-argon--effort-high","lowerRanked":"gemini-4-argon--effort-low","higherScore":0.8940216642928943,"lowerScore":0.7328455654459817,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition"],"higherWins":1,"lowerWins":3,"ties":0,"higherOnlyUnits":18,"lowerOnlyUnits":1},{"higherRanked":"gpt-6.1-sol--effort-high","lowerRanked":"gpt-6.1-sol--effort-xhigh","higherScore":0.8591089426089601,"lowerScore":0.8404179303166387,"sharedUnits":15,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":2,"lowerWins":12,"ties":1,"higherOnlyUnits":0,"lowerOnlyUnits":23},{"higherRanked":"gpt-6.1-sol--effort-high","lowerRanked":"gpt-6.1-sol--effort-max","higherScore":0.8591089426089601,"lowerScore":0.8231507026285795,"sharedUnits":15,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":2,"lowerWins":13,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":34},{"higherRanked":"gpt-6.1-sol--effort-xhigh","lowerRanked":"gpt-6.1-sol--effort-max","higherScore":0.8404179303166387,"lowerScore":0.8231507026285795,"sharedUnits":38,"sharedFamilies":20,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","LiveBench"],"higherWins":8,"lowerWins":20,"ties":10,"higherOnlyUnits":0,"lowerOnlyUnits":11},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-high","higherScore":0.8319049535030567,"lowerScore":0.790553136546194,"sharedUnits":17,"sharedFamilies":14,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":5,"lowerWins":12,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":3},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-xhigh","higherScore":0.8319049535030567,"lowerScore":0.7852468407834232,"sharedUnits":17,"sharedFamilies":14,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":13,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":3},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-max","higherScore":0.8319049535030567,"lowerScore":0.7308935047612021,"sharedUnits":17,"sharedFamilies":14,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":13,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":39},{"higherRanked":"gpt-6.1-sol--effort-medium","lowerRanked":"gpt-6.1-sol--effort-max","higherScore":0.8238506927309873,"lowerScore":0.8231507026285795,"sharedUnits":15,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":3,"lowerWins":12,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":34},{"higherRanked":"claude-fable-5--effort-high","lowerRanked":"claude-fable-5--effort-xhigh","higherScore":0.7974003321637468,"lowerScore":0.7409165255600528,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":0,"lowerWins":4,"ties":0,"higherOnlyUnits":5,"lowerOnlyUnits":5},{"higherRanked":"claude-fable-5--effort-high","lowerRanked":"claude-fable-5--effort-max","higherScore":0.7974003321637468,"lowerScore":0.7395803680955662,"sharedUnits":5,"sharedFamilies":4,"sharedSources":["ARC Prize","Cognition","Datacurve","Epoch AI"],"higherWins":2,"lowerWins":3,"ties":0,"higherOnlyUnits":4,"lowerOnlyUnits":53},{"higherRanked":"gpt-5.6-sol--effort-xhigh","lowerRanked":"gpt-5.6-sol--effort-max","higherScore":0.7927595850485814,"lowerScore":0.741123875720382,"sharedUnits":21,"sharedFamilies":16,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":2,"lowerWins":19,"ties":0,"higherOnlyUnits":1,"lowerOnlyUnits":44},{"higherRanked":"claude-opus-5--effort-high","lowerRanked":"claude-opus-5--effort-xhigh","higherScore":0.790553136546194,"lowerScore":0.7852468407834232,"sharedUnits":17,"sharedFamilies":14,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":6,"lowerWins":10,"ties":1,"higherOnlyUnits":3,"lowerOnlyUnits":3},{"higherRanked":"claude-opus-5--effort-high","lowerRanked":"claude-opus-5--effort-max","higherScore":0.790553136546194,"lowerScore":0.7308935047612021,"sharedUnits":18,"sharedFamilies":15,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":3,"lowerWins":15,"ties":0,"higherOnlyUnits":2,"lowerOnlyUnits":38},{"higherRanked":"claude-opus-5--effort-xhigh","lowerRanked":"claude-opus-5--effort-max","higherScore":0.7852468407834232,"lowerScore":0.7308935047612021,"sharedUnits":17,"sharedFamilies":14,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":13,"ties":0,"higherOnlyUnits":3,"lowerOnlyUnits":39},{"higherRanked":"claude-fable-5--effort-medium","lowerRanked":"claude-fable-5--effort-xhigh","higherScore":0.7531156528332978,"lowerScore":0.7409165255600528,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":0,"lowerWins":4,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":5},{"higherRanked":"claude-fable-5--effort-medium","lowerRanked":"claude-fable-5--effort-max","higherScore":0.7531156528332978,"lowerScore":0.7395803680955662,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":0,"lowerWins":4,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":54},{"higherRanked":"muse-spark-1.3--effort-xhigh","lowerRanked":"muse-spark-1.3--effort-max","higherScore":0.7427064995842336,"lowerScore":0.5831429105105554,"sharedUnits":12,"sharedFamilies":11,"sharedSources":["Artificial Analysis"],"higherWins":3,"lowerWins":8,"ties":1,"higherOnlyUnits":32,"lowerOnlyUnits":5},{"higherRanked":"grok-4.6--effort-medium","lowerRanked":"grok-4.6--effort-high","higherScore":0.6251983967534925,"lowerScore":0.6133733610287327,"sharedUnits":16,"sharedFamilies":14,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":12,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":17},{"higherRanked":"grok-4.6--effort-medium","lowerRanked":"grok-4.6--effort-xhigh","higherScore":0.6251983967534925,"lowerScore":0.5932497693964965,"sharedUnits":14,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Datacurve"],"higherWins":3,"lowerWins":9,"ties":2,"higherOnlyUnits":2,"lowerOnlyUnits":7},{"higherRanked":"grok-4.7--effort-xhigh","lowerRanked":"grok-4.7--effort-high","higherScore":0.6181766255704918,"lowerScore":0.5607762355448137,"sharedUnits":16,"sharedFamilies":14,"sharedSources":["ARC Prize","Artificial Analysis","Cognition"],"higherWins":7,"lowerWins":9,"ties":0,"higherOnlyUnits":35,"lowerOnlyUnits":0},{"higherRanked":"grok-4.6--effort-high","lowerRanked":"grok-4.6--effort-xhigh","higherScore":0.6133733610287327,"lowerScore":0.5932497693964965,"sharedUnits":17,"sharedFamilies":15,"sharedSources":["ARC Prize","Artificial Analysis","Datacurve","Epoch AI"],"higherWins":7,"lowerWins":10,"ties":0,"higherOnlyUnits":16,"lowerOnlyUnits":4},{"higherRanked":"gemini-3.7-flash--effort-medium","lowerRanked":"gemini-3.7-flash--effort-high","higherScore":0.6090790624154763,"lowerScore":0.5884455537670358,"sharedUnits":13,"sharedFamilies":12,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":5,"lowerWins":8,"ties":0,"higherOnlyUnits":1,"lowerOnlyUnits":45},{"higherRanked":"claude-haiku-5-5--effort-xhigh","lowerRanked":"claude-haiku-5-5--effort-max","higherScore":0.45399371763893637,"lowerScore":0.4388976713672646,"sharedUnits":36,"sharedFamilies":19,"sharedSources":["Artificial Analysis","Cognition","LiveBench"],"higherWins":16,"lowerWins":19,"ties":1,"higherOnlyUnits":1,"lowerOnlyUnits":4},{"higherRanked":"claude-sonnet-5--effort-xhigh","lowerRanked":"claude-sonnet-5--effort-max","higherScore":0.37796581882811126,"lowerScore":0.34355582708243687,"sharedUnits":16,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve","Epoch AI"],"higherWins":4,"lowerWins":12,"ties":0,"higherOnlyUnits":23,"lowerOnlyUnits":19},{"higherRanked":"claude-sonnet-4-6--effort-max","lowerRanked":"claude-sonnet-4-6--effort-high","higherScore":0.18970871566299438,"lowerScore":0.14681669541375963,"sharedUnits":5,"sharedFamilies":4,"sharedSources":["ARC Prize","Cognition","Epoch AI"],"higherWins":2,"lowerWins":3,"ties":0,"higherOnlyUnits":31,"lowerOnlyUnits":2},{"higherRanked":"grok-4.3--effort-medium","lowerRanked":"grok-4.3--effort-high","higherScore":0.17718383287117856,"lowerScore":0.13182479689142326,"sharedUnits":9,"sharedFamilies":9,"sharedSources":["Artificial Analysis"],"higherWins":2,"lowerWins":7,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":26},{"higherRanked":"qwen3.8-27b--effort-low","lowerRanked":"qwen3.8-27b--effort-medium","higherScore":0.13232120280947038,"lowerScore":0.13124370428032436,"sharedUnits":15,"sharedFamilies":14,"sharedSources":["ARC Prize","Artificial Analysis"],"higherWins":2,"lowerWins":11,"ties":2,"higherOnlyUnits":0,"lowerOnlyUnits":0},{"higherRanked":"gpt-5.6-terra--effort-low","lowerRanked":"gpt-5.6-terra--effort-medium","higherScore":0.11339897694701019,"lowerScore":0.10677516122948026,"sharedUnits":22,"sharedFamilies":18,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI"],"higherWins":3,"lowerWins":19,"ties":0,"higherOnlyUnits":3,"lowerOnlyUnits":0},{"higherRanked":"gemma-4-e4b-it--effort-non-reasoning","lowerRanked":"gemma-4-e4b-it--effort-reasoning","higherScore":0.007583993335564365,"lowerScore":0.006871027693573418,"sharedUnits":9,"sharedFamilies":9,"sharedSources":["Artificial Analysis"],"higherWins":2,"lowerWins":7,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":6},{"higherRanked":"qwen3.5-2b--effort-non-reasoning","lowerRanked":"qwen3.5-2b--effort-reasoning","higherScore":0.004434241330172628,"lowerScore":0.003941657235449699,"sharedUnits":11,"sharedFamilies":10,"sharedSources":["Artificial Analysis"],"higherWins":2,"lowerWins":7,"ties":2,"higherOnlyUnits":0,"lowerOnlyUnits":0}]},"astraFableMatched":[{"unit":"aa-aa-analyst-agent","family":"analyst-agent","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":51.24999999999999},{"id":"claude-fable-5-1--effort-max","score":57.49999999999999}]},{"unit":"aa-aa-briefcase","family":"briefcase","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":1568.99},{"id":"claude-fable-5-1--effort-max","score":1672.26}]},{"unit":"aa-artificial-analysis-long-context-reasoning","family":"aa-lcr","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":80.6666666666667},{"id":"claude-fable-5-1--effort-max","score":85.3333333333333}]},{"unit":"aa-automationbench-aa","family":"automationbench","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":68.49174806688876},{"id":"claude-fable-5-1--effort-max","score":59.37591715646424}]},{"unit":"aa-critpt","family":"critpt","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":31.7142857142857},{"id":"claude-fable-5-1--effort-max","score":29.714285714285698}]},{"unit":"aa-gdp-pdf","family":"gdp-pdf","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":31},{"id":"claude-fable-5-1--effort-max","score":26.200000000000003}]},{"unit":"aa-gdpval-aa","family":"gdpval","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":1572.84},{"id":"claude-fable-5-1--effort-max","score":1754.07}]},{"unit":"aa-gpqa-diamond","family":"gpqa","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":96.0606060606061},{"id":"claude-fable-5-1--effort-max","score":93.7373737373737}]},{"unit":"aa-harvey-lab-aa-v1.1","family":"harvey","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":8.611111111111109},{"id":"claude-fable-5-1--effort-max","score":6.388888888888888}]},{"unit":"aa-humanitys-last-exam","family":"hle","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":54.6802594995366},{"id":"claude-fable-5-1--effort-max","score":59.1288229842447}]},{"unit":"aa-itbench-aa","family":"itbench","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":48.5875706214689},{"id":"claude-fable-5-1--effort-max","score":49.5291902071563}]},{"unit":"aa-mlcr-aa","family":"aa-lcr","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":35},{"id":"claude-fable-5-1--effort-max","score":71.1111111111111}]},{"unit":"aa-omniscience-accuracy","family":"omniscience","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":62.6},{"id":"claude-fable-5-1--effort-max","score":67.23333333333333}]},{"unit":"aa-tau3-banking","family":"tau-bench","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":41.4432989690722},{"id":"claude-fable-5-1--effort-max","score":47.2164948453608}]},{"unit":"aa-terminal-bench-science","family":"terminal-bench-science","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":63.3333333333333},{"id":"claude-fable-5-1--effort-max","score":43.3333333333333}]},{"unit":"aa-terminalbench-v2-1","family":"terminal-bench","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":88.38951310861421},{"id":"claude-fable-5-1--effort-max","score":91.3857677902622}]},{"unit":"aa-terminalbench-v4-0","family":"terminal-bench","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":59.09090909090911},{"id":"claude-fable-5-1--effort-max","score":52.020202020202}]},{"unit":"arc-v2semiprivate","family":"arc-agi","source":"ARC Prize","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":95},{"id":"claude-fable-5-1--effort-max","score":90}]},{"unit":"livebench-2026-06-25-AMPS_Hard","family":"livebench-math","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":98},{"id":"claude-fable-5-1--effort-max","score":99}]},{"unit":"livebench-2026-06-25-code_completion","family":"livebench-coding","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":80.435},{"id":"claude-fable-5-1--effort-max","score":82.609}]},{"unit":"livebench-2026-06-25-code_generation","family":"livebench-coding","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":80.282},{"id":"claude-fable-5-1--effort-max","score":90.141}]},{"unit":"livebench-2026-06-25-connections","family":"livebench-language","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":100},{"id":"claude-fable-5-1--effort-max","score":99.333}]},{"unit":"livebench-2026-06-25-consecutive_events","family":"livebench-data","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":90.555},{"id":"claude-fable-5-1--effort-max","score":90.555}]},{"unit":"livebench-2026-06-25-integrals_with_game","family":"livebench-math","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":100},{"id":"claude-fable-5-1--effort-max","score":99}]},{"unit":"livebench-2026-06-25-javascript","family":"multi-swe-bench","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":63.636},{"id":"claude-fable-5-1--effort-max","score":68.182}]},{"unit":"livebench-2026-06-25-logic_with_navigation","family":"livebench-reasoning","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":88},{"id":"claude-fable-5-1--effort-max","score":86}]},{"unit":"livebench-2026-06-25-math_comp","family":"livebench-math","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":97.059},{"id":"claude-fable-5-1--effort-max","score":97.059}]},{"unit":"livebench-2026-06-25-olympiad","family":"livebench-math","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":92.166},{"id":"claude-fable-5-1--effort-max","score":92.968}]},{"unit":"livebench-2026-06-25-paraphrase","family":"livebench-instructions","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":78.25},{"id":"claude-fable-5-1--effort-max","score":71.517}]},{"unit":"livebench-2026-06-25-plot_unscrambling","family":"livebench-language","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":86.292},{"id":"claude-fable-5-1--effort-max","score":75.17}]},{"unit":"livebench-2026-06-25-python","family":"multi-swe-bench","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":65},{"id":"claude-fable-5-1--effort-max","score":70}]},{"unit":"livebench-2026-06-25-simplify","family":"livebench-instructions","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":70.533},{"id":"claude-fable-5-1--effort-max","score":70.167}]},{"unit":"livebench-2026-06-25-spatial","family":"livebench-reasoning","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":98},{"id":"claude-fable-5-1--effort-max","score":100}]},{"unit":"livebench-2026-06-25-story_generation","family":"livebench-instructions","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":73.983},{"id":"claude-fable-5-1--effort-max","score":78.1}]},{"unit":"livebench-2026-06-25-summarize","family":"livebench-instructions","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":79.55},{"id":"claude-fable-5-1--effort-max","score":72.167}]},{"unit":"livebench-2026-06-25-tablejoin","family":"livebench-data","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":58.365},{"id":"claude-fable-5-1--effort-max","score":56.154}]},{"unit":"livebench-2026-06-25-tablereformat","family":"livebench-data","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":100},{"id":"claude-fable-5-1--effort-max","score":94.118}]},{"unit":"livebench-2026-06-25-theory_of_mind","family":"livebench-reasoning","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":84.615},{"id":"claude-fable-5-1--effort-max","score":80.769}]},{"unit":"livebench-2026-06-25-typescript","family":"multi-swe-bench","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":43.333},{"id":"claude-fable-5-1--effort-max","score":60}]},{"unit":"livebench-2026-06-25-typos","family":"livebench-language","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":82},{"id":"claude-fable-5-1--effort-max","score":94}]},{"unit":"livebench-2026-06-25-zebra_puzzle","family":"livebench-reasoning","source":"LiveBench","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":100},{"id":"claude-fable-5-1--effort-max","score":100}]},{"unit":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","family":"frontiermath","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":97.6},{"id":"claude-fable-5-1--effort-max","score":87.8048780487805}]},{"unit":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","family":"frontiermath","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":93.6842105263158},{"id":"claude-fable-5-1--effort-max","score":90.17543859649123}]},{"unit":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","family":"epoch-game-puzzles","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":84},{"id":"claude-fable-5-1--effort-max","score":57.99999999999999}]},{"unit":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","family":"aime","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":100},{"id":"claude-fable-5-1--effort-max","score":100}]},{"unit":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","family":"simpleqa","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":75.6},{"id":"claude-fable-5-1--effort-max","score":70.8}]},{"unit":"vals-finance-agent-v2","family":"vals-finance-agent","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":53.54},{"id":"claude-fable-5-1--effort-max","score":58.877}]},{"unit":"vals-code-migration-v1","family":"vals-code-migration","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":67.74},{"id":"claude-fable-5-1--effort-max","score":54.607}]},{"unit":"vals-legal-research-v1","family":"vals-legal-research","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":39.423},{"id":"claude-fable-5-1--effort-max","score":55.288}]},{"unit":"vals-emb-v1","family":"vals-excel-modeling","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":71.7},{"id":"claude-fable-5-1--effort-max","score":76.67}]},{"unit":"vals-vibe-code-bench-v1.1","family":"vibe-code","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":89.594},{"id":"claude-fable-5-1--effort-max","score":90.263}]},{"unit":"vals-legal-agent-benchmark-v1","family":"harvey","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":5.417},{"id":"claude-fable-5-1--effort-max","score":6.667}]},{"unit":"vals-tax-agent-bench-v1","family":"vals-tax-agent","source":"Vals AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":63.335},{"id":"claude-fable-5-1--effort-max","score":77.642}]}],"gaps":{"rosterModelsWithoutMeasuredEfforts":["deepseek-r1-distill-qwen-7b","codegemma-7b-it","gemma-1-2b-it","gemma-1-7b-it","gemma-1.1-2b-it","gemma-1.1-7b-it","gemma-2-2b-it","recurrentgemma-2b-it","recurrentgemma-9b-it","llama-3.2-11b-vision-instruct","llama-3.2-3b-instruct","codestral-2508","devstral-medium-2507","devstral-small-2507","labs-mistral-small-creative","leanstral-1.5","pixtral-12b-2409","voxtral-mini-2507","voxtral-small","kimi-dev-72b","kimi-vl-a3b-instruct","kimi-vl-a3b-thinking-2506","nvidia-nemotron-nano-12b-v2","nvidia-nemotron-nano-9b-v2-japanese","gpt-3.5-turbo-instruct","gpt-5-pro","gpt-5.3-codex-spark","o1-pro","qvq-max","qvq-plus","qwen-coder-plus","qwen-coder-turbo","qwen-flash","qwen-flash-character","qwen-long","qwen-math-plus","qwen-math-turbo","qwen-max","qwen-omni-turbo","qwen-plus","qwen-plus-character","qwen-plus-character-ja","qwen-turbo","qwen-vl-max","qwen-vl-plus","qwen3-coder-flash","qwen3-coder-plus","qwen3-omni-30b-a3b-thinking","qwen3-omni-flash","qwen3-vl-235b-a22b-thinking","qwen3-vl-2b-instruct","qwen3-vl-2b-thinking","qwen3-vl-flash","qwen3-vl-plus","grok-4.20-0309-non-reasoning","grok-4.20-multi-agent-0309","grok-build-0.1","glm-4.7-flashx","glm-4.5-x","glm-4.5-airx","glm-4-32b-0414-128k","glm-4.5-flash","glm-4.6v-flashx","glm-4.6v-flash","glm-4.1v-9b-thinking","glm-z1-rumination-32b-0414","glm-z1-9b-0414","glm-z1-32b-0414","glm-4-9b-0414","glm-4-32b-0414","glm-4-9b-chat","glm-4-9b-chat-1m","glm-4v-9b","glm-edge-1.5b-chat","glm-edge-4b-chat","glm-edge-v-2b","glm-edge-v-5b","chatglm-6b","chatglm2-6b","chatglm2-6b-32k","chatglm3-6b","chatglm3-6b-32k","chatglm3-6b-128k","codegeex4-all-9b","autoglm-phone-9b","autoglm-phone-9b-multilingual","cogagent-9b-20241220","codegeex2-6b","visualglm-6b","cogvlm-chat-hf","cogagent-chat-hf","cogagent-vqa-hf","cogvlm2-llama3-chat-19b","cogvlm2-llama3-chinese-chat-19b","cogvlm2-video-llama3-chat","minimax-text-01","minimax-vl-01","synlogic-32b","synlogic-mix-3-32b","synlogic-7b","minimax-m2-her","command-a-03-2025","command-r7b-12-2024","command-a-translate-08-2025","command-a-reasoning-08-2025","command-a-vision-07-2025","command-r-08-2024","command-r-plus-08-2024","command-r-plus-04-2024","command-light","command","tiny-aya-earth","tiny-aya-fire","tiny-aya-water","c4ai-aya-expanse-32b","c4ai-aya-vision-32b","c4ai-command-r7b-arabic-02-2025","c4ai-aya-expanse-8b","c4ai-aya-vision-8b","aya-23-8b","aya-23-35b","aya-101","north-mini-code-1-0","north-micro-vision-instruct","phi-4-reasoning-vision-15b","phi-3-mini-4k-instruct","phi-3-mini-128k-instruct","phi-3.5-mini-instruct","phi-4-reasoning","phi-mini-moe-instruct","phi-tiny-moe-instruct","phi-3-medium-4k-instruct","phi-3-small-8k-instruct","phi-3-small-128k-instruct","phi-3-vision-128k-instruct","phi-3.5-vision-instruct","phi-3.5-moe-instruct","phi-4-reasoning-plus","phi-4-mini-reasoning","phi-4-mini-flash-reasoning","mai-ds-r1","mai-thinking-1","mai-code-1-1-flash","mai-code-1-flash","doubao-seed-1.6","doubao-seed-1.6-thinking","doubao-seed-1.6-vision","doubao-seed-1.8","doubao-seed-2.0-code","doubao-seed-2.0-lite","doubao-seed-2.0-mini","doubao-seed-2.0-pro","doubao-seed-2.1-pro","doubao-seed-2.1-turbo","doubao-seed-character","doubao-seed-evolving","seed-coder-8b-instruct","seed-coder-8b-reasoning","exaone-3.0-7.8b-instruct","exaone-3.5-2.4b-instruct","exaone-3.5-32b-instruct","exaone-3.5-7.8b-instruct","exaone-4.0.1-32b","exaone-deep-2.4b","exaone-deep-32b","exaone-deep-7.8b","step-3.5-flash","step3","solar-10.7b-instruct-v1.0","solar-mini-250422","solar-pro-preview-instruct","solar-pro2-251215","mimo-7b-rl","mimo-7b-rl-0530","mimo-7b-rl-zero","mimo-7b-sft","mimo-vl-7b-rl","mimo-vl-7b-rl-2508","mimo-vl-7b-sft","mimo-vl-7b-sft-2508","ernie-4.5-0.3b-pt","ernie-4.5-21b-a3b-pt","ernie-4.5-21b-a3b-thinking","ernie-4.5-vl-28b-a3b-pt","ernie-4.5-vl-28b-a3b-thinking","ernie-4.5-vl-424b-a47b-pt","qianfan-vl-3b","qianfan-vl-70b","qianfan-vl-8b","hunyuan-0.5b-instruct","hunyuan-1.8b-instruct","hunyuan-4b-instruct","hunyuan-7b-instruct","hunyuan-7b-instruct-0124","hunyuan-a13b-instruct","hunyuan-a52b-instruct","wedlm-7b-instruct","wedlm-8b-instruct","youtu-llm-2b","ernie-5.1","ernie-5.0","ernie-5.0-thinking-latest","ernie-5.0-thinking-exp","ernie-4.5-turbo-32k","ernie-4.5-turbo-128k","ernie-4.5-turbo-20260402","ernie-4.5-turbo-vl","ernie-4.5-turbo-vl-32k","agnes-2.5-pro-alpha","mimo-v2.6-pro-ultraspeed","minimax-m3.1-flash-preview","agnes-3.0-flash-preview"],"unadmittedEffortMeasurements":[{"id":"98da7bf72c754781eeedbe0f","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"af52f4d0de0e4af1d272cb6f","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"938024499b56b32b14c80f96","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5b5db7acabdd817b3e7dd73e","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8bcf6fb487bd4f7034945f07","model":"amazon-nova-2-pro-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9abe3df4334c51aad2aec0ad","model":"amazon-nova-2-pro-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"83c3679cc2593a1416e8ece0","model":"amazon-nova-2-pro-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed17e3be2f9a297198964c70","model":"amazon-nova-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"03faabf6a483486fa063a636","model":"amazon-nova-micro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9ba3c2f0a8977ad288a8f0ec","model":"amazon-nova-premier","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ffd340540d54b4c2be0c4e29","model":"amazon-nova-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"47c17bcc7ee4f167db21f164","model":"claude-fable-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"75d2e4404944756c0cba8a37","model":"claude-fable-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa0c7951aafc82ce0085649b","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0057ecc817d74d83239c4424","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f92c8f985db06aef5dfde1a6","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eb186484745af7365d75fb3b","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"85f939b76eb0784c35e2e46b","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fe65b606410257a83ae591b0","model":"claude-fable-5-1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"915c42fed9c168b0cd0d4ce3","model":"claude-fable-5-1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"24c940fd705993c6af78cc1f","model":"claude-fable-5-1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"63edf23165ae63ad675dd53b","model":"claude-fable-5-1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b65d0a7245c9b5e0c5392552","model":"claude-fable-5-1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6cbf4db0f85b1a9026199f02","model":"claude-haiku-4-5-20251001","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2da4c6c978b2c7fcd202e37f","model":"claude-haiku-4-5-20251001","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a4ab94d87626afc466c301f6","model":"claude-haiku-4-5-20251001","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"46e00a4ac847e9e09244d1db","model":"claude-haiku-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0843e6c11c75623edcb16a7c","model":"claude-haiku-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78eec329fdf447cf475f1472","model":"claude-haiku-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"794322d853e75058b2eaaf9d","model":"claude-haiku-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1c807b583a76289a7f8e81fb","model":"claude-haiku-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a149d9aace434b3cd553342b","model":"claude-haiku-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"594b2c9a79e1cdafab55d368","model":"claude-haiku-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"92825550c99ad8e6ecf875fd","model":"claude-haiku-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"43c470bb96d270e8d9f2a82d","model":"claude-haiku-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"84edbf4d0f88ca3f6ee43e8f","model":"claude-haiku-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"299cfb2488b1b12fb8bae121","model":"claude-opus-4-5-20251101","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"06bc173078345ce534aba7f3","model":"claude-opus-4-5-20251101","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1a525508a4fe8c81f1a4d4f0","model":"claude-opus-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"50535977bbb1720c8107ec69","model":"claude-opus-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0ac072efffbc910c90cc5e43","model":"claude-opus-4-7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dd3f3302d99c6e2a87da9709","model":"claude-opus-4-7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f512427635d3a1eb3986839a","model":"claude-opus-4-8","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9b13a6e2c09e8a7ad1375e15","model":"claude-opus-4-8","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8158b49aa1444c7311339716","model":"claude-opus-4-8","benchmark":"deepswe-minisweagent","reason":"Incomplete task coverage: 111 of 113 tasks. A common task set is required for ranking."},{"id":"140db294c5eb909c8ba208ee","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"88f928df06be55061e149bb6","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a164b566a82427182f1a3eab","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"da7415490fb983c56c6f4665","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ebdd606353ef09824dff9f22","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"093cf9f9fde9935f885cedee","model":"claude-opus-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c39d270141be864f2639eaff","model":"claude-opus-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9a471570f6a64ed79fca4964","model":"claude-opus-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d95e11216bddf1634c371c2f","model":"claude-opus-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"70dfe50b02b73db1cfa4c851","model":"claude-opus-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"302dc2a5ff2ef491e86105a8","model":"claude-opus-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ca17d9492048571313d749b5","model":"claude-opus-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"24768a7c096deb69be9c64d4","model":"claude-opus-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9e1c61275e8bbef77da24d59","model":"claude-opus-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"be3ac51366605e77ab20a4a1","model":"claude-opus-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"143dbd2e432d661d58233d8c","model":"claude-opus-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6943c8595f70352be7cf2957","model":"claude-opus-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5a1643112f9311f86075f36b","model":"claude-opus-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0ab225a78ac35909f1c0a198","model":"claude-opus-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b4f7c0523c077121c46b5f30","model":"claude-opus-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c712e425b0902b25a4bca75e","model":"claude-sonnet-4-5-20250929","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3efd3c04564d707cb7af0c5c","model":"claude-sonnet-4-5-20250929","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"843d8eff7e70d1387558ec55","model":"claude-sonnet-4-5-20250929","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"27530616174a8f787e91c784","model":"claude-sonnet-4-6","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8bbb15b7b00975fd75772621","model":"claude-sonnet-4-6","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6171bd1b3aeff19b98f03d67","model":"claude-sonnet-4-6","benchmark":"aa-global-mmlu-lite","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c0747a8f7573ade81afb51eb","model":"claude-sonnet-4-6","benchmark":"aa-global-mmlu-lite","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78a71abdf16dd749a78783cb","model":"claude-sonnet-4-6","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa1e4adb1a8ec6b26d22469f","model":"claude-sonnet-4-6","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8063019679e03cfb746392ce","model":"claude-sonnet-4-6","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d279070c2d38929fdb77aa85","model":"claude-sonnet-4-6","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"030e25b703a598bc1234cf6e","model":"claude-sonnet-4-6","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8afde1d0a2ccf273ca948fc3","model":"claude-sonnet-4-6","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"963a3c96c19569be4330ad94","model":"claude-sonnet-4-6","benchmark":"aa-mlcr-aa","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d8072c6c9d5fae1f30806393","model":"claude-sonnet-4-6","benchmark":"aa-mlcr-aa","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"19e63d8aec4216f5120452a9","model":"claude-sonnet-4-6","benchmark":"aa-mmmu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"be4e64ba8034537372c9c1d0","model":"claude-sonnet-4-6","benchmark":"aa-mmmu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7398421eab52c0e986070f4","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7392150f1198f62f4b2879f6","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a6fa79a6c14528865e202ae8","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8fea1adfc17b5869acd4794a","model":"claude-sonnet-4-6","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dd37dab3527fc9b73af7a482","model":"claude-sonnet-4-6","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ebff159fbc5de1bdcff80fec","model":"claude-sonnet-4-6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"490a984f281c9931dee460b5","model":"claude-sonnet-4-6","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b390d26c0a476ac3a49c3ea9","model":"claude-sonnet-4-6","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"03dbde466df814133b51e33d","model":"claude-sonnet-4-6","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d0969ff841573b014a09218e","model":"claude-sonnet-4-6","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"463b38ef7a40f6adff0048b2","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"21e96c3f3a26974f3c958514","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f93fe9ba3256a3c652bd27aa","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8b305b6faddeac3de70ff49b","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a60cdab1630c63ecb318ae4a","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9f4089dfbf594cbf7298e930","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c00af2ab066171f76a56a2ce","model":"claude-sonnet-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a14cc610ff685bf92eb2e9f2","model":"claude-sonnet-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8edb37e82094f84ce2b378b7","model":"claude-sonnet-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5f58711702294d24e90328ad","model":"claude-sonnet-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1b7342699ab8a254f4eccc48","model":"claude-sonnet-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c96e3100b2cb1ebe04115ed3","model":"claude-sonnet-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7d297321a0a395af5f0e3b03","model":"claude-sonnet-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"70aed5a8f5959e55dea3dfdd","model":"claude-sonnet-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a176441933be023f28218629","model":"claude-sonnet-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d1dfc5817dd62938a0537a02","model":"claude-sonnet-5-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78b9446cfe37098965498801","model":"claude-sonnet-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"68a4f73ee8faf5087dd463fb","model":"claude-sonnet-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"532918e7edc7acb0bc0e991b","model":"claude-sonnet-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d2563bf03bb787a9737d9e91","model":"claude-sonnet-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bbf569cf2c38fab3f89b8da3","model":"claude-sonnet-5-5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9fe83ac17762f2d5b91590ca","model":"command-a-plus-05-2026","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5ab70dacb88f83e57d5e2076","model":"command-a-plus-05-2026","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0f2099408e3868dd3f5bbd0d","model":"command-r-03-2024","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7b2966cb801f40d53a63d0d","model":"command-r-03-2024","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78c2d72883d8472bf84bb942","model":"command-r-03-2024","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c51be1971aa7732d0e3c9dec","model":"command-r-03-2024","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8738d7c5dfd75c32c1227708","model":"command-r-03-2024","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f43c9503098639be7baabd71","model":"command-r-03-2024","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"14c3bdfd1b0511c0d8bd8d7b","model":"command-r-03-2024","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9fd73563f403665e135e24bc","model":"command-r-03-2024","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2deb81947d71e3f165d2316b","model":"command-r-03-2024","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bfe86af3326b7bb69930545c","model":"command-r-03-2024","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"da46f877760d8faa5938e0c0","model":"deepseek-r1-0528","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dfd5bf4e982521e955c382fc","model":"deepseek-r1-0528-qwen3-8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c8e893e3e38807fa7c5bc79c","model":"deepseek-r1-distill-llama-70b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ad70fb15b77d81ac74c0ce38","model":"deepseek-v3.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9bdadba43260d89af264c859","model":"deepseek-v3.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f6d49d36dd36d19e284b4d40","model":"deepseek-v3.2-speciale","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7eddb21b48546623d8b9ceae","model":"deepseek-v4-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3788db944176c99c751ddcdd","model":"deepseek-v4-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2a4f099e8be9e64b14fbaafb","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0c1dafd1d8bac92ab1d83278","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d01834dbbcf94f0a87f0400b","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e23fd324f0b5dba92baee5f7","model":"deepseek-v4-flash-0424","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"045e27fe3e938eea61091981","model":"deepseek-v4-flash-0424","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c6f5d7997d3920e36cc9a135","model":"deepseek-v4-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"953fbb84fee7ea9bb2daa7f2","model":"deepseek-v4-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"71fbef21a92b2b9266e84dc4","model":"deepseek-v4-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8ccb6d811a15f748f06abe30","model":"deepseek-v4-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ac3167852c54be45702e8943","model":"deepseek-v4-pro","benchmark":"deepswe-minisweagent","reason":"DeepSeek V4 Pro checkpoint is not identified by this source; April and August revisions must not be combined."},{"id":"e78d8563438a3038e2add529","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1838ec314ba48dfcb0b88949","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ddbb8446868edde4b9b6f18","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26f09833a07c503224ee3196","model":"deepseek-v4-pro-0424","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"73dad6f716b874127cb09975","model":"deepseek-v4.1-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ae524fe73772814c961a1e1e","model":"deepseek-v4.1-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b95593ffc6d7d29e6a085c2d","model":"deepseek-v4.1-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3a7baacbe5fcf52f98f86cbc","model":"deepseek-v4.1-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f87d2326544d8fc4fc49d91d","model":"devstral-2512","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4656ead8373195f1a2848cdd","model":"devstral-2512","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0b3377f33c68c96e20808b3d","model":"diffusiongemma-26b-a4b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0dbac5be77e69634487925b3","model":"doubao-seed-code","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d15eb698c8417578a083d5a2","model":"ernie-4.5-300b-a47b-pt","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cec86b4c9567fb892efd3dde","model":"ernie-5.0-thinking-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"de9a29070b73434bde934a9d","model":"exaone-4.0-1.2b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"91f5aaaa147fa965a95ee6e2","model":"exaone-4.0-1.2b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"28161676227107f4bf1e949f","model":"exaone-4.0-32b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d18d1d42d9c3d891e66ccc05","model":"exaone-4.0-32b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"331c0bc96cdcb1aaa53a4c89","model":"exaone-4.5-33b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a6ea19c704d0cd6d45804ad9","model":"gemini-2.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"94436d1283ceade19a098e93","model":"gemini-2.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bd0e18878398a2cba1e2c630","model":"gemini-2.5-flash-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"54fcfd9dba64059091858233","model":"gemini-2.5-flash-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fed8f4ab77fcd5d31da67c95","model":"gemini-2.5-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b346e2f4d8c39e5b6a8796ce","model":"gemini-2.5-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e31d78ed7068e350eae0e017","model":"gemini-3-flash-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"31aec0c830003796ddb584fb","model":"gemini-3-flash-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"897f612ed5343edc51d5b099","model":"gemini-3.1-flash-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"097b9973b90993f5f5e7d1df","model":"gemini-3.1-flash-lite","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6a904d86ad7c12c3aac7713b","model":"gemini-3.1-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"72fd11da3d45e05f88f9fba5","model":"gemini-3.1-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"09a429372313877fb69d9077","model":"gemini-3.1-pro","benchmark":"terminal-geminicli","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d5a0fc830fec173a656f2b27","model":"gemini-3.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f2e6667b45d444dc018f8257","model":"gemini-3.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cacd42cf1c650df08447f0cc","model":"gemini-3.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8512428c087d4ab5e53a51cf","model":"gemini-3.5-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2996b27e98c9a488eb6dd898","model":"gemini-3.5-flash-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26f351bc48bbc25a81380a4b","model":"gemini-3.5-flash-lite","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3e2c1bfc05ec197865af08da","model":"gemini-3.6-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78d802fcdda621aaeea60836","model":"gemini-3.6-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"21324d1cf4d89f2207e1873c","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"53f605c1b4240fda286c18ec","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1aa81ba21023b341862cbd02","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"734f4b8552268ce3703442f7","model":"gemini-3.7-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"deb39ca13b6306b2fac84c4d","model":"gemini-3.7-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"22cf15a6eebc465978ec8936","model":"gemini-3.7-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"51ac259d6b101f8a33c37a10","model":"gemini-3.8-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78ab7ea85240b0570a09366a","model":"gemini-3.8-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0f099fd18d469ae207c64533","model":"gemini-3.8-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"002be94559a69a5b5d604dd9","model":"gemini-3.8-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2368f4b2a96dd8c54c52aa88","model":"gemini-3.8-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"45ab3f2daab0eb2d65b7194f","model":"gemini-3.8-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b593330a2d29d36cd3398658","model":"gemini-4-argon","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0aa4cb5bd3413e5f599b47fd","model":"gemini-4-argon","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5ac2366a97ebc55c10126e78","model":"gemma-3-12b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4dfa25465b0259154b3eed24","model":"gemma-3-12b-it","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d572ac181de7f4a7bd81c4e9","model":"gemma-3-1b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"20bea5cafe0c9e45a478f6d6","model":"gemma-3-270m-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"09f9d18827eea3ab094fd5d4","model":"gemma-3-27b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fe3bf9bdec38cedda2c4603a","model":"gemma-3-27b-it","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"84dea6e1e3ef3afc74262d95","model":"gemma-3-4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b27d10aabf75f3a064bc461e","model":"gemma-3n-e2b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9082176c134078aa550097ff","model":"gemma-3n-e4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2b90c9332daa18e534fd0fcf","model":"gemma-4-12b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ce50829c14122f3091899493","model":"gemma-4-12b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"67499adc1b46f586a1c3d2b0","model":"gemma-4-26b-a4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"49acca20990729f11bd62386","model":"gemma-4-26b-a4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7f48b80e0edac6838dffb50d","model":"gemma-4-26b-a4b-it","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ba8e82e53d70d6f8aafa303e","model":"gemma-4-31b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"098d80e8ba47d8a6ef0c241f","model":"gemma-4-31b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e131f49fc0290c2c251ad59d","model":"gemma-4-31b-it","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cc429fcc1335cb09f66d90b4","model":"gemma-4-e2b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e73a2705c80206386d342583","model":"gemma-4-e2b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6ecea92ea2a8f843cc72ea55","model":"gemma-4-e4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bf37eb7ed991ae1c14f31e61","model":"gemma-4-e4b-it","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bc1bd2b2d7480b7b9373c1c2","model":"gemma-4-e4b-it","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f36782bceb8f45f46260015d","model":"glm-4.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"01d4601ce35baf7582b2b1d6","model":"glm-4.5-air","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3448b6b298eb30f990513f92","model":"glm-4.5v","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d6ed32645d4db9e47a014182","model":"glm-4.5v","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"34147f34008b905a9aaccb96","model":"glm-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed586d5fb6e4774692dbe3d6","model":"glm-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"39a8e6640c8191a779ffb48c","model":"glm-4.6v","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6fddb525b5d0b94467ba8661","model":"glm-4.6v","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"99a720d42d9ab77eb33f8999","model":"glm-4.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4e7b558ad298402697e6731f","model":"glm-4.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a401455d8af56dc225e840c7","model":"glm-4.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7ce9b77baf9eb443d943cfaf","model":"glm-4.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7ee2916f2a458729d0bf1b6b","model":"glm-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9d54baf80501bc9f77e431c4","model":"glm-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0bdaf0c08a9f5d6437f640a7","model":"glm-5-turbo","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d5b509e455ea18ca2e688dc8","model":"glm-5.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7fdcae53e99c38cc6d93e736","model":"glm-5.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"751a38b92383dd44f4f4b6f8","model":"glm-5.1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8b1cd09ce3680fd3ede877c5","model":"glm-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d905bff8aaed379cbae34a55","model":"glm-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c5c56d14c19f67f323d70f3d","model":"glm-5.2","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4cf17b3752920a22bddf0931","model":"glm-5.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c3d5b20dd24762f5952922e6","model":"glm-5.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c6d35b78e0277163670c59a7","model":"glm-5.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ce9d876bde1429ca9f36479c","model":"glm-5.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed40864bcdafb5eb329dcd23","model":"glm-5.3-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e1954fd811496a176698b207","model":"glm-5.3-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6f7ad24f8763d179c05b02ec","model":"glm-5v-turbo","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1f1a98c6041a0347cedc067b","model":"gpt-4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"516b003dce56d5a7659fc6e1","model":"gpt-4.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d5aa5d02a1b67889fcf36b3d","model":"gpt-4.1-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"00077c09ee5961a857ea9812","model":"gpt-4.1-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"60cd4a91f69f107025375b3f","model":"gpt-4o","benchmark":"aa-aime-2025","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bc7edbd7f528efe446e8db18","model":"gpt-4o","benchmark":"aa-aime-2025","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"870a8a46a2b531f6c5af62e8","model":"gpt-4o","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ca8731b9c382bd00c0d8665b","model":"gpt-4o","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fddc09f5e0e8bc06d04874e4","model":"gpt-4o","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"24a10eeb3a46c7763c5a63b2","model":"gpt-4o","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4e82b51b3daf5aa1c8d98aee","model":"gpt-4o","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ba806794d6c0ebc1b2585e8f","model":"gpt-4o","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c88594bf8e16a074cc837dfb","model":"gpt-4o","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e0c41d17488dc4ec4ba0f0b7","model":"gpt-4o","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5b174d58d4c658ab3d23b8bd","model":"gpt-4o","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"676bf2b6f6b8d425be537a91","model":"gpt-4o","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c5b33db9dc0245a7fa091824","model":"gpt-4o","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c611da33ffcd9a9e78304e4b","model":"gpt-4o","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fd73d709f3bb83bda7f56ac0","model":"gpt-4o","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"adfbe98a4535a8b4dcbba8db","model":"gpt-4o","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e8a8172c365961fe52158eb8","model":"gpt-4o","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"111a771f0c518f482817be18","model":"gpt-4o","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8d6af27176cb848c0da30e16","model":"gpt-4o","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"952674fc62e371988760c75e","model":"gpt-4o","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e26cd77447c8fea5c2954d73","model":"gpt-4o","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"08df3f3cdd6b93731cef3bfe","model":"gpt-4o","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"51e4170d40d5c177fe0231db","model":"gpt-4o","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"60f11419a7766054a4108a18","model":"gpt-4o","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"67323d93d4710a1a34a75f0f","model":"gpt-4o","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"93d23dcf1ef65f2e23f876f9","model":"gpt-4o","benchmark":"aa-math-500","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26a5dad1362342e4f74d3ddc","model":"gpt-4o","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8196e10e1bf2c6ab7a48896c","model":"gpt-4o","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"893141e7225b21e42fa2ce7d","model":"gpt-4o","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ce9dd7a47db415076cf5f8f6","model":"gpt-4o","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"39324a10e110c667372e0e04","model":"gpt-4o","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a9b3da7256fa223acaa958e2","model":"gpt-4o","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"750e957428961c84d14679b0","model":"gpt-4o","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b29b60a9d0d8925b03ed31d5","model":"gpt-4o","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"007fbaa1f184a893e7a405b1","model":"gpt-4o","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79b4fb7fde5db57eeb15ccdc","model":"gpt-4o","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"89547fadc0a82f235410b5f8","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"48c2795f7767156dfb87810e","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d269fd7d536cdc788d304da2","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"83da1b801f784f99b059e2e3","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"27a8f43f659f15e583e7a1c2","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5e4c27dfeaca364435205d77","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d8b8696f5fe260c359a93780","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79c10f9e00a2b29918be9a1c","model":"gpt-5-mini","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"495bc899315c1581ce854e28","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"43575cdae591da725c3b65b4","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e0bdcd0f68066992a4330f39","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"671d0f66976d744d141136a9","model":"gpt-5.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ad964ce0ca054e729c02f3c7","model":"gpt-5.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79c7838d7d3a6bb22b1ce139","model":"gpt-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"818ef12ce3bfce5ac2c89f3b","model":"gpt-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d01377d4aa4c240dca9f6a14","model":"gpt-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"540b1d5498c3e0a301b1538c","model":"gpt-5.3-codex","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8327c80a5c4f5dae3387a82f","model":"gpt-5.4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0f3e47626675965f1c173e90","model":"gpt-5.4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f8d4a4b076f89d356e4af279","model":"gpt-5.4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2a3ca10746890e5987da723d","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bb219decdc8cf7631a71f8aa","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0df0c44f9dbd70c6d17a04aa","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"faea98938a0a1f3c02346703","model":"gpt-5.4-mini","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"41d8f84c096cece5209bb1f6","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"23051d6c0cf6193d2f9162bf","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e86607181dc76cf771cc5a79","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0052c5d0008eeb0968eb331d","model":"gpt-5.4-nano","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3c451d8f6634f505e51773a4","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b83d04c88c92bb3d49ebe682","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1913dc520d4a89f0ff9dcb21","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"631dd98cd9c042f570e09cdd","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a19566dbb3e95e4e2873ca6e","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7f175b942e3a8b257d84b73","model":"gpt-5.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f655094357b4e6bb3de7e139","model":"gpt-5.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7091723aa1a23c7293d6469e","model":"gpt-5.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f266a9323e42c26d29c56798","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ef6a561e2c83715a872c7f7a","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"02de7c94d0ab8b2ceba4512c","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b13a8bac5c637ce921467dbb","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"150c85bb1557c00c7a6d1ffe","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"05676a264b60533c21673971","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f7a065b0663ae0a319240f74","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"46a2ab6ca51572c3af625d9f","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ffd31be8a2c5dfaad4c42a10","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a1e6634a8ad09dda7a7f2e0d","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a26faa4f2758b30066d00e5c","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8c33016fdd4bbc68eb016673","model":"gpt-5.6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ee678562d47d22a6875558b3","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a63ab95a8a408b289abbb46d","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d23f488c99b2190b4e0982c2","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f646f68c571f26eb0fc17d00","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"52cbe7096d25c4e59ae6c392","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b79e0ff46dc455df5138ba5f","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"709e81a0a33a47d464af44aa","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c2177dc76be61711d1a61b06","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b155134d83a92a8e34c71988","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3136590de59224790e6fd89a","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b1479cb06719eda54907a9d9","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c4809acc90ab2c62f55cab04","model":"gpt-5.6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6ba5406295cfbfee0aeeb688","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fb08cf5faee0f46c6fec58ca","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5378a72f622a354a37276342","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6ad0c4bdf9b9ec84c4ee0711","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"acb6eaf0788afbef68320415","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4525fa025f453c3f7e18ba1f","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8440f260de487af3659ac24e","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cad30981cda759eddf24482f","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"722175536c6573787a0a82b7","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"24599291513403a2120872ee","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"200cba6f59d9e1ed30007fc7","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"84bbd4f88c501a6b5c239ee2","model":"gpt-5.6-terra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c2ed4078e8723069cad94348","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0bd39379aa60980372b1a483","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"936b4694f2d3e110c96c7d1d","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"29809c33eceeba5622b144bb","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"104d966ee15689cf157d5e7f","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8b41b672e41052e0cd3069a0","model":"gpt-6-astra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"976f352750456195751d0a56","model":"gpt-6-astra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"62be10449eb661358f9cb609","model":"gpt-6-astra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d8d8078f1b862e001d46f606","model":"gpt-6-astra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d9e2313727f7a8e1ad52e120","model":"gpt-6-astra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b5faeccd54fcda2954357a39","model":"gpt-6-astra","benchmark":"arc-v2semiprivate","reason":"Source-reported label. OpenAI documents Low through Max for Astra; this does not establish a supported non-reasoning API setting."},{"id":"20e3ef7fbf64984566407e4e","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9ea2580ef691d710d9cc2dd5","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9f2ebaa525d1bf0a2dcd8fc9","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2f88e138bda31c9cfa8ab817","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"63298170bbb423389ae897e0","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f663cb94aed0c489b8cd081e","model":"gpt-6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0fa34aea17e35cf7ae3beeb9","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2d547df4fe61b3c4b08abfc2","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f4c807a7e3a01a657b5dca3d","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"12f4aaf84c8045b8e65eeaa1","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7f3ec19d60fc54e1792d8e6a","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d5d2b5f5d6082482db5e6acf","model":"gpt-6-luna","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1154bdd990076a6f598e4ea3","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"94cfcf715e69e4cc2280424b","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f86dc82f576fec44f2d4cccf","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"34432444ac91998692a575ea","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eef671de884b38fd10c41087","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"72685ddb1ea0dff79cde3146","model":"gpt-6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8212c304db0a4fdfcf231c60","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1a0703351660c70d1889457a","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2a4c60137e91918664141ffa","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"561b959d2c87575ae98baabb","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f17dd5a9a9a4bbb5248c51e1","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ecef52afc6967c3cb896841f","model":"gpt-6-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"64f3fac7e6fe92bc9f326811","model":"gpt-6.1-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f8cc520aa71efc9d2cca2ed5","model":"gpt-6.1-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e386ccb4642f088a69b91e74","model":"gpt-6.1-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c0c872113c362c920957fa03","model":"gpt-6.1-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"03bdd4a2b19a8e8b281dfc5d","model":"gpt-6.1-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"39da558f9bc667508c72560e","model":"gpt-6.1-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9ed1c59bf4a943cdd58181e0","model":"gpt-6.1-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"74d95ec2338ee9f4688df1b0","model":"gpt-6.1-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"def63ce73e46d175b4c3e3cf","model":"gpt-6.1-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0d166f1c77c1d87e8fbd3608","model":"gpt-6.1-sol","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b859f17d0623493d9640fab8","model":"gpt-oss-120b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"85cce49d8e81f9bc7ee8e669","model":"gpt-oss-120b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"064d9c4a525afbedbc6ba21a","model":"gpt-oss-120b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4c7158036f4e41eb7f869001","model":"gpt-oss-20b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7740302bac02e4bf9f65a113","model":"gpt-oss-20b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ef5fecb56a2f9ee3eb881a3","model":"gpt-oss-20b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"09b6428fa759d908ccb5afae","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2e2d40dd58af61ba5dcf3f71","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4d7a7ea79d14224389100352","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"723887484db7ec3fbb615c5c","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"27b5321c003a7d31cf5acac8","model":"grok-4.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0561533dc2911a9c3050e1f3","model":"grok-4.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c682e32d9ea064efabe1dde6","model":"grok-4.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"16057f70ea8e1d33f54b0acc","model":"grok-4.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"43896251f67c4560c987eefb","model":"grok-4.5","benchmark":"terminal-cursorcli","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6f49a8c226bc88f3c493b4ba","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"505a2829d55dcb2770e948af","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e347da11309bbb7ed5c362fc","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4d8998f59334f3d8011e1014","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8bbdaf9bb9135654d3bcdac6","model":"grok-4.6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1a152b4c4e47ce624c9d5c0b","model":"grok-4.6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"05d718901ba5f820a250f83c","model":"grok-4.6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"456f8aba84ca2b03c8b14c6d","model":"grok-4.6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"631e579e32b7dd3021d1344f","model":"grok-4.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"454e9455a2788947b229c1ce","model":"grok-4.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"83ea092e007eb2478396ea2c","model":"grok-4.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c266f6af3648f79914736afb","model":"grok-4.7","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ff1791f34ffe41084fd03a43","model":"grok-4.7","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6b52ef79e2062a332869f28b","model":"grok-4.7","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4e3737c70846342ba1f20656","model":"hy3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"05c2f7fcf387f4cfcc374ac1","model":"hy3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5c695ae8e66e691e9c8f92ad","model":"hy3-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79511ae819bfc612c35a390d","model":"hy3-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7e86cbb35e9d7b3c2e6378d0","model":"k-exaone-2.0-750b-a37b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a01cd222d9ce7bcafe04151d","model":"k-exaone-2.0-750b-a37b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8e4b9809a8173b24a6492b4c","model":"k-exaone-236b-a23b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"577a7a49fdb90fe94610bce7","model":"k-exaone-236b-a23b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ca4100db60d1e0bc35d98c00","model":"kimi-k2.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b666fddeadc496e9d235901c","model":"kimi-k2.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fd0de66f868ec0aa650e1dc1","model":"kimi-k2.6","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b0a4a7295832157df8e2a492","model":"kimi-k2.7-code","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fda338029ff27052839f5dbc","model":"kimi-k2.7-code","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f791f4ab4c535b3db3488fc3","model":"kimi-k3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78944636973ac08414ad4917","model":"kimi-k3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9b559a9494066b39281413ff","model":"kimi-k3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a527b4e4b99a93b06905f9d1","model":"kimi-k3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2c975ec825cce37abe4db74e","model":"labs-devstral-small-2512","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3d79254e334d06a2ca47d4ed","model":"labs-devstral-small-2512","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7eec6f4e726f2ac2843e4d31","model":"llama-4-maverick","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6d6139083fe99c0d47d89705","model":"llama-4-maverick","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"825b3abf9640fc95590a58b5","model":"llama-4-scout","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b3e565fe11b60b81a60483f2","model":"llama-4-scout","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b059b84e2446c00ab8d4580f","model":"magistral-medium-2509","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f6035266fb17e74a06d13c9a","model":"magistral-small-2509","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"25c20a5aaee132cb4c3e9285","model":"mimo-v2-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f5425b9754a5e445a5236ede","model":"mimo-v2-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dce9246667e76d78df4c7435","model":"mimo-v2.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ad50ec8ea74deb9634c82d7","model":"mimo-v2.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f20dd3ebb423e6ee03f6caee","model":"mimo-v2.5-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3b6ed8afa3616df97c1fc388","model":"mimo-v2.5-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"36e58dcca98e609ebe513916","model":"mimo-v2.5-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"94ee2962270ea8b2bb18e906","model":"mimo-v2.6-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"534da180c485e3050ccb192c","model":"mimo-v2.6-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5a0b4274183464617d2486cc","model":"mimo-v2.6-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d78e8317840a98a149311435","model":"mimo-v2.6-pro","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"97a83445db5e3087c342c4f8","model":"minicpm5-2b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b37840fcc4887b193a7da1b9","model":"minicpm5-2b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"32652eb449f7c6cb3047e850","model":"minimax-m1-80k","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"511c96d55ac43f5883ed839a","model":"minimax-m2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c5300b173b3b63c3bb16dbd2","model":"minimax-m2.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa77f8427f177890a4cbbdd7","model":"minimax-m2.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e4e76f6bd4e0359ded238ed2","model":"minimax-m2.7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ffed6553b2632c7198bffaf9","model":"minimax-m2.7","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4fe2dbb70cb706ac86051368","model":"minimax-m3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ca3f36ad153ea45bc8abefbe","model":"minimax-m3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7d6441354088c9ffdd6ef7a3","model":"ministral-3-14b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"41e2bdc01aaf88a7862f9af3","model":"ministral-3-14b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"928da08d1319107c56189f07","model":"ministral-3-3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"719ae7fb0aa3a8f58828d8ad","model":"ministral-3-3b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"75e22a9892b66c0e65dfd55d","model":"ministral-3-8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"60d1bb31feedab5df58faad3","model":"ministral-3-8b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fe1a4682c062f12dbe7de410","model":"mistral-large-3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4eccbe09a60fef497d086249","model":"mistral-large-3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"530427155dcfa01e7115c354","model":"mistral-large-4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"75d0b63baab906a80f8fef86","model":"mistral-large-4","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"98b8086ecdd729adb943befa","model":"mistral-medium-2505","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"98f555a90b9ec68d099b3ccf","model":"mistral-medium-2508","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0bc62ae3ef77f27ee9feb8c3","model":"mistral-medium-2508","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"df8c0054af3ea000e16148ed","model":"mistral-medium-3.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"46f40618c1d6eceefad11b5e","model":"mistral-medium-3.5","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"be0fd3096da38b78e3aef989","model":"mistral-small-2506","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7a032bb7d27ac4f4a54dc043","model":"mistral-small-2506","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2af0431ee57da42eb9cd13d5","model":"mistral-small-4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"50d33b56ae65630b7fd1e35d","model":"mistral-small-4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f2789b044f471f6a2756d4f1","model":"mistral-small-4","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"181518e22756782a0bcc6529","model":"muse-spark-1.1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5fe09def3846dc24c2d5043a","model":"muse-spark-1.1","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4db8c7b47a313e0e8d926986","model":"muse-spark-1.1","benchmark":"terminal-minisweagent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7fc466dd87333128e87ed96e","model":"muse-spark-1.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7a82f88e55a398d5b725fff","model":"muse-spark-1.2","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4f219c79469e44d8cf6604a6","model":"muse-spark-1.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"afb2cd939c6a958c7a34bc70","model":"muse-spark-1.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e2006099a5d0417910b49e29","model":"muse-spark-1.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2580065e526b137c06fb4d34","model":"muse-spark-1.3","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a702440f484ecf067ab37730","model":"muse-wonder","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2494c3776c4a648aac942118","model":"muse-wonder","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"54b82abd2705526e243350f3","model":"muse-wonder-full","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9841a8670fe760a5c96f4521","model":"muse-wonder-full","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ac0a28355ceae30603057943","model":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5d823713f33e043edf26a0f7","model":"nemotron-3-ultra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"30b7b7ecf698984e25f319d1","model":"nemotron-3-ultra","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"055179e91fb700bc3a6f59f6","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"691104d3d04d79d51b9cc955","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7592763efd7af6d017ddbac4","model":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a9e95986995916b5c3500760","model":"nvidia-nemotron-3-nano-4b-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6547929be39454ebdb26b3f5","model":"nvidia-nemotron-3-nano-4b-bf16","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c608bf4dd61434f7ad16f374","model":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"deb1da1366abb23e09076986","model":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b1606fde6708193b5680178c","model":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"685493fcb0926afc1fc64549","model":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"794273354d8e571966e3c3cd","model":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0afea5460705df6d4ceff65e","model":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0c9b0458dabd028dcd7317d2","model":"nvidia-nemotron-nano-9b-v2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dd9503a5b07df03d5dd74bde","model":"nvidia-nemotron-nano-9b-v2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fe3b117476be77296f685c2b","model":"o1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"350484fd270e9192ba0525d4","model":"o3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9d9797f0abd5c758079a5414","model":"o3-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c215eed3a150084b6b203302","model":"o3-mini","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"254ca466b5e8ceb4828ba2d6","model":"o4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d4d5188cfd91b9b6ddb85ec5","model":"phi-4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ec4c88a12f8e0d0998cc68b9","model":"phi-4-mini-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3d42354ed91a3ab11dea3013","model":"qwen-3.8-max","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2132db3ad39a78473d68e747","model":"qwen-3.8-max","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c5748c028be706993862b536","model":"qwen-3.8-max-0902","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ea6fb5c196f9227bddf85436","model":"qwen-3.8-max-0902","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"607485fd1a1b0b822e375d3e","model":"qwen3-0.6b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7427f5729e938d7772017aa2","model":"qwen3-0.6b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"460ee126fa722ac88fa60ce9","model":"qwen3-1.7b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"33f988c4c7a2096720a36eb5","model":"qwen3-1.7b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f9876ccbd46960970f8661c0","model":"qwen3-14b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fffa4d922bb3d13549db3532","model":"qwen3-14b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a32d713ac22ff457128d16eb","model":"qwen3-14b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c8b44554d63181fae5555e52","model":"qwen3-235b-a22b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c34a248fd9868cde08c5ce20","model":"qwen3-235b-a22b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5f17f8f143ab442b52c0ca93","model":"qwen3-235b-a22b-instruct-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"963e940e7972f41eb041f884","model":"qwen3-235b-a22b-thinking-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"257a65544bb4192d4e6972b6","model":"qwen3-235b-a22b-thinking-2507","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"be9c4f9166e8a88c6c27dc71","model":"qwen3-30b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"48c5c21ee84158570d29b986","model":"qwen3-30b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"62854b9cc7a0052762824704","model":"qwen3-30b-a3b-instruct-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d309ffb9a64b671bdd150c8c","model":"qwen3-30b-a3b-thinking-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"97fe37c7f9321a9afbce9419","model":"qwen3-30b-a3b-thinking-2507","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"864945a3e7a9e02b314d1f06","model":"qwen3-32b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4f069f41ce299bb5371886aa","model":"qwen3-32b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"49c265837d27d2d2bf8e4efd","model":"qwen3-4b-instruct-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b3a3f857a9b6c30c32f5e781","model":"qwen3-4b-thinking-2507","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7d82a974e643a8d0e079950e","model":"qwen3-8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ab22b03c0bef227a91b34986","model":"qwen3-8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f14ac71d6c0d2283748b9d25","model":"qwen3-8b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26f52aa824dc36a26b030308","model":"qwen3-coder-30b-a3b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0b2034bca18006f3172a087a","model":"qwen3-coder-480b-a35b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6fb3b7bf91c4f655e0f9e5f6","model":"qwen3-coder-next","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e73b78f68f384f26a35c1f23","model":"qwen3-coder-next","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"379f3e03c5a75e45500083ec","model":"qwen3-max","benchmark":"aa-aime-2025","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d0ee451e3d70f7acbd7160ad","model":"qwen3-max","benchmark":"aa-aime-2025","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"41701e2d8384671332f59b80","model":"qwen3-max","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"873b3fc87079fb7d99451bb6","model":"qwen3-max","benchmark":"aa-artificial-analysis-long-context-reasoning","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"315935ae2fb0b8d9506630ce","model":"qwen3-max","benchmark":"aa-critpt","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"618ec7df142e33dee8639477","model":"qwen3-max","benchmark":"aa-critpt","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"18a603f0cb554eff82286b14","model":"qwen3-max","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"380908933be5913820054566","model":"qwen3-max","benchmark":"aa-humanitys-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"879326ff889e832b42641611","model":"qwen3-max","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c69c24d53e30040f4c162f6f","model":"qwen3-max","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3659c33ae93ad5a386c4057d","model":"qwen3-max","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eb581aed1e808fa587fdb05b","model":"qwen3-max","benchmark":"aa-livecodebench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"08a91161451f412505e30032","model":"qwen3-max","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2b16892f62e2b462f8dead01","model":"qwen3-max","benchmark":"aa-mmlu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"520b99ee426c18dd7f263df5","model":"qwen3-max","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c010e27462d3d72e8f96c438","model":"qwen3-max","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4bbb94159adbed7fb9c2fd95","model":"qwen3-max","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e392854706b6be7d554ebf84","model":"qwen3-max","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"12c287fe88bcaa562fa38631","model":"qwen3-max","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8e7b03c9d5c0d8dea1a9ebd9","model":"qwen3-max","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2bdf79ef92caebbcd2a7db59","model":"qwen3-max","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c942c318ad1475140efa1310","model":"qwen3-max","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2263e85fdc24b011ab25738f","model":"qwen3-next-80b-a3b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9e71a0ae62a979c3a73340e0","model":"qwen3-next-80b-a3b-thinking","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"96e0b755ad70d1c1e0ae9354","model":"qwen3-omni-30b-a3b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1648013dead8d8b7e3ccc5b7","model":"qwen3-vl-235b-a22b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3d168904477178b1120a9f97","model":"qwen3-vl-30b-a3b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bc8e92ab40faf29f9b4d4907","model":"qwen3-vl-30b-a3b-thinking","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"47a57d2d2d5bebced36433b6","model":"qwen3-vl-32b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79f1b817a8bf3ed314092aa1","model":"qwen3-vl-32b-thinking","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"edb4937174129ff14d58735a","model":"qwen3-vl-4b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"362b4a14df3cdc84afbc71f4","model":"qwen3-vl-4b-thinking","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"36cb2e462ea1e247f9f8aa78","model":"qwen3-vl-8b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bc245f925590016dc55fa53a","model":"qwen3-vl-8b-thinking","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f04c11d1b1e78ba49a626d3e","model":"qwen3.5-0.8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"937ba73b35a8ad5eb48af2c0","model":"qwen3.5-0.8b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"13945cfbd8edd56e3c0efd6b","model":"qwen3.5-122b-a10b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c7e647c2a4d2f6427799cdf3","model":"qwen3.5-122b-a10b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"515eeda369aef75d1b3b90a2","model":"qwen3.5-122b-a10b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"40ff7c5a40a01e803bb1cd8c","model":"qwen3.5-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"55cdfeeabac6031082ecb7d4","model":"qwen3.5-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0aba9d436f02774f10805fd1","model":"qwen3.5-2b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4ebd8fc4a160d868162f9b65","model":"qwen3.5-2b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f638bda28b9ca9b449743a3e","model":"qwen3.5-35b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eebdfc2b391ba014eacbdef5","model":"qwen3.5-35b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"263ebc7960a8a4cb108bd07c","model":"qwen3.5-397b-a17b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6a3a254fa11a7c706555dff3","model":"qwen3.5-397b-a17b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b223f7629fdf1388f9bed2a9","model":"qwen3.5-397b-a17b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7f8e4594adf9ffcf3ed6e8a","model":"qwen3.5-4b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ebe98a5e899b1dcb02f76998","model":"qwen3.5-4b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"70c7c662608af8f632662f38","model":"qwen3.5-9b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5686f65f304b0ae905401fe5","model":"qwen3.5-9b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6afd5cfd76652d0557349eb7","model":"qwen3.5-9b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ce044099dd1a13b985395372","model":"qwen3.5-omni-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"62d333463f4ce6b2f02693ee","model":"qwen3.5-omni-plus","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3388bc6451fc50d48d32f80f","model":"qwen3.6-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a670029bf642d55d2f29a869","model":"qwen3.6-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"db7758f0177deb0686de0fde","model":"qwen3.6-27b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eacdde9b4ef2d608c6c5db66","model":"qwen3.6-35b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bd2c4bd715ab130b5a7baa31","model":"qwen3.6-35b-a3b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed5c9e27d2893228f1baa185","model":"qwen3.6-35b-a3b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a62bce89fdb4d3abd526eb43","model":"qwen3.6-plus","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4355bc5b1225c68cd10d5191","model":"qwen3.7-max","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9ca0c4c478ac4a52d15f4f0c","model":"qwen3.7-max","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1d6fc7a9f857efb4ea8a4d09","model":"qwen3.7-plus","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ea57b2c6129ce72f6450114","model":"qwen3.7-plus","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"215c0a040e1f469b97f5f0d1","model":"qwen3.8-2.4t-a95b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"845e3104f356e8046a04495f","model":"qwen3.8-2.4t-a95b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"00aa46f0b5885d1c20a9313c","model":"qwen3.8-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"762bcd862dc8b06b020506b2","model":"qwen3.8-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"369ef6b3e1de52e3da9e761d","model":"qwen3.8-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2b8713e5794a859e545bb625","model":"qwen3.8-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"98f72127e05ee7de84bc5d32","model":"qwen3.8-27b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"287bbebec0f8e0c9081cb90e","model":"qwen3.8-27b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f0b6f28261f842ffd221371f","model":"qwen3.8-27b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f2649d3f975b64c3e63ec33f","model":"qwen3.8-27b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"19beb3218856ab5fe419a3c9","model":"qwen3.8-flash-next","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"107f8908a0e4a7c541544f2f","model":"qwen3.8-flash-next","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"12f82b95be07624d144534f1","model":"seed-oss-36b-instruct","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c463459225f8ca121c7dc6c7","model":"solar-mini4-260922","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bff4de9e9b972a0da4c3a48b","model":"solar-mini4-260922","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"786415bc21ec9ec2f6bbed5e","model":"solar-open-100b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f706a5ffc62ecf11d8aa11fc","model":"solar-open2-250b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"793184ef1385ac9eccdc0fef","model":"solar-open2-250b","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4c646f44d8a2f54dd28f759a","model":"solar-pro3-260323","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c09d36e66a2605d0626b8874","model":"solar-pro3-260323","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fcf8445fb274f138d2087141","model":"solar-pro4-260806","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8535449d0bca6e5ef4206e74","model":"solar-pro4-260806","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f10ed77c5f2a457b4875815a","model":"step-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"31c949451c135ca26418dd9e","model":"step-3.7-flash","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c6a5ec26e84ae07fde8aefcc","model":"step-5-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6142b034e5ac95d3051558ab","model":"step-5-preview","benchmark":"aa-scicode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0fcf0db8250ffa3a4b7f5ba1","model":"step3-vl-10b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"41c731de4263a48b615b716d","model":"tiny-aya-global","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0e654cd1466ae894d75cb1e8","model":"grok-4.5","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ffbbc7256f47ee72d321f094","model":"grok-4.5","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6568b269cb7681ea39a1097c","model":"gpt-5.6-sol","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"55c55b9ae75c2c789bb81880","model":"grok-4.5","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"82ad7650319190ab8ebf8f1a","model":"gpt-5.6-sol","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"07c58037116b0b06179f7fbf","model":"gpt-5.6-sol","benchmark":"vulcanbench-v3-07-grok-fable-sol","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"758fa2580c85027d05e4247c","model":"kimi-k3","benchmark":"vulcanbench-v3-08-kimi-k3","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a5c39da8a1cf93a9c675f0ee","model":"claude-opus-5","benchmark":"vulcanbench-v3-10-opus5-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7177575f578b9a510d14e532","model":"claude-opus-5","benchmark":"vulcanbench-v3-10-opus5-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f20cb695188c6fb09c7bfde6","model":"claude-opus-5","benchmark":"vulcanbench-v3-10-opus5-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"724e797747b99ab179cc86f3","model":"qwen-3.8-max","benchmark":"vulcanbench-v3-12-qwen38-max","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fc3245dd2348d67c6fe183bd","model":"qwen-3.8-max","benchmark":"vulcanbench-v3-12-qwen38-max","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"42a596f42d31c722ee3e28df","model":"qwen-3.8-max","benchmark":"vulcanbench-v3-12-qwen38-max","reason":"Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained."},{"id":"1bef904009c6a794c1dd2f03","model":"grok-4.6","benchmark":"vulcanbench-v3-14-grok-46-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5f32740262d72bbbdbf60a38","model":"grok-4.6","benchmark":"vulcanbench-v3-14-grok-46-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d99fc9802ae6b1d7987cad39","model":"grok-4.6","benchmark":"vulcanbench-v3-14-grok-46-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"47ae4c48e3377c9ee20c9652","model":"grok-4.6","benchmark":"vulcanbench-v3-14-grok-46-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"69dd3899f972d5a522219937","model":"qwen3.8-27b","benchmark":"vulcanbench-v3-17-qwen38-27b-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d6e683f349eb46ae01149f20","model":"qwen3.8-27b","benchmark":"vulcanbench-v3-17-qwen38-27b-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5a6667c8022196c74f1a2ccf","model":"qwen3.8-27b","benchmark":"vulcanbench-v3-17-qwen38-27b-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f796e96bd180b4dd9bd12eff","model":"glm-5.3","benchmark":"vulcanbench-v3-18-glm53-zcode-harness","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"d783859010d571f133e77356","model":"glm-5.3","benchmark":"vulcanbench-v3-18-glm53-zcode-harness","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"3bde5c20893b402a0e56ffb5","model":"glm-5.3","benchmark":"vulcanbench-v3-18-glm53-zcode-harness","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"1b7ece23e8756e740abb6e39","model":"muse-spark-1.2","benchmark":"vulcanbench-v3-19-musespark-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"970bc242697fc80101d9ac17","model":"muse-spark-1.2","benchmark":"vulcanbench-v3-19-musespark-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c5e80648923e0576c68a9c39","model":"muse-spark-1.2","benchmark":"vulcanbench-v3-19-musespark-effort","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0a5efdb346f5b8dbbb92cfe1","model":"mistral-large-4","benchmark":"frontiercode-1.1-extended-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"255229c9fb97665746c2f311","model":"nemotron-3-ultra","benchmark":"frontiercode-1.1-main-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"28a8f1e475f0000b4b484058","model":"deepseek-v4-pro","benchmark":"frontiercode-1.1-extended-mini-swe-agent","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"303f27de5519d24ea6491389","model":"nemotron-3-ultra","benchmark":"frontiercode-1.1-extended-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"336011e6d0e94555b099f00f","model":"gpt-6-astra","benchmark":"arc3-standard","reason":"Source-reported None does not establish a supported Astra API setting."},{"id":"34af973aab00ee6e3f8d8bf8","model":"mistral-medium-3.5","benchmark":"frontiercode-1.1-extended-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"364834ea4ff4cde79854901b","model":"kimi-k3","benchmark":"frontiercode-1.1-main-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"62f127539d56d2de5540a715","model":"kimi-k3","benchmark":"frontiercode-1.1-extended-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"6aa803cb83233f756479ec7d","model":"minimax-m3","benchmark":"frontiercode-1.1-main-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"7879d0685c077f756cc44783","model":"qwen3.7-plus","benchmark":"frontiercode-1.1-extended-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"8127d6db140d93c6a2a6f0fb","model":"glm-5.2","benchmark":"frontiercode-1.1-main-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"b3ef1bc9e68ff51e017bc544","model":"deepseek-v4-pro","benchmark":"frontiercode-1.1-main-mini-swe-agent","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"b5b2f35a4688fb053d31b0b3","model":"mistral-large-4","benchmark":"frontiercode-1.1-main-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"c2cebdbb75fc439d384a1645","model":"qwen3.7-plus","benchmark":"frontiercode-1.1-main-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"c9ea93dd77a44efafd8b2823","model":"mistral-medium-3.5","benchmark":"frontiercode-1.1-main-chisel","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"d2bdad5d6d457b8f28281e8f","model":"glm-5.2","benchmark":"frontiercode-1.1-extended-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"e5f0edaa48b4e6162542d4d5","model":"minimax-m3","benchmark":"frontiercode-1.1-extended-mini-swe-agent","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"e93116c3e86f122b9ce063bf","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"Source-reported None does not establish a supported Astra API setting."},{"id":"fe590a70de3d448e4da4dc99","model":"muse-spark-1.3","benchmark":"terminal4-musecode","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0e5a24ad5a3aa10c27a55eb7","model":"claude-fable-5-1","benchmark":"scale-sweatlas-tw-claudecode","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"60b0d52dd406e2a990549468","model":"gpt-6-astra","benchmark":"scale-sweatlas-qna-codex","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"6c79741b5a7ecef0ff4d0346","model":"muse-spark-1.1","benchmark":"scale-sweatlas-qna-miniswe","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bfc3139a28a8c37b769ae912","model":"claude-fable-5-1","benchmark":"scale-sweatlas-qna-claudecode","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"fc3ef3bbe098fd394ff0d2c8","model":"gpt-5.6-sol","benchmark":"scale-sweatlas-tw-codex","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"panel-c150be94540718c3712937db","model":"mistral-large-4","benchmark":"livebench-2026-06-25-AMPS_Hard","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-394dd3bdef92e8dcd0886faf","model":"mistral-large-4","benchmark":"livebench-2026-06-25-code_completion","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-9d17bc866a773505d636d87b","model":"mistral-large-4","benchmark":"livebench-2026-06-25-code_generation","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-8723236a70407e8aab03a7e1","model":"mistral-large-4","benchmark":"livebench-2026-06-25-connections","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-495c60b884a90bb39ef8b8f5","model":"mistral-large-4","benchmark":"livebench-2026-06-25-consecutive_events","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-881e35e28677c446d8b38378","model":"mistral-large-4","benchmark":"livebench-2026-06-25-integrals_with_game","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-ff03c9088659ae53d42267dd","model":"mistral-large-4","benchmark":"livebench-2026-06-25-javascript","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-0dc5b51301907163a7deaa45","model":"mistral-large-4","benchmark":"livebench-2026-06-25-logic_with_navigation","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-3025e1d8b41e854f23a4f5af","model":"mistral-large-4","benchmark":"livebench-2026-06-25-math_comp","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-5342d5279a0ed1a3e891243e","model":"mistral-large-4","benchmark":"livebench-2026-06-25-olympiad","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-8ed268ed656d254b108ce78f","model":"mistral-large-4","benchmark":"livebench-2026-06-25-paraphrase","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-853412c6f0ef9c6d08529d83","model":"mistral-large-4","benchmark":"livebench-2026-06-25-plot_unscrambling","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-3eff14e4aa41826f6862f62c","model":"mistral-large-4","benchmark":"livebench-2026-06-25-python","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-1601a1d64a7a9e15152dab7f","model":"mistral-large-4","benchmark":"livebench-2026-06-25-simplify","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-82eddc3d36552642e464eff7","model":"mistral-large-4","benchmark":"livebench-2026-06-25-spatial","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-f7389adfe8fd745b3a0404ca","model":"mistral-large-4","benchmark":"livebench-2026-06-25-story_generation","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-129bf3385c08a43a5f9c9647","model":"mistral-large-4","benchmark":"livebench-2026-06-25-summarize","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-0790444be4f573a3aef2e87f","model":"mistral-large-4","benchmark":"livebench-2026-06-25-tablejoin","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-59b1300c9612863d90094bd2","model":"mistral-large-4","benchmark":"livebench-2026-06-25-tablereformat","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-c581cbeec9d119e11354fb42","model":"mistral-large-4","benchmark":"livebench-2026-06-25-theory_of_mind","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-b12381047fc8f7dc3d32a8f2","model":"mistral-large-4","benchmark":"livebench-2026-06-25-typescript","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-01811e82cd9297d95f6995b3","model":"mistral-large-4","benchmark":"livebench-2026-06-25-typos","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-1b5121c6aff4d3d27981001a","model":"mistral-large-4","benchmark":"livebench-2026-06-25-zebra_puzzle","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"epoch-run-2CdomqtBVz2it7a2Zx2G2t","model":"gpt-5.5","benchmark":"epoch-gpqa-diamond-1-0-8-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2fQJP3brRApfBdQq7Zy3bm","model":"llama-3.1-405b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2gzNF2d53h2oCKDnojLtSP","model":"qwen3-30b-a3b-thinking-2507","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2jKf4iEfVQnHkgAwEtD9Nn","model":"claude-fable-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2y5jXmHGjyEyZvGjNDtRZe","model":"qwen3.6-flash","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2z7kL9DpfvY44T9Wo99FYx","model":"gemini-2.5-pro","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-3CGChL5vNDM6Df5C8Z8owN","model":"gemma-3-1b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-3n5KDcBaKqJh3WTg7qU2rs","model":"qwen3.6-35b-a3b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-3UbYVQELDHAcQgu7sTTnRf","model":"magistral-small-2509","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-452pB5w5ea6uy92e2q2NMv","model":"qwen3.6-27b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-4ACEC4x26HWRGiAepHGw43","model":"qwen3-235b-a22b-thinking-2507","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-4afZ2hjLiJnPy5pD7TfE3K","model":"claude-opus-4-5-20251101","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-4EayGByBV2xodNBkrZMcFb","model":"gpt-5.5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-4LWNorP8Fy8V8doxirNFcH","model":"qwen3.6-plus","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-58eQmyCfPa3FufhXJFvAL2","model":"claude-sonnet-4-6","benchmark":"epoch-gpqa-diamond-1-0-6-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5AijYw5bFJtSuahnbzNo6Z","model":"kimi-k2.7-code","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5e4Jp9dxtNisWx2wbRRZxM","model":"qwen3.7-flash","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5FVmQUSS4uRd23f6nNgeRe","model":"qwen3.5-9b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5mmrBSQb7hVSJ9VYtNm46i","model":"phi-4","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5Q7zWYmoRik8mhABL4wpVR","model":"gpt-5.6-luna","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-5u4XrDnQSRnuXSK6oXKAth","model":"gpt-5.5-pro","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-68KxyCJbfMSq8JBL3LRJfr","model":"gemini-3.5-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6gYpimjqJm3CL6mvKEN9qs","model":"glm-5.2","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6P9AJQmBzaPmE7ossbqLjz","model":"claude-sonnet-4-6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6phXzd4aCbnBUSQmBsaywa","model":"glm-4.7","benchmark":"epoch-gpqa-diamond-1-0-4-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6pTYmQCw3EMbErvAqpivH5","model":"qwen3.7-flash","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6rZFxNR3GjfhWey6DzEiYz","model":"qwen3-30b-a3b-thinking-2507","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6XZAenohp9pCgQ3gVeUAi8","model":"qwen3.5-flash","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-6YAzFq89fwWiJ3uJdptCMr","model":"llama-3.1-8b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-79ZP6iwoBaF5t9a5VRqPnw","model":"minimax-m3","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-89zcekqEYnE8zhwG4pR5Nu","model":"deepseek-r1-distill-llama-70b","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-8qwT2CF9U5zV99PFirnVsp","model":"llama-3.2-1b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-8UqaLobhmNJLuPGTTpeaCw","model":"deepseek-r1-distill-qwen-14b","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9ekki5tJhyjmA7ZMLoUxzo","model":"glm-4.7-flash","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9LWdzVN5w4ihNvncsaCWMu","model":"claude-sonnet-4-6","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9rDLegdh3zmBfFzTj3fkCc","model":"glm-4.7","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9SSHEP95FYVZvHDdoHSRy3","model":"llama-3.2-90b-vision-instruct","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9WS6kHXT8XFtJWtE2wWLAo","model":"qwen3.5-35b-a3b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9ZFhnyMNCKZ8XdR58WGD3D","model":"claude-fable-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-9zx2EXPTvPmxsL9qFCjP3x","model":"qwen3.6-flash","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-agebmxGseTvmvN4AHN8i4m","model":"qwen3-235b-a22b","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-aKc2rzsA6YPYwCkE7nhvvB","model":"claude-opus-4-6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-aLrHd8RCiNo3Yb4GqSawM7","model":"claude-fable-5-1","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Atc4F5iuMZu3vNBWVGCBnv","model":"claude-sonnet-4-6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-awDKyKbPXRzBVZzfdQucef","model":"qwen3.5-flash","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-aYau6EG7CCaWVSyVq3vvQc","model":"glm-4.7","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-AZHoMLTNQEcKLwtv7QzBLZ","model":"claude-sonnet-5","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Azz52eFkXwVJiRCGpaUBwB","model":"deepseek-v4-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-b7Lw9ExxAhVY3hdExoh4MP","model":"glm-5.1","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-b9csPZ2c9CAsRXmzzfVoEW","model":"qwen3.5-flash","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bA5j9K2shzZVFGTMQ5g6EU","model":"gpt-5.6-terra","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BAi4jidcT3F6reBkSXDJKv","model":"qwen3-32b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BbM4xbJcS5sjrzZABGg8K7","model":"claude-opus-4-6","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bBV5wCrrZtihrgxEsg9jPD","model":"deepseek-r1-0528","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bCdwpRXgZtvQLYC4wA9JXr","model":"muse-spark-1.1","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bDS2AGEf3AywbVcdDyAKZK","model":"phi-3-medium-128k-instruct","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-beRGgJXTJggTi8PPEZNoZ5","model":"mistral-large-2411","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-beSbPHiiWcwJBSzYRh7Kh4","model":"gemini-3.6-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bJV4D8SEo9zMJPEYTTXJNZ","model":"ministral-3b-2410","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BLgwhLGGofDBzxoc34YFHK","model":"claude-haiku-4-5-20251001","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BnX67AoZzgVbHgaM8F8Brz","model":"qwen3-30b-a3b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BP3KYD8rYyFg3LviNGtjLL","model":"qwen3-235b-a22b-thinking-2507","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bpZy8tAbh7UV6A6U7XZtBg","model":"nemotron-3-ultra","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bq5y6Tp83KLtxC58UDfpyN","model":"qwen-3.8-max","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bSyTSKD8RiRNZCGNu6MnFp","model":"kimi-k2.7-code","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BTeRdhgt6TFBj6QkGX2j6P","model":"kimi-k2.6","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-3-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-buLf8Ne29xmzMZBRQkvrQG","model":"qwen3.6-27b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-BVat526nF6NUGoVaLCp7DT","model":"seed-oss-36b-instruct","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bWnggCv6to2QKSjngrtuos","model":"claude-opus-5","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bXgZZgzRE3wXoSRUgrbsVf","model":"gemini-3.1-pro","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","reason":"Run-specific qualification requires review: In the initial run, no epochs completed for 2/45 samples. Despite several re-runs of these two samples, no epochs completed. All epochs for the other 43/45 samples were correct. The model's score was edited to be 43/45."},{"id":"epoch-run-BxrNfyMffkVUq4n7U5eK3Q","model":"kimi-k2.6","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-bxS76CJuVws8iwWU2Wr2PM","model":"claude-fable-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-C56VHYLMeww2wXebeJh3gg","model":"deepseek-v4-pro","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-CAyLyhDHZiMQBZDB3qd8tG","model":"gemma-3-12b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-CBbeMKRRSeRsXnvSfn7Png","model":"glm-5.1","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-cbQnfsMSA3aQaBtjm3aFx2","model":"qwen3.7-max","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ccbx7KQY9bTD563vzBXwSg","model":"glm-5","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","reason":"Run-specific qualification requires review: Two samples did not complete, which is greater than our 2% error tolerance setting. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-cFbntXuxUtfreULvt7vEt7","model":"qwen3.5-plus","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-cgnopvpB6mzsfb9yGnYK2z","model":"claude-haiku-4-5-20251001","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-cqUZ6gcq2HBnShFRWvKjGr","model":"gemini-2.5-pro","benchmark":"epoch-gpqa-diamond-1-0-1-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-cSTYZ3FKp5Mbs3xopn68NK","model":"magistral-small-2509","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-CtmxkTPbFRofQWTkEw5aSe","model":"minimax-m3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-cXkPywkhy3NnW992ri73yG","model":"claude-opus-4-5-20251101","benchmark":"epoch-gpqa-diamond-1-0-2-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-D3YDUZSfEUDsS4frLbEKDu","model":"qwen3.7-max","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-D5cbXacPnJ8akq2jAtifEQ","model":"gemma-4-31b-it","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-d5QCJNq9uLtxjhiMhqXLmg","model":"gemini-3.5-flash-lite","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DFWQcrbMegFAcEWZKWoJxC","model":"gpt-5.5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DFzqUCfxnQPUdK8b8D7aYu","model":"claude-sonnet-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DGEzZA6nvTne4MEGSuo3Tm","model":"ministral-8b-2410","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DhJ248BX3ZPBHXvkRG4Qsz","model":"gemma-3-27b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DiXCMhdfhcjaCUSzYWgACy","model":"claude-opus-4-6","benchmark":"epoch-gpqa-diamond-1-0-4-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DMjUrG6eZEqwcQ4SqUoViu","model":"qwen3.7-max","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DmptTSPXx5uM5TYZoV59JT","model":"qwen3.7-plus","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-dqgqP2uEPswfECCVj2Kbr9","model":"claude-opus-4-8","benchmark":"epoch-gpqa-diamond-1-0-10-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-dszRh7ELyCEukWnwYnUxMp","model":"deepseek-r1-0528-qwen3-8b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-dwyb2yzFewGT6w6oFdVMAc","model":"deepseek-r1-distill-qwen-32b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-dYYtcwENFRtm9jZTDA2p9C","model":"gemini-3.5-flash","benchmark":"epoch-gpqa-diamond-1-0-9-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-eB9e2mtd5nRwqdFyLEsz6k","model":"claude-opus-4-6","benchmark":"epoch-gpqa-diamond-1-0-4-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-EceR3NeHzSxacdmAmfRxgT","model":"deepseek-r1-distill-qwen-14b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ehqiuEDETZTqJ8zt6Mc7Ja","model":"kimi-k2.6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-eJvV6RezECZwh3b4ekg4pm","model":"seed-oss-36b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ENc5ZM5TpBYNKkTWN4xyQM","model":"kimi-k2.7-code","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-enhRcQmfN6RFB2zu7R3Uxr","model":"gpt-3.5-turbo-1106","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Eo5cAQJK28CHpKDfCSDYG4","model":"qwen3-30b-a3b-instruct-2507","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ESnXA8LqMqhjcsoWQaMLVQ","model":"deepseek-r1-distill-qwen-1.5b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-EtgrDq6ei6kZe8K7QbXUe3","model":"gemini-3-flash-preview","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ETNzxNbPKwj4qxkdo3VVgT","model":"grok-4.20-0309-reasoning","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-eVKA2eavdRAbSN6AnzyBxA","model":"kimi-k2.6","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-EWAyxFsRUvuu4NpmmLqWkn","model":"qwen3.6-35b-a3b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-eXVWr3RBeSsWy5DAU8ed46","model":"gemini-3.1-pro","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-eYmgjYJfM7Utm46nfoRfZ6","model":"gemini-3.5-flash","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-4-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-EzMaDdXs4YQTMLgppBGxAb","model":"qwen3.5-397b-a17b","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-F3CtjUceBrMi9iYmjULx7J","model":"qwen3-1.7b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-f6pnAATjxmrFJS353EjQKi","model":"deepseek-r1-distill-llama-70b","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-f6ZdMtRpdfskGbrBCzrKSn","model":"qwen3.6-plus","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-f7dotY9NheKNKK2zz6bfKZ","model":"qwen3.7-max","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FagAUZ7m5PJHseDATvp2vf","model":"gpt-5.6-luna","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-fEgRyzyFYZraNnkkbRVSSg","model":"qwen3.5-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Ffoxqm7YsZr3FimCGsGAJv","model":"qwen3-32b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FGEsLTxzZ7fE9aq7DhdqZb","model":"llama-3.2-1b-instruct","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FHZCKbtfvpKGXU99vZFnXN","model":"qwen3.7-max","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FkywQ2KS4AkLPzjSPmhHcS","model":"gemini-2.5-pro","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FLDt53waLTeshC7PK9uVy2","model":"grok-4.20-0309-reasoning","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FNMbfvEEm9PRnrJnrqk2PH","model":"mistral-medium-2505","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FoMSS4FmH3VxpsvZiUJPCv","model":"qwen3.6-flash","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-fQjoHKyUEPAuwdrBGfL8SG","model":"gemma-2-9b-it","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-fsZmzw8jjyUgMQGwxodBwN","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FTDFCpXzDTgfgWBNdHLHGc","model":"gemini-3.1-pro","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-FueK5bFAzGbkUao9JAibms","model":"muse-spark-1.2","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-fWNxmiSUC7BX8whqvzssY8","model":"glm-5.3-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-fxwRTtt8bLV4DNutwtMEox","model":"llama-3.1-8b-instruct","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-G3dinPvwrci2Nu3m9pby2i","model":"qwen3-4b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gG2B6fLUDBy5jRraxL2pz8","model":"qwen3-8b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ggG3n6WVPZn7Gu2RNyfQbK","model":"qwen3.6-35b-a3b","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-GGpgwGRFVATVJdQr8TgRc9","model":"minimax-m3","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gJizntrYwhnbpCviv9mNBN","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-GL7htq7XRnbzqpAVK5f862","model":"glm-4.7-flash","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gRRQHECkYhz5UaYsRKDh2F","model":"qwen3-14b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Gs234P3jzGiLm68KjyzYZL","model":"deepseek-r1-distill-qwen-1.5b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gsBidnvEcmCfLnn5sxePtk","model":"claude-opus-5","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gu39ndv9QxWP3NRxSUJRaX","model":"qwen3-235b-a22b-thinking-2507","benchmark":"epoch-gpqa-diamond-1-0-3-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-GVm7khGvtdnQKGfkgAHD8q","model":"grok-4.20-0309-reasoning","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-GYzmrzMfeSjNjm2J6L9PeT","model":"glm-4.7","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gZMFRbVKnBmcnZU4YqqKMN","model":"qwen3.5-397b-a17b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-gzQH7StUXaxAtXgxkTgyxJ","model":"gemini-3.5-flash-lite","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-H2FvRXagQRQmiNa7WrNMU2","model":"qwen3.6-flash","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-H3E7EjjXfGCPnm9ooLdmAo","model":"gemini-3-flash-preview","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-3-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-H8CebpQyV2qEE8SQzjBrWe","model":"gemini-3.5-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-hDESmyGFrbZDomjff3rqzD","model":"minimax-m3","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-hHnQVatVTbQjM4sfrjw7GH","model":"kimi-k2.6","benchmark":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-hJ6XXLBm9yfXtSbbhWuwpw","model":"gemini-3.6-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Hpyy6CpmXmd5q7Zbdq63CR","model":"gemini-3.8-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-htvM9QKQJ8TfBxTzDxfZfp","model":"claude-sonnet-4-6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Hui8iZgjwKPxz7DkRU8sJX","model":"glm-5.2","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-hVifTUdQZrFEYabgCRu8Qq","model":"gemini-3.1-pro","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-HzNnNaRmyNExSVaMjmFCHe","model":"gpt-5.6-terra","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-i6i3gQf3ng2aAipvowPpws","model":"qwen3.7-flash","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-icTHLT2S2egxYtgbjQHUng","model":"claude-opus-4-8","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ikUWdu6HJ2qRgZynfzDCFe","model":"claude-opus-4-5-20251101","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-J2kUEjR9r6Spd594qDNTTf","model":"claude-haiku-4-5-20251001","benchmark":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-J2ZgtxyaQZfyDMPTPxS8nm","model":"gpt-5.6-terra","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-j99TDv5LAYUSvTUcR47T75","model":"qwen3.6-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jbyVWnEvvFVNNc8AEF6WcQ","model":"qwen3.6-plus","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jD6rJdvfNPErKEz9qkpssj","model":"gemma-2-27b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jdFH2zZdssYKDVJQPKXvNB","model":"gemma-3-27b-it","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jDWEviMweCdzGxLfz8sdBm","model":"claude-opus-4-8","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Jevnk9hi9oRBbGcFu2JxBC","model":"gpt-6-luna","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-JJyzHWKJUA3iTZDU8iYefz","model":"gemini-3.5-flash-lite","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jrawnM2wHFbVfJFJsap4kS","model":"qwen3.5-plus","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jRiWmBxtBAyiXiRBRMY8wX","model":"qwen3-8b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jTuYE8VJTos73Kw77UFevq","model":"grok-4.5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Jvdw6GAXiS6T79bkpbk6Ra","model":"qwen3.7-plus","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-jyCZnpXG2bh9G43X8pT75m","model":"claude-opus-4-7","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-2-model-extracted-exact-match","reason":"Run-specific qualification requires review: All incorrect answers were actually cases of the model failing to submit an answer. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign a score of 0. Then we average these scores across all samples. The resulting score is 44/45."},{"id":"epoch-run-jYiGAFfUQKJuRStPzU3PX3","model":"qwen3.6-plus","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-JYuFdyZZSiMvmSZNzMTywb","model":"qwen3.5-397b-a17b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-K8zTckSXLKLesoLBv24TWc","model":"qwen3.5-flash","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KaEir82ukWPm2Fq4FanY2M","model":"gpt-6-astra","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KAPGpH2CLMafAt8MnAQJT3","model":"gemma-3-4b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KbUNQf8nnwPa8ixg6AnEwB","model":"deepseek-r1-distill-qwen-32b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-kCQr6ARwJyUfkwWqKAfuDX","model":"qwen3.5-plus","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KfQKr2ibCFMx5xBELoiM3Y","model":"gemma-3-12b-it","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-kG3hbd8qLEd6fLAJHyQTiN","model":"glm-5.3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KH7KfZvFc9kZbqiJFdfYTc","model":"qwen3-4b-instruct-2507","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-kR9F3oHBCnwQW4AiTPKwpd","model":"gemini-3.1-pro","benchmark":"epoch-gpqa-diamond-1-0-5-choice","reason":"Run-specific qualification requires review: In the initial run, 3% of samples failed to complete. Inspect defaults to not scoring these at all, but we override this behavior when >2% of epochs fail. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign the random baseline of 25%. Then we average these scores across all samples. In this case, the resulting difference is very small: 94.1% modified vs. 94.4% original."},{"id":"epoch-run-Kwwo3UFcPDk6iLAeSeeRaa","model":"claude-opus-4-5-20251101","benchmark":"epoch-gpqa-diamond-1-0-2-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-kZ3VgrQJxfKQ5msjpmSaAz","model":"claude-opus-4-6","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LHRL6nQJZXGJmYppR7kbGw","model":"llama-3.2-90b-vision-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LiRiryJsGb3h5UuxX8bmJv","model":"deepseek-r1-0528","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LjgJoDosTLkiGVT59smA7q","model":"kimi-k2.6","benchmark":"epoch-gpqa-diamond-1-0-8-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LsnPrukDADRTP8fsn8zD9S","model":"claude-opus-4-7","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LUfGWqWQim7rdBPgSpbrXS","model":"gpt-5.6-luna","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-LWbCXNGMXtjQYxyM2uoFMV","model":"deepseek-r1-0528-qwen3-8b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-m4WQuAN88hKsqbT9zXbg7z","model":"grok-4.3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-McJyXLHBzx5VjAqXjmrrsb","model":"gemma-3-4b-it","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-mEkZaYpiurQ6TEMAALK3su","model":"claude-opus-4-5-20251101","benchmark":"epoch-gpqa-diamond-1-0-2-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-MEwMcmSV32JHrsNoAq4BFL","model":"llama-3.1-70b-instruct","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-mGXYSUNCMisvaRzhQp6g2L","model":"qwen3.5-plus","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-MhqeuRVx4JcRfxPQDYPq7Z","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Mhwme9odWJMzMjoYkW8r6B","model":"glm-5.1","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-mLmUnBuX6DYKtb6x46GteM","model":"claude-opus-5","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-mM6vdJpgjLY9prnetXzZJS","model":"grok-4.20-0309-reasoning","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-MsXAXDEKP3xBKtiA7aTBBG","model":"llama-4-scout","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-n4hyz75SVpwPEisKVVjvNg","model":"glm-5","benchmark":"epoch-gpqa-diamond-1-0-5-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-n9gpXfUzo8SbWqvrG2q4xM","model":"mistral-large-2411","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-N9uFn7EZFsvHNcHEwEy3J6","model":"gpt-6-sol","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-nDsNFM5ioGzyWcpeUKVotg","model":"qwen3.6-flash","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-NiuExVccWkWbWqi6ex6vvf","model":"grok-4.6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-nSb2focDRMyPJXErk3MV94","model":"claude-opus-4-5-20251101","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-NyAvSf73nUe84HuY6Vpjkh","model":"claude-opus-4-7","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-nzQV9YvictnDF2EwxqTJQs","model":"kimi-k3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-o6migB5WP27uLr9nUWpCiM","model":"qwen3.5-9b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-oAu9CZSNPZgwiwKnoNpM8Q","model":"gemini-3-flash-preview","benchmark":"epoch-gpqa-diamond-1-0-3-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-oWqwMmwEd7LU3eU5Ftak64","model":"gpt-5.6-sol","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Pc6CyTEYKbcdDUDKzGZnS9","model":"gemma-3-1b-it","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-PEZpuEuU65bu3ZtvjLytHq","model":"claude-opus-4-8","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-PN9exWpeJGXJB8tZGX32e4","model":"claude-sonnet-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-PtxHF8BH8WuNdNfDnutGBb","model":"qwq-plus","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-QfS2PrjUFMNnceRZmCmewP","model":"gpt-5.5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-QWw65xeTn8x42SymMsVREN","model":"mistral-medium-2505","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-R2fMFAtRXah864hMifdQGV","model":"glm-5.1","benchmark":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-R7XgJMi2R9sv7tZdx5SZTv","model":"glm-5.1","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RA5MRbmWJpFPR29BQxfvZt","model":"kimi-k2.6","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RAwuPRwJedy7P2KeQhEmr8","model":"phi-4","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RG2biwnmGybSVTVxxMdRWa","model":"qwen3.7-max","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RHbNnWqK6x8f6pR2AZ8VAq","model":"claude-opus-4-7","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RLN98bmQSMnc5Zv39BF4M2","model":"claude-opus-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RuQX7KA7owzqzf8Le9veeM","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-RWjuCuVGvaRd4vDjJJ6aP2","model":"qwen3.5-35b-a3b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-S5QYXSvQBRSbUbXSnAGbMm","model":"llama-3.1-405b-instruct","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-S7wbot7JR53BAjM8F9gaws","model":"qwen3.5-flash","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-SH5jr76ni3RnpXVMETMy2H","model":"claude-opus-4-5-20251101","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-SP9UFPzxVnsbzs2kExP2bh","model":"qwen3.6-plus","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-STxFZiSPAPScUuENvXBWLc","model":"grok-4.20-0309-reasoning","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-SX5FCWMk3HF83gGsP3WFA6","model":"grok-4.20-0309-reasoning","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-T3X5DeC47iqCaoRYXu5k8L","model":"llama-4-scout","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-TjoS7sNuqVTc4LVyGRo4wa","model":"qwen3.7-flash","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-TUPC8VdX4jApFa4MGfNP4t","model":"claude-opus-4-6","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-TxXS78Wg2pSCDbpmeJuzQn","model":"llama-3.3-70b-instruct","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-U8H8juE3Ko83jsR6TRntbh","model":"nemotron-3-ultra","benchmark":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-URoWjw9Htc6QPwABVcrybw","model":"qwen3.7-plus","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Ut4d4rvkUygdLTRomFb5rh","model":"qwen-3.8-max-0902","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-UTVSgirxQpTgmTHbgE9EUk","model":"kimi-k2.7-code","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-UUNZJtgib9XbCjLEdhtGaT","model":"gemini-3-flash-preview","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-V6aVGtn9gAmRep2oBGsqVN","model":"gpt-5.6-sol","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-V7seJ9yeHu4LYjrkomhEQm","model":"claude-opus-4-5-20251101","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VajBDnUCyX7uqAfMTbi63j","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VhQBa9AViRt2UKSNpEAyjN","model":"qwen3-4b-instruct-2507","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VJezHrJ5YPCbpui8pZgcJg","model":"claude-opus-4-7","benchmark":"epoch-gpqa-diamond-1-0-7-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VjfWxdhdNerrh4huSHT8PT","model":"claude-sonnet-4-6","benchmark":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VonoEhAsGSJ2FHU33qnhui","model":"qwen3.6-27b","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-VPSX7EnwWuBrCPnpYGMUEM","model":"kimi-k3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-W6mTanyjvXhasFBzHukv4S","model":"qwen3.7-max","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-WNE7cveVN8rsi7DmsFsFVy","model":"gemma-2-9b-it","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Ws3g7xtto2fZ7AhuXJfecf","model":"minimax-m3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-WvV6QREDDXeDEGdrKztDsy","model":"gpt-5.6-sol","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-WYTWr3Xk4qxymhMsm7vRQ2","model":"nemotron-3-ultra","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-X2QNPHFXuWosA6AiuvVtDv","model":"kimi-k3","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-X2tQXGELXtEbc2VX6gARd7","model":"llama-3.1-70b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-X3HfncZtnLKUPoUuRc9YsR","model":"qwen3-30b-a3b-instruct-2507","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-X3RxRkt2pBUXYJjAQHsUo6","model":"kimi-k2.7-code","benchmark":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XCSWtbDquA7FUiWfd7kh9q","model":"open-mistral-nemo-2407","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XEaDaqM3oaPcrtQ6XH5fGS","model":"qwen3.5-plus","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XfjRkSyP4ub4gDsWcgS7KY","model":"qwen3-30b-a3b","benchmark":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XGK9DjJHHVWr2LyT298ooL","model":"qwen3-14b","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Xi45sLZGyn5sutf7nKRHTk","model":"glm-5.2","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XneEig6pACkAWeekvgCwNk","model":"kimi-k2.7-code","benchmark":"epoch-gpqa-diamond-1-0-11-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XTW92PMsypptnTGBFuLCxe","model":"claude-opus-5","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-Xu34dKTAdpBWL6advf6DMg","model":"gemini-3.7-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XUDdWKUZBhdWPPQBRgx8Pw","model":"gemini-3.5-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XWpHpVPCaVjcwPpdpXuuGH","model":"qwen3-235b-a22b-thinking-2507","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-3-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-XXPqVNR7WCFFA2Rnzjcbk6","model":"claude-opus-4-7","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-YoAJyC3j8dZ6ZpDZ5rSDLw","model":"grok-4.6","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ZczEhu69FQ9Cnns8NT6ew4","model":"gemini-3-flash-preview","benchmark":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ZDeGG5QYkdgVqzGPmmnbfx","model":"gemini-3.6-flash","benchmark":"epoch-chess-puzzles-2-0-0-exact","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ZjsXQpZ7SsejXDo52aetZZ","model":"llama-3.3-70b-instruct","benchmark":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ZUJxsJDpHnLXxNiDcvj22W","model":"gemma-2-27b-it","benchmark":"epoch-gpqa-diamond-1-0-0-choice","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:anthropic/claude-opus-5","model":"claude-opus-5","benchmark":"vals-finance-agent-v2","reason":"One run-task used an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-finance-agent-v2:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-finance-agent-v2","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-finance-agent-v2:zai/glm-5.2","model":"glm-5.2","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-finance-agent-v2:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-finance-agent-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-code-migration-v1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-code-migration-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:kimi/kimi-k2.7-code","model":"kimi-k2.7-code","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-code-migration-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-code-migration-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-legal-research-v1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-legal-research-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-legal-research-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:zai/glm-5.2","model":"glm-5.2","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-emb-v1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-emb-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-emb-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-emb-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:zai/glm-5.2","model":"glm-5.2","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-mmlu-pro-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-mmlu-pro-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-5","model":"claude-opus-5","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k3","model":"kimi-k3","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-fable-5","model":"claude-fable-5","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-flash-0731","model":"deepseek-v4-flash","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.7-code","model":"kimi-k2.7-code","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-terminal-bench-2-1-v2.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-5","model":"claude-opus-5","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-vibe-code-bench-v1.1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.7-code","model":"kimi-k2.7-code","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-vibe-code-bench-v1.1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-legal-agent-benchmark-v1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-fable-5","model":"claude-fable-5","benchmark":"vals-legal-agent-benchmark-v1","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.1","model":"glm-5.1","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-legal-agent-benchmark-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:mistralai/mistral-large-4","model":"mistral-large-4","benchmark":"vals-tax-agent-bench-v1","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-tax-agent-bench-v1:minimax/MiniMax-M3","model":"minimax-m3","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:alibaba/qwen3.7-max","model":"qwen3.7-max","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:kimi/kimi-k2.6","model":"kimi-k2.6","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:alibaba/qwen3.7-plus","model":"qwen3.7-plus","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:xiaomi/mimo-v2.5-pro","model":"mimo-v2.5-pro","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:alibaba/qwen3.6-plus","model":"qwen3.6-plus","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:grok/grok-4.20-0309-reasoning","model":"grok-4.20-0309-reasoning","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:xiaomi/mimo-v2.5","model":"mimo-v2.5","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:anthropic/claude-haiku-4-5-20251001-thinking","model":"claude-haiku-4-5-20251001","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"vals-tax-agent-bench-v1:minimax/MiniMax-M2.7","model":"minimax-m2.7","benchmark":"vals-tax-agent-bench-v1","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"36d6df353b16e177cd44e3ec","model":"gpt-6-astra","benchmark":"real-swe-gpt-6-astra-codex-cli","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d886f6a08b775c8731f741ca","model":"claude-fable-5-1","benchmark":"real-swe-fable-5-1-claude-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3d5f434c3cbe85ca3b4ccb8d","model":"gemini-3.8-flash","benchmark":"real-swe-gemini-3-8-flash-gemini-cli","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a98dea2e9467129aeca8c8e1","model":"glm-5.3","benchmark":"real-swe-glm-5-3-claude-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f07a75cfe72239d502ceb6ac","model":"muse-spark-1.3","benchmark":"real-swe-muse-spark-1-3-muse-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bf75f254142209a0515e1cc0","model":"grok-4.6","benchmark":"real-swe-grok-4-6-grok-build","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3db0287be8f5aec2207ea3d8","model":"gpt-5.6-sol","benchmark":"real-swe-gpt-5-6-sol-codex-cli","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1e52efc02b7e8795cc3d9569","model":"kimi-k3","benchmark":"real-swe-kimi-k3-kimi-code","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-claude-fable-5-1","model":"claude-fable-5-1","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-claude-opus-5-5","model":"claude-opus-5-5","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-deepseek-v4-1-flash","model":"deepseek-v4.1-flash","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-gemini-3-8-flash","model":"gemini-3.8-flash","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-glm-5-3","model":"glm-5.3","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-glm-5-3-flash","model":"glm-5.3-flash","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-gpt-6-astra","model":"gpt-6-astra","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-gpt-6-luna","model":"gpt-6-luna","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-gpt-6-sol","model":"gpt-6-sol","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-grok-4-7","model":"grok-4.7","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-kimi-k3","model":"kimi-k3","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-mimo-v2-6-pro","model":"mimo-v2.6-pro","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-minimax-m3","model":"minimax-m3","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-mistral-large-4","model":"mistral-large-4","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-muse-spark-1-3-xhigh","model":"muse-spark-1.3","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-nvidia-nemotron-3-ultra-550b-a55b","model":"nemotron-3-ultra","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-qwen3-8-27b","model":"qwen3.8-27b","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa-cyber-index-step-5","model":"step-5-preview","benchmark":"aa-cyber-index","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cb2e3515b80b12af3303866a","model":"claude-fable-5-1","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ea1ff84c5a751f4d8b772b62","model":"claude-opus-5","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1b012811a9b967f7ffd89f2c","model":"gpt-5.6-sol","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7ecb39c599db2cdf2d237740","model":"kimi-k3","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"668de7b6d6dc4a5d877776b7","model":"qwen-3.8-max","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"50c9d59622809091b00ba9d6","model":"gemini-3.8-flash","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5be8f052b58e62435776e382","model":"muse-spark-1.3","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d383f75d80bc4b00f394602f","model":"grok-4.6","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a1a12c7c5eca0c65ca4cc66b","model":"gpt-6-astra","benchmark":"autoresearchexam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d069057c75d5f66dec371d2d","model":"gpt-6-astra","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e95242c2a0ee491639498eaa","model":"gpt-5.6-sol","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"79867e42f55ea4a657c228d6","model":"gpt-6-astra","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e3421f54ae0ea255729f0eff","model":"claude-opus-5-5","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"69b8475f557646e661eaa00d","model":"claude-fable-5-1","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1ca7abeef4fe3150af253415","model":"gpt-5.6-sol","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4b93ad5f00ede5ee6f7eab30","model":"claude-fable-5-1","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4ec2e25ea3dec7936c3149e9","model":"muse-spark-1.3","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b1bb14b9843b3977bed0580f","model":"gpt-5.6-luna","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aefc1e5e687f5fccd2b5b878","model":"grok-4.7","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cfc2b44701cc8afdf833989a","model":"grok-4.6","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b222fcaa4ad0fedda81b2c5b","model":"claude-opus-5","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8c81bb270658bc572ac23413","model":"qwen-3.8-max","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d718dd7c1ee1a7bd0a102862","model":"kimi-k3","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"78a9c78f4cb3495ab080ba7c","model":"claude-opus-5","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"98c6c82eda4d51ad59d6d651","model":"muse-spark-1.3","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7f7d2d73ed6a8716bfedc645","model":"glm-5.3","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"119b4de295f86b5a42fe9bf2","model":"gemini-3.8-flash","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c454aaeeca53fc8beee03ad8","model":"glm-5.3-flash","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4c3732f9bf8749e94adb0d68","model":"qwen3.8-27b","benchmark":"bughunt-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8013f488929a27c953d0969a","model":"claude-opus-5-5","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e58469b1ddb1dd8c54509141","model":"gpt-6-astra","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3a062742525c19ec510ae326","model":"claude-fable-5-1","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b51f4f94cce16b585d3c6596","model":"gemini-4-argon","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"df9df7eaca39913a5b4ca84c","model":"claude-opus-5","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2c3b1aa370c48a623350ef1a","model":"grok-4.7","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8778b1b5186749b45aa39c62","model":"muse-spark-1.3","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"10715c1dd8c16e77f6575e4f","model":"claude-fable-5","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b5b40be041ab8147dd1281c5","model":"gpt-6-sol","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"23a57717b22b7f3394b62313","model":"grok-4.6","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c7f06f5e3c3bedd1a2ef4c69","model":"muse-spark-1.2","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed78cae115b8991a86c3e524","model":"qwen-3.8-max","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c697fccffb7cd3fbe0c3f595","model":"gpt-5.6-sol","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"23f334ec20ec3b7754b09fc2","model":"gpt-5.6-terra","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e770c30699b657336304ff1d","model":"kimi-k3","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e81945732df3cbf866f89ad9","model":"gemini-3.8-flash","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b904deb8ba6d1f0fbb5abf52","model":"hy4-preview","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0dcf485cda88a796ea217e9b","model":"glm-5.3","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"30a1b9fb05051a44e7b29e97","model":"glm-5.3-flash","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cc05393a564054b0ba49074f","model":"gpt-5.6-luna","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"db7d58ab530db9a06359328c","model":"hy3","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"571df1e8692ba33af9730e5e","model":"claude-sonnet-5","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"21a80c1cc36483d8cbbb51c3","model":"gemini-3.7-flash","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f8657c77aa8f68ed4c4caf98","model":"gemini-3.1-pro","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"42f706e6aed03b32501d07b6","model":"kimi-k2.7-code","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cc67f59bc6a200eabb3e48dd","model":"muse-glimmer-30b","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c79b4e01f0296958f4e65108","model":"nemotron-3-ultra","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4d180b6e6141701640fba711","model":"mistral-large-3","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9a074a7174126349ffd8c560","model":"gpt-6-luna","benchmark":"dayjob-healthcare","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f51c91469a44f016098a8082","model":"claude-opus-5-5","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ac82b48e4e980b527e69036f","model":"gpt-6-astra","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"55267a53a60ce4470d84800f","model":"gemini-4-argon","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6f15b12f701a09c117318c08","model":"claude-fable-5-1","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ac96c565d7d95c5322117f2","model":"muse-spark-1.3","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2f1659e33b93ef2e6c349481","model":"grok-4.7","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ad304890a5734df3813236b3","model":"grok-4.6","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7a1c2608ea8895d1a4d7b471","model":"claude-opus-5","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a01c1873f75e2a70abdf61e2","model":"gpt-6-sol","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a6a3b9b6d8edb7dd7f9ddbc7","model":"claude-fable-5","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"319cd5622cf0976b6dbcc4b7","model":"hy4-preview","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"36778994cf17b13267691d55","model":"glm-5.3","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"025e1dec2153bb55b486a00e","model":"gpt-5.6-sol","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e8b9d521c56996897b3ce54a","model":"kimi-k3","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2a81aed5bec1a34551da1b5f","model":"qwen-3.8-max","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"af9cc3681ea9343205ff64e9","model":"gemini-3.7-flash","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c93e77782f6d7094c410a0d5","model":"gemini-3.8-flash","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c147538da8246c3f2fdf28b3","model":"glm-5.3-flash","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"73aabc3298ba34589e56d013","model":"muse-spark-1.2","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c4873c69d18cf220189ce836","model":"claude-sonnet-5","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a638443a7f29edaab94f9f5c","model":"gpt-6-luna","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d694f8a18fee8ea1437b2810","model":"gpt-5.6-luna","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"50a7dd1087d296dce7264938","model":"gpt-5.6-terra","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a9b2e868353b5c8513d0ee62","model":"hy3","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3cfecdce0dc5c8bb730f6237","model":"gemini-3.1-pro","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ef0ac274d47dee038a98960f","model":"kimi-k2.7-code","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"044f47e30edf2bd7ef2f7e11","model":"mistral-large-3","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1508d434a180819441288e92","model":"muse-glimmer-30b","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"383e806eadeaa5b8ecdf2a7b","model":"nemotron-3-ultra","benchmark":"dayjob-finance","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4ded310383d6b785107f1ade","model":"claude-opus-5-5","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fbc0f0f865af728782bed96d","model":"claude-sonnet-5-5","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"00219f3f31423184f4551a76","model":"gpt-6-astra","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dc0a5cb0ca2545c23c7b5471","model":"claude-fable-5-1","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d787b9d0f4ebffdda7ed4fc6","model":"gpt-6.1-sol","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"40b376f16dbe985410e92967","model":"qwen-3.8-max","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3e501f4d0b20047e61d77985","model":"gemini-4-argon","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e1e12d053abcdc3d71fc670d","model":"grok-4.7","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"56b7367f12ba25eff56d498e","model":"muse-wonder","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26e073377f2d99d8a5641e53","model":"glm-5.3","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8d3e2266956b474121a94b0b","model":"muse-spark-1.3","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"82e3d518d84c3fa1ed18811f","model":"kimi-k3","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"65a34d1fa2ecb6776ad932e8","model":"hy4-preview","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9de87fb166bcde7c385fe449","model":"gemini-3.8-flash","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3d2825650bc7c062cb4fcaa5","model":"mistral-large-4","benchmark":"sudo-l7","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"93e8c9c93a2b86f54cc4ddfe","model":"glm-5.3-flash","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed142fb4c94a739efadbde83","model":"kimi-k3","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"307df7fc7a3d2d3ff13aace2","model":"claude-opus-4-8","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b05cfbac1378b456dd269c8e","model":"muse-spark-1.2","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4387ffd488958a7423b7bfdc","model":"muse-spark-1.1","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a121b744f81681eeb0a5bdcd","model":"deepseek-v4-pro","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0dccc75a81b29bb448bbb01f","model":"gpt-5.5","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"93d29ea51280a4052f57e0b0","model":"claude-sonnet-5","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f0e924dd1959da90f31e2e52","model":"deepseek-v4-flash","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"988bef362bd1da11693ac376","model":"gemini-3.5-flash","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f05f6616344b6f716ee1b57b","model":"gemini-3.1-pro","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4c831ab57740da7b10d0478f","model":"glm-5.2","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5b23fe5f72e981524de657d2","model":"kimi-k2.6","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f18d0bf828c5790b39fd9ee1","model":"kimi-k2.7-code","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ce84a5798f0f7841fc7a0de5","model":"gemini-3.5-flash-lite","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f6479b251dbe0fc5d9a2f509","model":"hy3","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b7828d377cc351ebffaf8ee7","model":"mimo-v2.5","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"85d0aff28b7c742f5fea4f6d","model":"minimax-m2.7","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8c4f541f61193e7f74975f3a","model":"qwen3.5-397b-a17b","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a01a99f4b87edab5843043fe","model":"nemotron-3-ultra","benchmark":"toolathlon-verified","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"928a6287955f80f9c247d66c","model":"claude-opus-5-5","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9071c8ae8d43dc082d693afa","model":"claude-opus-5","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"76bf67b013e8cce12b46f750","model":"gpt-5.4","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"37ab3536a9071a1c6c69e56f","model":"gpt-5.6-sol","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a5fda3d68db6727d126c2bc3","model":"claude-sonnet-4-6","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6443ce88b910f5f8cec310e4","model":"gpt-6-astra","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"721f8b012c30e72f2728dec0","model":"gpt-5.2","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"12d2562c02df44096210cbea","model":"claude-opus-4-6","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b53d062aa5e966280e6fda54","model":"o3-pro","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fdc2300ebb4c72d77640314f","model":"grok-4.3","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5b2a06cf1828e45d7c05a243","model":"kimi-k3","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9256ed2307760a832eed1407","model":"qwen3.8-27b","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"83f5603530c661eb65ae1ec1","model":"kimi-k2.6","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"33acac6fb60fe4ed590d73f2","model":"glm-5.1","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1e899bc63c10d6af15cb3f90","model":"qwen3.6-27b","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8a9d50b279ed4dfb4489c2aa","model":"qwen3.5-9b","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c22ff89deca0e83a54901d48","model":"mistral-large-3","benchmark":"thinkingbox-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"frontiermath-erdos-bloom68-fable-vn2l2xoe9902k9rt","model":"claude-fable-5","benchmark":"frontiermath-erdos","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"frontiermath-erdos-bloom68-fable51-8t9up8nw9358oyrl","model":"claude-fable-5-1","benchmark":"frontiermath-erdos","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"frontiermath-erdos-bloom68-gpt55-4nh07xafb8lf7jqp","model":"gpt-5.5","benchmark":"frontiermath-erdos","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"frontiermath-erdos-bloom68-sol-jx4yy8n4naukwwge","model":"gpt-5.6-sol","benchmark":"frontiermath-erdos","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"frontiermath-erdos-bloom68-ultima-e1dhs43ykrmakree","model":"gpt-6-astra","benchmark":"frontiermath-erdos","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts1-a20h-3a714bccadb811b3","model":"claude-fable-5-1","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts1-a20h-c8709a73c9fd54e3","model":"gpt-6-astra","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts1-a20h-ee8cb2987a2c6c37","model":"gpt-6-sol","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts1-a20h-fc581bcaa7f17d12","model":"gpt-6-luna","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts2-a10-0e148062f8e47c4a","model":"gpt-6-luna","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts2-a10-413d1cc930f6d4c6","model":"claude-fable-5-1","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"spireclimb-steambench-sts2-a10-cdf1c9fa85cb6300","model":"gpt-6-astra","benchmark":"spireclimb","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9c995be124820e515fae18f2","model":"gpt-5.6-sol","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"76d20e5abf2ab8e7bd3c9193","model":"claude-opus-5-5","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"349dde94caf88259e8ae0882","model":"gpt-5.6-luna","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a5ecfe2a2bd08a24e15e424e","model":"gpt-5.6-terra","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"692fcd7f94d1bcdbe3cf4c17","model":"gpt-5.6-luna","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2fe37b6bde125afef22914e1","model":"claude-opus-5","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"480bc916d7108ac0ee2030d6","model":"kimi-k3","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c8c9452d1622e46697875765","model":"gpt-5.6-luna","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5dc7185c20fd87aef971c46f","model":"gpt-5.4-mini","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"291eeb8fecc4dc27ef24cc33","model":"gpt-5.4-mini","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bb238d1c6ede7b766c6c5b7c","model":"gemini-3.5-flash-lite","benchmark":"swe-sweep","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8f602902f4f283bbb57f68a6","model":"claude-opus-5-5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"872386cc451a062a3659974a","model":"gpt-6-astra","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bc30496970a9d59834c5cbea","model":"gpt-6-sol","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"94f176bea93c5ff3cf9fd62d","model":"claude-opus-5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"676de6ee897817d1d1995fa9","model":"muse-spark-1.3","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7182b41ada71f4ea331578ae","model":"gpt-5.6-sol","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3843a03d8c0c83f7c0f2fd5c","model":"gpt-5.6-luna","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d147d87d8825b885876e54e8","model":"kimi-k3","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"da1b7a5f88650cd956a5d434","model":"gpt-5.6-terra","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e8cb99d37aa15cde0f079ce3","model":"qwen-3.8-max","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"40e5b714c33333961838af83","model":"grok-4.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eb302e48cfc1131b785921eb","model":"kimi-k3","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f9b3e2c57ef651d836e9b514","model":"claude-opus-4-8","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"99aaf2eec3bdecbcdd6ac1ae","model":"gpt-5.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4791f23ba358c833ebb34cf0","model":"claude-fable-5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"29ec421af5ec87c489812279","model":"gpt-6-luna","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6ff9b78c83312245d7e2e18a","model":"gpt-5.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8b848b06bec07b325290f58b","model":"gpt-5.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b401da83d711f0c01e26e3c2","model":"gpt-5.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1c189d546f25ecf35d1cef0f","model":"claude-opus-4-7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"85767195c6630f480c84d715","model":"gpt-5.4","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6db38ff867f86b76eb7ce119","model":"glm-5.2","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"99b9bc14d37a54c4472bf028","model":"gpt-5.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6ca7f9471855c52d650102c4","model":"claude-opus-4-7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4db1bc3faa17daebe263884f","model":"gemini-3.1-pro","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7e17e17174ee5e6776535383","model":"claude-opus-4-7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ff1f22b4d68310bc283968c3","model":"gemini-3.1-pro","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3c177d8a521629c80a420cba","model":"claude-opus-4-7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a776154c46f2cc0828eb39a0","model":"claude-opus-4-7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d5fd02cd82ec9b3e9de42bff","model":"qwen3.7-max","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f38f231a2fc30b1d26dc2c51","model":"gpt-5.4","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"99c13e65612f655c0f444506","model":"glm-5.1","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"6a05810f60840d208e7d7a5c","model":"kimi-k2.6","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ee1282ce96154165b172e969","model":"qwen3.6-plus","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bd81d0ff1a33ba4825491483","model":"mimo-v2.5","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c29cbf6cb5c6183084b940ba","model":"grok-4.3","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a2c07f57afd3fa445d3d2ddd","model":"minimax-m2.7","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"34f1a58bf158b01775e872a6","model":"grok-4.3","benchmark":"agents-last-exam","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d0340ac19be6cfb68ecb513d","model":"claude-fable-5-1","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c4b3229a8f23f808571e12f1","model":"claude-opus-5-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0776624889a32af4fb08e2bd","model":"claude-sonnet-5-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"45c8d6cbfc9d9cd5ff4e4ad5","model":"gpt-6-astra","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"947bac6664a523899cdba3f9","model":"gpt-6.1-sol","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a9a25cfcdd0ec17e5a09ebe7","model":"gpt-6-sol","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3282f64a5da3e2dcd05537fb","model":"claude-opus-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ab25c1100a249db08a0ccc50","model":"claude-fable-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8c35a383b0dd6e6ab648d6f6","model":"claude-opus-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d636f326988768d1353e6613","model":"gemini-4-argon","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"03ae20fc24f1f2bebe6a8f10","model":"claude-opus-4-8","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7ee13b6baf57fa44f4ecf9f5","model":"gpt-5.6-sol","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f1407dd17f71174872700d81","model":"claude-sonnet-5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"790e1a899cce18c5e7115e5e","model":"kimi-k3","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8f9242e8ec4831420dfa6cf8","model":"gpt-5.5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"eb38bdb02586fc5c7b56eb43","model":"grok-4.7","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a9c19f28b6b35f1cfecff3f7","model":"deepseek-v4.1-flash","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"543bed84dd98726b9cda8ed0","model":"muse-spark-1.3","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"279ad2ba50cd782c323458b5","model":"hy4-preview","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9bab6207f50373b71744538c","model":"glm-5.2","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4f27cdab99c08b380ea60eff","model":"gemini-3.8-flash","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"95296dde8063cef39635d0b9","model":"qwen-3.8-max","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e481a590d3ab672be6892c52","model":"glm-5.3","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4e865ae63f79c95b4a197ebc","model":"gpt-6-luna","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dcc7c5758d6865db29bb27be","model":"grok-4.6","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"54aed1470c504f06fe839893","model":"grok-4.5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a4195a4f532e0d321ef0c94c","model":"deepseek-v4-pro","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e0c64dea01582f2b42d1b4b8","model":"gpt-5.4","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"312698f57dded23365430ed8","model":"gpt-5.5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"510b1906e1532d94112acce2","model":"gpt-5.6-terra","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"64d37dff5c0b2237fd2dc9fb","model":"glm-5.3-flash","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"166578670251d544d464c5f8","model":"qwen3.8-flash-next","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fb4286feccac496c1b6396cd","model":"gpt-5.6-luna","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3a21c505486d52bd5f114c15","model":"gemini-3.7-flash","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f0693c6f295f758d738c52e6","model":"qwen3.8-27b","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c1360f99a929ad065c2ff5ec","model":"muse-spark-1.2","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a197a7064aa5d129c4f73d78","model":"muse-spark-1.1","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"aa3b48be077bc3d95033a274","model":"qwen3.7-max","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dad0090bcc37a9b2dc9499a8","model":"hy3","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"929e18aebcc14c0d353763d0","model":"minimax-m3","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"73ea539ceb5e9b232c4b9323","model":"qwen3.7-plus","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3415c8a3bffb156dd40d6a7d","model":"mimo-v2.5-pro","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9ce8a035d41740b238aab251","model":"gemini-3.6-flash","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b4fc9a81e348fec4b20f2754","model":"gemini-3.1-pro","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f15486c1efb571ab847d2fba","model":"mistral-medium-3.5","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5b7e5263e136f2def58c73e5","model":"solar-pro4-260806","benchmark":"lmarena-agent","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"81e9970add62c0c7b2531bfb","model":"gpt-6-astra","benchmark":"frontierswe-v2","reason":"The task table records 169 trials of the nominal 170."},{"id":"041dbc44ffd19c2b84b093db","model":"claude-opus-5-5","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ac99b7569548ee908cfe0fb3","model":"claude-sonnet-5-5","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"44d1ed48497d24a4dd085aaa","model":"claude-fable-5-1","benchmark":"frontierswe-v2","reason":"The v2 methodology discloses Opus 5 fallback on tasks blocked by content filters. The task-summary mean 56.52830% differs from the published headline mean@5 56.29079%; the headline score is retained."},{"id":"ff3051d2f04ecd2ad550e7a0","model":"gemini-4-argon","benchmark":"frontierswe-v2","reason":"Cache hit rate is much lower due to a non-production setting."},{"id":"e8f2358815c124dd0449c1ca","model":"claude-opus-5","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f0129750ffae88478acefff0","model":"claude-fable-5","benchmark":"frontierswe-v2","reason":"The task-summary mean 47.20200% differs from the published headline mean@5 46.96449%; the headline score is retained."},{"id":"60d94bb8cee7478e8cff443b","model":"claude-haiku-5-5","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b7ebc08725286a2ecf054772","model":"gpt-5.6-sol","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"89528e3aa6e3997d416741b6","model":"glm-5.3","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ded42586dbefafa89c12009f","model":"grok-4.7","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"da50ef39dd8b9399b3ee8d7f","model":"kimi-k3","benchmark":"frontierswe-v2","reason":"The task table records 165 trials of the nominal 170."},{"id":"00b5696cd7c263fe4470e081","model":"muse-spark-1.3","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bb0115557a23b53b4fe10b76","model":"grok-4.6","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"676afe6774d1ab6eaf6a7ccd","model":"gemini-3.7-flash","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0b258d6cd8b710583beb5bbb","model":"gemini-3.8-flash","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ccb8c9a318581c00f767d922","model":"glm-5.3-flash","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"69de10246886f142905d7542","model":"qwen-3.8-max-0902","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3228a6cefadba28448a44428","model":"qwen-3.8-max","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"455c653df3d24ea2e0c4851f","model":"deepseek-v4-flash-vision-exp","benchmark":"frontierswe-v2","reason":"The task table records 167 trials of the nominal 170."},{"id":"060fac95feb6422df27091c3","model":"muse-spark-1.2","benchmark":"frontierswe-v2","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a15e4bf3befd7f7ae09a6858","model":"gpt-6-astra","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a4ada587a84348711490c89b","model":"gpt-6.1-sol","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4dbe3c30fa34d2b33ef22677","model":"claude-opus-5-5","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c7a097bc2e305075826d2a59","model":"gemini-3.8-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0311f7bd1351961cee7a9240","model":"claude-fable-5-1","benchmark":"hss","reason":"The board does not publish an effort setting for this row."},{"id":"830ca9b63ce7eb52b8dce017","model":"gemini-3.7-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b399eabdcbf649daa5218245","model":"muse-spark-1.3","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7d021e24a2dc6e213f69d17a","model":"claude-fable-5","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2131b16c32557cee50a60f92","model":"qwen-3.8-max","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"795aea8aba98f63ce3479cc8","model":"gemini-3.5-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bd64e697822e6c9e153a5ef8","model":"gemini-3.6-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4d0badf71b8d3d8c61801909","model":"gpt-6-sol","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2a2fe835120323f80463fd8b","model":"qwen3.8-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"884750c61c8ee37b44c56c69","model":"claude-opus-5","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"46659376ecba1fe13fffb611","model":"gpt-5.6-sol","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e7a8767f88bd7aea8058ac83","model":"glm-5.3-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ded2e2416b8e56ec60ecee9b","model":"kimi-k3","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"49cd86f41454a9710c05d448","model":"mimo-v2.6-flash","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"21471cb42e2a96c3549bf8ee","model":"mimo-v2.6-pro","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7ab4b62bef03e4fc16ac041d","model":"claude-sonnet-5","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e4fa929703a4d06882d14187","model":"muse-spark-1.2","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fbb82323532284442cdd12f7","model":"claude-opus-4-8","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"695ded2356d3f25584dd210d","model":"gpt-5.6-terra","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f884228e6423471428032523","model":"gpt-5.6-luna","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0e78b9edbdbf167341a3174a","model":"gpt-6-luna","benchmark":"hss","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"}],"launchEffortLabels":[{"model":"gpt-6-astra","labels":{"Not specified":62,"Best across efforts":34,"Low":6,"Medium":6,"High":6,"XHigh":7,"Max":10}},{"model":"claude-fable-5-1","labels":{"Max":34,"Not specified":65,"Medium":3,"Auto thinking":2,"XHigh":4,"High":1}}]}}