{"version":"configuration-source-5","generatedAt":"2026-09-12T09:05:29.922Z","snapshotId":"sha256-df858793dcb753b0f77beb223fce04e1de99a2c08f2c7b5f14534efcafa8c7c5","effortDatasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","inputHash":"sha256-ee6b3be5103cdc568e602475d5ab739b5ddd1c99aec98e13cd571b40f1166202","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-5","smoothing":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":5},"summary":{"family":{"totalFolds":49,"predictableFolds":48,"meanCoverageAllFolds":0.9669487752722931,"weightedCoverage":0.9821838576809794,"methods":{"source-balanced":{"meanLogLossPredictableFolds":0.4307104939826168},"equal-family":{"meanLogLossPredictableFolds":0.42961535607755913},"equal-model-exposure":{"meanLogLossPredictableFolds":0.43982487616901866},"configuration-exposure":{"meanLogLossPredictableFolds":0.44159671316074783},"equal-model-pair":{"meanLogLossPredictableFolds":0.46098744750862736}}},"source":{"totalFolds":11,"predictableFolds":11,"meanCoverageAllFolds":0.7876253489645275,"weightedCoverage":0.534755185867682,"methods":{"source-balanced":{"meanLogLossPredictableFolds":0.45957279693544834},"equal-family":{"meanLogLossPredictableFolds":0.4658837008529679},"equal-model-exposure":{"meanLogLossPredictableFolds":0.4819862428452362},"configuration-exposure":{"meanLogLossPredictableFolds":0.4761521665151271},"equal-model-pair":{"meanLogLossPredictableFolds":0.49715006006677526}}}},"folds":[{"kind":"family","key":"analyst-agent","totalWeight":14.500000000000092,"predictableWeight":14.500000000000092,"coverage":1,"methods":{"source-balanced":{"logLoss":0.36650424893253486,"accuracy":0.8546798029556636,"converged":true},"equal-family":{"logLoss":0.3546718067186944,"accuracy":0.8522167487684714,"converged":true},"equal-model-exposure":{"logLoss":0.3677914936190375,"accuracy":0.8559113300492597,"converged":true},"configuration-exposure":{"logLoss":0.37160076136415826,"accuracy":0.8559113300492597,"converged":true},"equal-model-pair":{"logLoss":0.39006732455242626,"accuracy":0.8645320197044319,"converged":true}}},{"kind":"family","key":"briefcase","totalWeight":46.793103448271864,"predictableWeight":46.793103448271864,"coverage":1,"methods":{"source-balanced":{"logLoss":0.347226675093152,"accuracy":0.858343568328849,"converged":true},"equal-family":{"logLoss":0.3409852938435676,"accuracy":0.8564357651682809,"converged":true},"equal-model-exposure":{"logLoss":0.35479941429283346,"accuracy":0.8565749611070345,"converged":true},"configuration-exposure":{"logLoss":0.3597946424184659,"accuracy":0.8572381888152145,"converged":true},"equal-model-pair":{"logLoss":0.3763209850804537,"accuracy":0.8541554081716386,"converged":true}}},{"kind":"family","key":"aime","totalWeight":86.45833333332831,"predictableWeight":86.45833333332831,"coverage":1,"methods":{"source-balanced":{"logLoss":0.395666861460256,"accuracy":0.8362347166443682,"converged":true},"equal-family":{"logLoss":0.39979156873491734,"accuracy":0.8320356983489647,"converged":true},"equal-model-exposure":{"logLoss":0.4116547426059198,"accuracy":0.8301704596162561,"converged":true},"configuration-exposure":{"logLoss":0.4128837497597092,"accuracy":0.8313235162873844,"converged":true},"equal-model-pair":{"logLoss":0.4218948511781831,"accuracy":0.8258563141454838,"converged":true}}},{"kind":"family","key":"apex-agents","totalWeight":13.499999999999961,"predictableWeight":13.499999999999961,"coverage":1,"methods":{"source-balanced":{"logLoss":0.40867797552125884,"accuracy":0.8490028490028491,"converged":true},"equal-family":{"logLoss":0.3915093903505406,"accuracy":0.8803418803418804,"converged":true},"equal-model-exposure":{"logLoss":0.41783249823540414,"accuracy":0.8632478632478633,"converged":true},"configuration-exposure":{"logLoss":0.4218251531130953,"accuracy":0.8660968660968662,"converged":true},"equal-model-pair":{"logLoss":0.4375912920091332,"accuracy":0.8547008547008548,"converged":true}}},{"kind":"family","key":"aa-lcr","totalWeight":111.45908139639475,"predictableWeight":111.45908139639475,"coverage":1,"methods":{"source-balanced":{"logLoss":0.31982879138008485,"accuracy":0.8813874992331331,"converged":true},"equal-family":{"logLoss":0.3290330553787434,"accuracy":0.8751916012318017,"converged":true},"equal-model-exposure":{"logLoss":0.32806266043271115,"accuracy":0.8818843069762174,"converged":true},"configuration-exposure":{"logLoss":0.3308774809019441,"accuracy":0.8819520217084733,"converged":true},"equal-model-pair":{"logLoss":0.3337025204314788,"accuracy":0.8825067631669342,"converged":true}}},{"kind":"family","key":"automationbench","totalWeight":47.3483146067392,"predictableWeight":47.3483146067392,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3078312904163172,"accuracy":0.8862007593735177,"converged":true},"equal-family":{"logLoss":0.30650271422179076,"accuracy":0.882360386014872,"converged":true},"equal-model-exposure":{"logLoss":0.31976656231066664,"accuracy":0.8854888467014722,"converged":true},"configuration-exposure":{"logLoss":0.3232732361547499,"accuracy":0.8857696566998902,"converged":true},"equal-model-pair":{"logLoss":0.3359412801957415,"accuracy":0.8833214681221334,"converged":true}}},{"kind":"family","key":"critpt","totalWeight":109.90999999995148,"predictableWeight":109.90999999995148,"coverage":1,"methods":{"source-balanced":{"logLoss":0.39733430932092145,"accuracy":0.8204457687602854,"converged":true},"equal-family":{"logLoss":0.40691279067349,"accuracy":0.8159962949483697,"converged":true},"equal-model-exposure":{"logLoss":0.4023285135589846,"accuracy":0.8216550915395338,"converged":true},"configuration-exposure":{"logLoss":0.4020576081915429,"accuracy":0.8223314024605899,"converged":true},"equal-model-pair":{"logLoss":0.40378640326486753,"accuracy":0.8230139053164619,"converged":true}}},{"kind":"family","key":"enterprise-ops","totalWeight":21.02439024390195,"predictableWeight":21.02439024390195,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4389160295407255,"accuracy":0.7987238979118366,"converged":true},"equal-family":{"logLoss":0.41538608934127297,"accuracy":0.8236658932714651,"converged":true},"equal-model-exposure":{"logLoss":0.43967561928231935,"accuracy":0.8138051044083562,"converged":true},"configuration-exposure":{"logLoss":0.4457639487965694,"accuracy":0.8091647331786578,"converged":true},"equal-model-pair":{"logLoss":0.45887593731260845,"accuracy":0.8022041763341103,"converged":true}}},{"kind":"family","key":"gdp-pdf","totalWeight":46.55681818181579,"predictableWeight":46.55681818181579,"coverage":1,"methods":{"source-balanced":{"logLoss":0.31635892417967004,"accuracy":0.8756651208201298,"converged":true},"equal-family":{"logLoss":0.31035983986407195,"accuracy":0.8778476120738948,"converged":true},"equal-model-exposure":{"logLoss":0.32098830775199927,"accuracy":0.8831095923846944,"converged":true},"configuration-exposure":{"logLoss":0.323756379421225,"accuracy":0.8845130583353897,"converged":true},"equal-model-pair":{"logLoss":0.33647779845192716,"accuracy":0.8829489057033831,"converged":true}}},{"kind":"family","key":"gdpval","totalWeight":66.57723577236797,"predictableWeight":66.57723577236797,"coverage":1,"methods":{"source-balanced":{"logLoss":0.30643259381090293,"accuracy":0.8860381813001091,"converged":true},"equal-family":{"logLoss":0.30454783978811967,"accuracy":0.8859628770301551,"converged":true},"equal-model-exposure":{"logLoss":0.31428321396573317,"accuracy":0.8884764114462425,"converged":true},"configuration-exposure":{"logLoss":0.31821849452297996,"accuracy":0.8895652704847907,"converged":true},"equal-model-pair":{"logLoss":0.328888702307597,"accuracy":0.8866813204705442,"converged":true}}},{"kind":"family","key":"gmmlu","totalWeight":33.904761904763355,"predictableWeight":33.904761904763355,"coverage":1,"methods":{"source-balanced":{"logLoss":0.36374095216716856,"accuracy":0.8715667915106121,"converged":true},"equal-family":{"logLoss":0.38024475299059646,"accuracy":0.8606429463171037,"converged":true},"equal-model-exposure":{"logLoss":0.37269352011168083,"accuracy":0.8789013732833968,"converged":true},"configuration-exposure":{"logLoss":0.37461388255640504,"accuracy":0.8800717852684156,"converged":true},"equal-model-pair":{"logLoss":0.36987794661523615,"accuracy":0.8853776529338342,"converged":true}}},{"kind":"family","key":"gpqa","totalWeight":133.8579929412826,"predictableWeight":132.87450237524482,"coverage":0.9926527318658573,"methods":{"source-balanced":{"logLoss":0.29490012795424686,"accuracy":0.9127265151867512,"converged":true},"equal-family":{"logLoss":0.30438384485488396,"accuracy":0.9036162367128378,"converged":true},"equal-model-exposure":{"logLoss":0.3089050563455643,"accuracy":0.90797954321246,"converged":true},"configuration-exposure":{"logLoss":0.3115558858346895,"accuracy":0.9090963682007995,"converged":true},"equal-model-pair":{"logLoss":0.3159301492710821,"accuracy":0.9065145711527542,"converged":true}}},{"kind":"family","key":"harvey","totalWeight":23.0574324324324,"predictableWeight":23.0574324324324,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5151573732452435,"accuracy":0.7462692307692286,"converged":true},"equal-family":{"logLoss":0.5012446933459443,"accuracy":0.7486282051282029,"converged":true},"equal-model-exposure":{"logLoss":0.501154242851175,"accuracy":0.753173992673991,"converged":true},"configuration-exposure":{"logLoss":0.5029765569969569,"accuracy":0.7563791208791191,"converged":true},"equal-model-pair":{"logLoss":0.5102288487425387,"accuracy":0.7531227106227085,"converged":true}}},{"kind":"family","key":"hle","totalWeight":124.62307692303467,"predictableWeight":122.44807692303469,"coverage":0.9825473736189066,"methods":{"source-balanced":{"logLoss":0.3071570035641744,"accuracy":0.8930613577708347,"converged":true},"equal-family":{"logLoss":0.3170741436555642,"accuracy":0.8865466262519834,"converged":true},"equal-model-exposure":{"logLoss":0.318484060837758,"accuracy":0.8918621969543741,"converged":true},"configuration-exposure":{"logLoss":0.31959661176749193,"accuracy":0.893720978018037,"converged":true},"equal-model-pair":{"logLoss":0.3236266223450533,"accuracy":0.8918402750513156,"converged":true}}},{"kind":"family","key":"ifbench","totalWeight":103.08988764044788,"predictableWeight":103.08988764044788,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4084870408076163,"accuracy":0.8216866485013302,"converged":true},"equal-family":{"logLoss":0.4310882928308483,"accuracy":0.807637602179805,"converged":true},"equal-model-exposure":{"logLoss":0.4211483187403636,"accuracy":0.8165077202542823,"converged":true},"configuration-exposure":{"logLoss":0.4212017625282975,"accuracy":0.8180417801997864,"converged":true},"equal-model-pair":{"logLoss":0.41612952604072384,"accuracy":0.82271298819252,"converged":true}}},{"kind":"family","key":"itbench","totalWeight":14.535714285714352,"predictableWeight":14.535714285714352,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3993599866223137,"accuracy":0.8378378378378396,"converged":true},"equal-family":{"logLoss":0.39495287664837203,"accuracy":0.8427518427518437,"converged":true},"equal-model-exposure":{"logLoss":0.41094423871968166,"accuracy":0.84889434889435,"converged":true},"configuration-exposure":{"logLoss":0.41521029656911185,"accuracy":0.8452088452088466,"converged":true},"equal-model-pair":{"logLoss":0.4336549772802105,"accuracy":0.8329238329238345,"converged":true}}},{"kind":"family","key":"livecodebench","totalWeight":62.455357142851426,"predictableWeight":62.455357142851426,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3849388047178427,"accuracy":0.8694412675720845,"converged":true},"equal-family":{"logLoss":0.3893971189776955,"accuracy":0.8591076959733223,"converged":true},"equal-model-exposure":{"logLoss":0.39475182148440846,"accuracy":0.8670586132952202,"converged":true},"configuration-exposure":{"logLoss":0.39670858720207725,"accuracy":0.8688050988801618,"converged":true},"equal-model-pair":{"logLoss":0.40057172033791677,"accuracy":0.8665106028115412,"converged":true}}},{"kind":"family","key":"math500","totalWeight":31.799999999999073,"predictableWeight":31.799999999999073,"coverage":1,"methods":{"source-balanced":{"logLoss":0.39586849958834414,"accuracy":0.8687106918239044,"converged":true},"equal-family":{"logLoss":0.39952363568347327,"accuracy":0.8647798742138416,"converged":true},"equal-model-exposure":{"logLoss":0.4155864115606962,"accuracy":0.8539046121593346,"converged":true},"configuration-exposure":{"logLoss":0.41949337879655496,"accuracy":0.852070230607972,"converged":true},"equal-model-pair":{"logLoss":0.42871644299333433,"accuracy":0.8408018867924589,"converged":true}}},{"kind":"family","key":"mmlu-pro","totalWeight":79.16666666666933,"predictableWeight":79.16666666666933,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3876182606480145,"accuracy":0.8622907097965626,"converged":true},"equal-family":{"logLoss":0.38604800584335486,"accuracy":0.8687690703839386,"converged":true},"equal-model-exposure":{"logLoss":0.39697602859927816,"accuracy":0.8648499091531888,"converged":true},"configuration-exposure":{"logLoss":0.4002941205496176,"accuracy":0.8651114883984155,"converged":true},"equal-model-pair":{"logLoss":0.4070900841937322,"accuracy":0.8581865189289015,"converged":true}}},{"kind":"family","key":"mmmu-pro","totalWeight":70.12280701754003,"predictableWeight":70.12280701754003,"coverage":1,"methods":{"source-balanced":{"logLoss":0.29293934874053174,"accuracy":0.9100210574598327,"converged":true},"equal-family":{"logLoss":0.3045998860381491,"accuracy":0.8965693019765537,"converged":true},"equal-model-exposure":{"logLoss":0.307737716151001,"accuracy":0.9027739554666707,"converged":true},"configuration-exposure":{"logLoss":0.3101351332380627,"accuracy":0.9036120840631174,"converged":true},"equal-model-pair":{"logLoss":0.3129529426465855,"accuracy":0.9051257192895376,"converged":true}}},{"kind":"family","key":"omniscience","totalWeight":117.14141414132928,"predictableWeight":117.14141414132928,"coverage":1,"methods":{"source-balanced":{"logLoss":0.39066681726490554,"accuracy":0.8215005317467915,"converged":true},"equal-family":{"logLoss":0.3883414101354493,"accuracy":0.8252349745624554,"converged":true},"equal-model-exposure":{"logLoss":0.3890182611230717,"accuracy":0.8267820700756583,"converged":true},"configuration-exposure":{"logLoss":0.39116901194106857,"accuracy":0.8261468483229079,"converged":true},"equal-model-pair":{"logLoss":0.3956797082883209,"accuracy":0.8229578051795715,"converged":true}}},{"kind":"family","key":"scicode","totalWeight":48.549450549456644,"predictableWeight":48.549450549456644,"coverage":1,"methods":{"source-balanced":{"logLoss":0.31157759630698256,"accuracy":0.8867209898898016,"converged":true},"equal-family":{"logLoss":0.3147463973298087,"accuracy":0.8826052512448626,"converged":true},"equal-model-exposure":{"logLoss":0.32223561327128686,"accuracy":0.8885411951108666,"converged":true},"configuration-exposure":{"logLoss":0.32478391508491694,"accuracy":0.8894069714802645,"converged":true},"equal-model-pair":{"logLoss":0.33063287304353545,"accuracy":0.8947091444091931,"converged":true}}},{"kind":"family","key":"tau-bench","totalWeight":108.76104410333312,"predictableWeight":108.76104410333312,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4221427829047382,"accuracy":0.8097466727561575,"converged":true},"equal-family":{"logLoss":0.4307665244439634,"accuracy":0.8052605087022474,"converged":true},"equal-model-exposure":{"logLoss":0.42610005868389667,"accuracy":0.8109724018639869,"converged":true},"configuration-exposure":{"logLoss":0.4274000037517948,"accuracy":0.8112928744445647,"converged":true},"equal-model-pair":{"logLoss":0.4285893484543469,"accuracy":0.8107987093659107,"converged":true}}},{"kind":"family","key":"terminal-bench","totalWeight":110.13431513071143,"predictableWeight":109.44681513071143,"coverage":0.993757622234414,"methods":{"source-balanced":{"logLoss":0.36027553713945076,"accuracy":0.8592136975209255,"converged":true},"equal-family":{"logLoss":0.36449422856640845,"accuracy":0.8571239719915859,"converged":true},"equal-model-exposure":{"logLoss":0.36643510011275654,"accuracy":0.866332896017732,"converged":true},"configuration-exposure":{"logLoss":0.3684173624076477,"accuracy":0.8692375013701018,"converged":true},"equal-model-pair":{"logLoss":0.3724708601348025,"accuracy":0.8709918422250505,"converged":true}}},{"kind":"family","key":"arc-agi","totalWeight":57.868421052627035,"predictableWeight":33.67763157894894,"coverage":0.5819690768531879,"methods":{"source-balanced":{"logLoss":0.38295896998934675,"accuracy":0.8474929999348859,"converged":true},"equal-family":{"logLoss":0.38037810273060213,"accuracy":0.8468483427752844,"converged":true},"equal-model-exposure":{"logLoss":0.40248645007860706,"accuracy":0.8489092921794654,"converged":true},"configuration-exposure":{"logLoss":0.4041683157312694,"accuracy":0.8470925310933155,"converged":true},"equal-model-pair":{"logLoss":0.4264519079113779,"accuracy":0.8393078075144904,"converged":true}}},{"kind":"family","key":"deepswe","totalWeight":20.71999999999947,"predictableWeight":20.71999999999947,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4576116978215761,"accuracy":0.8135135135135135,"converged":true},"equal-family":{"logLoss":0.46375943492047694,"accuracy":0.7842664092664084,"converged":true},"equal-model-exposure":{"logLoss":0.4963787550423192,"accuracy":0.8064671814671815,"converged":true},"configuration-exposure":{"logLoss":0.4955351590048599,"accuracy":0.8192084942084946,"converged":true},"equal-model-pair":{"logLoss":0.5242490627286466,"accuracy":0.8140604890604904,"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":7.333333333333329,"predictableWeight":7.333333333333329,"coverage":1,"methods":{"source-balanced":{"logLoss":0.3214409448636654,"accuracy":0.9083333333333333,"converged":true},"equal-family":{"logLoss":0.340761319030868,"accuracy":0.8859848484848484,"converged":true},"equal-model-exposure":{"logLoss":0.3929871249476601,"accuracy":0.8867424242424241,"converged":true},"configuration-exposure":{"logLoss":0.38897433276425564,"accuracy":0.8969696969696969,"converged":true},"equal-model-pair":{"logLoss":0.44786510399839763,"accuracy":0.8687499999999998,"converged":true}}},{"kind":"family","key":"frontiercode","totalWeight":37.50952380952525,"predictableWeight":36.59523809523932,"coverage":0.97562523803478,"methods":{"source-balanced":{"logLoss":0.3726015337990344,"accuracy":0.8552700065061666,"converged":true},"equal-family":{"logLoss":0.3658341013236388,"accuracy":0.8732053784428392,"converged":true},"equal-model-exposure":{"logLoss":0.3941511542581273,"accuracy":0.8833680329646345,"converged":true},"configuration-exposure":{"logLoss":0.39629087067544855,"accuracy":0.87416829321187,"converged":true},"equal-model-pair":{"logLoss":0.42658696218801395,"accuracy":0.8742550422901614,"converged":true}}},{"kind":"family","key":"enigma-eval","totalWeight":2.5,"predictableWeight":2.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5215756033188964,"accuracy":0.7,"converged":true},"equal-family":{"logLoss":0.5627014157789024,"accuracy":0.7,"converged":true},"equal-model-exposure":{"logLoss":0.5508656281773477,"accuracy":0.7,"converged":true},"configuration-exposure":{"logLoss":0.524497802125913,"accuracy":0.7,"converged":true},"equal-model-pair":{"logLoss":0.5841053698834807,"accuracy":0.7,"converged":true}}},{"kind":"family","key":"swe-atlas-qna","totalWeight":3,"predictableWeight":3,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5666266607119327,"accuracy":0.8333333333333334,"converged":true},"equal-family":{"logLoss":0.525342221903911,"accuracy":0.8333333333333334,"converged":true},"equal-model-exposure":{"logLoss":0.6334035058513843,"accuracy":0.8333333333333334,"converged":true},"configuration-exposure":{"logLoss":0.652050119369885,"accuracy":0.8333333333333334,"converged":true},"equal-model-pair":{"logLoss":0.7997618553836361,"accuracy":0.5,"converged":true}}},{"kind":"family","key":"swe-atlas-refactoring","totalWeight":2.5,"predictableWeight":2.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.40820107537094585,"accuracy":1,"converged":true},"equal-family":{"logLoss":0.2904333718995047,"accuracy":1,"converged":true},"equal-model-exposure":{"logLoss":0.36809171635693216,"accuracy":1,"converged":true},"configuration-exposure":{"logLoss":0.39936537910134373,"accuracy":1,"converged":true},"equal-model-pair":{"logLoss":0.5637728340802133,"accuracy":0.6,"converged":true}}},{"kind":"family","key":"swe-atlas-test-writing","totalWeight":3,"predictableWeight":3,"coverage":1,"methods":{"source-balanced":{"logLoss":0.46335356985180626,"accuracy":0.9166666666666666,"converged":true},"equal-family":{"logLoss":0.39938921872115934,"accuracy":0.75,"converged":true},"equal-model-exposure":{"logLoss":0.41007755638136634,"accuracy":0.9166666666666666,"converged":true},"configuration-exposure":{"logLoss":0.4318678010345103,"accuracy":0.9166666666666666,"converged":true},"equal-model-pair":{"logLoss":0.5336176479598368,"accuracy":0.5833333333333334,"converged":true}}},{"kind":"family","key":"livebench-math","totalWeight":13.500000000000393,"predictableWeight":13.500000000000393,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5444145597144104,"accuracy":0.7129629629629594,"converged":true},"equal-family":{"logLoss":0.5469326990746807,"accuracy":0.7193732193732159,"converged":true},"equal-model-exposure":{"logLoss":0.5475540823911492,"accuracy":0.7165242165242129,"converged":true},"configuration-exposure":{"logLoss":0.5480077700148779,"accuracy":0.7143874643874608,"converged":true},"equal-model-pair":{"logLoss":0.5622877242503906,"accuracy":0.7115384615384579,"converged":true}}},{"kind":"family","key":"livebench-coding","totalWeight":13.50000000000021,"predictableWeight":13.50000000000021,"coverage":1,"methods":{"source-balanced":{"logLoss":0.6082063214825741,"accuracy":0.6666666666666586,"converged":true},"equal-family":{"logLoss":0.596364637624874,"accuracy":0.6695156695156614,"converged":true},"equal-model-exposure":{"logLoss":0.5782848738250265,"accuracy":0.6866096866096791,"converged":true},"configuration-exposure":{"logLoss":0.5799916712438912,"accuracy":0.6809116809116733,"converged":true},"equal-model-pair":{"logLoss":0.5845422559851386,"accuracy":0.6880341880341806,"converged":true}}},{"kind":"family","key":"livebench-language","totalWeight":13.499999999999956,"predictableWeight":13.499999999999956,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5486006810409653,"accuracy":0.6999050332383674,"converged":true},"equal-family":{"logLoss":0.564783884492205,"accuracy":0.7094017094017103,"converged":true},"equal-model-exposure":{"logLoss":0.5668743746662597,"accuracy":0.6904083570750246,"converged":true},"configuration-exposure":{"logLoss":0.562054305857653,"accuracy":0.6970560303893646,"converged":true},"equal-model-pair":{"logLoss":0.5653204869597283,"accuracy":0.7150997150997159,"converged":true}}},{"kind":"family","key":"livebench-data","totalWeight":13.499999999999956,"predictableWeight":13.499999999999956,"coverage":1,"methods":{"source-balanced":{"logLoss":0.7660639284886271,"accuracy":0.5826210826210827,"converged":true},"equal-family":{"logLoss":0.7358097774804473,"accuracy":0.5797720797720798,"converged":true},"equal-model-exposure":{"logLoss":0.7213006528575954,"accuracy":0.5797720797720798,"converged":true},"configuration-exposure":{"logLoss":0.7190157178406411,"accuracy":0.5892687559354226,"converged":true},"equal-model-pair":{"logLoss":0.7033289524216844,"accuracy":0.5940170940170942,"converged":true}}},{"kind":"family","key":"multi-swe-bench","totalWeight":13.499999999999956,"predictableWeight":13.499999999999956,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5452719275337814,"accuracy":0.7217473884140561,"converged":true},"equal-family":{"logLoss":0.5595888129311507,"accuracy":0.717948717948719,"converged":true},"equal-model-exposure":{"logLoss":0.5580011222078066,"accuracy":0.7132003798670475,"converged":true},"configuration-exposure":{"logLoss":0.5571266039077035,"accuracy":0.7188983855650533,"converged":true},"equal-model-pair":{"logLoss":0.5592559262008382,"accuracy":0.7188983855650533,"converged":true}}},{"kind":"family","key":"livebench-reasoning","totalWeight":13.500000000000393,"predictableWeight":13.500000000000393,"coverage":1,"methods":{"source-balanced":{"logLoss":0.555195032904981,"accuracy":0.7190170940170902,"converged":true},"equal-family":{"logLoss":0.5623357924733365,"accuracy":0.7104700854700817,"converged":true},"equal-model-exposure":{"logLoss":0.5531960083324904,"accuracy":0.7147435897435861,"converged":true},"configuration-exposure":{"logLoss":0.5526186536685798,"accuracy":0.7175925925925888,"converged":true},"equal-model-pair":{"logLoss":0.5551931853579971,"accuracy":0.7211538461538425,"converged":true}}},{"kind":"family","key":"livebench-instructions","totalWeight":13.500000000000393,"predictableWeight":13.500000000000393,"coverage":1,"methods":{"source-balanced":{"logLoss":0.6182595534026857,"accuracy":0.6542022792022746,"converged":true},"equal-family":{"logLoss":0.6145285395043215,"accuracy":0.6826923076923035,"converged":true},"equal-model-exposure":{"logLoss":0.6363381359720619,"accuracy":0.642806267806263,"converged":true},"configuration-exposure":{"logLoss":0.632331168348463,"accuracy":0.6442307692307645,"converged":true},"equal-model-pair":{"logLoss":0.644418578699032,"accuracy":0.632834757834753,"converged":true}}},{"kind":"family","key":"swe-rebench","totalWeight":7.759920634920638,"predictableWeight":7.759920634920638,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4901222388609468,"accuracy":0.8032472513423675,"converged":true},"equal-family":{"logLoss":0.4862818194516525,"accuracy":0.7925083098951676,"converged":true},"equal-model-exposure":{"logLoss":0.5178306578638895,"accuracy":0.7360010227563283,"converged":true},"configuration-exposure":{"logLoss":0.5178840004625044,"accuracy":0.768217847097929,"converged":true},"equal-model-pair":{"logLoss":0.5462656324115736,"accuracy":0.7467399642035285,"converged":true}}},{"kind":"family","key":"epoch-game-puzzles","totalWeight":37.69326388889039,"predictableWeight":32.18770833333419,"coverage":0.8539379457352089,"methods":{"source-balanced":{"logLoss":0.44220824264451375,"accuracy":0.7741406204490424,"converged":true},"equal-family":{"logLoss":0.45004510657002117,"accuracy":0.7697630867545463,"converged":true},"equal-model-exposure":{"logLoss":0.46052678190570917,"accuracy":0.76975661430453,"converged":true},"configuration-exposure":{"logLoss":0.45892988977797006,"accuracy":0.7726390120452137,"converged":true},"equal-model-pair":{"logLoss":0.46630731817133747,"accuracy":0.7752905590686414,"converged":true}}},{"kind":"family","key":"frontiermath","totalWeight":18.452991452991707,"predictableWeight":18.452991452991707,"coverage":1,"methods":{"source-balanced":{"logLoss":0.41080437628726757,"accuracy":0.8259680806886849,"converged":true},"equal-family":{"logLoss":0.408586000516664,"accuracy":0.838561714395222,"converged":true},"equal-model-exposure":{"logLoss":0.41259658611486516,"accuracy":0.8445810241011842,"converged":true},"configuration-exposure":{"logLoss":0.41128994722392814,"accuracy":0.850857876411481,"converged":true},"equal-model-pair":{"logLoss":0.4258750603093706,"accuracy":0.8445770311925898,"converged":true}}},{"kind":"family","key":"simpleqa","totalWeight":16.539999999999814,"predictableWeight":16.539999999999814,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5345360560453711,"accuracy":0.714228133817012,"converged":true},"equal-family":{"logLoss":0.5731589596733768,"accuracy":0.7311567916162865,"converged":true},"equal-model-exposure":{"logLoss":0.5861038315714269,"accuracy":0.6977025392986725,"converged":true},"configuration-exposure":{"logLoss":0.5750342199966747,"accuracy":0.7190648931882332,"converged":true},"equal-model-pair":{"logLoss":0.5920532140499553,"accuracy":0.7110036275695311,"converged":true}}},{"kind":"family","key":"vals-finance-agent","totalWeight":15.499999999999956,"predictableWeight":15.499999999999956,"coverage":1,"methods":{"source-balanced":{"logLoss":0.5014543625263257,"accuracy":0.752688172043011,"converged":true},"equal-family":{"logLoss":0.49926350110556467,"accuracy":0.7333333333333335,"converged":true},"equal-model-exposure":{"logLoss":0.5064087629849556,"accuracy":0.7268817204301077,"converged":true},"configuration-exposure":{"logLoss":0.5056170265182635,"accuracy":0.731182795698925,"converged":true},"equal-model-pair":{"logLoss":0.5108930727786862,"accuracy":0.7247311827956991,"converged":true}}},{"kind":"family","key":"vals-code-migration","totalWeight":17.00000000000025,"predictableWeight":17.00000000000025,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4772051220149742,"accuracy":0.7557932263814583,"converged":true},"equal-family":{"logLoss":0.48602514099114036,"accuracy":0.7540106951871623,"converged":true},"equal-model-exposure":{"logLoss":0.47262570753108113,"accuracy":0.7914438502673768,"converged":true},"configuration-exposure":{"logLoss":0.4733115359459256,"accuracy":0.7914438502673768,"converged":true},"equal-model-pair":{"logLoss":0.47592929634505726,"accuracy":0.7932263814616727,"converged":true}}},{"kind":"family","key":"vals-legal-research","totalWeight":16.5,"predictableWeight":16.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.43455804988322805,"accuracy":0.8049242424242424,"converged":true},"equal-family":{"logLoss":0.4574871762266324,"accuracy":0.7803030303030303,"converged":true},"equal-model-exposure":{"logLoss":0.4517580378472462,"accuracy":0.803030303030303,"converged":true},"configuration-exposure":{"logLoss":0.45055257206590166,"accuracy":0.8125,"converged":true},"equal-model-pair":{"logLoss":0.46577332640983365,"accuracy":0.8106060606060606,"converged":true}}},{"kind":"family","key":"vals-excel-modeling","totalWeight":16.5,"predictableWeight":16.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.42944107304534807,"accuracy":0.8049242424242424,"converged":true},"equal-family":{"logLoss":0.4459754208451979,"accuracy":0.7954545454545454,"converged":true},"equal-model-exposure":{"logLoss":0.43379308747073436,"accuracy":0.8257575757575758,"converged":true},"configuration-exposure":{"logLoss":0.43453938099027484,"accuracy":0.821969696969697,"converged":true},"equal-model-pair":{"logLoss":0.4462602375629054,"accuracy":0.821969696969697,"converged":true}}},{"kind":"family","key":"vibe-code","totalWeight":16.5,"predictableWeight":16.5,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4337842982350028,"accuracy":0.8106060606060606,"converged":true},"equal-family":{"logLoss":0.4391644361927944,"accuracy":0.7992424242424242,"converged":true},"equal-model-exposure":{"logLoss":0.43060598682861995,"accuracy":0.8484848484848485,"converged":true},"configuration-exposure":{"logLoss":0.43198002417602743,"accuracy":0.8484848484848485,"converged":true},"equal-model-pair":{"logLoss":0.4475833231951488,"accuracy":0.8314393939393939,"converged":true}}},{"kind":"source","key":"Artificial Analysis","totalWeight":115.24037566432071,"predictableWeight":8.850965179702186,"coverage":0.07680437631931906,"methods":{"source-balanced":{"logLoss":0.39256928548256587,"accuracy":0.8215092719092175,"converged":true},"equal-family":{"logLoss":0.4188643382687562,"accuracy":0.8111223153470527,"converged":true},"equal-model-exposure":{"logLoss":0.40882141710942266,"accuracy":0.8191465137132572,"converged":true},"configuration-exposure":{"logLoss":0.4052279334672384,"accuracy":0.8216162336473226,"converged":true},"equal-model-pair":{"logLoss":0.4082518758270506,"accuracy":0.8199704813202601,"converged":true}}},{"kind":"source","key":"ARC Prize","totalWeight":57.17916666666249,"predictableWeight":34.10328947368399,"coverage":0.596428585126048,"methods":{"source-balanced":{"logLoss":0.38692271361119573,"accuracy":0.8476667245403857,"converged":true},"equal-family":{"logLoss":0.38552125769761986,"accuracy":0.8475284706548085,"converged":true},"equal-model-exposure":{"logLoss":0.4111329244000503,"accuracy":0.8471297850312823,"converged":true},"configuration-exposure":{"logLoss":0.4123251432996284,"accuracy":0.8448212666628064,"converged":true},"equal-model-pair":{"logLoss":0.4351580552733128,"accuracy":0.8363588427828235,"converged":true}}},{"kind":"source","key":"Datacurve","totalWeight":20.71999999999947,"predictableWeight":20.71999999999947,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4574059084444191,"accuracy":0.8138996138996141,"converged":true},"equal-family":{"logLoss":0.4635593948057467,"accuracy":0.7837837837837829,"converged":true},"equal-model-exposure":{"logLoss":0.49596569323235434,"accuracy":0.8081081081081084,"converged":true},"configuration-exposure":{"logLoss":0.4951749857503118,"accuracy":0.8196911196911202,"converged":true},"equal-model-pair":{"logLoss":0.5241435627452857,"accuracy":0.813577863577865,"converged":true}}},{"kind":"source","key":"LiveCodeBench","totalWeight":1,"predictableWeight":1,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4415822324590895,"accuracy":0.6666666666666666,"converged":true},"equal-family":{"logLoss":0.43903376990238646,"accuracy":1,"converged":true},"equal-model-exposure":{"logLoss":0.43955686651069154,"accuracy":1,"converged":true},"configuration-exposure":{"logLoss":0.4420441839882988,"accuracy":1,"converged":true},"equal-model-pair":{"logLoss":0.4386324779638886,"accuracy":1,"converged":true}}},{"kind":"source","key":"Scale","totalWeight":7.216666666666665,"predictableWeight":4.5666666666666655,"coverage":0.6327944572748267,"methods":{"source-balanced":{"logLoss":0.5528468315281514,"accuracy":0.7208029197080291,"converged":true},"equal-family":{"logLoss":0.5068296782394011,"accuracy":0.7034671532846714,"converged":true},"equal-model-exposure":{"logLoss":0.5678621315931125,"accuracy":0.730839416058394,"converged":true},"configuration-exposure":{"logLoss":0.5416565528818739,"accuracy":0.7034671532846714,"converged":true},"equal-model-pair":{"logLoss":0.6093756878634241,"accuracy":0.6669708029197079,"converged":true}}},{"kind":"source","key":"Terminal-Bench","totalWeight":10.166666666666668,"predictableWeight":9.291666666666671,"coverage":0.9139344262295086,"methods":{"source-balanced":{"logLoss":0.4152178457214033,"accuracy":0.8215246636771303,"converged":true},"equal-family":{"logLoss":0.46765407181982216,"accuracy":0.7820627802690584,"converged":true},"equal-model-exposure":{"logLoss":0.4827967359814263,"accuracy":0.7829596412556055,"converged":true},"configuration-exposure":{"logLoss":0.46517786692685364,"accuracy":0.9121076233183857,"converged":true},"equal-model-pair":{"logLoss":0.4837677743750691,"accuracy":0.9865470852017937,"converged":true}}},{"kind":"source","key":"Cognition","totalWeight":37.50952380952525,"predictableWeight":36.59523809523932,"coverage":0.97562523803478,"methods":{"source-balanced":{"logLoss":0.3726015337990344,"accuracy":0.8552700065061666,"converged":true},"equal-family":{"logLoss":0.3658341013236388,"accuracy":0.8732053784428392,"converged":true},"equal-model-exposure":{"logLoss":0.3941511542581273,"accuracy":0.8833680329646345,"converged":true},"configuration-exposure":{"logLoss":0.39629087067544855,"accuracy":0.87416829321187,"converged":true},"equal-model-pair":{"logLoss":0.42658696218801395,"accuracy":0.8742550422901614,"converged":true}}},{"kind":"source","key":"LiveBench","totalWeight":13.499999999999698,"predictableWeight":12.50000000000003,"coverage":0.9259259259259489,"methods":{"source-balanced":{"logLoss":0.6057970302246941,"accuracy":0.6824542124542448,"converged":true},"equal-family":{"logLoss":0.6081254342969409,"accuracy":0.6796336996337318,"converged":true},"equal-model-exposure":{"logLoss":0.5999087109392186,"accuracy":0.6810256410256728,"converged":true},"configuration-exposure":{"logLoss":0.596988408039963,"accuracy":0.6815018315018632,"converged":true},"equal-model-pair":{"logLoss":0.6032943671218037,"accuracy":0.6805494505494815,"converged":true}}},{"kind":"source","key":"SWE-rebench","totalWeight":7.759920634920638,"predictableWeight":7.759920634920638,"coverage":1,"methods":{"source-balanced":{"logLoss":0.4901222388609468,"accuracy":0.8032472513423675,"converged":true},"equal-family":{"logLoss":0.4862818194516525,"accuracy":0.7925083098951676,"converged":true},"equal-model-exposure":{"logLoss":0.5178306578638895,"accuracy":0.7360010227563283,"converged":true},"configuration-exposure":{"logLoss":0.5178840004625044,"accuracy":0.768217847097929,"converged":true},"equal-model-pair":{"logLoss":0.5462656324115736,"accuracy":0.7467399642035285,"converged":true}}},{"kind":"source","key":"Epoch AI","totalWeight":35.6538276675955,"predictableWeight":21.48130399662459,"coverage":0.6024964331150393,"methods":{"source-balanced":{"logLoss":0.4343082909536107,"accuracy":0.789701757733177,"converged":true},"equal-family":{"logLoss":0.44555256751402633,"accuracy":0.7953383737085334,"converged":true},"equal-model-exposure":{"logLoss":0.45560186299458616,"accuracy":0.7964082516468342,"converged":true},"configuration-exposure":{"logLoss":0.45092772549923726,"accuracy":0.8019736855351997,"converged":true},"equal-model-pair":{"logLoss":0.46188846316087434,"accuracy":0.805296916910064,"converged":true}}},{"kind":"source","key":"Vals AI","totalWeight":16.630466737331602,"predictableWeight":15.630466737331647,"coverage":0.9398693965843313,"methods":{"source-balanced":{"logLoss":0.505926855204821,"accuracy":0.7498103305703867,"converged":true},"equal-family":{"logLoss":0.5374642760626558,"accuracy":0.7231884251749221,"converged":true},"equal-model-exposure":{"logLoss":0.5282205164147179,"accuracy":0.7319045089204504,"converged":true},"configuration-exposure":{"logLoss":0.51397616067504,"accuracy":0.7489304109194392,"converged":true},"equal-model-pair":{"logLoss":0.5312858018042314,"accuracy":0.7415163241833302,"converged":true}}}],"sourceSensitivity":[{"source":"Artificial Analysis","disconnectedSupportedConfigurations":234,"largestScoreChanges":[{"id":"gpt-5.3-codex--effort-xhigh","baseline":0.23025253409883203,"withoutSource":0.047784817639114165,"change":-0.18246771645971788},{"id":"deepseek-v4-pro-0424--effort-high","baseline":0.14687571597873708,"withoutSource":0.08418949181391787,"change":-0.06268622416481921},{"id":"claude-opus-5--effort-medium","baseline":0.756588545187245,"withoutSource":0.8159976838333668,"change":0.05940913864612174},{"id":"kimi-k3--effort-low","baseline":0.20513417721002192,"withoutSource":0.14668909337447175,"change":-0.058445083835550166},{"id":"kimi-k2.6--effort-non-reasoning","baseline":0.08855555108764535,"withoutSource":0.03605483629378873,"change":-0.052500714793856616},{"id":"gemini-3.8-flash--effort-medium","baseline":0.7002495102547243,"withoutSource":0.7498965473856387,"change":0.04964703713091445},{"id":"qwen3.5-397b-a17b--effort-non-reasoning","baseline":0.15088247869700758,"withoutSource":0.19739282682512457,"change":0.046510348128116996},{"id":"gpt-5--effort-low","baseline":0.07766638319251114,"withoutSource":0.036124687608952655,"change":-0.04154169558355848},{"id":"gpt-5.6-sol--effort-xhigh","baseline":0.7200558869962235,"withoutSource":0.7613870216897457,"change":0.04133113469352223},{"id":"gpt-5.6-terra--effort-medium","baseline":0.17966497894323227,"withoutSource":0.14187022277533554,"change":-0.03779475616789674}]},{"source":"ARC Prize","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"gemini-3.6-flash--effort-minimal","baseline":0.12326136435379197,"withoutSource":0.3037839934546713,"change":0.1805226291008793},{"id":"gpt-5--effort-low","baseline":0.07766638319251114,"withoutSource":0.1801545944711752,"change":0.10248821127866407},{"id":"grok-4.6--effort-medium","baseline":0.5960357182482909,"withoutSource":0.6956808783257035,"change":0.09964516007741253},{"id":"grok-4.5--effort-medium","baseline":0.32618923151353835,"withoutSource":0.4241774511141057,"change":0.09798821960056736},{"id":"kimi-k3--effort-high","baseline":0.364230262068402,"withoutSource":0.4609963572166876,"change":0.0967660951482856},{"id":"grok-4.5--effort-low","baseline":0.17654588924074235,"withoutSource":0.08060513699841783,"change":-0.09594075224232453},{"id":"gemini-3.7-flash--effort-low","baseline":0.4199521185670017,"withoutSource":0.508042254159506,"change":0.08809013559250428},{"id":"gemini-3.5-flash--effort-low","baseline":0.3951779988548216,"withoutSource":0.4804784311868295,"change":0.0853004323320079},{"id":"gpt-5.2--effort-medium","baseline":0.27568279262350615,"withoutSource":0.3585895017491058,"change":0.08290670912559966},{"id":"gpt-5.6-luna--effort-xhigh","baseline":0.4043653730313383,"withoutSource":0.4868802507616074,"change":0.08251487773026911}]},{"source":"Datacurve","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"gemini-3.8-flash--effort-medium","baseline":0.7002495102547243,"withoutSource":0.5552286423889249,"change":-0.14502086786579937},{"id":"glm-5.3-flash--effort-max","baseline":0.39031487577235063,"withoutSource":0.2726159578072232,"change":-0.11769891796512744},{"id":"glm-5.3--effort-max","baseline":0.5751539158922038,"withoutSource":0.477268999355972,"change":-0.09788491653623177},{"id":"kimi-k3--effort-max","baseline":0.6199710263061422,"withoutSource":0.5395860598243595,"change":-0.08038496648178273},{"id":"gemini-3.8-flash--effort-high","baseline":0.6889002380190533,"withoutSource":0.612811291908221,"change":-0.07608894611083228},{"id":"gpt-5.6-luna--effort-max","baseline":0.4074665735133989,"withoutSource":0.3362172446597223,"change":-0.07124932885367657},{"id":"grok-4.6--effort-xhigh","baseline":0.547225173220304,"withoutSource":0.47842899074336875,"change":-0.0687961824769352},{"id":"gpt-5.6-terra--effort-max","baseline":0.5473326004506027,"withoutSource":0.4792973861787824,"change":-0.0680352142718203},{"id":"grok-4.6--effort-medium","baseline":0.5960357182482909,"withoutSource":0.5338125506067563,"change":-0.06222316764153468},{"id":"gpt-5.6-terra--effort-xhigh","baseline":0.45622943003312894,"withoutSource":0.3953401028987196,"change":-0.06088932713440931}]},{"source":"LiveCodeBench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"o4-mini--effort-high","baseline":0.17672216851847145,"withoutSource":0.12076494584090712,"change":-0.055957222677564325},{"id":"claude-sonnet-4-5-20250929--effort-thinking-32k","baseline":0.1893336140090298,"withoutSource":0.1917731508733381,"change":0.0024395368643083115},{"id":"gpt-5.2--effort-high","baseline":0.2863072577355285,"withoutSource":0.2881936517361567,"change":0.0018863940006281776},{"id":"qwen3.8-flash-next--effort-reasoning","baseline":0.4070235787925161,"withoutSource":0.40528548670562303,"change":-0.0017380920868930727},{"id":"gemini-3.5-flash--effort-medium","baseline":0.3160782905658032,"withoutSource":0.3143626769177364,"change":-0.0017156136480668271},{"id":"gemini-3-flash-preview--effort-reasoning","baseline":0.30545878840274493,"withoutSource":0.30375474177761425,"change":-0.001704046625130684},{"id":"gemini-3.8-flash--effort-low","baseline":0.3919734880060828,"withoutSource":0.39032778474676655,"change":-0.0016457032593162335},{"id":"qwen-3.8-max--effort-reasoning","baseline":0.45155155035803135,"withoutSource":0.4499536924953504,"change":-0.0015978578626809625},{"id":"claude-opus-4-5-20251101--effort-reasoning","baseline":0.23493920596936355,"withoutSource":0.23335361608009142,"change":-0.0015855898892721265},{"id":"gpt-5.4--effort-low","baseline":0.23748306937651487,"withoutSource":0.23906373633008923,"change":0.0015806669535743667}]},{"source":"Scale","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-fable-5--effort-xhigh","baseline":0.6812306339389292,"withoutSource":0.7995324220587975,"change":0.11830178811986825},{"id":"claude-opus-5--effort-xhigh","baseline":0.7327225480424163,"withoutSource":0.6458218086311771,"change":-0.08690073941123921},{"id":"claude-opus-4-8--effort-xhigh","baseline":0.4898225268184147,"withoutSource":0.5481958074831454,"change":0.05837328066473074},{"id":"claude-opus-4-6--effort-max","baseline":0.42017033135830634,"withoutSource":0.38028449188044805,"change":-0.03988583947785829},{"id":"claude-fable-5-1--effort-xhigh","baseline":0.7526172333936344,"withoutSource":0.7143624504260996,"change":-0.03825478296753482},{"id":"claude-opus-4-6--effort-non-reasoning","baseline":0.15339627214044602,"withoutSource":0.18498032265547248,"change":0.03158405051502647},{"id":"claude-fable-5--effort-high","baseline":0.7395423399417836,"withoutSource":0.7088855692547634,"change":-0.03065677068702022},{"id":"gemini-3.1-pro--effort-high","baseline":0.36232959944541454,"withoutSource":0.3349972292827195,"change":-0.02733237016269502},{"id":"gemini-3.5-flash--effort-high","baseline":0.39848519209283234,"withoutSource":0.4204819913980125,"change":0.02199679930518017},{"id":"gpt-5.4--effort-xhigh","baseline":0.38312804209091134,"withoutSource":0.40442357563898385,"change":0.02129553354807251}]},{"source":"Terminal-Bench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"gemini-3.8-flash--effort-high","baseline":0.6889002380190533,"withoutSource":0.6302725090658288,"change":-0.058627728953224545},{"id":"gemini-3.7-flash--effort-high","baseline":0.5762273256525265,"withoutSource":0.630284741654397,"change":0.05405741600187042},{"id":"grok-4.6--effort-high","baseline":0.6242971525570876,"withoutSource":0.588357564597371,"change":-0.035939587959716635},{"id":"claude-sonnet-5--effort-max","baseline":0.38026735724676114,"withoutSource":0.41367464669521636,"change":0.033407289448455224},{"id":"claude-opus-5--effort-max","baseline":0.6903251978361186,"withoutSource":0.6597203696816206,"change":-0.030604828154497943},{"id":"gpt-5.6-luna--effort-max","baseline":0.4074665735133989,"withoutSource":0.43585686636824567,"change":0.028390292854846788},{"id":"claude-fable-5-1--effort-max","baseline":0.8576392906630036,"withoutSource":0.8331751980986746,"change":-0.02446409256432902},{"id":"grok-4.5--effort-high","baseline":0.37280852725243996,"withoutSource":0.3971049568437793,"change":0.02429642959133932},{"id":"claude-fable-5--effort-xhigh","baseline":0.6812306339389292,"withoutSource":0.6582002229372631,"change":-0.02303041100166614},{"id":"gpt-6-astra--effort-max","baseline":0.7761279033001186,"withoutSource":0.7542113865995833,"change":-0.021916516700535293}]},{"source":"Cognition","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"deepseek-v4-flash--effort-high","baseline":0.2406782058095042,"withoutSource":0.38836414709103934,"change":0.14768594128153514},{"id":"claude-opus-5--effort-medium","baseline":0.756588545187245,"withoutSource":0.639602636030431,"change":-0.11698590915681406},{"id":"claude-opus-5--effort-xhigh","baseline":0.7327225480424163,"withoutSource":0.8355450266985273,"change":0.10282247865611094},{"id":"grok-4.5--effort-low","baseline":0.17654588924074235,"withoutSource":0.26827687863462424,"change":0.09173098939388188},{"id":"claude-opus-4-6--effort-high","baseline":0.33226081076280295,"withoutSource":0.41370785521846604,"change":0.08144704445566309},{"id":"claude-opus-4-7--effort-xhigh","baseline":0.38240451476925225,"withoutSource":0.46107471744017503,"change":0.07867020267092278},{"id":"claude-fable-5--effort-medium","baseline":0.6902082179471911,"withoutSource":0.6158406777766143,"change":-0.07436754017057678},{"id":"gemini-3.7-flash--effort-medium","baseline":0.6008659847874989,"withoutSource":0.5276123855998012,"change":-0.0732535991876977},{"id":"claude-fable-5--effort-low","baseline":0.5548028564797248,"withoutSource":0.48248390494982624,"change":-0.07231895152989859},{"id":"claude-fable-5-1--effort-low","baseline":0.6552335291648791,"withoutSource":0.5832234091198014,"change":-0.07201012004507767}]},{"source":"LiveBench","disconnectedSupportedConfigurations":1,"largestScoreChanges":[{"id":"gemini-3.8-flash--effort-high","baseline":0.6889002380190533,"withoutSource":0.7426343511081316,"change":0.05373411308907827},{"id":"claude-sonnet-4-6--effort-medium","baseline":0.17140037618560014,"withoutSource":0.12360508790099896,"change":-0.04779528828460118},{"id":"claude-opus-5--effort-max","baseline":0.6903251978361186,"withoutSource":0.7237049832916836,"change":0.03337978545556508},{"id":"gpt-6-astra--effort-max","baseline":0.7761279033001186,"withoutSource":0.8042194782451136,"change":0.028091574944995035},{"id":"claude-fable-5--effort-max","baseline":0.6904521243576524,"withoutSource":0.7142579692828853,"change":0.023805844925232966},{"id":"gemini-3.7-flash--effort-high","baseline":0.5762273256525265,"withoutSource":0.5993803758857453,"change":0.023153050233218786},{"id":"gpt-5.6-luna--effort-max","baseline":0.4074665735133989,"withoutSource":0.43035109034499525,"change":0.02288451683159637},{"id":"claude-fable-5-1--effort-max","baseline":0.8576392906630036,"withoutSource":0.8790136999245393,"change":0.021374409261535665},{"id":"claude-opus-4-7--effort-xhigh","baseline":0.38240451476925225,"withoutSource":0.3624682915047454,"change":-0.019936223264506836},{"id":"gpt-5.4-nano--effort-xhigh","baseline":0.16482232269288688,"withoutSource":0.14504164515097645,"change":-0.01978067754191043}]},{"source":"SWE-rebench","disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"deepseek-v4-pro-0424--effort-high","baseline":0.14687571597873708,"withoutSource":0.28641711491349403,"change":0.13954139893475695},{"id":"gpt-5.3-codex--effort-xhigh","baseline":0.23025253409883203,"withoutSource":0.329654044929141,"change":0.09940151083030899},{"id":"gpt-5.2--effort-medium","baseline":0.27568279262350615,"withoutSource":0.21607183245153885,"change":-0.05961096017196729},{"id":"gpt-5.6-sol--effort-medium","baseline":0.47844941945122593,"withoutSource":0.523439332928047,"change":0.044989913476821075},{"id":"claude-fable-5--effort-high","baseline":0.7395423399417836,"withoutSource":0.7786883973229668,"change":0.03914605738118315},{"id":"claude-opus-4-7--effort-high","baseline":0.36866718089711087,"withoutSource":0.32975547080981954,"change":-0.03891171008729133},{"id":"claude-opus-4-8--effort-xhigh","baseline":0.4898225268184147,"withoutSource":0.452004486870951,"change":-0.03781803994746369},{"id":"claude-opus-5--effort-high","baseline":0.7242879139590591,"withoutSource":0.6883496208747713,"change":-0.035938293084287865},{"id":"gpt-5.5--effort-medium","baseline":0.460678236556126,"withoutSource":0.42612402747725714,"change":-0.03455420907886886},{"id":"claude-sonnet-5--effort-high","baseline":0.3145273975549942,"withoutSource":0.33691827249724643,"change":0.022390874942252226}]},{"source":"Epoch AI","disconnectedSupportedConfigurations":17,"largestScoreChanges":[{"id":"claude-opus-4-6--effort-low","baseline":0.11634139662190564,"withoutSource":0.23816848354188283,"change":0.12182708691997719},{"id":"claude-fable-5--effort-low","baseline":0.5548028564797248,"withoutSource":0.645509921904882,"change":0.09070706542515716},{"id":"claude-opus-5--effort-low","baseline":0.45044593109808845,"withoutSource":0.5265888852327422,"change":0.07614295413465372},{"id":"gemini-3-flash-preview--effort-high","baseline":0.2795032932263614,"withoutSource":0.20359506721918427,"change":-0.07590822600717714},{"id":"gemini-3.6-flash--effort-minimal","baseline":0.12326136435379197,"withoutSource":0.062082671658886195,"change":-0.06117869269490577},{"id":"claude-sonnet-4-6--effort-max","baseline":0.2322996393999656,"withoutSource":0.2896803900297999,"change":0.057380750629834304},{"id":"glm-5.3--effort-max","baseline":0.5751539158922038,"withoutSource":0.6321300598613101,"change":0.05697614396910633},{"id":"claude-sonnet-5--effort-max","baseline":0.38026735724676114,"withoutSource":0.43473704411324504,"change":0.0544696868664839},{"id":"claude-opus-4-6--effort-max","baseline":0.42017033135830634,"withoutSource":0.47412896054943393,"change":0.053958629191127594},{"id":"glm-5.3-flash--effort-max","baseline":0.39031487577235063,"withoutSource":0.43989431890040787,"change":0.04957944312805723}]},{"source":"Vals AI","disconnectedSupportedConfigurations":1,"largestScoreChanges":[{"id":"gemini-3-flash-preview--effort-high","baseline":0.2795032932263614,"withoutSource":0.34118990001308,"change":0.06168660678671861},{"id":"deepseek-v4-flash--effort-high","baseline":0.2406782058095042,"withoutSource":0.18368040451890186,"change":-0.056997801290602335},{"id":"claude-sonnet-5--effort-max","baseline":0.38026735724676114,"withoutSource":0.33006659982783804,"change":-0.0502007574189231},{"id":"claude-opus-4-7--effort-max","baseline":0.3578778505154514,"withoutSource":0.31520314588151327,"change":-0.04267470463393813},{"id":"claude-opus-4-8--effort-max","baseline":0.5154012816616055,"withoutSource":0.48452605195094006,"change":-0.03087522971066542},{"id":"claude-sonnet-4-6--effort-max","baseline":0.2322996393999656,"withoutSource":0.20150198059639657,"change":-0.030797658803569022},{"id":"muse-spark-1.1--effort-xhigh","baseline":0.41129890156180154,"withoutSource":0.385571987709546,"change":-0.025726913852255562},{"id":"grok-4.3--effort-high","baseline":0.18441296084940173,"withoutSource":0.20998963682659144,"change":0.02557667597718971},{"id":"muse-spark-1.2--effort-xhigh","baseline":0.4560441657225609,"withoutSource":0.4324996935135701,"change":-0.023544472208990808},{"id":"claude-fable-5-1--effort-high","baseline":0.7221616261433992,"withoutSource":0.6999268848746776,"change":-0.022234741268721603}]},{"source":"Provider reports · Anthropic","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-fable-5-1--effort-max","baseline":0.8576392906630036,"withoutSource":0.7901859676644677,"change":-0.0674533229985359},{"id":"claude-fable-5--effort-max","baseline":0.6904521243576524,"withoutSource":0.7339882003249446,"change":0.043536075967292254},{"id":"claude-opus-5--effort-max","baseline":0.6903251978361186,"withoutSource":0.7094015110432176,"change":0.019076313207099016},{"id":"gpt-6-astra--effort-max","baseline":0.7761279033001186,"withoutSource":0.7751353973605654,"change":-0.0009925059395532454},{"id":"claude-fable-5-1--effort-high","baseline":0.7221616261433992,"withoutSource":0.7230938385509614,"change":0.0009322124075622495},{"id":"claude-fable-5--effort-medium","baseline":0.6902082179471911,"withoutSource":0.6892856890392268,"change":-0.0009225289079642929},{"id":"claude-fable-5-1--effort-medium","baseline":0.7078792508208632,"withoutSource":0.7087960875883242,"change":0.0009168367674610156},{"id":"glm-5.3--effort-max","baseline":0.5751539158922038,"withoutSource":0.5742675190067484,"change":-0.0008863968854553317},{"id":"claude-fable-5-1--effort-low","baseline":0.6552335291648791,"withoutSource":0.6561031170697236,"change":0.0008695879048444821},{"id":"claude-fable-5--effort-high","baseline":0.7395423399417836,"withoutSource":0.7386847538805101,"change":-0.0008575860612735076}]},{"source":"Provider reports · Moonshot AI","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"kimi-k3--effort-max","baseline":0.6199710263061422,"withoutSource":0.5339143447398257,"change":-0.08605668156631652},{"id":"gpt-5.5--effort-xhigh","baseline":0.5486217356893452,"withoutSource":0.6103088906975455,"change":0.06168715500820021},{"id":"glm-5.2--effort-max","baseline":0.29149981365172783,"withoutSource":0.3110752199653872,"change":0.019575406313659338},{"id":"claude-opus-4-8--effort-max","baseline":0.5154012816616055,"withoutSource":0.5056996130612667,"change":-0.00970166860033883},{"id":"gpt-5.6-sol--effort-max","baseline":0.698487650282616,"withoutSource":0.6919432492367065,"change":-0.006544401045909476},{"id":"gpt-6-astra--effort-xhigh","baseline":0.8305846911657017,"withoutSource":0.8353692414915912,"change":0.004784550325889536},{"id":"gpt-5.4--effort-xhigh","baseline":0.38312804209091134,"withoutSource":0.3864368646941414,"change":0.003308822603230066},{"id":"gpt-5.6-sol--effort-xhigh","baseline":0.7200558869962235,"withoutSource":0.7232396999634106,"change":0.0031838129671871718},{"id":"claude-opus-4-7--effort-high","baseline":0.36866718089711087,"withoutSource":0.370935950763599,"change":0.0022687698664881073},{"id":"glm-5.3--effort-max","baseline":0.5751539158922038,"withoutSource":0.5732655919622561,"change":-0.001888323929947644}]},{"source":"Provider reports · Meta","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"muse-spark-1.3--effort-xhigh","baseline":0.7034116319092588,"withoutSource":0.6193723324429602,"change":-0.08403929946629862},{"id":"muse-spark-1.2--effort-xhigh","baseline":0.4560441657225609,"withoutSource":0.5044923660203685,"change":0.04844820029780761},{"id":"claude-opus-4-5-20251101--effort-thinking-64k","baseline":0.2932907782775482,"withoutSource":0.2911267792925788,"change":-0.002163998984969384},{"id":"qwen-3.8-max--effort-xhigh","baseline":0.4987155368393635,"withoutSource":0.4998013888131925,"change":0.001085851973829044},{"id":"gpt-5.2--effort-high","baseline":0.2863072577355285,"withoutSource":0.28523298747303266,"change":-0.0010742702624958467},{"id":"gpt-6-astra--effort-max","baseline":0.7761279033001186,"withoutSource":0.7752225872993419,"change":-0.0009053160007767014},{"id":"claude-opus-5--effort-max","baseline":0.6903251978361186,"withoutSource":0.6894836527379429,"change":-0.0008415450981756889},{"id":"claude-fable-5--effort-max","baseline":0.6904521243576524,"withoutSource":0.6896221335680766,"change":-0.0008299907895757963},{"id":"claude-fable-5-1--effort-high","baseline":0.7221616261433992,"withoutSource":0.721371441334329,"change":-0.0007901848090702268},{"id":"claude-opus-4-5-20251101--effort-thinking-32k","baseline":0.210410723714046,"withoutSource":0.21114971951556238,"change":0.0007389958015163733}]},{"source":"Provider reports · Mistral","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"claude-fable-5-1--effort-max","baseline":0.8576392906630036,"withoutSource":0.8576392906630036,"change":0},{"id":"gpt-6-astra--effort-xhigh","baseline":0.8305846911657017,"withoutSource":0.8305846911657017,"change":0},{"id":"gpt-6-astra--effort-high","baseline":0.8083096377180565,"withoutSource":0.8083096377180565,"change":0},{"id":"gpt-6-astra--effort-medium","baseline":0.796076035284861,"withoutSource":0.796076035284861,"change":0},{"id":"gpt-6-astra--effort-max","baseline":0.7761279033001186,"withoutSource":0.7761279033001186,"change":0},{"id":"claude-opus-5--effort-medium","baseline":0.756588545187245,"withoutSource":0.756588545187245,"change":0},{"id":"claude-fable-5-1--effort-xhigh","baseline":0.7526172333936344,"withoutSource":0.7526172333936344,"change":0},{"id":"claude-fable-5--effort-high","baseline":0.7395423399417836,"withoutSource":0.7395423399417836,"change":0},{"id":"claude-opus-5--effort-xhigh","baseline":0.7327225480424163,"withoutSource":0.7327225480424163,"change":0},{"id":"claude-opus-5--effort-high","baseline":0.7242879139590591,"withoutSource":0.7242879139590591,"change":0}]},{"source":"All provider reports","independent":false,"disconnectedSupportedConfigurations":0,"largestScoreChanges":[{"id":"kimi-k3--effort-max","baseline":0.6199710263061422,"withoutSource":0.5344327625071074,"change":-0.08553826379903484},{"id":"muse-spark-1.3--effort-xhigh","baseline":0.7034116319092588,"withoutSource":0.6187710107021112,"change":-0.08464062120714766},{"id":"claude-fable-5-1--effort-max","baseline":0.8576392906630036,"withoutSource":0.7883941516399734,"change":-0.0692451390230302},{"id":"gpt-5.5--effort-xhigh","baseline":0.5486217356893452,"withoutSource":0.6095334329042226,"change":0.060911697214877325},{"id":"muse-spark-1.2--effort-xhigh","baseline":0.4560441657225609,"withoutSource":0.5032507685802451,"change":0.04720660285768419},{"id":"claude-fable-5--effort-max","baseline":0.6904521243576524,"withoutSource":0.7318843773485036,"change":0.04143225299085129},{"id":"glm-5.2--effort-max","baseline":0.29149981365172783,"withoutSource":0.31107874747217346,"change":0.01957893382044562},{"id":"claude-opus-5--effort-max","baseline":0.6903251978361186,"withoutSource":0.707544613481727,"change":0.01721941564560847},{"id":"claude-opus-4-8--effort-max","baseline":0.5154012816616055,"withoutSource":0.5061143256822513,"change":-0.009286955979354139},{"id":"gpt-5.6-sol--effort-max","baseline":0.698487650282616,"withoutSource":0.6907297345684933,"change":-0.007757915714122654}]}],"configurationStability":{"claude-fable-5-1--effort-max":{"score":0.8576392906630036,"rank":1,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8576165129834599,"rank":2,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.861541578093568,"rank":1,"remainingConfigurations":398},{"removed":"Datacurve","score":0.8411106546031114,"rank":1,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.8576386129171073,"rank":1,"remainingConfigurations":398},{"removed":"Scale","score":0.8608062168176902,"rank":1,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.8331751980986746,"rank":1,"remainingConfigurations":398},{"removed":"Cognition","score":0.8671321853352688,"rank":1,"remainingConfigurations":398},{"removed":"LiveBench","score":0.8790136999245393,"rank":1,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.8556878266830422,"rank":1,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.8654607096863872,"rank":1,"remainingConfigurations":381},{"removed":"Vals AI","score":0.8522757343715853,"rank":1,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7901859676644677,"rank":4,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.8569401061113603,"rank":1,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.856972385040938,"rank":1,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.8576392906630036,"rank":1,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7883941516399734,"rank":4,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.8570233552493803,"rank":1,"remainingConfigurations":398},{"removed":"briefcase","score":0.8572565040822937,"rank":1,"remainingConfigurations":398},{"removed":"aime","score":0.8563097114483825,"rank":1,"remainingConfigurations":398},{"removed":"apex-agents","score":0.8577525339442896,"rank":1,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.8572347237883674,"rank":1,"remainingConfigurations":398},{"removed":"automationbench","score":0.8577469554425484,"rank":1,"remainingConfigurations":398},{"removed":"critpt","score":0.8584929674087891,"rank":1,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.8575611291975164,"rank":1,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.8586713090323932,"rank":1,"remainingConfigurations":398},{"removed":"gdpval","score":0.8575570552642501,"rank":1,"remainingConfigurations":398},{"removed":"gmmlu","score":0.8576851569165829,"rank":1,"remainingConfigurations":398},{"removed":"gpqa","score":0.8599390631166197,"rank":1,"remainingConfigurations":398},{"removed":"harvey","score":0.8637210328717276,"rank":1,"remainingConfigurations":398},{"removed":"hle","score":0.857865358026009,"rank":1,"remainingConfigurations":398},{"removed":"ifbench","score":0.8566971816317848,"rank":1,"remainingConfigurations":398},{"removed":"itbench","score":0.8575033330654013,"rank":1,"remainingConfigurations":398},{"removed":"livecodebench","score":0.857699391587566,"rank":1,"remainingConfigurations":398},{"removed":"math500","score":0.8576860784329498,"rank":1,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.8568697674022873,"rank":1,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.8606944481601785,"rank":1,"remainingConfigurations":398},{"removed":"omniscience","score":0.8584748941023143,"rank":1,"remainingConfigurations":398},{"removed":"scicode","score":0.85779576902575,"rank":1,"remainingConfigurations":398},{"removed":"tau-bench","score":0.8566409394345597,"rank":1,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.8335132548520385,"rank":1,"remainingConfigurations":398},{"removed":"arc-agi","score":0.8612381968491164,"rank":1,"remainingConfigurations":398},{"removed":"deepswe","score":0.8413110478394191,"rank":1,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.8576525189712424,"rank":1,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.8557753987057652,"rank":1,"remainingConfigurations":398},{"removed":"frontiercode","score":0.8671321853352688,"rank":1,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.8578605449576274,"rank":1,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.856467991153846,"rank":1,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.857549366720534,"rank":1,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.8563539043701928,"rank":1,"remainingConfigurations":398},{"removed":"livebench-math","score":0.8549235994162455,"rank":1,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.8544012088243477,"rank":1,"remainingConfigurations":398},{"removed":"livebench-language","score":0.85768333532372,"rank":1,"remainingConfigurations":398},{"removed":"livebench-data","score":0.8623334186748887,"rank":1,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.8543163522883134,"rank":1,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.8576621790939288,"rank":1,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.8621360403087497,"rank":1,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.8556878266830422,"rank":1,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.8581809295402495,"rank":1,"remainingConfigurations":398},{"removed":"frontiermath","score":0.8553460816813107,"rank":1,"remainingConfigurations":398},{"removed":"simpleqa","score":0.8594780060985195,"rank":1,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.8589149677465251,"rank":1,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.8567084119577094,"rank":1,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.854780959605303,"rank":1,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.8548885569074066,"rank":1,"remainingConfigurations":398},{"removed":"vibe-code","score":0.8558833826167279,"rank":1,"remainingConfigurations":398}]},"gpt-6-astra--effort-xhigh":{"score":0.8305846911657017,"rank":2,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8595234857780367,"rank":1,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.8388871831572983,"rank":2,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7948621590824653,"rank":2,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.8305227390287252,"rank":2,"remainingConfigurations":398},{"removed":"Scale","score":0.8220536402946806,"rank":2,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.8282907819106432,"rank":2,"remainingConfigurations":398},{"removed":"Cognition","score":0.8331096821194293,"rank":3,"remainingConfigurations":398},{"removed":"LiveBench","score":0.8352658860816078,"rank":2,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.8289495187173537,"rank":2,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.8316713607682845,"rank":2,"remainingConfigurations":381},{"removed":"Vals AI","score":0.8319594558410796,"rank":2,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.8306541741472137,"rank":1,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.8353692414915912,"rank":2,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.8305031727052293,"rank":2,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.8305846911657017,"rank":2,"remainingConfigurations":398},{"removed":"All provider reports","score":0.8353022697921428,"rank":1,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.8305714718178039,"rank":2,"remainingConfigurations":398},{"removed":"briefcase","score":0.8304292981987093,"rank":2,"remainingConfigurations":398},{"removed":"aime","score":0.8301322859052692,"rank":2,"remainingConfigurations":398},{"removed":"apex-agents","score":0.8306561422369979,"rank":2,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.8318025247249502,"rank":2,"remainingConfigurations":398},{"removed":"automationbench","score":0.8294430520767566,"rank":2,"remainingConfigurations":398},{"removed":"critpt","score":0.8312343327482475,"rank":2,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.8306271355965881,"rank":2,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.8299874387592584,"rank":2,"remainingConfigurations":398},{"removed":"gdpval","score":0.8317991131483069,"rank":2,"remainingConfigurations":398},{"removed":"gmmlu","score":0.8305195821315688,"rank":2,"remainingConfigurations":398},{"removed":"gpqa","score":0.8290962037876016,"rank":2,"remainingConfigurations":398},{"removed":"harvey","score":0.8307313958170769,"rank":2,"remainingConfigurations":398},{"removed":"hle","score":0.8322359979999429,"rank":2,"remainingConfigurations":398},{"removed":"ifbench","score":0.8293156609214957,"rank":2,"remainingConfigurations":398},{"removed":"itbench","score":0.8304060060572996,"rank":2,"remainingConfigurations":398},{"removed":"livecodebench","score":0.830441682111605,"rank":2,"remainingConfigurations":398},{"removed":"math500","score":0.830541359709598,"rank":2,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.8325192567452911,"rank":2,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.8340875971095226,"rank":2,"remainingConfigurations":398},{"removed":"omniscience","score":0.8312422326875445,"rank":2,"remainingConfigurations":398},{"removed":"scicode","score":0.8320969376546253,"rank":2,"remainingConfigurations":398},{"removed":"tau-bench","score":0.8304463298603283,"rank":2,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.8290155484137852,"rank":2,"remainingConfigurations":398},{"removed":"arc-agi","score":0.8473882679257135,"rank":2,"remainingConfigurations":398},{"removed":"deepswe","score":0.7941827460452915,"rank":2,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.8304031328750208,"rank":2,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.8230948929768784,"rank":2,"remainingConfigurations":398},{"removed":"frontiercode","score":0.8331096821194293,"rank":3,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.8306791938783933,"rank":2,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.8324981177108866,"rank":2,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.8282065886859815,"rank":2,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.8279166193232602,"rank":2,"remainingConfigurations":398},{"removed":"livebench-math","score":0.8309102252437466,"rank":2,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.829827717857427,"rank":2,"remainingConfigurations":398},{"removed":"livebench-language","score":0.8311195290123307,"rank":2,"remainingConfigurations":398},{"removed":"livebench-data","score":0.8305554088753785,"rank":2,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.8297362660126016,"rank":2,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.82999200918509,"rank":2,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.8319463706822412,"rank":2,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.8289495187173537,"rank":2,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.8288450224986899,"rank":2,"remainingConfigurations":398},{"removed":"frontiermath","score":0.8259542882593237,"rank":2,"remainingConfigurations":398},{"removed":"simpleqa","score":0.8338185461686494,"rank":2,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.8304839592431715,"rank":2,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.8300279998666403,"rank":2,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.8299794251598424,"rank":2,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.8301167058307896,"rank":2,"remainingConfigurations":398},{"removed":"vibe-code","score":0.8300753280758421,"rank":2,"remainingConfigurations":398}]},"gpt-6-astra--effort-high":{"score":0.8083096377180565,"rank":3,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8429228272424307,"rank":3,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.8154721847639909,"rank":3,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7671700244895302,"rank":3,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.8082458880465255,"rank":3,"remainingConfigurations":398},{"removed":"Scale","score":0.8131195955261443,"rank":3,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.805597326689932,"rank":3,"remainingConfigurations":398},{"removed":"Cognition","score":0.8022340674460381,"rank":4,"remainingConfigurations":398},{"removed":"LiveBench","score":0.8133953776611701,"rank":3,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.8071111855756947,"rank":3,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.8095759307582786,"rank":3,"remainingConfigurations":381},{"removed":"Vals AI","score":0.8075196198089071,"rank":3,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.8084004618829667,"rank":2,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.8088913641447147,"rank":3,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.8082375122356503,"rank":3,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.8083096377180565,"rank":3,"remainingConfigurations":398},{"removed":"All provider reports","score":0.808879394041881,"rank":2,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.8083229678074545,"rank":3,"remainingConfigurations":398},{"removed":"briefcase","score":0.8080408348346223,"rank":3,"remainingConfigurations":398},{"removed":"aime","score":0.8074723996684366,"rank":3,"remainingConfigurations":398},{"removed":"apex-agents","score":0.8085506762942948,"rank":3,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.8099279916379373,"rank":3,"remainingConfigurations":398},{"removed":"automationbench","score":0.8067131774318312,"rank":3,"remainingConfigurations":398},{"removed":"critpt","score":0.8097105920266617,"rank":3,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.8082725732726755,"rank":3,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.8072306216305855,"rank":3,"remainingConfigurations":398},{"removed":"gdpval","score":0.8096520143076518,"rank":3,"remainingConfigurations":398},{"removed":"gmmlu","score":0.8080793004765553,"rank":3,"remainingConfigurations":398},{"removed":"gpqa","score":0.8074323151018401,"rank":3,"remainingConfigurations":398},{"removed":"harvey","score":0.8078804996722546,"rank":3,"remainingConfigurations":398},{"removed":"hle","score":0.810443433714653,"rank":3,"remainingConfigurations":398},{"removed":"ifbench","score":0.8066504423916429,"rank":3,"remainingConfigurations":398},{"removed":"itbench","score":0.8080527099320022,"rank":3,"remainingConfigurations":398},{"removed":"livecodebench","score":0.8079184620700989,"rank":3,"remainingConfigurations":398},{"removed":"math500","score":0.808150594372647,"rank":3,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.810360925703673,"rank":3,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.8122814017530606,"rank":3,"remainingConfigurations":398},{"removed":"omniscience","score":0.8091245406181464,"rank":3,"remainingConfigurations":398},{"removed":"scicode","score":0.8100126130099424,"rank":3,"remainingConfigurations":398},{"removed":"tau-bench","score":0.8085721358772059,"rank":3,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.8045966551672353,"rank":3,"remainingConfigurations":398},{"removed":"arc-agi","score":0.8295268919122126,"rank":3,"remainingConfigurations":398},{"removed":"deepswe","score":0.7668600914114783,"rank":3,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.8083371267608689,"rank":3,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7976132124230343,"rank":3,"remainingConfigurations":398},{"removed":"frontiercode","score":0.8022340674460381,"rank":4,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.8086379771014647,"rank":3,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.8060857642790116,"rank":3,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.8083112290311699,"rank":3,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.8073859226297081,"rank":3,"remainingConfigurations":398},{"removed":"livebench-math","score":0.8085272653692792,"rank":3,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.8074758822859222,"rank":3,"remainingConfigurations":398},{"removed":"livebench-language","score":0.8091126795418905,"rank":3,"remainingConfigurations":398},{"removed":"livebench-data","score":0.8084971353886808,"rank":3,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.8071525768433135,"rank":3,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.8076191964017125,"rank":3,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.8097673646572362,"rank":3,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.8071111855756947,"rank":3,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.8065111088250204,"rank":3,"remainingConfigurations":398},{"removed":"frontiermath","score":0.8044271406404606,"rank":3,"remainingConfigurations":398},{"removed":"simpleqa","score":0.8121588914341622,"rank":3,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.8081063146718434,"rank":3,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.8078989164370257,"rank":3,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.8077859875740995,"rank":3,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.8079250573473322,"rank":3,"remainingConfigurations":398},{"removed":"vibe-code","score":0.807714662424423,"rank":3,"remainingConfigurations":398}]},"gpt-6-astra--effort-medium":{"score":0.796076035284861,"rank":4,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8320814799776648,"rank":4,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.8001673029798825,"rank":4,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7544773423608877,"rank":4,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7960097487301697,"rank":4,"remainingConfigurations":398},{"removed":"Scale","score":0.8012788277309958,"rank":4,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7927109542165373,"rank":4,"remainingConfigurations":398},{"removed":"Cognition","score":0.7937040763665905,"rank":5,"remainingConfigurations":398},{"removed":"LiveBench","score":0.8007097024760103,"rank":5,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7948815582790889,"rank":4,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7974248674168073,"rank":4,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7945542402894522,"rank":5,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7961770445577917,"rank":3,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7966863606301904,"rank":4,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7960046193084094,"rank":4,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.796076035284861,"rank":4,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7966840982793993,"rank":3,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7960726785540784,"rank":4,"remainingConfigurations":398},{"removed":"briefcase","score":0.7959896572680861,"rank":4,"remainingConfigurations":398},{"removed":"aime","score":0.7952360712924559,"rank":4,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7963313383788063,"rank":4,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7977880060772414,"rank":4,"remainingConfigurations":398},{"removed":"automationbench","score":0.7942205275167712,"rank":4,"remainingConfigurations":398},{"removed":"critpt","score":0.7972967327321155,"rank":4,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7960070487318346,"rank":4,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7947639658873764,"rank":4,"remainingConfigurations":398},{"removed":"gdpval","score":0.7974626567503124,"rank":4,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7958505343194543,"rank":4,"remainingConfigurations":398},{"removed":"gpqa","score":0.7952116320817794,"rank":4,"remainingConfigurations":398},{"removed":"harvey","score":0.7955770152096612,"rank":4,"remainingConfigurations":398},{"removed":"hle","score":0.7982145179520189,"rank":4,"remainingConfigurations":398},{"removed":"ifbench","score":0.7943641009577274,"rank":4,"remainingConfigurations":398},{"removed":"itbench","score":0.7958018545188738,"rank":4,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7956900858199334,"rank":4,"remainingConfigurations":398},{"removed":"math500","score":0.7959215350390711,"rank":4,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7982770461664295,"rank":4,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.800217989024,"rank":4,"remainingConfigurations":398},{"removed":"omniscience","score":0.7967447055712751,"rank":4,"remainingConfigurations":398},{"removed":"scicode","score":0.7982184431225963,"rank":4,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7968189469185614,"rank":4,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7916675328520889,"rank":4,"remainingConfigurations":398},{"removed":"arc-agi","score":0.818068124612902,"rank":4,"remainingConfigurations":398},{"removed":"deepswe","score":0.7541616751012746,"rank":4,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7961039896731109,"rank":4,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7851880960558462,"rank":4,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7937040763665905,"rank":5,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7964355737826212,"rank":4,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7937538281575106,"rank":4,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7960695830979634,"rank":4,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7951437439121044,"rank":4,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7963085117295418,"rank":4,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7951966188309871,"rank":4,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7969299457562049,"rank":4,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7962654512542207,"rank":4,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.794848991431513,"rank":4,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7953497981223713,"rank":4,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7976153528783466,"rank":4,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7948815582790889,"rank":4,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7942689672094364,"rank":4,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7923279040134362,"rank":4,"remainingConfigurations":398},{"removed":"simpleqa","score":0.8001669836567284,"rank":4,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7958500241582488,"rank":4,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7956425235012135,"rank":4,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7955300516194203,"rank":4,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7956744139337935,"rank":4,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7954483444089394,"rank":4,"remainingConfigurations":398}]},"gpt-6-astra--effort-max":{"score":0.7761279033001186,"rank":5,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7836933926851071,"rank":6,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7819259271600689,"rank":5,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7377909273377666,"rank":7,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7760838727560339,"rank":5,"remainingConfigurations":398},{"removed":"Scale","score":0.7810504652768402,"rank":6,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7542113865995833,"rank":6,"remainingConfigurations":398},{"removed":"Cognition","score":0.7727392025222833,"rank":7,"remainingConfigurations":398},{"removed":"LiveBench","score":0.8042194782451136,"rank":4,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7734485532931469,"rank":6,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.77303099835623,"rank":6,"remainingConfigurations":381},{"removed":"Vals AI","score":0.797687894152716,"rank":4,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7751353973605654,"rank":5,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7762455551413536,"rank":5,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7752225872993419,"rank":5,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7761279033001186,"rank":5,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7743115734025737,"rank":5,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.775694200825814,"rank":5,"remainingConfigurations":398},{"removed":"briefcase","score":0.775824767053448,"rank":5,"remainingConfigurations":398},{"removed":"aime","score":0.7772446384585922,"rank":5,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7762385329826174,"rank":5,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7766041187526671,"rank":5,"remainingConfigurations":398},{"removed":"automationbench","score":0.7752407655356294,"rank":5,"remainingConfigurations":398},{"removed":"critpt","score":0.7765826689213834,"rank":5,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7763819465253973,"rank":5,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7763120240780504,"rank":5,"remainingConfigurations":398},{"removed":"gdpval","score":0.7765803878990093,"rank":5,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7762015584314956,"rank":5,"remainingConfigurations":398},{"removed":"gpqa","score":0.7763525847047363,"rank":5,"remainingConfigurations":398},{"removed":"harvey","score":0.7831509365564505,"rank":5,"remainingConfigurations":398},{"removed":"hle","score":0.7772377938210152,"rank":5,"remainingConfigurations":398},{"removed":"ifbench","score":0.7748504182331734,"rank":5,"remainingConfigurations":398},{"removed":"itbench","score":0.7758433092710573,"rank":5,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7761584988529008,"rank":5,"remainingConfigurations":398},{"removed":"math500","score":0.776184095126483,"rank":5,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7784864472824612,"rank":5,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7801130797646724,"rank":5,"remainingConfigurations":398},{"removed":"omniscience","score":0.7770321815520926,"rank":5,"remainingConfigurations":398},{"removed":"scicode","score":0.7767785110260682,"rank":5,"remainingConfigurations":398},{"removed":"tau-bench","score":0.775413397933932,"rank":5,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7480179151209997,"rank":7,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7912582798539346,"rank":5,"remainingConfigurations":398},{"removed":"deepswe","score":0.7373688358882012,"rank":7,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7761390703842724,"rank":5,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7721792039226966,"rank":5,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7727392025222833,"rank":7,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7763667837441885,"rank":5,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7742421501492028,"rank":6,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7758818620120418,"rank":5,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7750590589665033,"rank":5,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7750342927350601,"rank":5,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7779929645330702,"rank":5,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7765181560038231,"rank":5,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7730569385755593,"rank":5,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.778074621217342,"rank":5,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7744235571075665,"rank":5,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7779258622384687,"rank":5,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7734485532931469,"rank":6,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7743137914891077,"rank":5,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7748623954004374,"rank":5,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7771991405544484,"rank":5,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7840667377553953,"rank":5,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7694464508459659,"rank":5,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.78044858813446,"rank":5,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7728397840782258,"rank":5,"remainingConfigurations":398},{"removed":"vibe-code","score":0.770703717530605,"rank":5,"remainingConfigurations":398}]},"claude-opus-5--effort-medium":{"score":0.756588545187245,"rank":6,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.8159976838333668,"rank":5,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7658956900728731,"rank":6,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7531473112492585,"rank":5,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7564988746718585,"rank":6,"remainingConfigurations":398},{"removed":"Scale","score":0.7640513297732255,"rank":7,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7555262304240333,"rank":5,"remainingConfigurations":398},{"removed":"Cognition","score":0.639602636030431,"rank":23,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7594647602083859,"rank":6,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7549459997012171,"rank":7,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7715558075885661,"rank":7,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7519095923137084,"rank":6,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7559096957503636,"rank":6,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7559847833083732,"rank":6,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7564806247048682,"rank":6,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.756588545187245,"rank":6,"remainingConfigurations":398},{"removed":"All provider reports","score":0.755183677173226,"rank":6,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7564092595400923,"rank":6,"remainingConfigurations":398},{"removed":"briefcase","score":0.7561735426851213,"rank":6,"remainingConfigurations":398},{"removed":"aime","score":0.7531728094134632,"rank":6,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7569603764229589,"rank":6,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7557057761049659,"rank":6,"remainingConfigurations":398},{"removed":"automationbench","score":0.7578093166007398,"rank":6,"remainingConfigurations":398},{"removed":"critpt","score":0.7574009032444423,"rank":6,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7559569946046066,"rank":6,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7583569118493182,"rank":6,"remainingConfigurations":398},{"removed":"gdpval","score":0.757400015983483,"rank":6,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7560934487050966,"rank":6,"remainingConfigurations":398},{"removed":"gpqa","score":0.7600630140614509,"rank":6,"remainingConfigurations":398},{"removed":"harvey","score":0.7552142146583941,"rank":6,"remainingConfigurations":398},{"removed":"hle","score":0.7592293333673569,"rank":7,"remainingConfigurations":398},{"removed":"ifbench","score":0.7525327961414301,"rank":6,"remainingConfigurations":398},{"removed":"itbench","score":0.7561958720965851,"rank":6,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7554761320663234,"rank":6,"remainingConfigurations":398},{"removed":"math500","score":0.7560667740873113,"rank":6,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7578601241461264,"rank":6,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7641221439342517,"rank":6,"remainingConfigurations":398},{"removed":"omniscience","score":0.7577843293967216,"rank":6,"remainingConfigurations":398},{"removed":"scicode","score":0.7610692951686846,"rank":6,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7548344703006241,"rank":6,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7556180527213492,"rank":5,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7686830181779009,"rank":6,"remainingConfigurations":398},{"removed":"deepswe","score":0.7533536574839667,"rank":5,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7566292861360039,"rank":6,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7545178520786234,"rank":6,"remainingConfigurations":398},{"removed":"frontiercode","score":0.639602636030431,"rank":23,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.75599723487408,"rank":6,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7544764082442903,"rank":7,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7555582225061613,"rank":6,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7549047507394494,"rank":7,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7564234169943781,"rank":6,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7550428487234092,"rank":6,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7579230293695284,"rank":6,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7574266565510596,"rank":6,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7551425068535144,"rank":6,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.755597473338092,"rank":6,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7585446320965551,"rank":6,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7549459997012171,"rank":7,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7574205938972938,"rank":6,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7557036159579794,"rank":6,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7581473256133732,"rank":7,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7564377555551646,"rank":6,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7563133983428129,"rank":6,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.75593111630792,"rank":6,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7563013922749571,"rank":6,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7558397404535978,"rank":6,"remainingConfigurations":398}]},"claude-fable-5-1--effort-xhigh":{"score":0.7526172333936344,"rank":7,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.758029701679051,"rank":8,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7537932186065704,"rank":7,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7446707252347732,"rank":6,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7526223885286066,"rank":7,"remainingConfigurations":398},{"removed":"Scale","score":0.7143624504260996,"rank":11,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7539540764817133,"rank":7,"remainingConfigurations":398},{"removed":"Cognition","score":0.7624812512443494,"rank":8,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7512536536253598,"rank":7,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.751534590588039,"rank":8,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7673092556458179,"rank":8,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7440511245694509,"rank":7,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7532678551183875,"rank":7,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7520266053696304,"rank":7,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7523788901330315,"rank":7,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7526172333936344,"rank":7,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7524314199805467,"rank":7,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7526500867169766,"rank":7,"remainingConfigurations":398},{"removed":"briefcase","score":0.7515112224236214,"rank":7,"remainingConfigurations":398},{"removed":"aime","score":0.7504917100942258,"rank":7,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7529121382364438,"rank":7,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7536350183184819,"rank":7,"remainingConfigurations":398},{"removed":"automationbench","score":0.753600053770088,"rank":7,"remainingConfigurations":398},{"removed":"critpt","score":0.756062436014514,"rank":7,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7524950163569724,"rank":7,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7540206336233491,"rank":7,"remainingConfigurations":398},{"removed":"gdpval","score":0.7528169469646141,"rank":7,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7518825229123086,"rank":7,"remainingConfigurations":398},{"removed":"gpqa","score":0.7551210715982504,"rank":8,"remainingConfigurations":398},{"removed":"harvey","score":0.7517086443258671,"rank":7,"remainingConfigurations":398},{"removed":"hle","score":0.7712754396736554,"rank":6,"remainingConfigurations":398},{"removed":"ifbench","score":0.7504975159674364,"rank":7,"remainingConfigurations":398},{"removed":"itbench","score":0.7523904410796766,"rank":7,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7519724236195402,"rank":7,"remainingConfigurations":398},{"removed":"math500","score":0.7522307363740333,"rank":7,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7539664805340299,"rank":7,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7570680287583561,"rank":7,"remainingConfigurations":398},{"removed":"omniscience","score":0.7530497374273567,"rank":7,"remainingConfigurations":398},{"removed":"scicode","score":0.7531298276157891,"rank":7,"remainingConfigurations":398},{"removed":"tau-bench","score":0.751481478679512,"rank":7,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7531866994557485,"rank":6,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7534794635668404,"rank":8,"remainingConfigurations":398},{"removed":"deepswe","score":0.744812142319495,"rank":6,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7526429473991308,"rank":7,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7505500556019186,"rank":7,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7624812512443494,"rank":8,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7452393973938795,"rank":8,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7745950990891245,"rank":5,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7074756690901628,"rank":13,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7629498707986465,"rank":6,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7524926243736237,"rank":7,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7513647296252263,"rank":7,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7537066921986827,"rank":7,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7531916299428447,"rank":7,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7513210491782814,"rank":7,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7518071209058667,"rank":7,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7544055949773175,"rank":7,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.751534590588039,"rank":8,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7521714432345331,"rank":7,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7535048946258422,"rank":7,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7616439277589792,"rank":6,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7525533368724232,"rank":7,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7522542674207778,"rank":7,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.75204774284057,"rank":7,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7523674695960878,"rank":7,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7519258187939503,"rank":7,"remainingConfigurations":398}]},"claude-fable-5--effort-high":{"score":0.7395423399417836,"rank":8,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7319860127948737,"rank":13,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7521998649687015,"rank":8,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7307946023900631,"rank":8,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7395596529716069,"rank":8,"remainingConfigurations":398},{"removed":"Scale","score":0.7088855692547634,"rank":13,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7287951311115429,"rank":9,"remainingConfigurations":398},{"removed":"Cognition","score":0.7159520387346315,"rank":12,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7420056269660495,"rank":9,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7786883973229668,"rank":5,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7805341206023654,"rank":5,"remainingConfigurations":381},{"removed":"Vals AI","score":0.734459929942564,"rank":8,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7386847538805101,"rank":8,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7407700350707173,"rank":8,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7395566715563205,"rank":8,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7395423399417836,"rank":8,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7399071972292336,"rank":8,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7394841398047682,"rank":8,"remainingConfigurations":398},{"removed":"briefcase","score":0.7393495091910421,"rank":8,"remainingConfigurations":398},{"removed":"aime","score":0.728232044540133,"rank":9,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7397364077422663,"rank":8,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.739584389894123,"rank":8,"remainingConfigurations":398},{"removed":"automationbench","score":0.7396603121668498,"rank":8,"remainingConfigurations":398},{"removed":"critpt","score":0.7405727495509001,"rank":8,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.739474302000164,"rank":8,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.74035355385663,"rank":8,"remainingConfigurations":398},{"removed":"gdpval","score":0.7394757682358852,"rank":8,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7396205970474359,"rank":8,"remainingConfigurations":398},{"removed":"gpqa","score":0.7589492270935132,"rank":7,"remainingConfigurations":398},{"removed":"harvey","score":0.7389530508915213,"rank":8,"remainingConfigurations":398},{"removed":"hle","score":0.7415136166345566,"rank":8,"remainingConfigurations":398},{"removed":"ifbench","score":0.7383921157085109,"rank":8,"remainingConfigurations":398},{"removed":"itbench","score":0.7392989037596541,"rank":8,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7396114699723326,"rank":8,"remainingConfigurations":398},{"removed":"math500","score":0.739574956504666,"rank":8,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7406876744090664,"rank":8,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7429999008980387,"rank":8,"remainingConfigurations":398},{"removed":"omniscience","score":0.7396658170904841,"rank":8,"remainingConfigurations":398},{"removed":"scicode","score":0.7401122532501625,"rank":8,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7383500650983889,"rank":8,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7288992135096558,"rank":9,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7556746654044235,"rank":7,"remainingConfigurations":398},{"removed":"deepswe","score":0.7307500953188648,"rank":8,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.739510867245964,"rank":8,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7361989681087402,"rank":8,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7159520387346315,"rank":12,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7056653890285732,"rank":13,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7383552049651002,"rank":8,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7391750013392132,"rank":8,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7411995228988918,"rank":8,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7395587345708073,"rank":8,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7387025325144393,"rank":8,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7399598594287458,"rank":8,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7402346594392005,"rank":8,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7386615587284263,"rank":8,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7390836514586766,"rank":8,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7405970614691387,"rank":8,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7786883973229668,"rank":5,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.735335805861227,"rank":9,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7376343681545929,"rank":8,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7404659453731953,"rank":9,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7393681613813327,"rank":8,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.739381276262928,"rank":8,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7392249111486106,"rank":8,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7393173159588463,"rank":8,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7393810384523504,"rank":8,"remainingConfigurations":398}]},"claude-opus-5--effort-xhigh":{"score":0.7327225480424163,"rank":9,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7440349108951771,"rank":11,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7457020790620102,"rank":9,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6901648625311232,"rank":12,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7326717028038622,"rank":9,"remainingConfigurations":398},{"removed":"Scale","score":0.6458218086311771,"rank":25,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7349018829054671,"rank":8,"remainingConfigurations":398},{"removed":"Cognition","score":0.8355450266985273,"rank":2,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7343657925352786,"rank":10,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.728419563565268,"rank":9,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7558120391944984,"rank":9,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7242439069517976,"rank":9,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7321850509867849,"rank":10,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.732409619303967,"rank":9,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7326538774082852,"rank":9,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7327225480424163,"rank":9,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7317868666671107,"rank":10,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7326710585413198,"rank":9,"remainingConfigurations":398},{"removed":"briefcase","score":0.7309669900500316,"rank":9,"remainingConfigurations":398},{"removed":"aime","score":0.7295948547153389,"rank":8,"remainingConfigurations":398},{"removed":"apex-agents","score":0.733181633879919,"rank":9,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7329428384326752,"rank":9,"remainingConfigurations":398},{"removed":"automationbench","score":0.7345067462991216,"rank":9,"remainingConfigurations":398},{"removed":"critpt","score":0.7342149764673612,"rank":9,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7325162241666088,"rank":9,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7344151978703609,"rank":9,"remainingConfigurations":398},{"removed":"gdpval","score":0.7321410878452438,"rank":9,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7324480530344246,"rank":9,"remainingConfigurations":398},{"removed":"gpqa","score":0.7343538972548439,"rank":9,"remainingConfigurations":398},{"removed":"harvey","score":0.7316259793560717,"rank":9,"remainingConfigurations":398},{"removed":"hle","score":0.7364301144274005,"rank":9,"remainingConfigurations":398},{"removed":"ifbench","score":0.7298029777683025,"rank":9,"remainingConfigurations":398},{"removed":"itbench","score":0.7324104635712366,"rank":9,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7320126799010959,"rank":9,"remainingConfigurations":398},{"removed":"math500","score":0.7323898262473266,"rank":9,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7344862993218785,"rank":9,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7393675793048163,"rank":9,"remainingConfigurations":398},{"removed":"omniscience","score":0.7341849243104058,"rank":9,"remainingConfigurations":398},{"removed":"scicode","score":0.73421251182578,"rank":9,"remainingConfigurations":398},{"removed":"tau-bench","score":0.731249933313396,"rank":9,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7340050711297997,"rank":8,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7456241680910377,"rank":10,"remainingConfigurations":398},{"removed":"deepswe","score":0.6903149324807427,"rank":12,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7327541656061358,"rank":9,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7308186775068305,"rank":9,"remainingConfigurations":398},{"removed":"frontiercode","score":0.8355450266985273,"rank":2,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7487616427409004,"rank":7,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7136213722067476,"rank":11,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.754748382951164,"rank":7,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7113963718099393,"rank":12,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7326241713409982,"rank":9,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7311639834944286,"rank":9,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7339723573958555,"rank":9,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7335815421018287,"rank":9,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7311922720949999,"rank":9,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7316821367013072,"rank":9,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7348149823732234,"rank":9,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.728419563565268,"rank":9,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7355829169673312,"rank":8,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7333619706910269,"rank":9,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7432459227937277,"rank":8,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7325362178962509,"rank":9,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7324007966177232,"rank":9,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.732054726861355,"rank":9,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7323935063468779,"rank":9,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7319987080995598,"rank":9,"remainingConfigurations":398}]},"claude-opus-5--effort-high":{"score":0.7242879139590591,"rank":10,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.735449202754188,"rank":12,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7153374100796613,"rank":16,"remainingConfigurations":398},{"removed":"Datacurve","score":0.686625286943053,"rank":13,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.724247115416436,"rank":10,"remainingConfigurations":398},{"removed":"Scale","score":0.7318726642242064,"rank":8,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.725526684749247,"rank":10,"remainingConfigurations":398},{"removed":"Cognition","score":0.7814504463166306,"rank":6,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7271738177482088,"rank":11,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6883496208747713,"rank":17,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7389641354185518,"rank":10,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7178543918346184,"rank":11,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7237933887386309,"rank":11,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7239158871278306,"rank":10,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7242147114423708,"rank":10,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7242879139590591,"rank":10,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7233257330324019,"rank":11,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7243523901289283,"rank":10,"remainingConfigurations":398},{"removed":"briefcase","score":0.7229929833032444,"rank":10,"remainingConfigurations":398},{"removed":"aime","score":0.7214833798907913,"rank":10,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7247860065530766,"rank":10,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7248527717758958,"rank":10,"remainingConfigurations":398},{"removed":"automationbench","score":0.7248610876086216,"rank":10,"remainingConfigurations":398},{"removed":"critpt","score":0.7251478671750352,"rank":11,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7242700163256894,"rank":10,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7256334370855809,"rank":10,"remainingConfigurations":398},{"removed":"gdpval","score":0.724367311989831,"rank":10,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7241843476714244,"rank":10,"remainingConfigurations":398},{"removed":"gpqa","score":0.7255318723467942,"rank":11,"remainingConfigurations":398},{"removed":"harvey","score":0.7230757344837518,"rank":10,"remainingConfigurations":398},{"removed":"hle","score":0.7273937310238646,"rank":10,"remainingConfigurations":398},{"removed":"ifbench","score":0.7221234174444637,"rank":11,"remainingConfigurations":398},{"removed":"itbench","score":0.7240173556864099,"rank":10,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7240285476287204,"rank":10,"remainingConfigurations":398},{"removed":"math500","score":0.7241845103021003,"rank":10,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7265532370047638,"rank":10,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7306338614862019,"rank":10,"remainingConfigurations":398},{"removed":"omniscience","score":0.7251532790112565,"rank":10,"remainingConfigurations":398},{"removed":"scicode","score":0.7253148919313436,"rank":10,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7229566502990638,"rank":11,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7249104521758772,"rank":10,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7496150900126438,"rank":9,"remainingConfigurations":398},{"removed":"deepswe","score":0.6866281155081461,"rank":13,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7243146198933005,"rank":10,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7115118759171432,"rank":12,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7814504463166306,"rank":6,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.724530184761155,"rank":9,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7224670368129488,"rank":9,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7236593435173194,"rank":10,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7228573545892267,"rank":10,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7243170547292527,"rank":10,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.722941377998036,"rank":10,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7254999129452671,"rank":10,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7249090015162607,"rank":10,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7227299559718262,"rank":10,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7233039633033166,"rank":10,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7262851939745246,"rank":10,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6883496208747713,"rank":17,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7233154005960337,"rank":10,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7239899661607959,"rank":10,"remainingConfigurations":398},{"removed":"simpleqa","score":0.727882725328776,"rank":10,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7243049542575101,"rank":10,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.723807652590299,"rank":10,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7236782907582832,"rank":10,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7240206700672315,"rank":10,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7235081799921108,"rank":10,"remainingConfigurations":398}]},"claude-fable-5-1--effort-high":{"score":0.7221616261433992,"rank":11,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7467567411796224,"rank":10,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7202284485499643,"rank":13,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7094314035929273,"rank":9,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7222228837317957,"rank":11,"remainingConfigurations":398},{"removed":"Scale","score":0.7283549657853424,"rank":9,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7221658927510508,"rank":11,"remainingConfigurations":398},{"removed":"Cognition","score":0.7044547509001625,"rank":15,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7262674084380977,"rank":12,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7218523821082911,"rank":10,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7365499533812511,"rank":11,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6999268848746776,"rank":14,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7230938385509614,"rank":12,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7215518588174873,"rank":12,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.721371441334329,"rank":11,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7221616261433992,"rank":11,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7216869169218176,"rank":13,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7221811951973517,"rank":11,"remainingConfigurations":398},{"removed":"briefcase","score":0.7210795765031808,"rank":11,"remainingConfigurations":398},{"removed":"aime","score":0.7192130243089084,"rank":11,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7226993616152454,"rank":11,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7225427387305258,"rank":11,"remainingConfigurations":398},{"removed":"automationbench","score":0.7240929904052079,"rank":11,"remainingConfigurations":398},{"removed":"critpt","score":0.7266063763992409,"rank":10,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7218953656155929,"rank":11,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7226115148988163,"rank":11,"remainingConfigurations":398},{"removed":"gdpval","score":0.7225779086572747,"rank":11,"remainingConfigurations":398},{"removed":"gmmlu","score":0.721806263584599,"rank":11,"remainingConfigurations":398},{"removed":"gpqa","score":0.7270668817506626,"rank":10,"remainingConfigurations":398},{"removed":"harvey","score":0.7211221865852958,"rank":11,"remainingConfigurations":398},{"removed":"hle","score":0.7255247435749386,"rank":11,"remainingConfigurations":398},{"removed":"ifbench","score":0.718661893760268,"rank":12,"remainingConfigurations":398},{"removed":"itbench","score":0.7218618765270092,"rank":11,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7213976369486274,"rank":11,"remainingConfigurations":398},{"removed":"math500","score":0.7217488373108546,"rank":11,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7243360991733869,"rank":11,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7276538361787575,"rank":11,"remainingConfigurations":398},{"removed":"omniscience","score":0.7235072637894054,"rank":11,"remainingConfigurations":398},{"removed":"scicode","score":0.7229124821189069,"rank":11,"remainingConfigurations":398},{"removed":"tau-bench","score":0.721204875471857,"rank":12,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7066173904701354,"rank":14,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7196799157951626,"rank":15,"remainingConfigurations":398},{"removed":"deepswe","score":0.7096118037315583,"rank":9,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7222007997681278,"rank":11,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7206070337932995,"rank":10,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7044547509001625,"rank":15,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7222796018659653,"rank":10,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7191082556525705,"rank":10,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7229287334694038,"rank":11,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7195528288832403,"rank":11,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7220381457923096,"rank":11,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7206101137795585,"rank":11,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7236160024718009,"rank":11,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7229321260867022,"rank":11,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7204549895243425,"rank":11,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7211398559920613,"rank":11,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.724310793168728,"rank":11,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7218523821082911,"rank":10,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7228105738224392,"rank":11,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7231559473774972,"rank":11,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7245986930560943,"rank":12,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.723246015905751,"rank":11,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7221002599109689,"rank":11,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7222437501549414,"rank":11,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7227284511275179,"rank":11,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7219940420033417,"rank":11,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-xhigh":{"score":0.7200558869962235,"rank":12,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7613870216897457,"rank":7,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7272762555742784,"rank":10,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6714692197012849,"rank":15,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7200360853553938,"rank":12,"remainingConfigurations":398},{"removed":"Scale","score":0.7088049012712947,"rank":14,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7202906069354188,"rank":12,"remainingConfigurations":398},{"removed":"Cognition","score":0.7255926042667232,"rank":9,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7257087026290132,"rank":13,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7182571350030232,"rank":11,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7272861165360536,"rank":12,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7215471428201209,"rank":10,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7201373677273581,"rank":13,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7232396999634106,"rank":11,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7199901850907212,"rank":12,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7200558869962235,"rank":12,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7232146147889642,"rank":12,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7200259748752296,"rank":12,"remainingConfigurations":398},{"removed":"briefcase","score":0.7197195209135433,"rank":12,"remainingConfigurations":398},{"removed":"aime","score":0.7189062696551938,"rank":12,"remainingConfigurations":398},{"removed":"apex-agents","score":0.72030557173953,"rank":12,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7206725799294992,"rank":12,"remainingConfigurations":398},{"removed":"automationbench","score":0.720025263708298,"rank":12,"remainingConfigurations":398},{"removed":"critpt","score":0.7227580976560048,"rank":12,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.719796560853112,"rank":12,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7182943697575391,"rank":12,"remainingConfigurations":398},{"removed":"gdpval","score":0.7200818954716709,"rank":12,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7197986495496126,"rank":12,"remainingConfigurations":398},{"removed":"gpqa","score":0.7184273660822326,"rank":12,"remainingConfigurations":398},{"removed":"harvey","score":0.7194467232184051,"rank":12,"remainingConfigurations":398},{"removed":"hle","score":0.7225908438100627,"rank":12,"remainingConfigurations":398},{"removed":"ifbench","score":0.7232797326211441,"rank":10,"remainingConfigurations":398},{"removed":"itbench","score":0.7197802402930903,"rank":12,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7195685344768048,"rank":12,"remainingConfigurations":398},{"removed":"math500","score":0.7198210043425995,"rank":12,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7227902805760174,"rank":12,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7262004628780527,"rank":12,"remainingConfigurations":398},{"removed":"omniscience","score":0.7198486004080588,"rank":12,"remainingConfigurations":398},{"removed":"scicode","score":0.7198116948811092,"rank":12,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7230909461167595,"rank":10,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.721604914996896,"rank":11,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7323477835596078,"rank":11,"remainingConfigurations":398},{"removed":"deepswe","score":0.6711108260826819,"rank":15,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7213971993241413,"rank":12,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7177127429720871,"rank":11,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7255926042667232,"rank":9,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7206191327390831,"rank":11,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6983850615196001,"rank":15,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7255152059504134,"rank":9,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7249776064971346,"rank":9,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7203653529567223,"rank":12,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7192192382241674,"rank":12,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7210489770393539,"rank":12,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7200425878892983,"rank":12,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7184964987683128,"rank":12,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7192453680011285,"rank":12,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7219433613768184,"rank":12,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7182571350030232,"rank":11,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7172958377065853,"rank":12,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7187591503079499,"rank":12,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7251201157551357,"rank":11,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7197856514014059,"rank":12,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.719366106886294,"rank":12,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7194503002451921,"rank":12,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7195734486473601,"rank":12,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7191073605559976,"rank":12,"remainingConfigurations":398}]},"claude-fable-5-1--effort-medium":{"score":0.7078792508208632,"rank":13,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7307888304392351,"rank":14,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7185540810932681,"rank":15,"remainingConfigurations":398},{"removed":"Datacurve","score":0.7020042834140444,"rank":10,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.707775771400703,"rank":13,"remainingConfigurations":398},{"removed":"Scale","score":0.715836094812666,"rank":10,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.707983825911366,"rank":13,"remainingConfigurations":398},{"removed":"Cognition","score":0.6500968262336267,"rank":21,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7096656322586963,"rank":17,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7067555404275762,"rank":12,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.725160366384657,"rank":13,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7006625445065158,"rank":13,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7087960875883242,"rank":15,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7072083555787563,"rank":13,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7075582258031347,"rank":13,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7078792508208632,"rank":13,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7077943166319156,"rank":14,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7078795840044975,"rank":13,"remainingConfigurations":398},{"removed":"briefcase","score":0.7068073234745175,"rank":13,"remainingConfigurations":398},{"removed":"aime","score":0.7046556794952893,"rank":13,"remainingConfigurations":398},{"removed":"apex-agents","score":0.708473666297199,"rank":13,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7078359494585528,"rank":13,"remainingConfigurations":398},{"removed":"automationbench","score":0.7096382097759899,"rank":13,"remainingConfigurations":398},{"removed":"critpt","score":0.7126346173043482,"rank":13,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7075410993566872,"rank":13,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7080057262273582,"rank":13,"remainingConfigurations":398},{"removed":"gdpval","score":0.7093270322781283,"rank":13,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7074558037264689,"rank":13,"remainingConfigurations":398},{"removed":"gpqa","score":0.714846256452062,"rank":13,"remainingConfigurations":398},{"removed":"harvey","score":0.706165696466435,"rank":13,"remainingConfigurations":398},{"removed":"hle","score":0.7113387743282952,"rank":13,"remainingConfigurations":398},{"removed":"ifbench","score":0.7037134474440266,"rank":13,"remainingConfigurations":398},{"removed":"itbench","score":0.7075763980023075,"rank":13,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7068271869236483,"rank":13,"remainingConfigurations":398},{"removed":"math500","score":0.707405460105034,"rank":13,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7097155738071227,"rank":13,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7133838560966498,"rank":13,"remainingConfigurations":398},{"removed":"omniscience","score":0.708845296344342,"rank":14,"remainingConfigurations":398},{"removed":"scicode","score":0.7092386706512898,"rank":13,"remainingConfigurations":398},{"removed":"tau-bench","score":0.7065687944266684,"rank":13,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7066295061597717,"rank":13,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7183744885747642,"rank":17,"remainingConfigurations":398},{"removed":"deepswe","score":0.7021869064265024,"rank":10,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7079128012553486,"rank":13,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7054383897593276,"rank":13,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6500968262336267,"rank":21,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7076774582090725,"rank":12,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7047098771729235,"rank":13,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7085971760875026,"rank":12,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.705178553721912,"rank":13,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7077063969469264,"rank":13,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7061211491418905,"rank":13,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7094096683941747,"rank":14,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7085723341186746,"rank":13,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.7061940662159198,"rank":13,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7067776884638067,"rank":13,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7103319323240193,"rank":13,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7067555404275762,"rank":12,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7080554544741621,"rank":13,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7088674659550714,"rank":13,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7100503387498032,"rank":13,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7077119190429153,"rank":13,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7074117229357446,"rank":13,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7071730167041808,"rank":13,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7075382867816199,"rank":14,"remainingConfigurations":398},{"removed":"vibe-code","score":0.7069440921605245,"rank":13,"remainingConfigurations":398}]},"muse-spark-1.3--effort-xhigh":{"score":0.7034116319092588,"rank":14,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7007113303075153,"rank":17,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7205643591689023,"rank":12,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6795181385682502,"rank":14,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7032074453705834,"rank":14,"remainingConfigurations":398},{"removed":"Scale","score":0.709975305749837,"rank":12,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7054381374939962,"rank":14,"remainingConfigurations":398},{"removed":"Cognition","score":0.717223919605099,"rank":11,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7081651687705408,"rank":18,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.7005478620923823,"rank":13,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7044432389197048,"rank":18,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6927970890556466,"rank":16,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7026281573119634,"rank":16,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.7031710416944351,"rank":14,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6193723324429602,"rank":27,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7034116319092588,"rank":14,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6187710107021112,"rank":26,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7035513379402459,"rank":14,"remainingConfigurations":398},{"removed":"briefcase","score":0.702809524711907,"rank":15,"remainingConfigurations":398},{"removed":"aime","score":0.7039039041557599,"rank":14,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7037689181866612,"rank":14,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.7033507032551246,"rank":14,"remainingConfigurations":398},{"removed":"automationbench","score":0.7037542325406049,"rank":14,"remainingConfigurations":398},{"removed":"critpt","score":0.7048838558460483,"rank":14,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.7029712035060468,"rank":14,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7038647683472429,"rank":14,"remainingConfigurations":398},{"removed":"gdpval","score":0.7023090635253667,"rank":14,"remainingConfigurations":398},{"removed":"gmmlu","score":0.7035502816043558,"rank":14,"remainingConfigurations":398},{"removed":"gpqa","score":0.7025403317247602,"rank":15,"remainingConfigurations":398},{"removed":"harvey","score":0.6878506039023567,"rank":20,"remainingConfigurations":398},{"removed":"hle","score":0.7054270864902555,"rank":14,"remainingConfigurations":398},{"removed":"ifbench","score":0.7009093231070088,"rank":14,"remainingConfigurations":398},{"removed":"itbench","score":0.7033143864005567,"rank":14,"remainingConfigurations":398},{"removed":"livecodebench","score":0.7033549870474239,"rank":14,"remainingConfigurations":398},{"removed":"math500","score":0.7035103204412669,"rank":14,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7068714382447095,"rank":14,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7108273654229721,"rank":14,"remainingConfigurations":398},{"removed":"omniscience","score":0.7090101942719406,"rank":13,"remainingConfigurations":398},{"removed":"scicode","score":0.7016792365825477,"rank":14,"remainingConfigurations":398},{"removed":"tau-bench","score":0.700970060455736,"rank":14,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7164811517651465,"rank":12,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7186264607871443,"rank":16,"remainingConfigurations":398},{"removed":"deepswe","score":0.6796037152994097,"rank":14,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7035032973567503,"rank":14,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7018907417309009,"rank":15,"remainingConfigurations":398},{"removed":"frontiercode","score":0.717223919605099,"rank":11,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7038774565328723,"rank":14,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7016593627210712,"rank":14,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7031006870011481,"rank":14,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.7021008214479171,"rank":14,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7018492684746086,"rank":14,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7037819721744177,"rank":14,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7153654016390468,"rank":13,"remainingConfigurations":398},{"removed":"livebench-data","score":0.705355218108599,"rank":14,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.695175487570017,"rank":16,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.7045304600098756,"rank":14,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6979877184311493,"rank":17,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.7005478620923823,"rank":13,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.7011117406123687,"rank":14,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7050895629838646,"rank":14,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7019400827210012,"rank":16,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6938471639235694,"rank":16,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.7064235897975374,"rank":14,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.7061960986089203,"rank":14,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7141518725736651,"rank":13,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6958450502736081,"rank":16,"remainingConfigurations":398}]},"gemini-3.8-flash--effort-medium":{"score":0.7002495102547243,"rank":15,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7498965473856387,"rank":9,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7202191419601008,"rank":14,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5552286423889249,"rank":26,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.7002768541298275,"rank":15,"remainingConfigurations":398},{"removed":"Scale","score":0.7080657324639562,"rank":15,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.7026690525551941,"rank":15,"remainingConfigurations":398},{"removed":"Cognition","score":0.7185235594124242,"rank":10,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7046146172221751,"rank":19,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6967061454483563,"rank":14,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7137980149637176,"rank":14,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6978696299949162,"rank":15,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7006057015729686,"rank":17,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.699325126817398,"rank":15,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.7004121937073361,"rank":14,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.7002495102547243,"rank":15,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6998294100594885,"rank":16,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.7001645564123825,"rank":15,"remainingConfigurations":398},{"removed":"briefcase","score":0.7044076735582516,"rank":14,"remainingConfigurations":398},{"removed":"aime","score":0.6986733253817371,"rank":15,"remainingConfigurations":398},{"removed":"apex-agents","score":0.7007284436633817,"rank":15,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6992785177693875,"rank":15,"remainingConfigurations":398},{"removed":"automationbench","score":0.6966469563384873,"rank":17,"remainingConfigurations":398},{"removed":"critpt","score":0.7041749560376575,"rank":15,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.699908744070752,"rank":15,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.7001877059218189,"rank":15,"remainingConfigurations":398},{"removed":"gdpval","score":0.702279231001162,"rank":15,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6999117623293062,"rank":15,"remainingConfigurations":398},{"removed":"gpqa","score":0.6982716241900322,"rank":16,"remainingConfigurations":398},{"removed":"harvey","score":0.6976151863504896,"rank":16,"remainingConfigurations":398},{"removed":"hle","score":0.705021630498007,"rank":15,"remainingConfigurations":398},{"removed":"ifbench","score":0.6968619288121235,"rank":16,"remainingConfigurations":398},{"removed":"itbench","score":0.6999219473023124,"rank":15,"remainingConfigurations":398},{"removed":"livecodebench","score":0.699827690914883,"rank":15,"remainingConfigurations":398},{"removed":"math500","score":0.7000448666828972,"rank":15,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7035411442783165,"rank":16,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.7065219771716095,"rank":15,"remainingConfigurations":398},{"removed":"omniscience","score":0.7024088919609709,"rank":15,"remainingConfigurations":398},{"removed":"scicode","score":0.7008325738277229,"rank":15,"remainingConfigurations":398},{"removed":"tau-bench","score":0.696876958129573,"rank":16,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7032837423200675,"rank":16,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7218998171243082,"rank":14,"remainingConfigurations":398},{"removed":"deepswe","score":0.5554144596986412,"rank":26,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.7003141409586835,"rank":15,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6976927559158814,"rank":16,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7185235594124242,"rank":10,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.7006992458255886,"rank":15,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6978637310546505,"rank":16,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.7003027557653737,"rank":15,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.698742925062784,"rank":15,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7005536864729707,"rank":15,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6996109312647544,"rank":16,"remainingConfigurations":398},{"removed":"livebench-language","score":0.7010976188962396,"rank":15,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7014605298385371,"rank":16,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6983382799911632,"rank":15,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6994570151649722,"rank":15,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7012057550028796,"rank":15,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6967061454483563,"rank":14,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6967412744151766,"rank":15,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7010179816637039,"rank":16,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7050411378643163,"rank":15,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.698899360977519,"rank":15,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.700391701353681,"rank":15,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6993167817026814,"rank":15,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.7003222000710577,"rank":15,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6997120440338599,"rank":14,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-max":{"score":0.698487650282616,"rank":16,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7051734294532978,"rank":16,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7137235699048063,"rank":17,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6525912332618075,"rank":18,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6984207728852562,"rank":16,"remainingConfigurations":398},{"removed":"Scale","score":0.7069224416374137,"rank":16,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6969656461044078,"rank":16,"remainingConfigurations":398},{"removed":"Cognition","score":0.698054489930132,"rank":16,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7111396795752881,"rank":16,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6928931194407596,"rank":15,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7042595473984273,"rank":19,"remainingConfigurations":381},{"removed":"Vals AI","score":0.7028059324729877,"rank":12,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6983183574557176,"rank":18,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6919432492367065,"rank":17,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6978062160388161,"rank":15,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.698487650282616,"rank":16,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6907297345684933,"rank":18,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6982749933794169,"rank":16,"remainingConfigurations":398},{"removed":"briefcase","score":0.6981617419766565,"rank":16,"remainingConfigurations":398},{"removed":"aime","score":0.6982119167332829,"rank":16,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6984798158892981,"rank":16,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6982445833559492,"rank":16,"remainingConfigurations":398},{"removed":"automationbench","score":0.6978766650440017,"rank":16,"remainingConfigurations":398},{"removed":"critpt","score":0.6987432060392932,"rank":16,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6996533267940057,"rank":16,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6987999269859761,"rank":16,"remainingConfigurations":398},{"removed":"gdpval","score":0.6985460018060287,"rank":16,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6986040814429897,"rank":16,"remainingConfigurations":398},{"removed":"gpqa","score":0.692948445587314,"rank":18,"remainingConfigurations":398},{"removed":"harvey","score":0.7047705182088039,"rank":14,"remainingConfigurations":398},{"removed":"hle","score":0.6979666689442051,"rank":16,"remainingConfigurations":398},{"removed":"ifbench","score":0.6978085574457825,"rank":15,"remainingConfigurations":398},{"removed":"itbench","score":0.6973036575347482,"rank":16,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6985426735119221,"rank":16,"remainingConfigurations":398},{"removed":"math500","score":0.6985711971063656,"rank":16,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.7042167867501865,"rank":15,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6978244167677993,"rank":17,"remainingConfigurations":398},{"removed":"omniscience","score":0.6995295590026208,"rank":16,"remainingConfigurations":398},{"removed":"scicode","score":0.6987877518505443,"rank":16,"remainingConfigurations":398},{"removed":"tau-bench","score":0.697788115304995,"rank":15,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6942472959008358,"rank":17,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7112836245258505,"rank":18,"remainingConfigurations":398},{"removed":"deepswe","score":0.6470646110457191,"rank":20,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6982966893619613,"rank":16,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.7027198586128526,"rank":14,"remainingConfigurations":398},{"removed":"frontiercode","score":0.698054489930132,"rank":16,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6988984695208079,"rank":16,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6964427671965905,"rank":17,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6977159088448014,"rank":16,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6978870224862995,"rank":16,"remainingConfigurations":398},{"removed":"livebench-math","score":0.7000497716896649,"rank":16,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6936976846009829,"rank":17,"remainingConfigurations":398},{"removed":"livebench-language","score":0.69855890451097,"rank":16,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6996863760067771,"rank":17,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6989629942272151,"rank":14,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6957735131848443,"rank":16,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7027299392150974,"rank":14,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6928931194407596,"rank":15,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6967283144815802,"rank":16,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6934025138964177,"rank":17,"remainingConfigurations":398},{"removed":"simpleqa","score":0.7056318396665073,"rank":14,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.7020655436888626,"rank":14,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6962317532321541,"rank":17,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6955035618921098,"rank":16,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6943557410043137,"rank":16,"remainingConfigurations":398},{"removed":"vibe-code","score":0.696198036755432,"rank":15,"remainingConfigurations":398}]},"gpt-6-astra--effort-low":{"score":0.6921058360398131,"rank":17,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.7173240513735036,"rank":15,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6954972247744355,"rank":22,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6691317734054908,"rank":16,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.692018884618279,"rank":17,"remainingConfigurations":398},{"removed":"Scale","score":0.7004142014066441,"rank":17,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6835406235408591,"rank":19,"remainingConfigurations":398},{"removed":"Cognition","score":0.6850148659534478,"rank":17,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6983473537058078,"rank":20,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6884495716781912,"rank":16,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6947632879261469,"rank":22,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6891714620728829,"rank":17,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6922666913873851,"rank":19,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6928975451459838,"rank":16,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6920511567549815,"rank":16,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6921058360398131,"rank":17,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6929652445876865,"rank":17,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6922535989612495,"rank":17,"remainingConfigurations":398},{"removed":"briefcase","score":0.693683638437308,"rank":17,"remainingConfigurations":398},{"removed":"aime","score":0.6911324872536687,"rank":17,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6926360221899349,"rank":17,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6931502806031489,"rank":17,"remainingConfigurations":398},{"removed":"automationbench","score":0.6902279096068491,"rank":19,"remainingConfigurations":398},{"removed":"critpt","score":0.6934149553345149,"rank":17,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6921536694575905,"rank":17,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6899989528043179,"rank":20,"remainingConfigurations":398},{"removed":"gdpval","score":0.6935820128329299,"rank":17,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6919821842669395,"rank":17,"remainingConfigurations":398},{"removed":"gpqa","score":0.6911383303707113,"rank":19,"remainingConfigurations":398},{"removed":"harvey","score":0.6914101369934113,"rank":18,"remainingConfigurations":398},{"removed":"hle","score":0.6953613281204211,"rank":17,"remainingConfigurations":398},{"removed":"ifbench","score":0.6903679303846699,"rank":18,"remainingConfigurations":398},{"removed":"itbench","score":0.6918372267299252,"rank":17,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6917708758966263,"rank":17,"remainingConfigurations":398},{"removed":"math500","score":0.6919925531211152,"rank":17,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6955014595650043,"rank":17,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6980970112163859,"rank":16,"remainingConfigurations":398},{"removed":"omniscience","score":0.6925356456252496,"rank":17,"remainingConfigurations":398},{"removed":"scicode","score":0.6937759714267902,"rank":17,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6927866163740696,"rank":17,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6828622346223975,"rank":19,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7229727294959428,"rank":13,"remainingConfigurations":398},{"removed":"deepswe","score":0.6688009366885165,"rank":16,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6921359501382124,"rank":17,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6784005251261722,"rank":22,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6850148659534478,"rank":17,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6923325936141262,"rank":17,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6892244880733857,"rank":18,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6920228923452215,"rank":18,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.69121705647244,"rank":17,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6924570544569612,"rank":17,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6908716748192151,"rank":18,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6933758980334132,"rank":17,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6922899033169468,"rank":20,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6903126259854527,"rank":17,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6911151358382331,"rank":18,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6942830978371145,"rank":19,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6884495716781912,"rank":16,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6902256993893596,"rank":18,"remainingConfigurations":398},{"removed":"frontiermath","score":0.687027952966357,"rank":19,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6981140128729114,"rank":18,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6916678399176074,"rank":19,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6914986566041051,"rank":18,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6914105970451884,"rank":18,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6915860627921239,"rank":17,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6912230622895281,"rank":17,"remainingConfigurations":398}]},"claude-fable-5--effort-max":{"score":0.6904521243576524,"rank":18,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6998872107230838,"rank":18,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.701792053088766,"rank":19,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6550371967703703,"rank":17,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6904370664107456,"rank":18,"remainingConfigurations":398},{"removed":"Scale","score":0.6971263377318846,"rank":20,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6860254891121981,"rank":18,"remainingConfigurations":398},{"removed":"Cognition","score":0.6838240102399705,"rank":18,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7142579692828853,"rank":15,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6865386058240158,"rank":20,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7081698562392251,"rank":16,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6709647327606446,"rank":22,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7339882003249446,"rank":9,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6891311462712784,"rank":20,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6896221335680766,"rank":18,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6904521243576524,"rank":18,"remainingConfigurations":398},{"removed":"All provider reports","score":0.7318843773485036,"rank":9,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6897690093512261,"rank":19,"remainingConfigurations":398},{"removed":"briefcase","score":0.6897809122566004,"rank":19,"remainingConfigurations":398},{"removed":"aime","score":0.6805891485862209,"rank":21,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6907328260321134,"rank":18,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6897233575821612,"rank":20,"remainingConfigurations":398},{"removed":"automationbench","score":0.68211161833343,"rank":21,"remainingConfigurations":398},{"removed":"critpt","score":0.6916600747000211,"rank":18,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6894860361267191,"rank":20,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6916039370200303,"rank":18,"remainingConfigurations":398},{"removed":"gdpval","score":0.6903796338343878,"rank":18,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6905229934298304,"rank":18,"remainingConfigurations":398},{"removed":"gpqa","score":0.703452947026118,"rank":14,"remainingConfigurations":398},{"removed":"harvey","score":0.6929304888072513,"rank":17,"remainingConfigurations":398},{"removed":"hle","score":0.6918151968278088,"rank":20,"remainingConfigurations":398},{"removed":"ifbench","score":0.6908367713044686,"rank":17,"remainingConfigurations":398},{"removed":"itbench","score":0.6901790767848529,"rank":18,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6904990138680277,"rank":18,"remainingConfigurations":398},{"removed":"math500","score":0.6905094524526799,"rank":18,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6919374637341161,"rank":19,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.697259464231388,"rank":18,"remainingConfigurations":398},{"removed":"omniscience","score":0.6916268803087798,"rank":18,"remainingConfigurations":398},{"removed":"scicode","score":0.6904144251018637,"rank":20,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6892391735748357,"rank":18,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.7060127779161762,"rank":15,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7007890003997835,"rank":21,"remainingConfigurations":398},{"removed":"deepswe","score":0.655540905922792,"rank":17,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6904800853496269,"rank":18,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6885738704318771,"rank":17,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6838240102399705,"rank":18,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.691168099455645,"rank":18,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6883267399790692,"rank":20,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6900231594544767,"rank":19,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.688960618734103,"rank":18,"remainingConfigurations":398},{"removed":"livebench-math","score":0.688470588501295,"rank":19,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.686418372937506,"rank":20,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6903222305908981,"rank":19,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6959660789312512,"rank":19,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6857528704692211,"rank":19,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6915077065546225,"rank":17,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6948166674296052,"rank":18,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6865386058240158,"rank":20,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6897750380495172,"rank":19,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6849817746292626,"rank":21,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6949831245812179,"rank":19,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6937754618429509,"rank":17,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6888336157746576,"rank":20,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6873966510892449,"rank":20,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6873125479127465,"rank":19,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6868415100864179,"rank":21,"remainingConfigurations":398}]},"claude-opus-5--effort-max":{"score":0.6903251978361186,"rank":19,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6958632465462337,"rank":20,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6963182367120178,"rank":20,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6453954800529627,"rank":21,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.690317597422078,"rank":19,"remainingConfigurations":398},{"removed":"Scale","score":0.6982705143612163,"rank":18,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6597203696816206,"rank":20,"remainingConfigurations":398},{"removed":"Cognition","score":0.7088832023548536,"rank":14,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7237049832916836,"rank":14,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6867605201536638,"rank":19,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7129032010869247,"rank":15,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6744890749621558,"rank":20,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.7094015110432176,"rank":14,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6892040162019545,"rank":19,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6894836527379429,"rank":19,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6903251978361186,"rank":19,"remainingConfigurations":398},{"removed":"All provider reports","score":0.707544613481727,"rank":15,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.689183847755544,"rank":20,"remainingConfigurations":398},{"removed":"briefcase","score":0.6896218511940951,"rank":21,"remainingConfigurations":398},{"removed":"aime","score":0.6871640350113103,"rank":20,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6905971833389583,"rank":20,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6900306084041444,"rank":19,"remainingConfigurations":398},{"removed":"automationbench","score":0.6992911177158113,"rank":15,"remainingConfigurations":398},{"removed":"critpt","score":0.691455969470717,"rank":19,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6901710508970972,"rank":18,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6917980775630183,"rank":17,"remainingConfigurations":398},{"removed":"gdpval","score":0.6901422594741892,"rank":20,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6903903043880492,"rank":19,"remainingConfigurations":398},{"removed":"gpqa","score":0.6933727278640754,"rank":17,"remainingConfigurations":398},{"removed":"harvey","score":0.6978317780552813,"rank":15,"remainingConfigurations":398},{"removed":"hle","score":0.6920524136771345,"rank":19,"remainingConfigurations":398},{"removed":"ifbench","score":0.689028625003079,"rank":19,"remainingConfigurations":398},{"removed":"itbench","score":0.6900498948402779,"rank":19,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6903782153671655,"rank":19,"remainingConfigurations":398},{"removed":"math500","score":0.6903815394335137,"rank":19,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.69040907236477,"rank":20,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6969200194433016,"rank":19,"remainingConfigurations":398},{"removed":"omniscience","score":0.6916046291618314,"rank":19,"remainingConfigurations":398},{"removed":"scicode","score":0.6908289460311284,"rank":19,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6890080240997359,"rank":19,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6459337523773753,"rank":24,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6951366137983318,"rank":22,"remainingConfigurations":398},{"removed":"deepswe","score":0.6457206297114568,"rank":21,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6903554789327006,"rank":19,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6884822278920221,"rank":18,"remainingConfigurations":398},{"removed":"frontiercode","score":0.7088832023548536,"rank":14,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6907648123256666,"rank":19,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.68855969175774,"rank":19,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6899467604365787,"rank":20,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6886598604965397,"rank":19,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6873927757507389,"rank":20,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6859297792061647,"rank":21,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6891480164341376,"rank":20,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6971513356447298,"rank":18,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6836887389413535,"rank":21,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6887388645517701,"rank":20,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.7002504320915804,"rank":16,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6867605201536638,"rank":19,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6878216725382984,"rank":20,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6858545113790866,"rank":20,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6989366297625277,"rank":17,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6919870856096777,"rank":18,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6874305565285109,"rank":21,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6856897796097092,"rank":21,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6868205287125662,"rank":20,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6891718611476826,"rank":20,"remainingConfigurations":398}]},"claude-fable-5--effort-medium":{"score":0.6902082179471911,"rank":20,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6875082454606497,"rank":22,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7232289959400601,"rank":11,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6975731038548131,"rank":11,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6903009821786594,"rank":20,"remainingConfigurations":398},{"removed":"Scale","score":0.697514253763671,"rank":19,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6910264977636573,"rank":17,"remainingConfigurations":398},{"removed":"Cognition","score":0.6158406777766143,"rank":25,"remainingConfigurations":398},{"removed":"LiveBench","score":0.693526182900371,"rank":21,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6870109856560763,"rank":18,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7062933509090715,"rank":17,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6823746313525806,"rank":19,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6892856890392268,"rank":20,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6894424272748924,"rank":18,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6902034252517599,"rank":17,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6902082179471911,"rank":20,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6885003708555538,"rank":19,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6902563378263622,"rank":18,"remainingConfigurations":398},{"removed":"briefcase","score":0.6897367494845423,"rank":20,"remainingConfigurations":398},{"removed":"aime","score":0.6881521262246745,"rank":19,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6907322078379098,"rank":19,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6900579673952899,"rank":18,"remainingConfigurations":398},{"removed":"automationbench","score":0.6904458098324424,"rank":18,"remainingConfigurations":398},{"removed":"critpt","score":0.6868432019021594,"rank":21,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6900998477741611,"rank":19,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6912644845291798,"rank":19,"remainingConfigurations":398},{"removed":"gdpval","score":0.6903766943386628,"rank":19,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6901732104129858,"rank":20,"remainingConfigurations":398},{"removed":"gpqa","score":0.6907180400011034,"rank":20,"remainingConfigurations":398},{"removed":"harvey","score":0.6889433194603644,"rank":19,"remainingConfigurations":398},{"removed":"hle","score":0.6938402038758538,"rank":18,"remainingConfigurations":398},{"removed":"ifbench","score":0.6879485701373956,"rank":20,"remainingConfigurations":398},{"removed":"itbench","score":0.6899560871226896,"rank":20,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6901424369010813,"rank":20,"remainingConfigurations":398},{"removed":"math500","score":0.6901662046412277,"rank":20,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6933223357086679,"rank":18,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6968247937091409,"rank":20,"remainingConfigurations":398},{"removed":"omniscience","score":0.6899498786071558,"rank":21,"remainingConfigurations":398},{"removed":"scicode","score":0.6912143972067087,"rank":18,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6889680010703944,"rank":20,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6903859158923605,"rank":18,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7272855892978148,"rank":12,"remainingConfigurations":398},{"removed":"deepswe","score":0.6977642830708061,"rank":11,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6902512961163714,"rank":20,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6855781787312681,"rank":20,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6158406777766143,"rank":25,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6907603375679399,"rank":20,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6865955588457502,"rank":22,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.689545506920668,"rank":21,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6884412850680647,"rank":20,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6900663356689627,"rank":18,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6884158964717729,"rank":19,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6917248633648508,"rank":18,"remainingConfigurations":398},{"removed":"livebench-data","score":0.691044766391506,"rank":21,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.688413160478393,"rank":18,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6890100568669446,"rank":19,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.692751338959725,"rank":20,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6870109856560763,"rank":18,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6912713519187291,"rank":17,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6883252732489901,"rank":18,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6946191120067627,"rank":20,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6899454278452243,"rank":20,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6898223892185008,"rank":19,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6894453503741284,"rank":19,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6898269671062384,"rank":18,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6893248487320679,"rank":19,"remainingConfigurations":398}]},"gemini-3.8-flash--effort-high":{"score":0.6889002380190533,"rank":21,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6960174103715295,"rank":19,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.7076536697729056,"rank":18,"remainingConfigurations":398},{"removed":"Datacurve","score":0.612811291908221,"rank":24,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6889241512898213,"rank":21,"remainingConfigurations":398},{"removed":"Scale","score":0.6959414610238341,"rank":21,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6302725090658288,"rank":26,"remainingConfigurations":398},{"removed":"Cognition","score":0.708946778697675,"rank":13,"remainingConfigurations":398},{"removed":"LiveBench","score":0.7426343511081316,"rank":8,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6849470912922886,"rank":21,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.7030974971054733,"rank":20,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6869691356418274,"rank":18,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6880555379833169,"rank":21,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6881639411429382,"rank":21,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6882449913584207,"rank":20,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6889002380190533,"rank":21,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6866507837366881,"rank":20,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6883249966918333,"rank":21,"remainingConfigurations":398},{"removed":"briefcase","score":0.6902491546214248,"rank":18,"remainingConfigurations":398},{"removed":"aime","score":0.6884012339975444,"rank":18,"remainingConfigurations":398},{"removed":"apex-agents","score":0.689118581231876,"rank":21,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6894599786253822,"rank":21,"remainingConfigurations":398},{"removed":"automationbench","score":0.6874775458824677,"rank":20,"remainingConfigurations":398},{"removed":"critpt","score":0.6900539835286565,"rank":20,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.688948635933554,"rank":21,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6899593305195921,"rank":21,"remainingConfigurations":398},{"removed":"gdpval","score":0.6894476251529599,"rank":21,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6889946564848284,"rank":21,"remainingConfigurations":398},{"removed":"gpqa","score":0.683324267568559,"rank":21,"remainingConfigurations":398},{"removed":"harvey","score":0.6850494788630604,"rank":21,"remainingConfigurations":398},{"removed":"hle","score":0.6905121411334049,"rank":21,"remainingConfigurations":398},{"removed":"ifbench","score":0.6869428751783447,"rank":21,"remainingConfigurations":398},{"removed":"itbench","score":0.6886289340091719,"rank":21,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6890475789429572,"rank":21,"remainingConfigurations":398},{"removed":"math500","score":0.6889918201568768,"rank":21,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6897820460293924,"rank":21,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6945141788342427,"rank":21,"remainingConfigurations":398},{"removed":"omniscience","score":0.6900908194716046,"rank":20,"remainingConfigurations":398},{"removed":"scicode","score":0.6889443708078119,"rank":21,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6869932230187289,"rank":21,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6290402766891675,"rank":26,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7078552946233162,"rank":19,"remainingConfigurations":398},{"removed":"deepswe","score":0.6129042205158538,"rank":24,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6889577839986636,"rank":21,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6872066877140884,"rank":19,"remainingConfigurations":398},{"removed":"frontiercode","score":0.708946778697675,"rank":13,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6894229990650077,"rank":21,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6869403841891851,"rank":21,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6886288745521972,"rank":22,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6876071157354707,"rank":21,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6870832182113945,"rank":21,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.7012607499300438,"rank":15,"remainingConfigurations":398},{"removed":"livebench-language","score":0.681972237615414,"rank":22,"remainingConfigurations":398},{"removed":"livebench-data","score":0.7029812454526058,"rank":15,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6855682849066684,"rank":20,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6863554088104474,"rank":21,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6772841425914059,"rank":22,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6849470912922886,"rank":21,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6834575130175103,"rank":21,"remainingConfigurations":398},{"removed":"frontiermath","score":0.7034190471002505,"rank":15,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6851507492697181,"rank":21,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6814468288704164,"rank":21,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6972337832833926,"rank":16,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6945290899128378,"rank":17,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6856000363943121,"rank":21,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6901277612393887,"rank":18,"remainingConfigurations":398}]},"claude-fable-5--effort-xhigh":{"score":0.6812306339389292,"rank":22,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6836715299682768,"rank":23,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6771102225797879,"rank":26,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6479694238625434,"rank":20,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.681338711597606,"rank":22,"remainingConfigurations":398},{"removed":"Scale","score":0.7995324220587975,"rank":5,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6582002229372631,"rank":22,"remainingConfigurations":398},{"removed":"Cognition","score":0.6420959165832151,"rank":22,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6851232046664221,"rank":22,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.676096620971458,"rank":22,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6971670426708713,"rank":21,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6740783704130028,"rank":21,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6808008210614579,"rank":22,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6807486172238099,"rank":22,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.681202845677678,"rank":21,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6812306339389292,"rank":22,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6802726118515611,"rank":21,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6811664333416565,"rank":22,"remainingConfigurations":398},{"removed":"briefcase","score":0.6804848148925116,"rank":22,"remainingConfigurations":398},{"removed":"aime","score":0.6784231811323583,"rank":22,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6817084928059427,"rank":22,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6813480797372673,"rank":22,"remainingConfigurations":398},{"removed":"automationbench","score":0.6817371577435973,"rank":22,"remainingConfigurations":398},{"removed":"critpt","score":0.6834973586597352,"rank":22,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.681171145433949,"rank":22,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6825775278633509,"rank":22,"remainingConfigurations":398},{"removed":"gdpval","score":0.6811335979984485,"rank":22,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6811431149255968,"rank":22,"remainingConfigurations":398},{"removed":"gpqa","score":0.6810995325133886,"rank":22,"remainingConfigurations":398},{"removed":"harvey","score":0.680344466705875,"rank":22,"remainingConfigurations":398},{"removed":"hle","score":0.6866518549172351,"rank":22,"remainingConfigurations":398},{"removed":"ifbench","score":0.6793159220301067,"rank":22,"remainingConfigurations":398},{"removed":"itbench","score":0.6808242254639869,"rank":22,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6811422046384573,"rank":22,"remainingConfigurations":398},{"removed":"math500","score":0.6811421581996936,"rank":22,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6835641081469381,"rank":22,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6875587153126457,"rank":22,"remainingConfigurations":398},{"removed":"omniscience","score":0.6814591605884273,"rank":22,"remainingConfigurations":398},{"removed":"scicode","score":0.6820478284241647,"rank":22,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6798881600146994,"rank":22,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6578673066274575,"rank":21,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6774890898205183,"rank":25,"remainingConfigurations":398},{"removed":"deepswe","score":0.6480612126504489,"rank":19,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6812598054541947,"rank":22,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6798361210293523,"rank":21,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6420959165832151,"rank":22,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6859661672218845,"rank":22,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.7056308306073532,"rank":12,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6956332254606057,"rank":17,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6506623591159397,"rank":25,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6811724263321132,"rank":22,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6795245984119639,"rank":22,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6825271353141028,"rank":21,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6820952804881194,"rank":22,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6794776104417446,"rank":22,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6800660767874964,"rank":22,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6837216730270673,"rank":21,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.676096620971458,"rank":22,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6812712358527441,"rank":22,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6829284955454943,"rank":22,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6824002434887132,"rank":22,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6811068668454506,"rank":22,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6806476890477926,"rank":22,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6805391933415167,"rank":22,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6807236076163333,"rank":22,"remainingConfigurations":398},{"removed":"vibe-code","score":0.680510259285447,"rank":22,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-high":{"score":0.663948779715899,"rank":23,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6930490501117221,"rank":21,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6780243846258674,"rank":25,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6205090690334157,"rank":23,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6638668049505178,"rank":23,"remainingConfigurations":398},{"removed":"Scale","score":0.672395905420888,"rank":22,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6596729417537656,"rank":21,"remainingConfigurations":398},{"removed":"Cognition","score":0.6538065510437782,"rank":20,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6714792746112971,"rank":23,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6620297242427761,"rank":23,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6734976918827099,"rank":24,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6646811962658029,"rank":23,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6639663721802528,"rank":23,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6644497052207646,"rank":23,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.663921748909032,"rank":22,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.663948779715899,"rank":23,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6644167574649505,"rank":22,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6639392335289979,"rank":23,"remainingConfigurations":398},{"removed":"briefcase","score":0.6637949897722019,"rank":23,"remainingConfigurations":398},{"removed":"aime","score":0.6618891587570975,"rank":23,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6642433521987278,"rank":23,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6646247208738303,"rank":23,"remainingConfigurations":398},{"removed":"automationbench","score":0.6633322022890824,"rank":23,"remainingConfigurations":398},{"removed":"critpt","score":0.6641144471740869,"rank":24,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.663676208034465,"rank":23,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6621647695968608,"rank":23,"remainingConfigurations":398},{"removed":"gdpval","score":0.6638837753340198,"rank":23,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6638147859689537,"rank":23,"remainingConfigurations":398},{"removed":"gpqa","score":0.6644630683311491,"rank":23,"remainingConfigurations":398},{"removed":"harvey","score":0.6633425290699829,"rank":23,"remainingConfigurations":398},{"removed":"hle","score":0.670064583888882,"rank":23,"remainingConfigurations":398},{"removed":"ifbench","score":0.6665190943298017,"rank":23,"remainingConfigurations":398},{"removed":"itbench","score":0.6636664409067612,"rank":23,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6635647646410345,"rank":23,"remainingConfigurations":398},{"removed":"math500","score":0.6637949385666942,"rank":23,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6664512513728106,"rank":23,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6699787589396031,"rank":23,"remainingConfigurations":398},{"removed":"omniscience","score":0.6638624817628835,"rank":23,"remainingConfigurations":398},{"removed":"scicode","score":0.6635270632886989,"rank":23,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6664036818855134,"rank":23,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6596253400020351,"rank":20,"remainingConfigurations":398},{"removed":"arc-agi","score":0.676960325416561,"rank":26,"remainingConfigurations":398},{"removed":"deepswe","score":0.6204225252517489,"rank":23,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.663953697700976,"rank":23,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6663535497081493,"rank":23,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6538065510437782,"rank":20,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6646277990373559,"rank":23,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6638821504115993,"rank":23,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6638792524949987,"rank":23,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6674393759221612,"rank":22,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6641790858428623,"rank":23,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6630996298501826,"rank":23,"remainingConfigurations":398},{"removed":"livebench-language","score":0.664703357467494,"rank":23,"remainingConfigurations":398},{"removed":"livebench-data","score":0.664354570600315,"rank":23,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6625190157665649,"rank":23,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6633622430392331,"rank":23,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.665409246872115,"rank":23,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6620297242427761,"rank":23,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6626320039654248,"rank":23,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6625422771783146,"rank":23,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6679959959938216,"rank":23,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.663227339848737,"rank":23,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6636706021241793,"rank":23,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.663732342838745,"rank":23,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6634896665639859,"rank":23,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6633696968463049,"rank":23,"remainingConfigurations":398}]},"claude-fable-5-1--effort-low":{"score":0.6552335291648791,"rank":24,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6685953281310159,"rank":24,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6824996496099232,"rank":23,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6493588153667228,"rank":19,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6552385192579159,"rank":25,"remainingConfigurations":398},{"removed":"Scale","score":0.665411060259193,"rank":23,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6562300613462616,"rank":23,"remainingConfigurations":398},{"removed":"Cognition","score":0.5832234091198014,"rank":27,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6578277716927393,"rank":25,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6548310183614244,"rank":24,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6749614246015178,"rank":23,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6474541331137816,"rank":25,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6561031170697236,"rank":24,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6545434809679506,"rank":24,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6548992194899683,"rank":24,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6552335291648791,"rank":24,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6550670171060332,"rank":23,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.655326879412031,"rank":25,"remainingConfigurations":398},{"removed":"briefcase","score":0.6539822445845099,"rank":25,"remainingConfigurations":398},{"removed":"aime","score":0.6518635418459604,"rank":25,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6559984717906309,"rank":24,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6556260610824148,"rank":24,"remainingConfigurations":398},{"removed":"automationbench","score":0.6570949549308411,"rank":24,"remainingConfigurations":398},{"removed":"critpt","score":0.652406384903686,"rank":25,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6550187528024911,"rank":25,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6548173586603901,"rank":25,"remainingConfigurations":398},{"removed":"gdpval","score":0.6566080468156207,"rank":24,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6549017289800975,"rank":24,"remainingConfigurations":398},{"removed":"gpqa","score":0.6620328962165662,"rank":24,"remainingConfigurations":398},{"removed":"harvey","score":0.6530831747903524,"rank":25,"remainingConfigurations":398},{"removed":"hle","score":0.6594639036193685,"rank":24,"remainingConfigurations":398},{"removed":"ifbench","score":0.6511524419796212,"rank":24,"remainingConfigurations":398},{"removed":"itbench","score":0.654971832179505,"rank":24,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6543753850925844,"rank":24,"remainingConfigurations":398},{"removed":"math500","score":0.6548073342747571,"rank":24,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6576438879996888,"rank":24,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.661933966833462,"rank":24,"remainingConfigurations":398},{"removed":"omniscience","score":0.6560394605395157,"rank":24,"remainingConfigurations":398},{"removed":"scicode","score":0.6560256231207159,"rank":25,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6539533476634919,"rank":24,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6548870066637902,"rank":22,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6821001793311483,"rank":24,"remainingConfigurations":398},{"removed":"deepswe","score":0.6495573197330597,"rank":18,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6552706993946761,"rank":24,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6512965527517541,"rank":24,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5832234091198014,"rank":27,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6550518257293546,"rank":24,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6519159959986102,"rank":25,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6558751562262795,"rank":24,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6525777452866183,"rank":24,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6550766084269358,"rank":25,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6532504001419847,"rank":25,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6569839991753721,"rank":24,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6559623807795699,"rank":24,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6533132303933303,"rank":24,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6539797806138586,"rank":25,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6580194918982224,"rank":24,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6548310183614244,"rank":24,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6555773337349303,"rank":24,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6541914705310806,"rank":24,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6582056995243161,"rank":25,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6549849840001337,"rank":24,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.654697665704433,"rank":25,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6544633765408957,"rank":24,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6548487006280026,"rank":24,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6541816317319299,"rank":24,"remainingConfigurations":398}]},"gpt-5.5-pro--effort-xhigh":{"score":0.655099015064508,"rank":25,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6608931215021303,"rank":25,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6552432538047583,"rank":29,"remainingConfigurations":398},{"removed":"Datacurve","score":0.6316797152183141,"rank":22,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6554161097685998,"rank":24,"remainingConfigurations":398},{"removed":"Scale","score":0.6637961151476638,"rank":24,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6550646329759308,"rank":24,"remainingConfigurations":398},{"removed":"Cognition","score":0.6662363380879722,"rank":19,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6588060929812243,"rank":24,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.653432208975974,"rank":25,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6456257893354683,"rank":25,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6521794580105892,"rank":24,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.65476086980955,"rank":25,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6539108700162238,"rank":25,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6548996691721539,"rank":23,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.655099015064508,"rank":25,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6533553956060739,"rank":24,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6553854650985278,"rank":24,"remainingConfigurations":398},{"removed":"briefcase","score":0.6551566536593648,"rank":24,"remainingConfigurations":398},{"removed":"aime","score":0.6574740220358303,"rank":24,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6557899663622929,"rank":25,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6532478076052504,"rank":25,"remainingConfigurations":398},{"removed":"automationbench","score":0.6549100134865073,"rank":25,"remainingConfigurations":398},{"removed":"critpt","score":0.6699296915130014,"rank":23,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.655185466333139,"rank":24,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6565988187939187,"rank":24,"remainingConfigurations":398},{"removed":"gdpval","score":0.6551199991648043,"rank":25,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6546763320209861,"rank":25,"remainingConfigurations":398},{"removed":"gpqa","score":0.6555515743970487,"rank":25,"remainingConfigurations":398},{"removed":"harvey","score":0.6536639239618729,"rank":24,"remainingConfigurations":398},{"removed":"hle","score":0.6574157095105164,"rank":25,"remainingConfigurations":398},{"removed":"ifbench","score":0.6510544537872646,"rank":25,"remainingConfigurations":398},{"removed":"itbench","score":0.6548807106457314,"rank":25,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6542088607298778,"rank":25,"remainingConfigurations":398},{"removed":"math500","score":0.6545965392222516,"rank":25,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6573043829547561,"rank":25,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6615590769237572,"rank":25,"remainingConfigurations":398},{"removed":"omniscience","score":0.6528345763294495,"rank":25,"remainingConfigurations":398},{"removed":"scicode","score":0.6568184395065337,"rank":24,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6519434763764752,"rank":25,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6541822454557159,"rank":23,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6540865162629651,"rank":29,"remainingConfigurations":398},{"removed":"deepswe","score":0.6317701472759332,"rank":22,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6551142102402324,"rank":25,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6478959207122522,"rank":25,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6662363380879722,"rank":19,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6545862259581651,"rank":25,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6532650873994413,"rank":24,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6543352516427884,"rank":25,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6536809230331667,"rank":23,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6552129063612998,"rank":24,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6540131645266533,"rank":24,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6562236791071906,"rank":25,"remainingConfigurations":398},{"removed":"livebench-data","score":0.655752957335979,"rank":25,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6530435766505356,"rank":25,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6542865497388856,"rank":24,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6571050552909018,"rank":25,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.653432208975974,"rank":25,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6527679204756404,"rank":25,"remainingConfigurations":398},{"removed":"frontiermath","score":0.64736974297185,"rank":25,"remainingConfigurations":398},{"removed":"simpleqa","score":0.664856241633852,"rank":24,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6546703105558227,"rank":25,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6547837776873074,"rank":24,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.6543211231175927,"rank":25,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6547162256622172,"rank":25,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6540440027518075,"rank":25,"remainingConfigurations":398}]},"grok-4.6--effort-high":{"score":0.6242971525570876,"rank":26,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6207800819011586,"rank":26,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6744394857635437,"rank":27,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5917382535883272,"rank":25,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6243139750439891,"rank":26,"remainingConfigurations":398},{"removed":"Scale","score":0.6326384384175531,"rank":26,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.588357564597371,"rank":30,"remainingConfigurations":398},{"removed":"Cognition","score":0.610052702565364,"rank":26,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6292779696119354,"rank":26,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6233578915859895,"rank":26,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.642506811109561,"rank":27,"remainingConfigurations":381},{"removed":"Vals AI","score":0.620816352868044,"rank":27,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6239964985673615,"rank":26,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6233304199384854,"rank":26,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6242521113724668,"rank":25,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6242971525570876,"rank":26,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6229677059623371,"rank":25,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.626334991110209,"rank":26,"remainingConfigurations":398},{"removed":"briefcase","score":0.6229507806358211,"rank":26,"remainingConfigurations":398},{"removed":"aime","score":0.6222886211563466,"rank":26,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6248294269797002,"rank":26,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6268233406185036,"rank":26,"remainingConfigurations":398},{"removed":"automationbench","score":0.6220340547248394,"rank":26,"remainingConfigurations":398},{"removed":"critpt","score":0.6253712513933918,"rank":26,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6229641990122138,"rank":26,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6261884872189852,"rank":26,"remainingConfigurations":398},{"removed":"gdpval","score":0.6238218274176321,"rank":26,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6244190953467282,"rank":26,"remainingConfigurations":398},{"removed":"gpqa","score":0.6176090946038993,"rank":27,"remainingConfigurations":398},{"removed":"harvey","score":0.6146971499312802,"rank":27,"remainingConfigurations":398},{"removed":"hle","score":0.6281745152966045,"rank":27,"remainingConfigurations":398},{"removed":"ifbench","score":0.6221105844112015,"rank":26,"remainingConfigurations":398},{"removed":"itbench","score":0.624008616579699,"rank":26,"remainingConfigurations":398},{"removed":"livecodebench","score":0.624428924561908,"rank":26,"remainingConfigurations":398},{"removed":"math500","score":0.6243831284421867,"rank":26,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6273395984745515,"rank":26,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6316563495022841,"rank":26,"remainingConfigurations":398},{"removed":"omniscience","score":0.6257554330823583,"rank":26,"remainingConfigurations":398},{"removed":"scicode","score":0.6247205626338287,"rank":26,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6213727192505786,"rank":26,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5857947394441582,"rank":30,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6708659791402622,"rank":27,"remainingConfigurations":398},{"removed":"deepswe","score":0.5918547108017448,"rank":25,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6243535894603599,"rank":26,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6206877813344448,"rank":26,"remainingConfigurations":398},{"removed":"frontiercode","score":0.610052702565364,"rank":26,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6239307083050177,"rank":26,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.622065048219514,"rank":26,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6239714964462294,"rank":26,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6229184321126219,"rank":26,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6245371655247288,"rank":26,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.62332285233856,"rank":26,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6255900722671891,"rank":26,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6254558383411778,"rank":26,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6219730971255345,"rank":26,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6233707516536519,"rank":26,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6258084941017615,"rank":26,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6233578915859895,"rank":26,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6194913237105566,"rank":27,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6248068942036299,"rank":26,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6361128093087035,"rank":26,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6310946887663874,"rank":26,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6225793606898107,"rank":27,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.619143463024878,"rank":26,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6300894479049148,"rank":26,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6259772821988383,"rank":26,"remainingConfigurations":398}]},"kimi-k3--effort-max":{"score":0.6199710263061422,"rank":27,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6093561943238702,"rank":28,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6681861986757642,"rank":28,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5395860598243595,"rank":29,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6199011781556835,"rank":27,"remainingConfigurations":398},{"removed":"Scale","score":0.6296705716642855,"rank":27,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.6190483099553459,"rank":27,"remainingConfigurations":398},{"removed":"Cognition","score":0.6233135409052678,"rank":24,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6267183703679492,"rank":27,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.6145579407220519,"rank":27,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6359153121313926,"rank":28,"remainingConfigurations":381},{"removed":"Vals AI","score":0.6280861867904198,"rank":26,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6199077166707122,"rank":27,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5339143447398257,"rank":37,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.62014627082401,"rank":26,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6199710263061422,"rank":27,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5344327625071074,"rank":37,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6217621796251711,"rank":27,"remainingConfigurations":398},{"removed":"briefcase","score":0.6194456812252659,"rank":27,"remainingConfigurations":398},{"removed":"aime","score":0.6195612540879366,"rank":27,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6193741039291093,"rank":27,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6193948155241557,"rank":27,"remainingConfigurations":398},{"removed":"automationbench","score":0.615219232014076,"rank":27,"remainingConfigurations":398},{"removed":"critpt","score":0.6205326684852738,"rank":27,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.6201646372148297,"rank":27,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.6210884540669405,"rank":27,"remainingConfigurations":398},{"removed":"gdpval","score":0.6202129951923476,"rank":27,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6201089921109567,"rank":27,"remainingConfigurations":398},{"removed":"gpqa","score":0.6218942583581984,"rank":26,"remainingConfigurations":398},{"removed":"harvey","score":0.6148820063733993,"rank":26,"remainingConfigurations":398},{"removed":"hle","score":0.6332329962232067,"rank":26,"remainingConfigurations":398},{"removed":"ifbench","score":0.6184721029073817,"rank":27,"remainingConfigurations":398},{"removed":"itbench","score":0.6188872140676175,"rank":27,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6200382970926893,"rank":27,"remainingConfigurations":398},{"removed":"math500","score":0.6200646091876978,"rank":27,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6263267426717714,"rank":27,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6304872857384917,"rank":27,"remainingConfigurations":398},{"removed":"omniscience","score":0.6219886976525276,"rank":27,"remainingConfigurations":398},{"removed":"scicode","score":0.6199209929274235,"rank":27,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6182804128897729,"rank":27,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6200407355317873,"rank":27,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6682496284431253,"rank":28,"remainingConfigurations":398},{"removed":"deepswe","score":0.5422888822704596,"rank":28,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6197953673312012,"rank":27,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.6176303026993293,"rank":27,"remainingConfigurations":398},{"removed":"frontiercode","score":0.6233135409052678,"rank":24,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6202349338919096,"rank":27,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.6175602960061476,"rank":27,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6191138869418072,"rank":27,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.6192626293481038,"rank":27,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6200181336897495,"rank":27,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6178155169474785,"rank":27,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6212865560464312,"rank":27,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6217124357907148,"rank":27,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.6183568730509844,"rank":27,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.6186749580202067,"rank":27,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.621946156313141,"rank":27,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.6145579407220519,"rank":27,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.6199077588556791,"rank":26,"remainingConfigurations":398},{"removed":"frontiermath","score":0.615037966333292,"rank":27,"remainingConfigurations":398},{"removed":"simpleqa","score":0.629089545145633,"rank":27,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.6189190924759013,"rank":27,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6310457582876555,"rank":26,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.616604027898756,"rank":27,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.6138561101567129,"rank":27,"remainingConfigurations":398},{"removed":"vibe-code","score":0.6167442515034499,"rank":27,"remainingConfigurations":398}]},"gemini-3.7-flash--effort-medium":{"score":0.6008659847874989,"rank":28,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.6177191707763353,"rank":27,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6818906746373878,"rank":24,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5459032499448208,"rank":27,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.6010748694969044,"rank":28,"remainingConfigurations":398},{"removed":"Scale","score":0.6107021092241014,"rank":28,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.599431879482558,"rank":28,"remainingConfigurations":398},{"removed":"Cognition","score":0.5276123855998012,"rank":36,"remainingConfigurations":398},{"removed":"LiveBench","score":0.6078240476768016,"rank":28,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5963792066787121,"rank":28,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6146329152470589,"rank":30,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5986844224119449,"rank":28,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.6010511207499748,"rank":28,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5998250267823834,"rank":28,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.6009879211959593,"rank":28,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.6008659847874989,"rank":28,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6001131979262336,"rank":28,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.6011129408022037,"rank":28,"remainingConfigurations":398},{"removed":"briefcase","score":0.6005927244065042,"rank":28,"remainingConfigurations":398},{"removed":"aime","score":0.5993758667407557,"rank":28,"remainingConfigurations":398},{"removed":"apex-agents","score":0.6016100033903612,"rank":28,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.6003514374508527,"rank":28,"remainingConfigurations":398},{"removed":"automationbench","score":0.5997147827516439,"rank":28,"remainingConfigurations":398},{"removed":"critpt","score":0.6036714683528076,"rank":28,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5950821792320017,"rank":29,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.60183868885811,"rank":28,"remainingConfigurations":398},{"removed":"gdpval","score":0.6030001250594796,"rank":28,"remainingConfigurations":398},{"removed":"gmmlu","score":0.6007438778990193,"rank":28,"remainingConfigurations":398},{"removed":"gpqa","score":0.6007010854394108,"rank":28,"remainingConfigurations":398},{"removed":"harvey","score":0.5982912644480246,"rank":28,"remainingConfigurations":398},{"removed":"hle","score":0.607945821680164,"rank":28,"remainingConfigurations":398},{"removed":"ifbench","score":0.5978680349478132,"rank":28,"remainingConfigurations":398},{"removed":"itbench","score":0.6006682606527368,"rank":28,"remainingConfigurations":398},{"removed":"livecodebench","score":0.6008594710392231,"rank":28,"remainingConfigurations":398},{"removed":"math500","score":0.6008099484175381,"rank":28,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.6051665497946658,"rank":28,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6082824351556021,"rank":28,"remainingConfigurations":398},{"removed":"omniscience","score":0.6018951432038021,"rank":28,"remainingConfigurations":398},{"removed":"scicode","score":0.5982870723581718,"rank":28,"remainingConfigurations":398},{"removed":"tau-bench","score":0.6002924290279749,"rank":28,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.6009711956777423,"rank":28,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6855425845099918,"rank":23,"remainingConfigurations":398},{"removed":"deepswe","score":0.5460498084316087,"rank":27,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.6009258959879608,"rank":28,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5946201417785034,"rank":28,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5276123855998012,"rank":36,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.6006996138977206,"rank":28,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5983676035298637,"rank":28,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.6006575662174148,"rank":28,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5995278654374834,"rank":28,"remainingConfigurations":398},{"removed":"livebench-math","score":0.6011363071115214,"rank":28,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.6001154134382266,"rank":28,"remainingConfigurations":398},{"removed":"livebench-language","score":0.6019481226891524,"rank":28,"remainingConfigurations":398},{"removed":"livebench-data","score":0.6020386098902346,"rank":28,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.598534432814838,"rank":28,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5998306088344574,"rank":28,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.6024212751005474,"rank":28,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5963792066787121,"rank":28,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5955908344634702,"rank":28,"remainingConfigurations":398},{"removed":"frontiermath","score":0.6016882621862091,"rank":28,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6067342431506565,"rank":28,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5995622825685301,"rank":28,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.6008403099164652,"rank":28,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5998805929597165,"rank":28,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.600787410087424,"rank":28,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5999608772815835,"rank":28,"remainingConfigurations":398}]},"grok-4.6--effort-medium":{"score":0.5960357182482909,"rank":29,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5966056145828758,"rank":29,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6956808783257035,"rank":21,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5338125506067563,"rank":31,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5962089053442358,"rank":29,"remainingConfigurations":398},{"removed":"Scale","score":0.6059362777287205,"rank":29,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5981722024796107,"rank":29,"remainingConfigurations":398},{"removed":"Cognition","score":0.5384716840268207,"rank":35,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5995813937319261,"rank":29,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5931246881513129,"rank":29,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.603330862784362,"rank":31,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5908998670566268,"rank":29,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5961592510167489,"rank":29,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.595202666792067,"rank":29,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5960551456643634,"rank":29,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5960357182482909,"rank":29,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5953251618608743,"rank":29,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5964720776118687,"rank":29,"remainingConfigurations":398},{"removed":"briefcase","score":0.5939681214022711,"rank":29,"remainingConfigurations":398},{"removed":"aime","score":0.5943706793239404,"rank":29,"remainingConfigurations":398},{"removed":"apex-agents","score":0.596911918773351,"rank":29,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5968392029607837,"rank":29,"remainingConfigurations":398},{"removed":"automationbench","score":0.5924731441912284,"rank":29,"remainingConfigurations":398},{"removed":"critpt","score":0.5948426019686744,"rank":29,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5961542116473093,"rank":28,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5980068363052368,"rank":29,"remainingConfigurations":398},{"removed":"gdpval","score":0.5955169925315308,"rank":29,"remainingConfigurations":398},{"removed":"gmmlu","score":0.595849038727886,"rank":29,"remainingConfigurations":398},{"removed":"gpqa","score":0.5949173498839803,"rank":30,"remainingConfigurations":398},{"removed":"harvey","score":0.5932742219294882,"rank":29,"remainingConfigurations":398},{"removed":"hle","score":0.6026504576756658,"rank":29,"remainingConfigurations":398},{"removed":"ifbench","score":0.5928856255789555,"rank":29,"remainingConfigurations":398},{"removed":"itbench","score":0.5958722137089697,"rank":29,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5958437009644454,"rank":29,"remainingConfigurations":398},{"removed":"math500","score":0.5958568585875592,"rank":29,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5993217692650862,"rank":29,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.6038292394960293,"rank":29,"remainingConfigurations":398},{"removed":"omniscience","score":0.599347909495489,"rank":29,"remainingConfigurations":398},{"removed":"scicode","score":0.5967278286917758,"rank":29,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5942160550834755,"rank":29,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5993072029619283,"rank":29,"remainingConfigurations":398},{"removed":"arc-agi","score":0.7051875697561726,"rank":20,"remainingConfigurations":398},{"removed":"deepswe","score":0.5339024559396989,"rank":31,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5960944121031665,"rank":29,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.590563593903672,"rank":29,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5384716840268207,"rank":35,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5955772188741143,"rank":29,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5935074197596152,"rank":29,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5957646416502064,"rank":29,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5946151241923191,"rank":29,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5962939998231848,"rank":29,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5949079816544677,"rank":29,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5975173739770047,"rank":29,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5966120988671751,"rank":29,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5936251426536646,"rank":29,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5950345558342494,"rank":29,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.598195822462356,"rank":29,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5931246881513129,"rank":29,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5908513527343856,"rank":29,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5966327883690851,"rank":29,"remainingConfigurations":398},{"removed":"simpleqa","score":0.6019873920493779,"rank":29,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.595844345553773,"rank":29,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5956322188051697,"rank":29,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5952090628707022,"rank":29,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5962486810197914,"rank":29,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5951125703294015,"rank":29,"remainingConfigurations":398}]},"gemini-3.7-flash--effort-high":{"score":0.5762273256525265,"rank":30,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5792967833127519,"rank":31,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5816386089073672,"rank":32,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5188588819490351,"rank":32,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5763079444471132,"rank":30,"remainingConfigurations":398},{"removed":"Scale","score":0.5865648769657136,"rank":30,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.630284741654397,"rank":25,"remainingConfigurations":398},{"removed":"Cognition","score":0.5525088322752114,"rank":33,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5993803758857453,"rank":30,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5719784857410353,"rank":30,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5804519501464633,"rank":32,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5714935585469646,"rank":31,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5757565675533844,"rank":30,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.575600014365056,"rank":30,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5756792829416779,"rank":30,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5762273256525265,"rank":30,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5745633677040992,"rank":30,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5734844645681718,"rank":31,"remainingConfigurations":398},{"removed":"briefcase","score":0.5778116051007733,"rank":30,"remainingConfigurations":398},{"removed":"aime","score":0.5789572062654922,"rank":30,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5766052694051872,"rank":30,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5772761342850138,"rank":30,"remainingConfigurations":398},{"removed":"automationbench","score":0.5744400842565568,"rank":30,"remainingConfigurations":398},{"removed":"critpt","score":0.5778924994080622,"rank":30,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5763465269327593,"rank":31,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5768465462406228,"rank":31,"remainingConfigurations":398},{"removed":"gdpval","score":0.5769000785453693,"rank":30,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5763288135200977,"rank":30,"remainingConfigurations":398},{"removed":"gpqa","score":0.5719685755163691,"rank":31,"remainingConfigurations":398},{"removed":"harvey","score":0.5713394193862352,"rank":30,"remainingConfigurations":398},{"removed":"hle","score":0.5793157649629127,"rank":30,"remainingConfigurations":398},{"removed":"ifbench","score":0.574273803066707,"rank":30,"remainingConfigurations":398},{"removed":"itbench","score":0.5759288194555526,"rank":30,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5764200908495226,"rank":30,"remainingConfigurations":398},{"removed":"math500","score":0.5763208290774072,"rank":30,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5769273479260432,"rank":31,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5840125781413555,"rank":30,"remainingConfigurations":398},{"removed":"omniscience","score":0.5772647890535002,"rank":32,"remainingConfigurations":398},{"removed":"scicode","score":0.576376131015013,"rank":30,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5751762793256675,"rank":30,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.629874717439614,"rank":25,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5807126340172339,"rank":33,"remainingConfigurations":398},{"removed":"deepswe","score":0.5189478544387282,"rank":32,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5762893506210577,"rank":30,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5745095257529788,"rank":30,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5525088322752114,"rank":33,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5769273360085779,"rank":30,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5740290355982774,"rank":30,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5758779065375018,"rank":30,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.575078564498465,"rank":30,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5763631810003307,"rank":30,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.580753672493846,"rank":30,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5731761997244967,"rank":31,"remainingConfigurations":398},{"removed":"livebench-data","score":0.588210662372799,"rank":30,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5705205759430143,"rank":31,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5761761598963709,"rank":30,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5686421112747749,"rank":31,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5719784857410353,"rank":30,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5723718613013845,"rank":30,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5825423173016872,"rank":30,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5742980602013011,"rank":31,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5683425061007576,"rank":31,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5833252937946937,"rank":30,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5827842324572785,"rank":30,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5722827300910436,"rank":31,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5795276462173541,"rank":30,"remainingConfigurations":398}]},"glm-5.3--effort-max":{"score":0.5751539158922038,"rank":31,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5871645928276896,"rank":30,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5900667824606032,"rank":31,"remainingConfigurations":398},{"removed":"Datacurve","score":0.477268999355972,"rank":39,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5751488225193386,"rank":31,"remainingConfigurations":398},{"removed":"Scale","score":0.5849304052781863,"rank":31,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5711551631886068,"rank":31,"remainingConfigurations":398},{"removed":"Cognition","score":0.5574936377128249,"rank":31,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5841993708139294,"rank":31,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5709711704960461,"rank":31,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.6321300598613101,"rank":29,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5791026288484915,"rank":30,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5742675190067484,"rank":31,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5732655919622561,"rank":31,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5753121001360298,"rank":31,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5751539158922038,"rank":31,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5725339301082918,"rank":31,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.574896256397205,"rank":30,"remainingConfigurations":398},{"removed":"briefcase","score":0.5734710480635478,"rank":31,"remainingConfigurations":398},{"removed":"aime","score":0.5755971196701779,"rank":31,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5755402125877814,"rank":31,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5740623913883182,"rank":31,"remainingConfigurations":398},{"removed":"automationbench","score":0.5724630012594536,"rank":31,"remainingConfigurations":398},{"removed":"critpt","score":0.5759987595909123,"rank":31,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5797136946066546,"rank":30,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5796115857390501,"rank":30,"remainingConfigurations":398},{"removed":"gdpval","score":0.5737061234402372,"rank":31,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5752633919636495,"rank":31,"remainingConfigurations":398},{"removed":"gpqa","score":0.5711971576197433,"rank":32,"remainingConfigurations":398},{"removed":"harvey","score":0.570045125907736,"rank":31,"remainingConfigurations":398},{"removed":"hle","score":0.5782236120985765,"rank":31,"remainingConfigurations":398},{"removed":"ifbench","score":0.5733057725030014,"rank":31,"remainingConfigurations":398},{"removed":"itbench","score":0.5747435044206614,"rank":31,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5752769546470554,"rank":31,"remainingConfigurations":398},{"removed":"math500","score":0.5752487151913408,"rank":31,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5865992209176133,"rank":30,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5835863141102503,"rank":31,"remainingConfigurations":398},{"removed":"omniscience","score":0.5785722219358541,"rank":31,"remainingConfigurations":398},{"removed":"scicode","score":0.5738773042433138,"rank":31,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5716839731604891,"rank":31,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5742565507530114,"rank":31,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5895375519689163,"rank":32,"remainingConfigurations":398},{"removed":"deepswe","score":0.4777631221445809,"rank":40,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5752213121957914,"rank":31,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5733091660906237,"rank":31,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5574936377128249,"rank":31,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5757778167638292,"rank":31,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5728883197417486,"rank":31,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5748628131234007,"rank":31,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5737407350158742,"rank":31,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5749493357318823,"rank":31,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5740278250021706,"rank":31,"remainingConfigurations":398},{"removed":"livebench-language","score":0.576087078974833,"rank":30,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5780465675220048,"rank":31,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5723132271682175,"rank":30,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5741500568987075,"rank":31,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5765284258020774,"rank":30,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5709711704960461,"rank":31,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5717719623431842,"rank":31,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5708837391142353,"rank":31,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5873594989564092,"rank":30,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5724943489031996,"rank":30,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5735791306230295,"rank":31,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5666296048774779,"rank":31,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5806338850149454,"rank":30,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5722747060423162,"rank":31,"remainingConfigurations":398}]},"muse-spark-1.3--effort-max":{"score":0.5617102430924915,"rank":32,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.6055955672552145,"rank":30,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5414428459927696,"rank":28,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5602152371541581,"rank":32,"remainingConfigurations":398},{"removed":"Scale","score":0.5742057084024877,"rank":32,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5665334000918402,"rank":32,"remainingConfigurations":398},{"removed":"Cognition","score":0.5788745134258186,"rank":28,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5665045795268596,"rank":33,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5670588953016694,"rank":32,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5634735288721463,"rank":34,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5593673161676577,"rank":32,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5616284973247846,"rank":32,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5611571806152528,"rank":32,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5615747500913693,"rank":32,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5617102430924915,"rank":32,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5609150030704065,"rank":32,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5634046895326849,"rank":32,"remainingConfigurations":398},{"removed":"briefcase","score":0.5498479291688471,"rank":33,"remainingConfigurations":398},{"removed":"aime","score":0.5581084754271424,"rank":32,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5645940327791514,"rank":32,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5621364536673437,"rank":32,"remainingConfigurations":398},{"removed":"automationbench","score":0.5585890226890893,"rank":32,"remainingConfigurations":398},{"removed":"critpt","score":0.5744594220593046,"rank":32,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5639246294433163,"rank":32,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5587897652630119,"rank":32,"remainingConfigurations":398},{"removed":"gdpval","score":0.5593611848488839,"rank":32,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5604498471785037,"rank":32,"remainingConfigurations":398},{"removed":"gpqa","score":0.566088084712817,"rank":33,"remainingConfigurations":398},{"removed":"harvey","score":0.5616177104529793,"rank":32,"remainingConfigurations":398},{"removed":"hle","score":0.5756875530093245,"rank":32,"remainingConfigurations":398},{"removed":"ifbench","score":0.5522731302667561,"rank":33,"remainingConfigurations":398},{"removed":"itbench","score":0.5625225915372782,"rank":32,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5565570246345781,"rank":32,"remainingConfigurations":398},{"removed":"math500","score":0.559595286971979,"rank":32,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5613972735718732,"rank":32,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5709441192926749,"rank":32,"remainingConfigurations":398},{"removed":"omniscience","score":0.593653771873568,"rank":30,"remainingConfigurations":398},{"removed":"scicode","score":0.5582671094404222,"rank":32,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5491082971153557,"rank":33,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5650439361597402,"rank":32,"remainingConfigurations":398},{"removed":"arc-agi","score":0.6031097292583575,"rank":30,"remainingConfigurations":398},{"removed":"deepswe","score":0.5416260838708623,"rank":29,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5617808667743793,"rank":32,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5590829486820484,"rank":32,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5788745134258186,"rank":28,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5621313552926802,"rank":32,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5597375421685354,"rank":32,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5611360807000123,"rank":32,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5603632028065674,"rank":32,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5619646050041018,"rank":32,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5606660127872466,"rank":32,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5636022138499103,"rank":32,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5621044180695046,"rank":32,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.559099469533444,"rank":32,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5606798668795213,"rank":32,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5637537301150394,"rank":32,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5670588953016694,"rank":32,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5532029890099809,"rank":32,"remainingConfigurations":398},{"removed":"frontiermath","score":0.564376992495504,"rank":32,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5684237002009792,"rank":32,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.561000314544757,"rank":32,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5612698532088375,"rank":32,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5609309894530897,"rank":32,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.56167183870895,"rank":32,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5605113600700312,"rank":32,"remainingConfigurations":398}]},"claude-fable-5--effort-low":{"score":0.5548028564797248,"rank":33,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5417623933539492,"rank":36,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5453235740866297,"rank":37,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5388985982878852,"rank":30,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5551200413894012,"rank":33,"remainingConfigurations":398},{"removed":"Scale","score":0.5646563004746729,"rank":34,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5555574672455328,"rank":34,"remainingConfigurations":398},{"removed":"Cognition","score":0.48248390494982624,"rank":41,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5595721606656398,"rank":34,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5531760536097929,"rank":33,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.645509921904882,"rank":26,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5436229112783587,"rank":35,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5541739168811173,"rank":33,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5539190755927207,"rank":33,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5548105095662933,"rank":33,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5548028564797248,"rank":33,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5532795703379354,"rank":33,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5549177085748506,"rank":33,"remainingConfigurations":398},{"removed":"briefcase","score":0.5542864205929922,"rank":32,"remainingConfigurations":398},{"removed":"aime","score":0.529086758757478,"rank":37,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5555166383823038,"rank":33,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5547200500711532,"rank":33,"remainingConfigurations":398},{"removed":"automationbench","score":0.5547939347654469,"rank":33,"remainingConfigurations":398},{"removed":"critpt","score":0.5527278104797189,"rank":33,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5547191150683021,"rank":33,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5559206162313428,"rank":33,"remainingConfigurations":398},{"removed":"gdpval","score":0.5547716128025284,"rank":33,"remainingConfigurations":398},{"removed":"gmmlu","score":0.55487754682395,"rank":33,"remainingConfigurations":398},{"removed":"gpqa","score":0.5983520977928986,"rank":29,"remainingConfigurations":398},{"removed":"harvey","score":0.5529836063047465,"rank":34,"remainingConfigurations":398},{"removed":"hle","score":0.5599941151407118,"rank":33,"remainingConfigurations":398},{"removed":"ifbench","score":0.5529457603011605,"rank":32,"remainingConfigurations":398},{"removed":"itbench","score":0.554450776719546,"rank":33,"remainingConfigurations":398},{"removed":"livecodebench","score":0.555098903779367,"rank":33,"remainingConfigurations":398},{"removed":"math500","score":0.5548258194463269,"rank":33,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5585128483016156,"rank":33,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5637594012492648,"rank":33,"remainingConfigurations":398},{"removed":"omniscience","score":0.5543390236246033,"rank":33,"remainingConfigurations":398},{"removed":"scicode","score":0.555923662297691,"rank":33,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5531916159408008,"rank":32,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5552515724069822,"rank":33,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5468849206980285,"rank":37,"remainingConfigurations":398},{"removed":"deepswe","score":0.5391238734992436,"rank":30,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5548530625806043,"rank":33,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5532903518980231,"rank":34,"remainingConfigurations":398},{"removed":"frontiercode","score":0.48248390494982624,"rank":41,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5557661431750511,"rank":33,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5511189606431603,"rank":33,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.554208727453608,"rank":33,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5533131471273905,"rank":34,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5548396820553666,"rank":33,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5526159470789843,"rank":33,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5567118107878652,"rank":33,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5557602511473164,"rank":33,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5524310255466024,"rank":33,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5533111879038811,"rank":33,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5579056077172485,"rank":33,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5531760536097929,"rank":33,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5463430866083148,"rank":34,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5493529427101981,"rank":34,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5571567370983789,"rank":35,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5542859982917135,"rank":33,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5543127570706887,"rank":33,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5538490460286482,"rank":33,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5543958419560043,"rank":33,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5537411437417475,"rank":33,"remainingConfigurations":398}]},"gpt-5.5--effort-xhigh":{"score":0.5486217356893452,"rank":34,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5554338004991549,"rank":34,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5647854959245665,"rank":35,"remainingConfigurations":398},{"removed":"Datacurve","score":0.5078364459201665,"rank":33,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5485690382757453,"rank":34,"remainingConfigurations":398},{"removed":"Scale","score":0.567967014188802,"rank":33,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5389009205291936,"rank":37,"remainingConfigurations":398},{"removed":"Cognition","score":0.55890637599387,"rank":30,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5549031035815287,"rank":35,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5305473488894082,"rank":37,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5562909892310447,"rank":35,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5546725058982415,"rank":33,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.548493922873773,"rank":34,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.6103088906975455,"rank":27,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5482948346618007,"rank":34,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5486217356893452,"rank":34,"remainingConfigurations":398},{"removed":"All provider reports","score":0.6095334329042226,"rank":27,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5479613860214637,"rank":34,"remainingConfigurations":398},{"removed":"briefcase","score":0.5488741384735752,"rank":34,"remainingConfigurations":398},{"removed":"aime","score":0.548196040533338,"rank":33,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5483853073201178,"rank":34,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5485972396444067,"rank":34,"remainingConfigurations":398},{"removed":"automationbench","score":0.5495765260331473,"rank":34,"remainingConfigurations":398},{"removed":"critpt","score":0.548973971014493,"rank":35,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5485462878038887,"rank":35,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5491738512591003,"rank":35,"remainingConfigurations":398},{"removed":"gdpval","score":0.5488535969967372,"rank":34,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5487523109043194,"rank":34,"remainingConfigurations":398},{"removed":"gpqa","score":0.5401046881306096,"rank":37,"remainingConfigurations":398},{"removed":"harvey","score":0.5495006222446139,"rank":35,"remainingConfigurations":398},{"removed":"hle","score":0.556667575855601,"rank":34,"remainingConfigurations":398},{"removed":"ifbench","score":0.5477965299793549,"rank":34,"remainingConfigurations":398},{"removed":"itbench","score":0.5478806277975466,"rank":34,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5486719635162461,"rank":34,"remainingConfigurations":398},{"removed":"math500","score":0.5486993848806775,"rank":34,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5542707837541105,"rank":34,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5547418921060263,"rank":36,"remainingConfigurations":398},{"removed":"omniscience","score":0.5494511622904769,"rank":35,"remainingConfigurations":398},{"removed":"scicode","score":0.549127359743873,"rank":35,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5477681629254855,"rank":34,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.541756916861414,"rank":36,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5639902778813072,"rank":34,"remainingConfigurations":398},{"removed":"deepswe","score":0.5031029425222743,"rank":33,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5466591899265545,"rank":36,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5472616886590899,"rank":35,"remainingConfigurations":398},{"removed":"frontiercode","score":0.55890637599387,"rank":30,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5493019123798341,"rank":34,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5438692948354892,"rank":36,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5435920297683037,"rank":37,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5563659903286284,"rank":33,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5501605553265958,"rank":34,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5447010501326687,"rank":36,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5485384186961161,"rank":36,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5482224476217453,"rank":34,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5485250036773782,"rank":34,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5474066857336974,"rank":34,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5528301170966136,"rank":35,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5305473488894082,"rank":37,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5482292020174347,"rank":33,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5438833868615477,"rank":36,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5549747906457045,"rank":36,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5499314331853419,"rank":34,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5455795189826603,"rank":35,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5462795698889268,"rank":35,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5464702722771304,"rank":35,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5480449878333387,"rank":34,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-max":{"score":0.5473326004506027,"rank":35,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5565921277917433,"rank":33,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.570034054042932,"rank":34,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4792973861787824,"rank":37,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5472598921079513,"rank":35,"remainingConfigurations":398},{"removed":"Scale","score":0.5577396752195208,"rank":36,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.557763312721836,"rank":33,"remainingConfigurations":398},{"removed":"Cognition","score":0.5517331773427074,"rank":34,"remainingConfigurations":398},{"removed":"LiveBench","score":0.566854514340703,"rank":32,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5412422457778423,"rank":35,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5507069963443109,"rank":36,"remainingConfigurations":381},{"removed":"Vals AI","score":0.545959184101036,"rank":34,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5473289697370937,"rank":35,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5490976304148057,"rank":34,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5466304472908287,"rank":36,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5473326004506027,"rank":35,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5483303175620184,"rank":34,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.547341233218928,"rank":36,"remainingConfigurations":398},{"removed":"briefcase","score":0.5471357587290626,"rank":35,"remainingConfigurations":398},{"removed":"aime","score":0.5442309014431149,"rank":34,"remainingConfigurations":398},{"removed":"apex-agents","score":0.54670621413289,"rank":36,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5467704123397682,"rank":36,"remainingConfigurations":398},{"removed":"automationbench","score":0.5459789269898391,"rank":35,"remainingConfigurations":398},{"removed":"critpt","score":0.5475927796274127,"rank":36,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5501609278688413,"rank":34,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5471115097445742,"rank":36,"remainingConfigurations":398},{"removed":"gdpval","score":0.5473848313731238,"rank":35,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5474571783419023,"rank":35,"remainingConfigurations":398},{"removed":"gpqa","score":0.5450592072352172,"rank":34,"remainingConfigurations":398},{"removed":"harvey","score":0.5566321284610439,"rank":33,"remainingConfigurations":398},{"removed":"hle","score":0.5510637047127294,"rank":36,"remainingConfigurations":398},{"removed":"ifbench","score":0.5469264079996118,"rank":35,"remainingConfigurations":398},{"removed":"itbench","score":0.5456455197991322,"rank":36,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5473585943860447,"rank":35,"remainingConfigurations":398},{"removed":"math500","score":0.5474106283355921,"rank":35,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5519760248360265,"rank":35,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5553191710243198,"rank":35,"remainingConfigurations":398},{"removed":"omniscience","score":0.5483439489632672,"rank":36,"remainingConfigurations":398},{"removed":"scicode","score":0.5477691516883603,"rank":36,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5468858286006565,"rank":35,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5545669038708997,"rank":34,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5583321534449198,"rank":35,"remainingConfigurations":398},{"removed":"deepswe","score":0.4788102296917438,"rank":37,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5473191182779884,"rank":34,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5563342871151614,"rank":33,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5517331773427074,"rank":34,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5480138929023677,"rank":35,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5449871475765556,"rank":34,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5469604300512855,"rank":34,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5464384189214486,"rank":35,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5474351035885833,"rank":36,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5468631526610183,"rank":34,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5504071204864498,"rank":34,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5443952036889713,"rank":37,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5444232194242108,"rank":36,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5411072357938259,"rank":37,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5567167075667087,"rank":34,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5412422457778423,"rank":35,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.542963706743112,"rank":36,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5411797203869297,"rank":37,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5615647562584392,"rank":33,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5475481964652714,"rank":35,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5413772456347439,"rank":37,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5456005780646244,"rank":36,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5450917069305673,"rank":36,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5474281878681636,"rank":35,"remainingConfigurations":398}]},"grok-4.6--effort-xhigh":{"score":0.547225173220304,"rank":36,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5513497085006733,"rank":35,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5801016388575085,"rank":33,"remainingConfigurations":398},{"removed":"Datacurve","score":0.47842899074336875,"rank":38,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5470949846001263,"rank":36,"remainingConfigurations":398},{"removed":"Scale","score":0.5582213992422739,"rank":35,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5456306628801156,"rank":35,"remainingConfigurations":398},{"removed":"Cognition","score":0.5546895691467819,"rank":32,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5522730952795906,"rank":36,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5408801264226651,"rank":36,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5765142993729399,"rank":33,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5405559303115516,"rank":36,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5471533036448605,"rank":36,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5462896893355887,"rank":35,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5474293620340737,"rank":35,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.547225173220304,"rank":36,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5463936001887825,"rank":35,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5475368876604557,"rank":35,"remainingConfigurations":398},{"removed":"briefcase","score":0.5448683535182063,"rank":37,"remainingConfigurations":398},{"removed":"aime","score":0.5393917324618603,"rank":36,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5480598885489346,"rank":35,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5481725542251566,"rank":35,"remainingConfigurations":398},{"removed":"automationbench","score":0.5438432449565583,"rank":37,"remainingConfigurations":398},{"removed":"critpt","score":0.5491503758987133,"rank":34,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5475003731349913,"rank":36,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.549236618314744,"rank":34,"remainingConfigurations":398},{"removed":"gdpval","score":0.5458527280429741,"rank":36,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5471589827089126,"rank":36,"remainingConfigurations":398},{"removed":"gpqa","score":0.5409124458346785,"rank":36,"remainingConfigurations":398},{"removed":"harvey","score":0.5457081935029372,"rank":36,"remainingConfigurations":398},{"removed":"hle","score":0.5527146920897112,"rank":35,"remainingConfigurations":398},{"removed":"ifbench","score":0.5451420390297362,"rank":37,"remainingConfigurations":398},{"removed":"itbench","score":0.5469505796655151,"rank":35,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5468805441350781,"rank":36,"remainingConfigurations":398},{"removed":"math500","score":0.5470956932714774,"rank":36,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.551104019163363,"rank":36,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5557916554898337,"rank":34,"remainingConfigurations":398},{"removed":"omniscience","score":0.5507677907072895,"rank":34,"remainingConfigurations":398},{"removed":"scicode","score":0.5498636177704977,"rank":34,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5453442746600208,"rank":36,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.545762478741083,"rank":35,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5897419698049773,"rank":31,"remainingConfigurations":398},{"removed":"deepswe","score":0.4784498509849992,"rank":38,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5472646698690696,"rank":35,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5325840618346089,"rank":37,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5546895691467819,"rank":32,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5471510708029674,"rank":36,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5446269105572062,"rank":35,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.546915815033778,"rank":35,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.546163745680329,"rank":36,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5475004814915668,"rank":35,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5457115226808487,"rank":35,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5488744999077705,"rank":35,"remainingConfigurations":398},{"removed":"livebench-data","score":0.548085757489919,"rank":35,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5447584075644963,"rank":35,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5459917920182364,"rank":35,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5496174235759052,"rank":36,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5408801264226651,"rank":36,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5452127372035781,"rank":35,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5496015569947706,"rank":33,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5599473658936142,"rank":34,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5465439667244654,"rank":36,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5468006815202652,"rank":34,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5463182023190108,"rank":34,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5468379687793689,"rank":34,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5460790985711926,"rank":36,"remainingConfigurations":398}]},"gpt-5.5--effort-high":{"score":0.5443919929043515,"rank":37,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5607150077482996,"rank":32,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5469725781676326,"rank":36,"remainingConfigurations":398},{"removed":"Datacurve","score":0.49640312810559895,"rank":34,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5443379557508349,"rank":37,"remainingConfigurations":398},{"removed":"Scale","score":0.5567292621594561,"rank":37,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5421948174343352,"rank":36,"remainingConfigurations":398},{"removed":"Cognition","score":0.5766844737894709,"rank":29,"remainingConfigurations":398},{"removed":"LiveBench","score":0.552126763791695,"rank":37,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5424471925199255,"rank":34,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5453183087442924,"rank":38,"remainingConfigurations":381},{"removed":"Vals AI","score":0.5326450818986115,"rank":37,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5445679402429124,"rank":37,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5436473941102666,"rank":36,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5440462210755886,"rank":37,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5443919929043515,"rank":37,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5434494453638236,"rank":36,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5446334130313122,"rank":37,"remainingConfigurations":398},{"removed":"briefcase","score":0.5456503757529844,"rank":36,"remainingConfigurations":398},{"removed":"aime","score":0.5435628178986533,"rank":35,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5451958236342366,"rank":37,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5431345124678681,"rank":37,"remainingConfigurations":398},{"removed":"automationbench","score":0.5444590262033261,"rank":36,"remainingConfigurations":398},{"removed":"critpt","score":0.5445231337318767,"rank":37,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5444312079349228,"rank":37,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5427832302235186,"rank":37,"remainingConfigurations":398},{"removed":"gdpval","score":0.5449146260359905,"rank":37,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5444396138801259,"rank":37,"remainingConfigurations":398},{"removed":"gpqa","score":0.5419570276078559,"rank":35,"remainingConfigurations":398},{"removed":"harvey","score":0.5437716093782655,"rank":37,"remainingConfigurations":398},{"removed":"hle","score":0.548978425348572,"rank":37,"remainingConfigurations":398},{"removed":"ifbench","score":0.5456549926825224,"rank":36,"remainingConfigurations":398},{"removed":"itbench","score":0.5440845530105068,"rank":37,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5443226965990552,"rank":37,"remainingConfigurations":398},{"removed":"math500","score":0.5444319311210783,"rank":37,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5495848188076732,"rank":37,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5532585550984093,"rank":37,"remainingConfigurations":398},{"removed":"omniscience","score":0.54386084775077,"rank":37,"remainingConfigurations":398},{"removed":"scicode","score":0.5439967272969283,"rank":37,"remainingConfigurations":398},{"removed":"tau-bench","score":0.5446260210121522,"rank":37,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5356859636339371,"rank":37,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5505230924515957,"rank":36,"remainingConfigurations":398},{"removed":"deepswe","score":0.4963337977350311,"rank":34,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5444776883975243,"rank":37,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.5416854166398682,"rank":36,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5766844737894709,"rank":29,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5450613688468505,"rank":37,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5412902388813946,"rank":37,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.54427982494229,"rank":36,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5435460735645506,"rank":37,"remainingConfigurations":398},{"removed":"livebench-math","score":0.544767907318659,"rank":37,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5430637696000957,"rank":37,"remainingConfigurations":398},{"removed":"livebench-language","score":0.546107673238565,"rank":37,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5447472508272634,"rank":36,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5418890824160617,"rank":37,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5432292725703478,"rank":36,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5468978653355014,"rank":37,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5424471925199255,"rank":34,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5332973559339865,"rank":37,"remainingConfigurations":398},{"removed":"frontiermath","score":0.5459664770740122,"rank":35,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5515265971439766,"rank":37,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5445941878457264,"rank":37,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5443319697761193,"rank":36,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5447076432728382,"rank":37,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.544896621644391,"rank":37,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5441742942031832,"rank":37,"remainingConfigurations":398}]},"claude-opus-4-8--effort-max":{"score":0.5154012816616055,"rank":38,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5212217843850806,"rank":37,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5331147167164819,"rank":38,"remainingConfigurations":398},{"removed":"Datacurve","score":0.47302206125844176,"rank":41,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.5152939773055797,"rank":38,"remainingConfigurations":398},{"removed":"Scale","score":0.5272465499160399,"rank":39,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.5294855532261552,"rank":38,"remainingConfigurations":398},{"removed":"Cognition","score":0.5092555059563716,"rank":37,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5289761896821882,"rank":38,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.5102483916483955,"rank":39,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5460127909160288,"rank":37,"remainingConfigurations":381},{"removed":"Vals AI","score":0.48452605195094006,"rank":39,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.5161664448728059,"rank":38,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.5056996130612667,"rank":38,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5148296268231696,"rank":38,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.5154012816616055,"rank":38,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5061143256822513,"rank":38,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.5146483908587322,"rank":38,"remainingConfigurations":398},{"removed":"briefcase","score":0.5148660558476622,"rank":38,"remainingConfigurations":398},{"removed":"aime","score":0.5210290692774657,"rank":38,"remainingConfigurations":398},{"removed":"apex-agents","score":0.5155598708941821,"rank":38,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.5149204937871374,"rank":38,"remainingConfigurations":398},{"removed":"automationbench","score":0.5146440453124348,"rank":38,"remainingConfigurations":398},{"removed":"critpt","score":0.5159142230373838,"rank":38,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.5155333145330666,"rank":38,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.5159722293110399,"rank":38,"remainingConfigurations":398},{"removed":"gdpval","score":0.5152539540108202,"rank":38,"remainingConfigurations":398},{"removed":"gmmlu","score":0.5155335806994278,"rank":38,"remainingConfigurations":398},{"removed":"gpqa","score":0.5248347144624698,"rank":38,"remainingConfigurations":398},{"removed":"harvey","score":0.512093843744972,"rank":38,"remainingConfigurations":398},{"removed":"hle","score":0.5097908291440214,"rank":38,"remainingConfigurations":398},{"removed":"ifbench","score":0.5161876386663612,"rank":38,"remainingConfigurations":398},{"removed":"itbench","score":0.5147614630432417,"rank":38,"remainingConfigurations":398},{"removed":"livecodebench","score":0.5153926571107059,"rank":38,"remainingConfigurations":398},{"removed":"math500","score":0.5154791306834859,"rank":38,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5201245752978114,"rank":38,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5328025518726808,"rank":38,"remainingConfigurations":398},{"removed":"omniscience","score":0.5172118809079742,"rank":38,"remainingConfigurations":398},{"removed":"scicode","score":0.5157476098060659,"rank":38,"remainingConfigurations":398},{"removed":"tau-bench","score":0.51436032340141,"rank":38,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.5346027993911809,"rank":38,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5312049760653327,"rank":38,"remainingConfigurations":398},{"removed":"deepswe","score":0.4781855583017997,"rank":39,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.5152518420798292,"rank":38,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.514309880023467,"rank":38,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5092555059563716,"rank":37,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5161030308605374,"rank":39,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.5131269596995952,"rank":38,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.5145198392224035,"rank":38,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.5148764273937902,"rank":38,"remainingConfigurations":398},{"removed":"livebench-math","score":0.5116394538320111,"rank":38,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.5094319595097333,"rank":38,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5195374941962507,"rank":38,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5220149884807214,"rank":38,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.5148984825793953,"rank":38,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.5129064344668176,"rank":38,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.5174412937853904,"rank":38,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.5102483916483955,"rank":39,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.5235473525281408,"rank":38,"remainingConfigurations":398},{"removed":"frontiermath","score":0.504198529418017,"rank":38,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5176641702351721,"rank":39,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.5180314425604907,"rank":38,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.5146860193225652,"rank":38,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.5129606877511214,"rank":38,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.5131732626849231,"rank":38,"remainingConfigurations":398},{"removed":"vibe-code","score":0.5114667834671766,"rank":38,"remainingConfigurations":398}]},"qwen-3.8-max--effort-xhigh":{"score":0.4987155368393635,"rank":39,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.5034294183720148,"rank":38,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.5229412794853375,"rank":39,"remainingConfigurations":398},{"removed":"Datacurve","score":0.46598876404164713,"rank":42,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.49866243339587846,"rank":39,"remainingConfigurations":398},{"removed":"Scale","score":0.5118671206819693,"rank":40,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4978282388325142,"rank":39,"remainingConfigurations":398},{"removed":"Cognition","score":0.5000242331715518,"rank":39,"remainingConfigurations":398},{"removed":"LiveBench","score":0.5084773168960873,"rank":39,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4918800590233073,"rank":40,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.509962427664363,"rank":40,"remainingConfigurations":381},{"removed":"Vals AI","score":0.49329219759019227,"rank":38,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.49888259507469807,"rank":39,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.49743129214815474,"rank":39,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4998013888131925,"rank":40,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4987155368393635,"rank":39,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4986609286177956,"rank":40,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4988615667581678,"rank":39,"remainingConfigurations":398},{"removed":"briefcase","score":0.49840717757970915,"rank":39,"remainingConfigurations":398},{"removed":"aime","score":0.4842038979440759,"rank":40,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4991993171862013,"rank":39,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.49885896365142796,"rank":39,"remainingConfigurations":398},{"removed":"automationbench","score":0.4980090221910743,"rank":39,"remainingConfigurations":398},{"removed":"critpt","score":0.4989452620106416,"rank":39,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.49864666093362625,"rank":39,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4998118509599501,"rank":39,"remainingConfigurations":398},{"removed":"gdpval","score":0.498428084559503,"rank":39,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4988811020392944,"rank":39,"remainingConfigurations":398},{"removed":"gpqa","score":0.49369363671434024,"rank":39,"remainingConfigurations":398},{"removed":"harvey","score":0.49618395337628013,"rank":39,"remainingConfigurations":398},{"removed":"hle","score":0.5028597385676186,"rank":39,"remainingConfigurations":398},{"removed":"ifbench","score":0.4978178351966455,"rank":39,"remainingConfigurations":398},{"removed":"itbench","score":0.4982725629279368,"rank":39,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4988212810392773,"rank":39,"remainingConfigurations":398},{"removed":"math500","score":0.49880507154987463,"rank":39,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.5031373732347503,"rank":39,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.5078729111217873,"rank":39,"remainingConfigurations":398},{"removed":"omniscience","score":0.49929549067893664,"rank":39,"remainingConfigurations":398},{"removed":"scicode","score":0.49950162931549374,"rank":39,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4966394942905265,"rank":39,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4991843054907945,"rank":39,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5232070047135742,"rank":39,"remainingConfigurations":398},{"removed":"deepswe","score":0.4662603249550839,"rank":42,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.49878329567039104,"rank":39,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4965504166801649,"rank":39,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5000242331715518,"rank":39,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4997148327506867,"rank":40,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.49583405807145553,"rank":39,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4987193257529425,"rank":39,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4983065512506361,"rank":39,"remainingConfigurations":398},{"removed":"livebench-math","score":0.49907780683635194,"rank":39,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4972344973579003,"rank":39,"remainingConfigurations":398},{"removed":"livebench-language","score":0.5003583270197153,"rank":39,"remainingConfigurations":398},{"removed":"livebench-data","score":0.5001813548153722,"rank":39,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.49598277861213774,"rank":39,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.49743417948423524,"rank":39,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.500723787243268,"rank":39,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4918800590233073,"rank":40,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.49550322129641705,"rank":39,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4910943577588747,"rank":39,"remainingConfigurations":398},{"removed":"simpleqa","score":0.5288638489642191,"rank":38,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.49744707171442243,"rank":39,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4988876461242297,"rank":39,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.497499219708734,"rank":39,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.49862009897401105,"rank":39,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4978720357895443,"rank":39,"remainingConfigurations":398}]},"claude-opus-4-8--effort-xhigh":{"score":0.4898225268184147,"rank":40,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4789503896356338,"rank":40,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.503426719711242,"rank":41,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4820693735625125,"rank":36,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4898604366323753,"rank":40,"remainingConfigurations":398},{"removed":"Scale","score":0.5481958074831454,"rank":38,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.48828132567441135,"rank":40,"remainingConfigurations":398},{"removed":"Cognition","score":0.47994711084645303,"rank":42,"remainingConfigurations":398},{"removed":"LiveBench","score":0.495943554207736,"rank":40,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.452004486870951,"rank":44,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5039758496330676,"rank":41,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4796103362244659,"rank":40,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4897678230004398,"rank":40,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.49166224845745415,"rank":40,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4898318737806817,"rank":41,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4898225268184147,"rank":40,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4915823624819103,"rank":41,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4898553768364833,"rank":40,"remainingConfigurations":398},{"removed":"briefcase","score":0.48948233939296243,"rank":40,"remainingConfigurations":398},{"removed":"aime","score":0.4865690968465925,"rank":39,"remainingConfigurations":398},{"removed":"apex-agents","score":0.49049910362794913,"rank":40,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.49006619721079425,"rank":40,"remainingConfigurations":398},{"removed":"automationbench","score":0.49004411016157573,"rank":40,"remainingConfigurations":398},{"removed":"critpt","score":0.4899758028922212,"rank":40,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4896521301968753,"rank":40,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.49083082368774905,"rank":40,"remainingConfigurations":398},{"removed":"gdpval","score":0.4893409123262828,"rank":40,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4899684483930069,"rank":40,"remainingConfigurations":398},{"removed":"gpqa","score":0.4892724582775397,"rank":40,"remainingConfigurations":398},{"removed":"harvey","score":0.48842258752131534,"rank":40,"remainingConfigurations":398},{"removed":"hle","score":0.4950703966651664,"rank":40,"remainingConfigurations":398},{"removed":"ifbench","score":0.4885454460967984,"rank":40,"remainingConfigurations":398},{"removed":"itbench","score":0.4894723148874047,"rank":40,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4898646651703506,"rank":40,"remainingConfigurations":398},{"removed":"math500","score":0.48984222019445034,"rank":40,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.49358217224062734,"rank":40,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4987885837904846,"rank":40,"remainingConfigurations":398},{"removed":"omniscience","score":0.48956143296166044,"rank":40,"remainingConfigurations":398},{"removed":"scicode","score":0.4909124817424611,"rank":40,"remainingConfigurations":398},{"removed":"tau-bench","score":0.48836157055829094,"rank":40,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4882427180961529,"rank":40,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5043729215100309,"rank":42,"remainingConfigurations":398},{"removed":"deepswe","score":0.48199128516817974,"rank":36,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4898018139710636,"rank":40,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4884091899261162,"rank":40,"remainingConfigurations":398},{"removed":"frontiercode","score":0.47994711084645303,"rank":42,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.5245713726355462,"rank":38,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.44586542370276644,"rank":49,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.49696478157343865,"rank":40,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.49661754956501714,"rank":40,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4899571690473401,"rank":40,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.48770394390916216,"rank":40,"remainingConfigurations":398},{"removed":"livebench-language","score":0.491084884404762,"rank":40,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4908861841710585,"rank":40,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.48771490329841183,"rank":40,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.488321351403662,"rank":40,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.49307089722666725,"rank":40,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.452004486870951,"rank":44,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4841644111247913,"rank":40,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4907105344672529,"rank":40,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4976915053796664,"rank":40,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4892044514436104,"rank":40,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.48939406903950666,"rank":40,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.48900323859101347,"rank":40,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4892763028269404,"rank":40,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4889813118039679,"rank":40,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-medium":{"score":0.47844941945122593,"rank":41,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4829550145193398,"rank":39,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.495888448499936,"rank":42,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4190932026260632,"rank":46,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4783218082208039,"rank":41,"remainingConfigurations":398},{"removed":"Scale","score":0.4896117705997917,"rank":42,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.47318709887910176,"rank":41,"remainingConfigurations":398},{"removed":"Cognition","score":0.46416175901912354,"rank":45,"remainingConfigurations":398},{"removed":"LiveBench","score":0.48488884112351904,"rank":41,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.523439332928047,"rank":38,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.4865308929862799,"rank":43,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4689584079425812,"rank":41,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4785041500405291,"rank":41,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4788357260620056,"rank":41,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4784398597718051,"rank":42,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.47844941945122593,"rank":41,"remainingConfigurations":398},{"removed":"All provider reports","score":0.47885000080342727,"rank":42,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.47885690811945886,"rank":41,"remainingConfigurations":398},{"removed":"briefcase","score":0.4779107750598302,"rank":41,"remainingConfigurations":398},{"removed":"aime","score":0.47626056129412725,"rank":41,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4795051614406276,"rank":41,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.47949775598425165,"rank":41,"remainingConfigurations":398},{"removed":"automationbench","score":0.4773744476351031,"rank":41,"remainingConfigurations":398},{"removed":"critpt","score":0.47826320642143955,"rank":41,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.47863355733364815,"rank":41,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.47647012897555374,"rank":41,"remainingConfigurations":398},{"removed":"gdpval","score":0.4779140751530691,"rank":41,"remainingConfigurations":398},{"removed":"gmmlu","score":0.47858777072197173,"rank":41,"remainingConfigurations":398},{"removed":"gpqa","score":0.47705583723277706,"rank":41,"remainingConfigurations":398},{"removed":"harvey","score":0.4765959747518728,"rank":41,"remainingConfigurations":398},{"removed":"hle","score":0.4846037335108471,"rank":41,"remainingConfigurations":398},{"removed":"ifbench","score":0.480446573072268,"rank":41,"remainingConfigurations":398},{"removed":"itbench","score":0.4782159365458228,"rank":41,"remainingConfigurations":398},{"removed":"livecodebench","score":0.478236408016633,"rank":41,"remainingConfigurations":398},{"removed":"math500","score":0.4784008628412102,"rank":41,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.48304893390110976,"rank":41,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.48820437190336347,"rank":41,"remainingConfigurations":398},{"removed":"omniscience","score":0.47786874225046233,"rank":42,"remainingConfigurations":398},{"removed":"scicode","score":0.47760222039327654,"rank":41,"remainingConfigurations":398},{"removed":"tau-bench","score":0.48047706778073546,"rank":41,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.47267792716126883,"rank":41,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5146770727214783,"rank":40,"remainingConfigurations":398},{"removed":"deepswe","score":0.4190371539657356,"rank":46,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4784765076788391,"rank":41,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.47020716312320165,"rank":42,"remainingConfigurations":398},{"removed":"frontiercode","score":0.46416175901912354,"rank":45,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.47649882499090673,"rank":41,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4756844068265911,"rank":40,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.47822197780216236,"rank":41,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4774410910772049,"rank":41,"remainingConfigurations":398},{"removed":"livebench-math","score":0.47882427672096245,"rank":41,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4768955015849872,"rank":41,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4802822863721354,"rank":41,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4787354858968303,"rank":41,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.475827944352758,"rank":41,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4771778672334382,"rank":41,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.48136097268015265,"rank":41,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.523439332928047,"rank":38,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4757522967627545,"rank":41,"remainingConfigurations":398},{"removed":"frontiermath","score":0.47719245047843145,"rank":41,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4854905579075506,"rank":41,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.47796052719758625,"rank":41,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4776577172649097,"rank":41,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.477725935372521,"rank":41,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4781173158244758,"rank":41,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4772605212053884,"rank":41,"remainingConfigurations":398}]},"claude-opus-4-8--effort-high":{"score":0.47372162083868635,"rank":42,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.47178892927283567,"rank":42,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.44551739525272205,"rank":55,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4835519354714455,"rank":35,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4740199019763145,"rank":42,"remainingConfigurations":398},{"removed":"Scale","score":0.49260686529639225,"rank":41,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.45788454410478535,"rank":43,"remainingConfigurations":398},{"removed":"Cognition","score":0.4780695029744109,"rank":43,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4758763320786004,"rank":42,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4769243510968398,"rank":41,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.49071618979237536,"rank":42,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4619967176393603,"rank":43,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4737208385413855,"rank":42,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.47316491279494627,"rank":42,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4737537312936335,"rank":43,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.47372162083868635,"rank":42,"remainingConfigurations":398},{"removed":"All provider reports","score":0.47317217312188103,"rank":43,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4736845772459715,"rank":42,"remainingConfigurations":398},{"removed":"briefcase","score":0.4729805104373008,"rank":42,"remainingConfigurations":398},{"removed":"aime","score":0.4703755056738362,"rank":42,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4745036781506773,"rank":42,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4737922173033969,"rank":43,"remainingConfigurations":398},{"removed":"automationbench","score":0.47354713889017086,"rank":42,"remainingConfigurations":398},{"removed":"critpt","score":0.4733088031525268,"rank":42,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.47360202448630817,"rank":42,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.47497558390479205,"rank":42,"remainingConfigurations":398},{"removed":"gdpval","score":0.4736167060500134,"rank":42,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4737566326616767,"rank":42,"remainingConfigurations":398},{"removed":"gpqa","score":0.4747759847359796,"rank":42,"remainingConfigurations":398},{"removed":"harvey","score":0.4719540695039874,"rank":42,"remainingConfigurations":398},{"removed":"hle","score":0.4799764917614309,"rank":42,"remainingConfigurations":398},{"removed":"ifbench","score":0.47216953087485597,"rank":42,"remainingConfigurations":398},{"removed":"itbench","score":0.4731301693768673,"rank":42,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4739052826700391,"rank":42,"remainingConfigurations":398},{"removed":"math500","score":0.47370298207321665,"rank":42,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4775085471623462,"rank":42,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.483559151114701,"rank":42,"remainingConfigurations":398},{"removed":"omniscience","score":0.4732704846566282,"rank":43,"remainingConfigurations":398},{"removed":"scicode","score":0.47446098259562824,"rank":42,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4727754016412689,"rank":42,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4573688211575146,"rank":45,"remainingConfigurations":398},{"removed":"arc-agi","score":0.44861012448986887,"rank":54,"remainingConfigurations":398},{"removed":"deepswe","score":0.48369064289969455,"rank":35,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4737721369457484,"rank":42,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4722482086669846,"rank":41,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4780695029744109,"rank":43,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4740455902618519,"rank":42,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.47359894569162747,"rank":41,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.47463860408766106,"rank":42,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.46883059292824397,"rank":42,"remainingConfigurations":398},{"removed":"livebench-math","score":0.47381911007631583,"rank":42,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.47144054202109387,"rank":42,"remainingConfigurations":398},{"removed":"livebench-language","score":0.47567786484268043,"rank":42,"remainingConfigurations":398},{"removed":"livebench-data","score":0.47467287000670644,"rank":42,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.47114342704072887,"rank":42,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4721806087693441,"rank":42,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4770860177014738,"rank":42,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4769243510968398,"rank":41,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4750717052476426,"rank":42,"remainingConfigurations":398},{"removed":"frontiermath","score":0.472248818063392,"rank":42,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4760590739032226,"rank":42,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4732616975479207,"rank":42,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.47293926889278465,"rank":42,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4729527885717175,"rank":42,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.47313068099075045,"rank":42,"remainingConfigurations":398},{"removed":"vibe-code","score":0.472747591785839,"rank":42,"remainingConfigurations":398}]},"gpt-5.5--effort-medium":{"score":0.460678236556126,"rank":43,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4528161923173643,"rank":45,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4706887137059035,"rank":49,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4480907205906746,"rank":43,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4607209291380388,"rank":43,"remainingConfigurations":398},{"removed":"Scale","score":0.47613571331841786,"rank":43,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4569703449361504,"rank":44,"remainingConfigurations":398},{"removed":"Cognition","score":0.5049391055570684,"rank":38,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4655536150021519,"rank":44,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.42612402747725714,"rank":50,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.463453466372002,"rank":46,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4504173909528491,"rank":45,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4608036983876171,"rank":43,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.46053698248985936,"rank":43,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4606422279613141,"rank":44,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.460678236556126,"rank":43,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4605938027047334,"rank":44,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4609816415298438,"rank":43,"remainingConfigurations":398},{"removed":"briefcase","score":0.4617395816183376,"rank":43,"remainingConfigurations":398},{"removed":"aime","score":0.4590979273782987,"rank":43,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4616651717864569,"rank":43,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.45974373966428933,"rank":44,"remainingConfigurations":398},{"removed":"automationbench","score":0.4604859768112624,"rank":43,"remainingConfigurations":398},{"removed":"critpt","score":0.45956827017380836,"rank":43,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.45984723650826814,"rank":43,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4593415979948936,"rank":43,"remainingConfigurations":398},{"removed":"gdpval","score":0.46108911133256286,"rank":43,"remainingConfigurations":398},{"removed":"gmmlu","score":0.46085342359339965,"rank":43,"remainingConfigurations":398},{"removed":"gpqa","score":0.4586059257139148,"rank":43,"remainingConfigurations":398},{"removed":"harvey","score":0.4590491054664261,"rank":43,"remainingConfigurations":398},{"removed":"hle","score":0.4665958446754925,"rank":43,"remainingConfigurations":398},{"removed":"ifbench","score":0.4616424688984795,"rank":43,"remainingConfigurations":398},{"removed":"itbench","score":0.46041667172507034,"rank":43,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4607787330150037,"rank":43,"remainingConfigurations":398},{"removed":"math500","score":0.4607479607704841,"rank":43,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.46573232578112705,"rank":44,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4705174695926638,"rank":43,"remainingConfigurations":398},{"removed":"omniscience","score":0.4594197292922461,"rank":47,"remainingConfigurations":398},{"removed":"scicode","score":0.4607322876184821,"rank":43,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4614130573407272,"rank":43,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4574822050472788,"rank":44,"remainingConfigurations":398},{"removed":"arc-agi","score":0.47420141828507334,"rank":48,"remainingConfigurations":398},{"removed":"deepswe","score":0.44800068592072534,"rank":43,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4607408597758033,"rank":43,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4597824305724316,"rank":43,"remainingConfigurations":398},{"removed":"frontiercode","score":0.5049391055570684,"rank":38,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.46241252331986527,"rank":43,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4558403816785268,"rank":42,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4608222878584112,"rank":43,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4601255266417155,"rank":43,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4610476197517795,"rank":43,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4591074610667538,"rank":43,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4623403409010685,"rank":43,"remainingConfigurations":398},{"removed":"livebench-data","score":0.46099263024094944,"rank":43,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4580434313718004,"rank":43,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.45928401971905974,"rank":43,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4638906968179819,"rank":43,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.42612402747725714,"rank":50,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.45558052535849747,"rank":45,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4605802018090595,"rank":43,"remainingConfigurations":398},{"removed":"simpleqa","score":0.467150329701602,"rank":43,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.45997447896050775,"rank":43,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.46000346747206095,"rank":44,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.45990625423003,"rank":43,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4601383411081088,"rank":44,"remainingConfigurations":398},{"removed":"vibe-code","score":0.45933872418291233,"rank":43,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-xhigh":{"score":0.45622943003312894,"rank":44,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.46723607249446775,"rank":43,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4453185277480207,"rank":56,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3953401028987196,"rank":53,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4562333898288409,"rank":44,"remainingConfigurations":398},{"removed":"Scale","score":0.4693869925609526,"rank":44,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4512647297419667,"rank":47,"remainingConfigurations":398},{"removed":"Cognition","score":0.4953904738549739,"rank":40,"remainingConfigurations":398},{"removed":"LiveBench","score":0.46107920592834883,"rank":45,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4553351159983879,"rank":43,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.46073395503727066,"rank":47,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4629129622480435,"rank":42,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.45635101885097945,"rank":44,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4560189587694638,"rank":44,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.45629249348135525,"rank":45,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.45622943003312894,"rank":44,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4561713855363106,"rank":45,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4565821386589506,"rank":44,"remainingConfigurations":398},{"removed":"briefcase","score":0.45474821276076965,"rank":45,"remainingConfigurations":398},{"removed":"aime","score":0.4549131418017949,"rank":45,"remainingConfigurations":398},{"removed":"apex-agents","score":0.45723556225827994,"rank":44,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.45539669422301304,"rank":47,"remainingConfigurations":398},{"removed":"automationbench","score":0.45532776115968504,"rank":45,"remainingConfigurations":398},{"removed":"critpt","score":0.45367689893715024,"rank":46,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.456242129734012,"rank":44,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4533328340369093,"rank":47,"remainingConfigurations":398},{"removed":"gdpval","score":0.4553881266284517,"rank":44,"remainingConfigurations":398},{"removed":"gmmlu","score":0.45625704844670106,"rank":44,"remainingConfigurations":398},{"removed":"gpqa","score":0.4547570847972824,"rank":46,"remainingConfigurations":398},{"removed":"harvey","score":0.4522342580594066,"rank":45,"remainingConfigurations":398},{"removed":"hle","score":0.4622134981962425,"rank":44,"remainingConfigurations":398},{"removed":"ifbench","score":0.4595222183830847,"rank":44,"remainingConfigurations":398},{"removed":"itbench","score":0.4559932959151726,"rank":44,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4560330805333557,"rank":44,"remainingConfigurations":398},{"removed":"math500","score":0.4561433711873055,"rank":44,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.47523435575601236,"rank":43,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4665303041200639,"rank":44,"remainingConfigurations":398},{"removed":"omniscience","score":0.4560787527942234,"rank":49,"remainingConfigurations":398},{"removed":"scicode","score":0.45696747796654263,"rank":44,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4595529320901279,"rank":44,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4489061917733606,"rank":49,"remainingConfigurations":398},{"removed":"arc-agi","score":0.45029866449786365,"rank":53,"remainingConfigurations":398},{"removed":"deepswe","score":0.3952666531099695,"rank":53,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.456289059284443,"rank":44,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4549666237090497,"rank":45,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4953904738549739,"rank":40,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.456583525607255,"rank":45,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.45325040248844656,"rank":44,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.45602532023903075,"rank":44,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4553120993533531,"rank":44,"remainingConfigurations":398},{"removed":"livebench-math","score":0.45666307808381607,"rank":45,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4547343690878913,"rank":45,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4580353642933787,"rank":45,"remainingConfigurations":398},{"removed":"livebench-data","score":0.45654652830339265,"rank":45,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4534909729584065,"rank":44,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.45510777727087987,"rank":45,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.45898781965556995,"rank":44,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4553351159983879,"rank":43,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4492154770780594,"rank":47,"remainingConfigurations":398},{"removed":"frontiermath","score":0.45500706608646363,"rank":46,"remainingConfigurations":398},{"removed":"simpleqa","score":0.46293536493404247,"rank":44,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4540976958873097,"rank":45,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.45300070925183733,"rank":46,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.45379075283525355,"rank":46,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.45351277257799943,"rank":47,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4527929722533952,"rank":45,"remainingConfigurations":398}]},"muse-spark-1.2--effort-xhigh":{"score":0.4560441657225609,"rank":45,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.47633573741950697,"rank":41,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4772938140548317,"rank":47,"remainingConfigurations":398},{"removed":"Datacurve","score":0.42154760954891884,"rank":44,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.45586342251579165,"rank":45,"remainingConfigurations":398},{"removed":"Scale","score":0.46821684652491774,"rank":45,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4582451083372825,"rank":42,"remainingConfigurations":398},{"removed":"Cognition","score":0.46852860961140647,"rank":44,"remainingConfigurations":398},{"removed":"LiveBench","score":0.47153020863829537,"rank":43,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4516098436103768,"rank":45,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.4533292807352927,"rank":49,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4324996935135701,"rank":49,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4557415352094368,"rank":45,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4552900138008611,"rank":45,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.5044923660203685,"rank":39,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4560441657225609,"rank":45,"remainingConfigurations":398},{"removed":"All provider reports","score":0.5032507685802451,"rank":39,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4561297268930136,"rank":45,"remainingConfigurations":398},{"removed":"briefcase","score":0.4551381430032177,"rank":44,"remainingConfigurations":398},{"removed":"aime","score":0.4572329950531806,"rank":44,"remainingConfigurations":398},{"removed":"apex-agents","score":0.45649392009083173,"rank":45,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4558468727870038,"rank":46,"remainingConfigurations":398},{"removed":"automationbench","score":0.45674246108750793,"rank":44,"remainingConfigurations":398},{"removed":"critpt","score":0.45740322346674417,"rank":44,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4538311038238813,"rank":46,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4570684188027747,"rank":44,"remainingConfigurations":398},{"removed":"gdpval","score":0.45529806618414875,"rank":46,"remainingConfigurations":398},{"removed":"gmmlu","score":0.45616952521632914,"rank":45,"remainingConfigurations":398},{"removed":"gpqa","score":0.45664770873490274,"rank":44,"remainingConfigurations":398},{"removed":"harvey","score":0.44259946486382024,"rank":48,"remainingConfigurations":398},{"removed":"hle","score":0.46062232159888006,"rank":46,"remainingConfigurations":398},{"removed":"ifbench","score":0.4537383355748335,"rank":45,"remainingConfigurations":398},{"removed":"itbench","score":0.4557299298969469,"rank":45,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4559422558318407,"rank":45,"remainingConfigurations":398},{"removed":"math500","score":0.4561193578689926,"rank":45,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.46190694241472047,"rank":45,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4662051162556644,"rank":45,"remainingConfigurations":398},{"removed":"omniscience","score":0.4596915705253759,"rank":46,"remainingConfigurations":398},{"removed":"scicode","score":0.45455531557134865,"rank":48,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4542981812204127,"rank":46,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4687938976087098,"rank":42,"remainingConfigurations":398},{"removed":"arc-agi","score":0.47457799129242817,"rank":47,"remainingConfigurations":398},{"removed":"deepswe","score":0.4217043174255784,"rank":44,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4561755042017775,"rank":45,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4546700423093277,"rank":46,"remainingConfigurations":398},{"removed":"frontiercode","score":0.46852860961140647,"rank":44,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.456963317432983,"rank":44,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.45391285327723047,"rank":43,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4558558971420242,"rank":45,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4544635689018297,"rank":45,"remainingConfigurations":398},{"removed":"livebench-math","score":0.45870296775703095,"rank":44,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.45765654244564846,"rank":44,"remainingConfigurations":398},{"removed":"livebench-language","score":0.46202995115860007,"rank":44,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4572146493371348,"rank":44,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.44831703578281573,"rank":47,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.455452977738904,"rank":44,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.45308360315985546,"rank":48,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4516098436103768,"rank":45,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.45430595724383566,"rank":46,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4587727558999412,"rank":45,"remainingConfigurations":398},{"removed":"simpleqa","score":0.44804801107624787,"rank":49,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.44563710906619675,"rank":49,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4637658216851947,"rank":43,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.45379327323807256,"rank":45,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.463815864036835,"rank":43,"remainingConfigurations":398},{"removed":"vibe-code","score":0.45164040111601894,"rank":46,"remainingConfigurations":398}]},"claude-opus-4-8--effort-medium":{"score":0.4552510089463924,"rank":46,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4415862139591515,"rank":48,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4044815271017632,"rank":65,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4766922865044956,"rank":40,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4557368184999045,"rank":46,"remainingConfigurations":398},{"removed":"Scale","score":0.46343954170575113,"rank":48,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4523951102678125,"rank":46,"remainingConfigurations":398},{"removed":"Cognition","score":0.4584822718995847,"rank":48,"remainingConfigurations":398},{"removed":"LiveBench","score":0.45602171292171456,"rank":47,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.45046370736418795,"rank":46,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.4675004622495654,"rank":45,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4414900630021714,"rank":47,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.45530100281204505,"rank":46,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.454613598120401,"rank":46,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.45527688984172093,"rank":46,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4552510089463924,"rank":46,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4546654263655137,"rank":46,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4553724367457192,"rank":46,"remainingConfigurations":398},{"removed":"briefcase","score":0.45469781508815094,"rank":46,"remainingConfigurations":398},{"removed":"aime","score":0.45180781620359994,"rank":46,"remainingConfigurations":398},{"removed":"apex-agents","score":0.45602588858547194,"rank":46,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.45516151151094225,"rank":48,"remainingConfigurations":398},{"removed":"automationbench","score":0.4550270660443893,"rank":46,"remainingConfigurations":398},{"removed":"critpt","score":0.45331561328306313,"rank":47,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.45509397880100927,"rank":45,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.45614237966893983,"rank":45,"remainingConfigurations":398},{"removed":"gdpval","score":0.455335903725909,"rank":45,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4552428529577776,"rank":46,"remainingConfigurations":398},{"removed":"gpqa","score":0.4562660344795209,"rank":45,"remainingConfigurations":398},{"removed":"harvey","score":0.45331166191215416,"rank":44,"remainingConfigurations":398},{"removed":"hle","score":0.46176275410239204,"rank":45,"remainingConfigurations":398},{"removed":"ifbench","score":0.4532914424272308,"rank":46,"remainingConfigurations":398},{"removed":"itbench","score":0.4548866382556647,"rank":46,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4555908201486627,"rank":46,"remainingConfigurations":398},{"removed":"math500","score":0.45523570031587784,"rank":46,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4593738849457743,"rank":46,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4654250600467949,"rank":46,"remainingConfigurations":398},{"removed":"omniscience","score":0.45428429703195344,"rank":50,"remainingConfigurations":398},{"removed":"scicode","score":0.45626499349453065,"rank":45,"remainingConfigurations":398},{"removed":"tau-bench","score":0.45445574387852794,"rank":45,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.45191826835904975,"rank":46,"remainingConfigurations":398},{"removed":"arc-agi","score":0.40724513090421294,"rank":63,"remainingConfigurations":398},{"removed":"deepswe","score":0.4768429345010325,"rank":41,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4553067639164375,"rank":46,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.45619324248466003,"rank":44,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4584822718995847,"rank":48,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4549251481437436,"rank":46,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4526533313927737,"rank":45,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.45485742941129975,"rank":46,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4528571945589424,"rank":46,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4553173228531791,"rank":46,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4528787327521586,"rank":46,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4573485601457005,"rank":46,"remainingConfigurations":398},{"removed":"livebench-data","score":0.456110600613089,"rank":46,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4526368919363704,"rank":45,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4536684968870566,"rank":46,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4587639864263684,"rank":45,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.45046370736418795,"rank":46,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.45634601895839594,"rank":44,"remainingConfigurations":398},{"removed":"frontiermath","score":0.45434867830171477,"rank":47,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4603486301604181,"rank":45,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.45458013403889225,"rank":44,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4546608835414241,"rank":45,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.45432503237724653,"rank":44,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.454736282577832,"rank":46,"remainingConfigurations":398},{"removed":"vibe-code","score":0.45402504397032134,"rank":44,"remainingConfigurations":398}]},"qwen-3.8-max--effort-reasoning":{"score":0.45155155035803135,"rank":47,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.49208329542604057,"rank":43,"remainingConfigurations":398},{"removed":"Datacurve","score":0.41978419547576024,"rank":45,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4499536924953504,"rank":48,"remainingConfigurations":398},{"removed":"Scale","score":0.46635234375986423,"rank":46,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4543440956676746,"rank":45,"remainingConfigurations":398},{"removed":"Cognition","score":0.46113804670422026,"rank":46,"remainingConfigurations":398},{"removed":"LiveBench","score":0.45606466338567303,"rank":46,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4571340196627749,"rank":42,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.453735897604105,"rank":48,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4468906408070951,"rank":46,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.45151007765972717,"rank":47,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4510796658889962,"rank":47,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.45082018712056704,"rank":47,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.45155155035803135,"rank":47,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4502822034350773,"rank":47,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4530766988595151,"rank":47,"remainingConfigurations":398},{"removed":"briefcase","score":0.4448398831137344,"rank":49,"remainingConfigurations":398},{"removed":"aime","score":0.4509145471888408,"rank":47,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4546296277397475,"rank":47,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.45842495948051964,"rank":45,"remainingConfigurations":398},{"removed":"automationbench","score":0.45273030205138226,"rank":47,"remainingConfigurations":398},{"removed":"critpt","score":0.4541491494298684,"rank":45,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4531578057047056,"rank":47,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4460971953305776,"rank":49,"remainingConfigurations":398},{"removed":"gdpval","score":0.44402943591741306,"rank":49,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4514018081745577,"rank":47,"remainingConfigurations":398},{"removed":"gpqa","score":0.4484633791563039,"rank":49,"remainingConfigurations":398},{"removed":"harvey","score":0.4507169031599781,"rank":46,"remainingConfigurations":398},{"removed":"hle","score":0.4593301726925141,"rank":47,"remainingConfigurations":398},{"removed":"ifbench","score":0.4457222055165986,"rank":49,"remainingConfigurations":398},{"removed":"itbench","score":0.452331801775916,"rank":47,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4493732054836122,"rank":48,"remainingConfigurations":398},{"removed":"math500","score":0.45116337805483386,"rank":47,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.45464520795498053,"rank":48,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4620741856998641,"rank":47,"remainingConfigurations":398},{"removed":"omniscience","score":0.4837768339803406,"rank":41,"remainingConfigurations":398},{"removed":"scicode","score":0.45472655527751743,"rank":46,"remainingConfigurations":398},{"removed":"tau-bench","score":0.43291557939976233,"rank":49,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.45177949008644225,"rank":47,"remainingConfigurations":398},{"removed":"arc-agi","score":0.49123699094183176,"rank":43,"remainingConfigurations":398},{"removed":"deepswe","score":0.419969626849296,"rank":45,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.45162486406456365,"rank":47,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4492151325617179,"rank":47,"remainingConfigurations":398},{"removed":"frontiercode","score":0.46113804670422026,"rank":46,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4516879351280068,"rank":47,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4492441721605038,"rank":46,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4510329600459422,"rank":47,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4504529397931826,"rank":47,"remainingConfigurations":398},{"removed":"livebench-math","score":0.45185009451085323,"rank":47,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.45036155290686025,"rank":47,"remainingConfigurations":398},{"removed":"livebench-language","score":0.45372512888179023,"rank":47,"remainingConfigurations":398},{"removed":"livebench-data","score":0.45196012118630574,"rank":47,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.44860667910900814,"rank":46,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4504161115167153,"rank":47,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.45385652307079716,"rank":46,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4571340196627749,"rank":42,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.44284876725482625,"rank":48,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4538426389700514,"rank":48,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4587807032073405,"rank":46,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4506443711010301,"rank":47,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4510514122721547,"rank":47,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4507485834135388,"rank":47,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.45151907709336453,"rank":48,"remainingConfigurations":398},{"removed":"vibe-code","score":0.45020640316953103,"rank":47,"remainingConfigurations":398}]},"claude-opus-5--effort-low":{"score":0.45044593109808845,"rank":48,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.45343178295723113,"rank":44,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4604325778710477,"rank":52,"remainingConfigurations":398},{"removed":"Datacurve","score":0.40495693909741876,"rank":49,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4502051256893262,"rank":47,"remainingConfigurations":398},{"removed":"Scale","score":0.46374670768333087,"rank":47,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4498757491378574,"rank":48,"remainingConfigurations":398},{"removed":"Cognition","score":0.4103792067879189,"rank":59,"remainingConfigurations":398},{"removed":"LiveBench","score":0.452762837161181,"rank":49,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.44856556971139505,"rank":47,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.5265888852327422,"rank":39,"remainingConfigurations":381},{"removed":"Vals AI","score":0.43633478718792507,"rank":48,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4502879696194606,"rank":48,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.44979800029751277,"rank":48,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.450382214548573,"rank":48,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.45044593109808845,"rank":48,"remainingConfigurations":398},{"removed":"All provider reports","score":0.44955452208864793,"rank":48,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4506871481338188,"rank":48,"remainingConfigurations":398},{"removed":"briefcase","score":0.4499207011797,"rank":47,"remainingConfigurations":398},{"removed":"aime","score":0.44098676240395535,"rank":49,"remainingConfigurations":398},{"removed":"apex-agents","score":0.45154531323484154,"rank":48,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.44827969665771733,"rank":49,"remainingConfigurations":398},{"removed":"automationbench","score":0.44952188579269786,"rank":48,"remainingConfigurations":398},{"removed":"critpt","score":0.44991338778598494,"rank":48,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4504404838478198,"rank":49,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4512248829123751,"rank":48,"remainingConfigurations":398},{"removed":"gdpval","score":0.4506442216387823,"rank":47,"remainingConfigurations":398},{"removed":"gmmlu","score":0.45059797625392967,"rank":48,"remainingConfigurations":398},{"removed":"gpqa","score":0.4539038994939882,"rank":47,"remainingConfigurations":398},{"removed":"harvey","score":0.4484441996397912,"rank":47,"remainingConfigurations":398},{"removed":"hle","score":0.4561140087992184,"rank":48,"remainingConfigurations":398},{"removed":"ifbench","score":0.44816699604234894,"rank":47,"remainingConfigurations":398},{"removed":"itbench","score":0.45007971567387095,"rank":48,"remainingConfigurations":398},{"removed":"livecodebench","score":0.45002474567627343,"rank":47,"remainingConfigurations":398},{"removed":"math500","score":0.4503137606221556,"rank":48,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4541122506436081,"rank":49,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4613418860198974,"rank":48,"remainingConfigurations":398},{"removed":"omniscience","score":0.4508714277508002,"rank":51,"remainingConfigurations":398},{"removed":"scicode","score":0.4546041913076575,"rank":47,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4485881587863099,"rank":47,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.44931550992391606,"rank":48,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4622105822850348,"rank":50,"remainingConfigurations":398},{"removed":"deepswe","score":0.4052090741091425,"rank":49,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4505049934887067,"rank":48,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4488980296368221,"rank":48,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4103792067879189,"rank":59,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.45079800413810184,"rank":48,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4475543929040801,"rank":47,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.44983881246554236,"rank":48,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.44924475044209905,"rank":48,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4505921020640067,"rank":48,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.44797469404410784,"rank":48,"remainingConfigurations":398},{"removed":"livebench-language","score":0.45269035217756753,"rank":48,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4514526843276269,"rank":48,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.44786659325798234,"rank":48,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.44879703224368933,"rank":48,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4537063678144034,"rank":47,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.44856556971139505,"rank":47,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4628324851555914,"rank":43,"remainingConfigurations":398},{"removed":"frontiermath","score":0.44731051346043804,"rank":49,"remainingConfigurations":398},{"removed":"simpleqa","score":0.45168044228771476,"rank":47,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.449773116085022,"rank":48,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4499100219949,"rank":48,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4494263239416454,"rank":48,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.45007065693767806,"rank":49,"remainingConfigurations":398},{"removed":"vibe-code","score":0.44932570499940266,"rank":48,"remainingConfigurations":398}]},"deepseek-v4-pro--effort-max":{"score":0.4481709832879668,"rank":49,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.44288834630866636,"rank":46,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4899830014524049,"rank":44,"remainingConfigurations":398},{"removed":"Datacurve","score":0.4071400815689648,"rank":48,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.44809761423197075,"rank":49,"remainingConfigurations":398},{"removed":"Scale","score":0.459639188623076,"rank":49,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.44721434805519755,"rank":49,"remainingConfigurations":398},{"removed":"Cognition","score":0.4575658351536583,"rank":49,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4528590607788989,"rank":48,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.44571836157591643,"rank":48,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.4261520364623508,"rank":55,"remainingConfigurations":381},{"removed":"Vals AI","score":0.460743611097231,"rank":44,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.44789965052478437,"rank":49,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.44725865949468385,"rank":49,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4479185768904945,"rank":49,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4481709832879668,"rank":49,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4467208396593418,"rank":49,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4484866653500448,"rank":49,"remainingConfigurations":398},{"removed":"briefcase","score":0.4475930883546302,"rank":48,"remainingConfigurations":398},{"removed":"aime","score":0.444213386851345,"rank":48,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4489761787173246,"rank":49,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.44819322084466906,"rank":50,"remainingConfigurations":398},{"removed":"automationbench","score":0.4455518699291925,"rank":49,"remainingConfigurations":398},{"removed":"critpt","score":0.44763138777397815,"rank":49,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.44289875420930747,"rank":50,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.45379684740593795,"rank":46,"remainingConfigurations":398},{"removed":"gdpval","score":0.44743436484350313,"rank":48,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4483105523780649,"rank":49,"remainingConfigurations":398},{"removed":"gpqa","score":0.44854141619487287,"rank":48,"remainingConfigurations":398},{"removed":"harvey","score":0.43870385110715593,"rank":49,"remainingConfigurations":398},{"removed":"hle","score":0.4537524023823303,"rank":49,"remainingConfigurations":398},{"removed":"ifbench","score":0.4459154450921332,"rank":48,"remainingConfigurations":398},{"removed":"itbench","score":0.44781186131977463,"rank":49,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4482955642143307,"rank":49,"remainingConfigurations":398},{"removed":"math500","score":0.4483107395311101,"rank":49,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.458009242166233,"rank":47,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.45813643297554524,"rank":49,"remainingConfigurations":398},{"removed":"omniscience","score":0.4496072036582872,"rank":52,"remainingConfigurations":398},{"removed":"scicode","score":0.4516249018766643,"rank":49,"remainingConfigurations":398},{"removed":"tau-bench","score":0.44542301917874966,"rank":48,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.45964212540714416,"rank":43,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4887572049381692,"rank":45,"remainingConfigurations":398},{"removed":"deepswe","score":0.4073516378273194,"rank":48,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.44823934219667466,"rank":49,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.44566644511441567,"rank":49,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4575658351536583,"rank":49,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4480333595089769,"rank":49,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4460098325888368,"rank":48,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4476459964489363,"rank":49,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.44656677708949705,"rank":49,"remainingConfigurations":398},{"removed":"livebench-math","score":0.44853127571921614,"rank":49,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4468533950744411,"rank":49,"remainingConfigurations":398},{"removed":"livebench-language","score":0.44999288147587313,"rank":49,"remainingConfigurations":398},{"removed":"livebench-data","score":0.44929966131463855,"rank":49,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4452451673391544,"rank":49,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.44713028261146137,"rank":49,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.450111936813637,"rank":49,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.44571836157591643,"rank":48,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4334129462915823,"rank":49,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4600321886311866,"rank":44,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4514513328854511,"rank":48,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.45270564456754786,"rank":46,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.44269228425924956,"rank":49,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4417813840791937,"rank":49,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.45624983941348535,"rank":45,"remainingConfigurations":398},{"removed":"vibe-code","score":0.43527640199706813,"rank":49,"remainingConfigurations":398}]},"qwen3.8-2.4t-a95b--effort-reasoning":{"score":0.4352195473111215,"rank":50,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4750063293859246,"rank":48,"remainingConfigurations":398},{"removed":"Datacurve","score":0.40352215700598754,"rank":50,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4336575915788921,"rank":50,"remainingConfigurations":398},{"removed":"Scale","score":0.4502574637623629,"rank":50,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4381865655807577,"rank":50,"remainingConfigurations":398},{"removed":"Cognition","score":0.44457821643174494,"rank":50,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4400645806204983,"rank":50,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.44010234325328557,"rank":49,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.43694338110640746,"rank":51,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4305710960791785,"rank":50,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4352094519239362,"rank":50,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4347450578805609,"rank":50,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4346096371907236,"rank":50,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4352195473111215,"rank":50,"remainingConfigurations":398},{"removed":"All provider reports","score":0.43409932603915485,"rank":50,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4367322902895141,"rank":50,"remainingConfigurations":398},{"removed":"briefcase","score":0.42448380156139537,"rank":50,"remainingConfigurations":398},{"removed":"aime","score":0.43451244768061503,"rank":50,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4381485246377205,"rank":50,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.47577787963040424,"rank":42,"remainingConfigurations":398},{"removed":"automationbench","score":0.42198896811148473,"rank":50,"remainingConfigurations":398},{"removed":"critpt","score":0.436510455147709,"rank":50,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.42020147212460635,"rank":51,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4404224005252478,"rank":50,"remainingConfigurations":398},{"removed":"gdpval","score":0.4284890206789866,"rank":50,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4351163309984561,"rank":50,"remainingConfigurations":398},{"removed":"gpqa","score":0.42732523207415163,"rank":50,"remainingConfigurations":398},{"removed":"harvey","score":0.4345642755347406,"rank":50,"remainingConfigurations":398},{"removed":"hle","score":0.44329075966072223,"rank":50,"remainingConfigurations":398},{"removed":"ifbench","score":0.4289271391396225,"rank":51,"remainingConfigurations":398},{"removed":"itbench","score":0.43614544662579374,"rank":50,"remainingConfigurations":398},{"removed":"livecodebench","score":0.43312707607253764,"rank":50,"remainingConfigurations":398},{"removed":"math500","score":0.43485147220422576,"rank":50,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4384903871072878,"rank":50,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4456185225474199,"rank":50,"remainingConfigurations":398},{"removed":"omniscience","score":0.46685000027880125,"rank":44,"remainingConfigurations":398},{"removed":"scicode","score":0.4342842247461014,"rank":50,"remainingConfigurations":398},{"removed":"tau-bench","score":0.418768921543011,"rank":52,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.43741082813838134,"rank":50,"remainingConfigurations":398},{"removed":"arc-agi","score":0.47401878682329684,"rank":49,"remainingConfigurations":398},{"removed":"deepswe","score":0.40371572778803094,"rank":50,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4352914665875187,"rank":50,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4329722360080124,"rank":50,"remainingConfigurations":398},{"removed":"frontiercode","score":0.44457821643174494,"rank":50,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.43533415998786973,"rank":50,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4329498979743864,"rank":50,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.43470557255239256,"rank":50,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.43417219512969196,"rank":50,"remainingConfigurations":398},{"removed":"livebench-math","score":0.43551711436579826,"rank":50,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.43399797761163156,"rank":50,"remainingConfigurations":398},{"removed":"livebench-language","score":0.437428005739378,"rank":50,"remainingConfigurations":398},{"removed":"livebench-data","score":0.43563488429478014,"rank":50,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4322373707584859,"rank":50,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4340679575410908,"rank":50,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.43757378996853435,"rank":50,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.44010234325328557,"rank":49,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4263783332765389,"rank":50,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4375346799422883,"rank":50,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4425608302361825,"rank":50,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4343209677572661,"rank":50,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.43470580899876315,"rank":50,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4343830590154278,"rank":50,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.43519598124065073,"rank":50,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4338530389056139,"rank":50,"remainingConfigurations":398}]},"glm-5.3-flash--effort-reasoning":{"score":0.4209109290604369,"rank":51,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.46108012710832585,"rank":50,"remainingConfigurations":398},{"removed":"Datacurve","score":0.38874809008152345,"rank":54,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.41934981979272573,"rank":53,"remainingConfigurations":398},{"removed":"Scale","score":0.4362158178802538,"rank":51,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.42358986588429115,"rank":52,"remainingConfigurations":398},{"removed":"Cognition","score":0.42980584826521434,"rank":52,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4255084698316018,"rank":53,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.42535009014333536,"rank":51,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.4231832593097061,"rank":56,"remainingConfigurations":381},{"removed":"Vals AI","score":0.41581733040282026,"rank":51,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4209036717149613,"rank":51,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.42045433774035473,"rank":51,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4203207097626558,"rank":51,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4209109290604369,"rank":51,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4198307261946482,"rank":51,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4220236080296764,"rank":51,"remainingConfigurations":398},{"removed":"briefcase","score":0.40682463676124625,"rank":55,"remainingConfigurations":398},{"removed":"aime","score":0.4203722039753874,"rank":52,"remainingConfigurations":398},{"removed":"apex-agents","score":0.423708101276701,"rank":51,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4107107666431302,"rank":54,"remainingConfigurations":398},{"removed":"automationbench","score":0.4021090977902823,"rank":56,"remainingConfigurations":398},{"removed":"critpt","score":0.42577750025404476,"rank":51,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4508019689820582,"rank":48,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4278205792781887,"rank":51,"remainingConfigurations":398},{"removed":"gdpval","score":0.40811241512714674,"rank":54,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4208578050026845,"rank":51,"remainingConfigurations":398},{"removed":"gpqa","score":0.4202955096314769,"rank":51,"remainingConfigurations":398},{"removed":"harvey","score":0.41932429403128507,"rank":51,"remainingConfigurations":398},{"removed":"hle","score":0.43192373851985827,"rank":51,"remainingConfigurations":398},{"removed":"ifbench","score":0.41420293397319313,"rank":53,"remainingConfigurations":398},{"removed":"itbench","score":0.4212592914691336,"rank":51,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4190149452520458,"rank":53,"remainingConfigurations":398},{"removed":"math500","score":0.42064439461027986,"rank":51,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.42440409983988364,"rank":53,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4309180870056018,"rank":52,"remainingConfigurations":398},{"removed":"omniscience","score":0.46044502904557433,"rank":45,"remainingConfigurations":398},{"removed":"scicode","score":0.42616588485650536,"rank":51,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4067982952350244,"rank":55,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4131984085495178,"rank":56,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4598728687026918,"rank":52,"remainingConfigurations":398},{"removed":"deepswe","score":0.38893977388883655,"rank":54,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.42098235768677533,"rank":51,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4187165538782363,"rank":53,"remainingConfigurations":398},{"removed":"frontiercode","score":0.42980584826521434,"rank":52,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4210689309251911,"rank":51,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4187095068279337,"rank":52,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.42040709463085785,"rank":51,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4199050270962612,"rank":51,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4212118968811194,"rank":51,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4196744334435738,"rank":51,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4231279284681871,"rank":51,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4213226579554418,"rank":51,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.41791771670479966,"rank":51,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.41975160675239004,"rank":51,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.42329400122771715,"rank":51,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.42535009014333536,"rank":51,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4122815161963425,"rank":53,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4232215302456277,"rank":51,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4281383102660259,"rank":51,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.42000677349754545,"rank":51,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4203882369625433,"rank":51,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4200744839460094,"rank":51,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.420874707507443,"rank":51,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4195451632877454,"rank":51,"remainingConfigurations":398}]},"claude-opus-4-6--effort-max":{"score":0.42017033135830634,"rank":52,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4418561846430622,"rank":47,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4085424361225452,"rank":63,"remainingConfigurations":398},{"removed":"Datacurve","score":0.38458775644845167,"rank":56,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4199938459800026,"rank":52,"remainingConfigurations":398},{"removed":"Scale","score":0.38028449188044805,"rank":69,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4168136693913742,"rank":53,"remainingConfigurations":398},{"removed":"Cognition","score":0.43166331627524945,"rank":51,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4187705505198113,"rank":55,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4195366792448197,"rank":52,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.47412896054943393,"rank":44,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4092011959913096,"rank":53,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.41996155401774815,"rank":53,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4193258181766981,"rank":52,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4201236363807343,"rank":52,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.42017033135830634,"rank":52,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4190515921508973,"rank":53,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4203964909432674,"rank":52,"remainingConfigurations":398},{"removed":"briefcase","score":0.41988248065414147,"rank":51,"remainingConfigurations":398},{"removed":"aime","score":0.4222430605322958,"rank":51,"remainingConfigurations":398},{"removed":"apex-agents","score":0.41608785261025255,"rank":53,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.42003034934243266,"rank":52,"remainingConfigurations":398},{"removed":"automationbench","score":0.4197941621756977,"rank":51,"remainingConfigurations":398},{"removed":"critpt","score":0.4173418861465268,"rank":53,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.42002099802470244,"rank":53,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4215861329951384,"rank":52,"remainingConfigurations":398},{"removed":"gdpval","score":0.4204751933663993,"rank":51,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4178718539701079,"rank":53,"remainingConfigurations":398},{"removed":"gpqa","score":0.4193116356756934,"rank":52,"remainingConfigurations":398},{"removed":"harvey","score":0.4179038921586545,"rank":52,"remainingConfigurations":398},{"removed":"hle","score":0.3709971703868153,"rank":70,"remainingConfigurations":398},{"removed":"ifbench","score":0.43043717930735953,"rank":50,"remainingConfigurations":398},{"removed":"itbench","score":0.4198319299608803,"rank":52,"remainingConfigurations":398},{"removed":"livecodebench","score":0.42015757674477633,"rank":52,"remainingConfigurations":398},{"removed":"math500","score":0.42010353891955216,"rank":52,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4244489872074464,"rank":52,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4328871494764061,"rank":51,"remainingConfigurations":398},{"removed":"omniscience","score":0.41417236971559657,"rank":55,"remainingConfigurations":398},{"removed":"scicode","score":0.42147729505584003,"rank":52,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4205614713296469,"rank":50,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.41565951027629144,"rank":55,"remainingConfigurations":398},{"removed":"arc-agi","score":0.40782730299161046,"rank":62,"remainingConfigurations":398},{"removed":"deepswe","score":0.38476779962109414,"rank":56,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.42019756429458993,"rank":52,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.42088962623417564,"rank":51,"remainingConfigurations":398},{"removed":"frontiercode","score":0.43166331627524945,"rank":51,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4068483501050577,"rank":57,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4189327469053308,"rank":51,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.41462966418463676,"rank":54,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4196693461526162,"rank":52,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4203888752317168,"rank":52,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4188989317157679,"rank":52,"remainingConfigurations":398},{"removed":"livebench-language","score":0.42184211019693857,"rank":52,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4208371820395524,"rank":53,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.41767139668805914,"rank":52,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.41918123789190503,"rank":52,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.42231591975537836,"rank":52,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4195366792448197,"rank":52,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4188249919164495,"rank":51,"remainingConfigurations":398},{"removed":"frontiermath","score":0.41436149145537077,"rank":53,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4229892252119303,"rank":53,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4194173494733265,"rank":52,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.41978881293558623,"rank":52,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.41926767666074466,"rank":52,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4200252151741615,"rank":52,"remainingConfigurations":398},{"removed":"vibe-code","score":0.41904197766067425,"rank":52,"remainingConfigurations":398}]},"gemini-3.7-flash--effort-low":{"score":0.4199521185670017,"rank":53,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4156550352077857,"rank":50,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.508042254159506,"rank":40,"remainingConfigurations":398},{"removed":"Datacurve","score":0.36823891224509,"rank":60,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4202522126224204,"rank":51,"remainingConfigurations":398},{"removed":"Scale","score":0.43503762875188084,"rank":52,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4160566970675674,"rank":54,"remainingConfigurations":398},{"removed":"Cognition","score":0.3695126228061865,"rank":73,"remainingConfigurations":398},{"removed":"LiveBench","score":0.42727135916177006,"rank":52,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4157532607891103,"rank":53,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.426725594750857,"rank":54,"remainingConfigurations":381},{"removed":"Vals AI","score":0.41445438929719924,"rank":52,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.42007347463195793,"rank":52,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4191661252263428,"rank":53,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4200271134835815,"rank":53,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4199521185670017,"rank":53,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4193393332871472,"rank":52,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.42024530887152367,"rank":53,"remainingConfigurations":398},{"removed":"briefcase","score":0.41959831082382193,"rank":52,"remainingConfigurations":398},{"removed":"aime","score":0.418507022916701,"rank":53,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4209979518436195,"rank":52,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.42083989497815305,"rank":51,"remainingConfigurations":398},{"removed":"automationbench","score":0.4189551243148694,"rank":52,"remainingConfigurations":398},{"removed":"critpt","score":0.4228061856479471,"rank":52,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4200511298066297,"rank":52,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.420964020621015,"rank":53,"remainingConfigurations":398},{"removed":"gdpval","score":0.4204185365385333,"rank":52,"remainingConfigurations":398},{"removed":"gmmlu","score":0.41999563550041863,"rank":52,"remainingConfigurations":398},{"removed":"gpqa","score":0.41900533803783074,"rank":53,"remainingConfigurations":398},{"removed":"harvey","score":0.41691081225554866,"rank":53,"remainingConfigurations":398},{"removed":"hle","score":0.4285483973624637,"rank":52,"remainingConfigurations":398},{"removed":"ifbench","score":0.4173226364057559,"rank":52,"remainingConfigurations":398},{"removed":"itbench","score":0.4197082568237252,"rank":53,"remainingConfigurations":398},{"removed":"livecodebench","score":0.42016342272739376,"rank":51,"remainingConfigurations":398},{"removed":"math500","score":0.41996354027382354,"rank":53,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.42534835485469163,"rank":51,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.42799599373631886,"rank":53,"remainingConfigurations":398},{"removed":"omniscience","score":0.41845191863618253,"rank":53,"remainingConfigurations":398},{"removed":"scicode","score":0.4175056567087019,"rank":54,"remainingConfigurations":398},{"removed":"tau-bench","score":0.419338251062977,"rank":51,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.41664703921205115,"rank":54,"remainingConfigurations":398},{"removed":"arc-agi","score":0.5099286422142745,"rank":41,"remainingConfigurations":398},{"removed":"deepswe","score":0.368376769393679,"rank":60,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.4200176333690307,"rank":53,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4168477571022349,"rank":54,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3695126228061865,"rank":73,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.42030054528067473,"rank":52,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.41740929370693447,"rank":53,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.41972229243184955,"rank":52,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4191657674452485,"rank":53,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4203395064260225,"rank":53,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4188276388972632,"rank":53,"remainingConfigurations":398},{"removed":"livebench-language","score":0.421447280790381,"rank":53,"remainingConfigurations":398},{"removed":"livebench-data","score":0.42100577565517744,"rank":52,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4171479354450908,"rank":53,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4187405141718185,"rank":53,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4221165574411317,"rank":53,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4157532607891103,"rank":53,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4132714164834459,"rank":52,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4213195160261595,"rank":52,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4258846348592799,"rank":52,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.41843989703518897,"rank":53,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.41968753516399654,"rank":53,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4189691398169126,"rank":53,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4197845795629363,"rank":53,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4188436125334804,"rank":53,"remainingConfigurations":398}]},"muse-spark-1.1--effort-xhigh":{"score":0.41129890156180154,"rank":54,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4200825069483729,"rank":49,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.43449856589067387,"rank":57,"remainingConfigurations":398},{"removed":"Datacurve","score":0.39645500075480317,"rank":51,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.41106488635585703,"rank":54,"remainingConfigurations":398},{"removed":"Scale","score":0.4110325904839092,"rank":58,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4131693403848615,"rank":56,"remainingConfigurations":398},{"removed":"Cognition","score":0.42237406615327283,"rank":55,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4224657392841032,"rank":54,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4062281509660011,"rank":55,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.42203762381252,"rank":57,"remainingConfigurations":381},{"removed":"Vals AI","score":0.385571987709546,"rank":63,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.41131212461235284,"rank":54,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4106931296273639,"rank":54,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4113793123578027,"rank":54,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.41129890156180154,"rank":54,"remainingConfigurations":398},{"removed":"All provider reports","score":0.41077312324601395,"rank":54,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4113248526415618,"rank":54,"remainingConfigurations":398},{"removed":"briefcase","score":0.4154747648522246,"rank":53,"remainingConfigurations":398},{"removed":"aime","score":0.40988234978608884,"rank":55,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4116568885726127,"rank":54,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4123740570431756,"rank":53,"remainingConfigurations":398},{"removed":"automationbench","score":0.41126407539460436,"rank":53,"remainingConfigurations":398},{"removed":"critpt","score":0.4117078697775429,"rank":56,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.4111767986774581,"rank":54,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.41263657768941164,"rank":54,"remainingConfigurations":398},{"removed":"gdpval","score":0.41202451879402346,"rank":53,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4114707735323657,"rank":54,"remainingConfigurations":398},{"removed":"gpqa","score":0.40976015280991257,"rank":54,"remainingConfigurations":398},{"removed":"harvey","score":0.39787519263614257,"rank":59,"remainingConfigurations":398},{"removed":"hle","score":0.4143673940456017,"rank":54,"remainingConfigurations":398},{"removed":"ifbench","score":0.4090500844049791,"rank":54,"remainingConfigurations":398},{"removed":"itbench","score":0.41097009877741053,"rank":54,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4112007281249413,"rank":54,"remainingConfigurations":398},{"removed":"math500","score":0.4113981229329342,"rank":54,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4137701473993474,"rank":55,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.42118368421019214,"rank":55,"remainingConfigurations":398},{"removed":"omniscience","score":0.41156232231705814,"rank":56,"remainingConfigurations":398},{"removed":"scicode","score":0.4075204881787046,"rank":56,"remainingConfigurations":398},{"removed":"tau-bench","score":0.4095530167578179,"rank":53,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.42108692989347124,"rank":52,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4329556536258839,"rank":56,"remainingConfigurations":398},{"removed":"deepswe","score":0.3965732198759426,"rank":51,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.41535572345203575,"rank":54,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.41014372993409837,"rank":55,"remainingConfigurations":398},{"removed":"frontiercode","score":0.42237406615327283,"rank":55,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.412762211812339,"rank":53,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.41338489933679573,"rank":54,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4152080033928424,"rank":53,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.39505262118470713,"rank":60,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4169083392713651,"rank":54,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.41285389093654407,"rank":54,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4201089500832285,"rank":54,"remainingConfigurations":398},{"removed":"livebench-data","score":0.41138019804590814,"rank":54,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3987382341585381,"rank":58,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.40843114139947506,"rank":54,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.41077678144773216,"rank":56,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4062281509660011,"rank":55,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4077609896354218,"rank":54,"remainingConfigurations":398},{"removed":"frontiermath","score":0.41221263207522196,"rank":54,"remainingConfigurations":398},{"removed":"simpleqa","score":0.41614040409754544,"rank":56,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4032347411732234,"rank":57,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.41699153845904013,"rank":54,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4145918862050671,"rank":54,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4166759193699965,"rank":54,"remainingConfigurations":398},{"removed":"vibe-code","score":0.41084304873969063,"rank":54,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-max":{"score":0.4074665735133989,"rank":55,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.408139761577554,"rank":53,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.44772786899504385,"rank":53,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3362172446597223,"rank":70,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.40739452077861826,"rank":55,"remainingConfigurations":398},{"removed":"Scale","score":0.4208937523863137,"rank":54,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.43585686636824567,"rank":51,"remainingConfigurations":398},{"removed":"Cognition","score":0.40291647845375717,"rank":62,"remainingConfigurations":398},{"removed":"LiveBench","score":0.43035109034499525,"rank":51,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4017842223487232,"rank":56,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.41120504354706305,"rank":58,"remainingConfigurations":381},{"removed":"Vals AI","score":0.391348104079766,"rank":59,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.40756043735418485,"rank":55,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.40904438969087903,"rank":55,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.4070601038157258,"rank":55,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4074665735133989,"rank":55,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4086783908523269,"rank":55,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4075443344439695,"rank":56,"remainingConfigurations":398},{"removed":"briefcase","score":0.40707046904677924,"rank":54,"remainingConfigurations":398},{"removed":"aime","score":0.4036449562069892,"rank":57,"remainingConfigurations":398},{"removed":"apex-agents","score":0.40694462180835145,"rank":56,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4071294800007798,"rank":56,"remainingConfigurations":398},{"removed":"automationbench","score":0.4067705926275021,"rank":54,"remainingConfigurations":398},{"removed":"critpt","score":0.4078598000915609,"rank":57,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.40845448022328573,"rank":55,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4070337764125434,"rank":56,"remainingConfigurations":398},{"removed":"gdpval","score":0.40737353683590616,"rank":55,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4076082628505507,"rank":55,"remainingConfigurations":398},{"removed":"gpqa","score":0.40521749509013993,"rank":55,"remainingConfigurations":398},{"removed":"harvey","score":0.41179995729181873,"rank":54,"remainingConfigurations":398},{"removed":"hle","score":0.4129148863595989,"rank":55,"remainingConfigurations":398},{"removed":"ifbench","score":0.40625397053270973,"rank":55,"remainingConfigurations":398},{"removed":"itbench","score":0.4071451183004147,"rank":56,"remainingConfigurations":398},{"removed":"livecodebench","score":0.40749052291987614,"rank":55,"remainingConfigurations":398},{"removed":"math500","score":0.4075435802552297,"rank":55,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4199748559152652,"rank":54,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4175555365516361,"rank":56,"remainingConfigurations":398},{"removed":"omniscience","score":0.40857731026026634,"rank":57,"remainingConfigurations":398},{"removed":"scicode","score":0.40804928503256677,"rank":55,"remainingConfigurations":398},{"removed":"tau-bench","score":0.40690161638356104,"rank":54,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.43049954006156793,"rank":51,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4165799931411682,"rank":59,"remainingConfigurations":398},{"removed":"deepswe","score":0.3358954225776372,"rank":70,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.40747028692990334,"rank":55,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.41964284896690507,"rank":52,"remainingConfigurations":398},{"removed":"frontiercode","score":0.40291647845375717,"rank":62,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4082022786950694,"rank":55,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.405168000053669,"rank":55,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4071317251843847,"rank":55,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4068648901109855,"rank":54,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4102997334744045,"rank":55,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.39741803699034123,"rank":59,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4138681925993566,"rank":55,"remainingConfigurations":398},{"removed":"livebench-data","score":0.40218970806955306,"rank":59,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.40655078356011737,"rank":54,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.40684274767622947,"rank":55,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4151246103900123,"rank":54,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4017842223487232,"rank":56,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.40552655930689485,"rank":56,"remainingConfigurations":398},{"removed":"frontiermath","score":0.40027800800138075,"rank":59,"remainingConfigurations":398},{"removed":"simpleqa","score":0.421484921128464,"rank":54,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.40529823866310344,"rank":55,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.40315855782602544,"rank":57,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.41004567038078243,"rank":55,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.40261795474652384,"rank":57,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4043282913700745,"rank":56,"remainingConfigurations":398}]},"qwen3.8-flash-next--effort-reasoning":{"score":0.4070235787925161,"rank":56,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.44754069295528115,"rank":54,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3754355165684971,"rank":57,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.40528548670562303,"rank":56,"remainingConfigurations":398},{"removed":"Scale","score":0.4227058834169106,"rank":53,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.4099477907260118,"rank":57,"remainingConfigurations":398},{"removed":"Cognition","score":0.4167260374346868,"rank":57,"remainingConfigurations":398},{"removed":"LiveBench","score":0.4116286319149692,"rank":56,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4121246556222468,"rank":54,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.40935205444893,"rank":59,"remainingConfigurations":381},{"removed":"Vals AI","score":0.4020394057739964,"rank":54,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4069997009468334,"rank":56,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.4066112076505432,"rank":56,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.40634266318729734,"rank":56,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4070235787925161,"rank":56,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4058803628742594,"rank":56,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.4083508796797131,"rank":55,"remainingConfigurations":398},{"removed":"briefcase","score":0.3843784724896666,"rank":65,"remainingConfigurations":398},{"removed":"aime","score":0.4065092902588217,"rank":56,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4098110009805525,"rank":55,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.40797408782029665,"rank":55,"remainingConfigurations":398},{"removed":"automationbench","score":0.3965465627203863,"rank":61,"remainingConfigurations":398},{"removed":"critpt","score":0.41399607143807077,"rank":55,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.40827635392156836,"rank":56,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.4095660319795041,"rank":55,"remainingConfigurations":398},{"removed":"gdpval","score":0.3947661288359868,"rank":60,"remainingConfigurations":398},{"removed":"gmmlu","score":0.40697628874237973,"rank":56,"remainingConfigurations":398},{"removed":"gpqa","score":0.40214149451052195,"rank":57,"remainingConfigurations":398},{"removed":"harvey","score":0.4058756580314557,"rank":55,"remainingConfigurations":398},{"removed":"hle","score":0.41970216690979356,"rank":53,"remainingConfigurations":398},{"removed":"ifbench","score":0.4010399303656607,"rank":58,"remainingConfigurations":398},{"removed":"itbench","score":0.40744606619888635,"rank":55,"remainingConfigurations":398},{"removed":"livecodebench","score":0.4048827327232895,"rank":56,"remainingConfigurations":398},{"removed":"math500","score":0.4067272963932864,"rank":56,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.41036447768536566,"rank":57,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.42150767430959585,"rank":54,"remainingConfigurations":398},{"removed":"omniscience","score":0.4572148879416565,"rank":48,"remainingConfigurations":398},{"removed":"scicode","score":0.4178260580066308,"rank":53,"remainingConfigurations":398},{"removed":"tau-bench","score":0.394820024825198,"rank":60,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.39820239501496224,"rank":63,"remainingConfigurations":398},{"removed":"arc-agi","score":0.44625034709003364,"rank":55,"remainingConfigurations":398},{"removed":"deepswe","score":0.3756143919866168,"rank":57,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.40709525602452973,"rank":56,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4048310329051302,"rank":56,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4167260374346868,"rank":57,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4071505157042494,"rank":56,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.404827180907982,"rank":56,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.40652322486289777,"rank":56,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.40601493835308755,"rank":55,"remainingConfigurations":398},{"removed":"livebench-math","score":0.4073342694856292,"rank":56,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.4057808789516608,"rank":55,"remainingConfigurations":398},{"removed":"livebench-language","score":0.40922745773631747,"rank":57,"remainingConfigurations":398},{"removed":"livebench-data","score":0.40741482353490627,"rank":55,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.40404212142922113,"rank":55,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4058627912963419,"rank":56,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4094280499048142,"rank":57,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4121246556222468,"rank":54,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.39820283050932354,"rank":58,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4094989782768587,"rank":56,"remainingConfigurations":398},{"removed":"simpleqa","score":0.41432945649885133,"rank":57,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.40609915078294295,"rank":54,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.40649498819975366,"rank":55,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.40622178958831645,"rank":56,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.40695379309418983,"rank":55,"remainingConfigurations":398},{"removed":"vibe-code","score":0.405684120465188,"rank":55,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-xhigh":{"score":0.4043653730313383,"rank":57,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.4038737415754756,"rank":54,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4868802507616074,"rank":45,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3474914592982707,"rank":67,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.40460782253126676,"rank":57,"remainingConfigurations":398},{"removed":"Scale","score":0.41743357949459603,"rank":56,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.40104587724305274,"rank":58,"remainingConfigurations":398},{"removed":"Cognition","score":0.3712385510811625,"rank":72,"remainingConfigurations":398},{"removed":"LiveBench","score":0.41019148610306105,"rank":57,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.4016455178196156,"rank":57,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.40783877476968106,"rank":60,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3988839385308987,"rank":55,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.40446866614874016,"rank":57,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.40451940770824196,"rank":57,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.40432192071922585,"rank":57,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4043653730313383,"rank":57,"remainingConfigurations":398},{"removed":"All provider reports","score":0.40454562033943725,"rank":57,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.40477767183605495,"rank":57,"remainingConfigurations":398},{"removed":"briefcase","score":0.40309064569505243,"rank":56,"remainingConfigurations":398},{"removed":"aime","score":0.4028241076039953,"rank":58,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4055089247122961,"rank":57,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4039473130711961,"rank":57,"remainingConfigurations":398},{"removed":"automationbench","score":0.4034753873650791,"rank":55,"remainingConfigurations":398},{"removed":"critpt","score":0.40272966388992687,"rank":58,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.40439286331430385,"rank":57,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.40147155015999175,"rank":58,"remainingConfigurations":398},{"removed":"gdpval","score":0.40399562118589705,"rank":56,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4044640550196599,"rank":57,"remainingConfigurations":398},{"removed":"gpqa","score":0.40390609148982404,"rank":56,"remainingConfigurations":398},{"removed":"harvey","score":0.4027291273506331,"rank":56,"remainingConfigurations":398},{"removed":"hle","score":0.4117573200297712,"rank":56,"remainingConfigurations":398},{"removed":"ifbench","score":0.4024487133161425,"rank":57,"remainingConfigurations":398},{"removed":"itbench","score":0.40416662296288974,"rank":57,"remainingConfigurations":398},{"removed":"livecodebench","score":0.40439463037324447,"rank":57,"remainingConfigurations":398},{"removed":"math500","score":0.404278631288,"rank":57,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4109106089978383,"rank":56,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4158637114805413,"rank":57,"remainingConfigurations":398},{"removed":"omniscience","score":0.40483350201233503,"rank":58,"remainingConfigurations":398},{"removed":"scicode","score":0.4069255079892316,"rank":57,"remainingConfigurations":398},{"removed":"tau-bench","score":0.40456489422283176,"rank":57,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.40195194819167696,"rank":58,"remainingConfigurations":398},{"removed":"arc-agi","score":0.49099394366527926,"rank":44,"remainingConfigurations":398},{"removed":"deepswe","score":0.3474243348458949,"rank":67,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.40442275951954637,"rank":57,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.40007598915566933,"rank":58,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3712385510811625,"rank":72,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.40389756971053664,"rank":58,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.4008103296025057,"rank":57,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.404144313191539,"rank":57,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.40377488649648635,"rank":56,"remainingConfigurations":398},{"removed":"livebench-math","score":0.40473399766911805,"rank":57,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.40296127136583965,"rank":56,"remainingConfigurations":398},{"removed":"livebench-language","score":0.4062220887112414,"rank":58,"remainingConfigurations":398},{"removed":"livebench-data","score":0.4046205759543451,"rank":57,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.4015282612244418,"rank":56,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.40312536639112345,"rank":57,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4073308965638744,"rank":58,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.4016455178196156,"rank":57,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.39948575582697443,"rank":57,"remainingConfigurations":398},{"removed":"frontiermath","score":0.40397363147122567,"rank":57,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4115672272494653,"rank":58,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.40353133190231033,"rank":56,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4036826057370168,"rank":56,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4035893682761326,"rank":57,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.40389028073155636,"rank":56,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4030173926028205,"rank":57,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-high":{"score":0.4014771878406029,"rank":58,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.41344262720924924,"rank":51,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.40108721028746874,"rank":66,"remainingConfigurations":398},{"removed":"Datacurve","score":0.36055836701574373,"rank":63,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.4013601388248574,"rank":58,"remainingConfigurations":398},{"removed":"Scale","score":0.4141094167382137,"rank":57,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.39885913469847045,"rank":59,"remainingConfigurations":398},{"removed":"Cognition","score":0.4259092431225638,"rank":54,"remainingConfigurations":398},{"removed":"LiveBench","score":0.40803731781675706,"rank":58,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3968385569261827,"rank":60,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.405340599879548,"rank":61,"remainingConfigurations":381},{"removed":"Vals AI","score":0.39370163502116856,"rank":56,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.4015831323961958,"rank":58,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.40167190460924856,"rank":58,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.401440652862287,"rank":58,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.4014771878406029,"rank":58,"remainingConfigurations":398},{"removed":"All provider reports","score":0.4017049744052404,"rank":58,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.40184802620810495,"rank":58,"remainingConfigurations":398},{"removed":"briefcase","score":0.4000568391918779,"rank":58,"remainingConfigurations":398},{"removed":"aime","score":0.39998821768219256,"rank":59,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4026037489494089,"rank":58,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.40263070324147954,"rank":58,"remainingConfigurations":398},{"removed":"automationbench","score":0.3999061465603834,"rank":58,"remainingConfigurations":398},{"removed":"critpt","score":0.40006856290367176,"rank":59,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.40150979976685486,"rank":58,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.39846188466217297,"rank":60,"remainingConfigurations":398},{"removed":"gdpval","score":0.4004375006989262,"rank":57,"remainingConfigurations":398},{"removed":"gmmlu","score":0.4015738666059298,"rank":58,"remainingConfigurations":398},{"removed":"gpqa","score":0.39979179460493564,"rank":58,"remainingConfigurations":398},{"removed":"harvey","score":0.3998687382158492,"rank":58,"remainingConfigurations":398},{"removed":"hle","score":0.4080145671992705,"rank":57,"remainingConfigurations":398},{"removed":"ifbench","score":0.40499741678343576,"rank":56,"remainingConfigurations":398},{"removed":"itbench","score":0.40125024760198963,"rank":58,"remainingConfigurations":398},{"removed":"livecodebench","score":0.40110487415737156,"rank":58,"remainingConfigurations":398},{"removed":"math500","score":0.40135803382420465,"rank":58,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4061448772350464,"rank":58,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4116637303347718,"rank":58,"remainingConfigurations":398},{"removed":"omniscience","score":0.4007927372048555,"rank":60,"remainingConfigurations":398},{"removed":"scicode","score":0.4014954807010427,"rank":58,"remainingConfigurations":398},{"removed":"tau-bench","score":0.404850140541041,"rank":56,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.398561495145971,"rank":60,"remainingConfigurations":398},{"removed":"arc-agi","score":0.42816338859201636,"rank":58,"remainingConfigurations":398},{"removed":"deepswe","score":0.36043892821619655,"rank":63,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.401530431514416,"rank":58,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.4022513332872047,"rank":57,"remainingConfigurations":398},{"removed":"frontiercode","score":0.4259092431225638,"rank":54,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.40078787562062207,"rank":59,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3980280581365947,"rank":59,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.4013027029456236,"rank":58,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4009246500609791,"rank":58,"remainingConfigurations":398},{"removed":"livebench-math","score":0.40192293203646984,"rank":58,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.39984399302486145,"rank":57,"remainingConfigurations":398},{"removed":"livebench-language","score":0.40340126686738836,"rank":59,"remainingConfigurations":398},{"removed":"livebench-data","score":0.40169717637140107,"rank":60,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.39872762446129745,"rank":59,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.4002823875317516,"rank":59,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4044342710653593,"rank":59,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3968385569261827,"rank":60,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.394810484194966,"rank":59,"remainingConfigurations":398},{"removed":"frontiermath","score":0.4006652704300327,"rank":58,"remainingConfigurations":398},{"removed":"simpleqa","score":0.4082880173197581,"rank":59,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.4007361275421968,"rank":58,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.4008093355373307,"rank":59,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.400799522158022,"rank":59,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.4009814323160188,"rank":58,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4001473397207756,"rank":59,"remainingConfigurations":398}]},"claude-sonnet-5--effort-xhigh":{"score":0.3993635488772256,"rank":59,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.40292114831368026,"rank":55,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.40994814934243506,"rank":62,"remainingConfigurations":398},{"removed":"Datacurve","score":0.38744024827492546,"rank":55,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.39925785791098883,"rank":59,"remainingConfigurations":398},{"removed":"Scale","score":0.4108178132563656,"rank":59,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3973644098835842,"rank":61,"remainingConfigurations":398},{"removed":"Cognition","score":0.37296015379693404,"rank":71,"remainingConfigurations":398},{"removed":"LiveBench","score":0.40738108257583305,"rank":59,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.39433895553793974,"rank":61,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.43442071535513493,"rank":53,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3887477406689455,"rank":61,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.39928729782698996,"rank":59,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.39915236831879936,"rank":59,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.39910170096511727,"rank":59,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3993635488772256,"rank":59,"remainingConfigurations":398},{"removed":"All provider reports","score":0.39879383479600494,"rank":59,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3995251285867614,"rank":59,"remainingConfigurations":398},{"removed":"briefcase","score":0.3982753536677022,"rank":59,"remainingConfigurations":398},{"removed":"aime","score":0.39307084239706147,"rank":61,"remainingConfigurations":398},{"removed":"apex-agents","score":0.4001046984949976,"rank":59,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.4004566564479146,"rank":59,"remainingConfigurations":398},{"removed":"automationbench","score":0.40007694695112317,"rank":57,"remainingConfigurations":398},{"removed":"critpt","score":0.39954329427196056,"rank":60,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3979713068370138,"rank":59,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.40169484273668554,"rank":57,"remainingConfigurations":398},{"removed":"gdpval","score":0.3990703977161309,"rank":59,"remainingConfigurations":398},{"removed":"gmmlu","score":0.39949028296704087,"rank":59,"remainingConfigurations":398},{"removed":"gpqa","score":0.39375037256469486,"rank":61,"remainingConfigurations":398},{"removed":"harvey","score":0.3975297770754192,"rank":60,"remainingConfigurations":398},{"removed":"hle","score":0.40478101248696013,"rank":59,"remainingConfigurations":398},{"removed":"ifbench","score":0.39740805959746656,"rank":59,"remainingConfigurations":398},{"removed":"itbench","score":0.39909210556940716,"rank":59,"remainingConfigurations":398},{"removed":"livecodebench","score":0.39919597300838333,"rank":59,"remainingConfigurations":398},{"removed":"math500","score":0.39932495356058256,"rank":59,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.403315906474683,"rank":59,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.40944619787643965,"rank":59,"remainingConfigurations":398},{"removed":"omniscience","score":0.40147069468346636,"rank":59,"remainingConfigurations":398},{"removed":"scicode","score":0.39914685870551997,"rank":59,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3972721892614773,"rank":59,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.39842842996294037,"rank":61,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4095253356177128,"rank":60,"remainingConfigurations":398},{"removed":"deepswe","score":0.3876195928542834,"rank":55,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3994478811228916,"rank":59,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3981357176544144,"rank":59,"remainingConfigurations":398},{"removed":"frontiercode","score":0.37296015379693404,"rank":71,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.4002527383406675,"rank":60,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.39669662616407514,"rank":60,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.39918851085090296,"rank":59,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3975379857320534,"rank":59,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3985685398487801,"rank":60,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3897797909888603,"rank":63,"remainingConfigurations":398},{"removed":"livebench-language","score":0.41045851693921814,"rank":56,"remainingConfigurations":398},{"removed":"livebench-data","score":0.40712845195786174,"rank":56,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3849890531879057,"rank":65,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.39222408966900213,"rank":61,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.4126153732937478,"rank":55,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.39433895553793974,"rank":61,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3940111302659899,"rank":60,"remainingConfigurations":398},{"removed":"frontiermath","score":0.39809992845800973,"rank":61,"remainingConfigurations":398},{"removed":"simpleqa","score":0.418829973089609,"rank":55,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3980483761989668,"rank":59,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3992441283908586,"rank":60,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3986770514295181,"rank":60,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3990528458895828,"rank":59,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3981188967901263,"rank":60,"remainingConfigurations":398}]},"gemini-3.5-flash--effort-high":{"score":0.39848519209283234,"rank":60,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3964126982245661,"rank":56,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3961387719882396,"rank":67,"remainingConfigurations":398},{"removed":"Datacurve","score":0.41261740025583377,"rank":47,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.39846727858873293,"rank":60,"remainingConfigurations":398},{"removed":"Scale","score":0.4204819913980125,"rank":55,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3988067648722142,"rank":60,"remainingConfigurations":398},{"removed":"Cognition","score":0.41003039929571355,"rank":60,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3994516317671304,"rank":61,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3971535661978056,"rank":59,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.37779943149745515,"rank":70,"remainingConfigurations":381},{"removed":"Vals AI","score":0.38655230874358365,"rank":62,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.398402121437033,"rank":60,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.39773976288034724,"rank":60,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3985869503018577,"rank":60,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.39848519209283234,"rank":60,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3977475157082482,"rank":60,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3974883022226257,"rank":60,"remainingConfigurations":398},{"removed":"briefcase","score":0.4000669144396694,"rank":57,"remainingConfigurations":398},{"removed":"aime","score":0.39927751003724815,"rank":60,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3968390822369134,"rank":60,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.39886620767798414,"rank":60,"remainingConfigurations":398},{"removed":"automationbench","score":0.39827376649425195,"rank":59,"remainingConfigurations":398},{"removed":"critpt","score":0.3995088601898383,"rank":61,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3959361763222184,"rank":60,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3987985110313084,"rank":59,"remainingConfigurations":398},{"removed":"gdpval","score":0.399226848323432,"rank":58,"remainingConfigurations":398},{"removed":"gmmlu","score":0.39858924631989595,"rank":60,"remainingConfigurations":398},{"removed":"gpqa","score":0.39753659554321347,"rank":60,"remainingConfigurations":398},{"removed":"harvey","score":0.40130108824414384,"rank":57,"remainingConfigurations":398},{"removed":"hle","score":0.39422388982024775,"rank":63,"remainingConfigurations":398},{"removed":"ifbench","score":0.39736653243740655,"rank":60,"remainingConfigurations":398},{"removed":"itbench","score":0.3979970900280984,"rank":60,"remainingConfigurations":398},{"removed":"livecodebench","score":0.39855861278543564,"rank":60,"remainingConfigurations":398},{"removed":"math500","score":0.398567966201536,"rank":60,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3977444091088913,"rank":62,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4075014343202194,"rank":60,"remainingConfigurations":398},{"removed":"omniscience","score":0.39905472405509457,"rank":61,"remainingConfigurations":398},{"removed":"scicode","score":0.39894497859310113,"rank":60,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3977348106364118,"rank":58,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3982630021635319,"rank":62,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3943501411660397,"rank":67,"remainingConfigurations":398},{"removed":"deepswe","score":0.41286642619148334,"rank":47,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3985508871043944,"rank":60,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.39740141277663493,"rank":60,"remainingConfigurations":398},{"removed":"frontiercode","score":0.41003039929571355,"rank":60,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.40837889055958865,"rank":54,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.40029110488654546,"rank":58,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.39833155735027875,"rank":60,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.4030825804334072,"rank":57,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3990470146532262,"rank":59,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.39807580918695873,"rank":58,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3942823730661425,"rank":62,"remainingConfigurations":398},{"removed":"livebench-data","score":0.40291485093561974,"rank":58,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.39878455672954577,"rank":57,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.40146503208168766,"rank":58,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3948902036754398,"rank":61,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3971535661978056,"rank":59,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.38756167223740606,"rank":62,"remainingConfigurations":398},{"removed":"frontiermath","score":0.41129932920414575,"rank":55,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3944039524733525,"rank":62,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3903302114478699,"rank":62,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.40278429019243633,"rank":58,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.4016587516723802,"rank":58,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.39691188240354397,"rank":60,"remainingConfigurations":398},{"removed":"vibe-code","score":0.4021233750959601,"rank":58,"remainingConfigurations":398}]},"gemini-3.5-flash--effort-low":{"score":0.3951779988548216,"rank":61,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3756082247115098,"rank":60,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4804784311868295,"rank":46,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3623384187986181,"rank":61,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3951486873269549,"rank":61,"remainingConfigurations":398},{"removed":"Scale","score":0.4098522921271452,"rank":60,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.39712004794777217,"rank":62,"remainingConfigurations":398},{"removed":"Cognition","score":0.42869386185076763,"rank":53,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3958567420134189,"rank":62,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.39431571987364095,"rank":62,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3927035137269801,"rank":57,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3951293036606107,"rank":61,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3945125120549509,"rank":61,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3949823161933352,"rank":61,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3951779988548216,"rank":61,"remainingConfigurations":398},{"removed":"All provider reports","score":0.394248032886376,"rank":61,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3955609906663733,"rank":61,"remainingConfigurations":398},{"removed":"briefcase","score":0.39492362467507,"rank":61,"remainingConfigurations":398},{"removed":"aime","score":0.4154412058515827,"rank":54,"remainingConfigurations":398},{"removed":"apex-agents","score":0.39631943863545516,"rank":61,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3952694170397922,"rank":61,"remainingConfigurations":398},{"removed":"automationbench","score":0.39500521868510635,"rank":62,"remainingConfigurations":398},{"removed":"critpt","score":0.3943371067171923,"rank":62,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3953293901233133,"rank":61,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.39650305347503895,"rank":61,"remainingConfigurations":398},{"removed":"gdpval","score":0.3947014382517727,"rank":61,"remainingConfigurations":398},{"removed":"gmmlu","score":0.39573067576579146,"rank":61,"remainingConfigurations":398},{"removed":"gpqa","score":0.3986565759365079,"rank":59,"remainingConfigurations":398},{"removed":"harvey","score":0.3929040337123873,"rank":61,"remainingConfigurations":398},{"removed":"hle","score":0.4015990053683229,"rank":60,"remainingConfigurations":398},{"removed":"ifbench","score":0.3939878564576294,"rank":61,"remainingConfigurations":398},{"removed":"itbench","score":0.3948473242302257,"rank":61,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3955785027909236,"rank":61,"remainingConfigurations":398},{"removed":"math500","score":0.39546678980900657,"rank":61,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.399775235236014,"rank":61,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.4059206247875336,"rank":61,"remainingConfigurations":398},{"removed":"omniscience","score":0.3940127989897832,"rank":63,"remainingConfigurations":398},{"removed":"scicode","score":0.3968513896712154,"rank":61,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3909999956529346,"rank":61,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.39760766813336285,"rank":64,"remainingConfigurations":398},{"removed":"arc-agi","score":0.481388760244585,"rank":46,"remainingConfigurations":398},{"removed":"deepswe","score":0.3625425303553427,"rank":61,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3952252387534003,"rank":61,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3936952846444954,"rank":61,"remainingConfigurations":398},{"removed":"frontiercode","score":0.42869386185076763,"rank":53,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3957873415644817,"rank":61,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3927761038448043,"rank":61,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.39473175476837485,"rank":61,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3940144219886214,"rank":61,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3956210045086687,"rank":61,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3931629995343693,"rank":60,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3972382726113148,"rank":60,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3957304909833146,"rank":61,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3925136671220773,"rank":61,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3938925360068632,"rank":60,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.39799953929465665,"rank":60,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.39431571987364095,"rank":62,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.35282638386077575,"rank":74,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3979077167028837,"rank":62,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3999669953527279,"rank":60,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3944375981235962,"rank":60,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3948261008493313,"rank":61,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3941617471120136,"rank":62,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.39509378984836285,"rank":61,"remainingConfigurations":398},{"removed":"vibe-code","score":0.39425392504852746,"rank":62,"remainingConfigurations":398}]},"gemini-3.8-flash--effort-low":{"score":0.3919734880060828,"rank":62,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.43117486814628975,"rank":58,"remainingConfigurations":398},{"removed":"Datacurve","score":0.36076754980230974,"rank":62,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.39032778474676655,"rank":64,"remainingConfigurations":398},{"removed":"Scale","score":0.408009759975182,"rank":61,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.39401447609078594,"rank":64,"remainingConfigurations":398},{"removed":"Cognition","score":0.39942786197583385,"rank":63,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3956967917777426,"rank":63,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3979441154521027,"rank":58,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3917214480971099,"rank":63,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3854535878132867,"rank":64,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.39196163610221296,"rank":62,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3916018617741976,"rank":62,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3913780943828114,"rank":62,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3919734880060828,"rank":62,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3909677583199924,"rank":62,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3933276693311918,"rank":62,"remainingConfigurations":398},{"removed":"briefcase","score":0.39801346932576775,"rank":60,"remainingConfigurations":398},{"removed":"aime","score":0.39014757290429114,"rank":63,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3951860841835781,"rank":62,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3883382542671819,"rank":64,"remainingConfigurations":398},{"removed":"automationbench","score":0.3967153204679408,"rank":60,"remainingConfigurations":398},{"removed":"critpt","score":0.4148142262333696,"rank":54,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.392797950382714,"rank":62,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3868079358509911,"rank":64,"remainingConfigurations":398},{"removed":"gdpval","score":0.3937192839172534,"rank":62,"remainingConfigurations":398},{"removed":"gmmlu","score":0.39275314181456505,"rank":62,"remainingConfigurations":398},{"removed":"gpqa","score":0.3866434534523084,"rank":63,"remainingConfigurations":398},{"removed":"harvey","score":0.39089924003993737,"rank":62,"remainingConfigurations":398},{"removed":"hle","score":0.4049002484442192,"rank":58,"remainingConfigurations":398},{"removed":"ifbench","score":0.38537348058034865,"rank":64,"remainingConfigurations":398},{"removed":"itbench","score":0.39286013628291117,"rank":62,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3885768724082159,"rank":64,"remainingConfigurations":398},{"removed":"math500","score":0.39058118148201665,"rank":63,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3936458534534227,"rank":63,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.39486658807110686,"rank":65,"remainingConfigurations":398},{"removed":"omniscience","score":0.39424565600010336,"rank":62,"remainingConfigurations":398},{"removed":"scicode","score":0.3867509884580962,"rank":64,"remainingConfigurations":398},{"removed":"tau-bench","score":0.38688642173725435,"rank":64,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3893809268969437,"rank":66,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4305175994433303,"rank":57,"remainingConfigurations":398},{"removed":"deepswe","score":0.36094105941640325,"rank":62,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.39204123673467434,"rank":62,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3898402656505367,"rank":62,"remainingConfigurations":398},{"removed":"frontiercode","score":0.39942786197583385,"rank":63,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3920224473839029,"rank":62,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3897289229914968,"rank":62,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3914775666803629,"rank":62,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3909270332877051,"rank":62,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3922860149318388,"rank":63,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.39066938220632763,"rank":61,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3941903252735006,"rank":63,"remainingConfigurations":398},{"removed":"livebench-data","score":0.39231121383413187,"rank":63,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.38901113931965153,"rank":62,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.39080753060110496,"rank":62,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3944654416935462,"rank":62,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3979441154521027,"rank":58,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.38300670521787833,"rank":64,"remainingConfigurations":398},{"removed":"frontiermath","score":0.39428863604673386,"rank":63,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3991783686887606,"rank":61,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3910812476802881,"rank":61,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3914070572382194,"rank":64,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.39116494159097415,"rank":63,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3918756111490196,"rank":63,"remainingConfigurations":398},{"removed":"vibe-code","score":0.39065132502984184,"rank":64,"remainingConfigurations":398}]},"gemini-3.6-flash--effort-high":{"score":0.39050728542983953,"rank":63,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3889089244548207,"rank":58,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4105982981942891,"rank":61,"remainingConfigurations":398},{"removed":"Datacurve","score":0.37266251256469585,"rank":58,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3905818439501525,"rank":62,"remainingConfigurations":398},{"removed":"Scale","score":0.40369765728056595,"rank":64,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.38927589535475865,"rank":65,"remainingConfigurations":398},{"removed":"Cognition","score":0.39062051532407494,"rank":65,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3954206116402648,"rank":64,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.38611247765524476,"rank":63,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.38808947280959644,"rank":65,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3800101996880318,"rank":65,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3904133467353173,"rank":63,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3898029753807353,"rank":63,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.390562941259268,"rank":64,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.39050728542983953,"rank":63,"remainingConfigurations":398},{"removed":"All provider reports","score":0.38974689281343494,"rank":63,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3905312950518564,"rank":63,"remainingConfigurations":398},{"removed":"briefcase","score":0.39154803562368135,"rank":62,"remainingConfigurations":398},{"removed":"aime","score":0.3921295989112674,"rank":62,"remainingConfigurations":398},{"removed":"apex-agents","score":0.39101922412776063,"rank":63,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3907641379420539,"rank":62,"remainingConfigurations":398},{"removed":"automationbench","score":0.3892175050099312,"rank":64,"remainingConfigurations":398},{"removed":"critpt","score":0.3916533788211714,"rank":63,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3904230613373431,"rank":63,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3910064262334694,"rank":63,"remainingConfigurations":398},{"removed":"gdpval","score":0.3906877511236216,"rank":63,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3906283517028855,"rank":63,"remainingConfigurations":398},{"removed":"gpqa","score":0.3846524429334497,"rank":64,"remainingConfigurations":398},{"removed":"harvey","score":0.38988426932654546,"rank":64,"remainingConfigurations":398},{"removed":"hle","score":0.3956837693285952,"rank":61,"remainingConfigurations":398},{"removed":"ifbench","score":0.38865504451933974,"rank":63,"remainingConfigurations":398},{"removed":"itbench","score":0.39013002202944774,"rank":63,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3906873387965777,"rank":62,"remainingConfigurations":398},{"removed":"math500","score":0.39060366618486414,"rank":62,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.391878393449202,"rank":64,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3998368790169727,"rank":64,"remainingConfigurations":398},{"removed":"omniscience","score":0.3907908977711229,"rank":64,"remainingConfigurations":398},{"removed":"scicode","score":0.3907545771419709,"rank":62,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3894312892579675,"rank":62,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.38917508433990283,"rank":67,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4092646884115505,"rank":61,"remainingConfigurations":398},{"removed":"deepswe","score":0.37280879200961453,"rank":58,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3905960856873507,"rank":63,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.389389757875324,"rank":63,"remainingConfigurations":398},{"removed":"frontiercode","score":0.39062051532407494,"rank":65,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3910982494076096,"rank":64,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.38842041816269773,"rank":63,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.39024024539539987,"rank":63,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3893900944900646,"rank":64,"remainingConfigurations":398},{"removed":"livebench-math","score":0.39438591547372526,"rank":62,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3898660676548282,"rank":62,"remainingConfigurations":398},{"removed":"livebench-language","score":0.38637243629238416,"rank":65,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3953566315296449,"rank":62,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.39328649910775026,"rank":60,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.38928558995492807,"rank":63,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3850897491090126,"rank":66,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.38611247765524476,"rank":63,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3875036919091319,"rank":63,"remainingConfigurations":398},{"removed":"frontiermath","score":0.399511077478598,"rank":60,"remainingConfigurations":398},{"removed":"simpleqa","score":0.38666123487774273,"rank":67,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.38448873911911013,"rank":63,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.39369399976484193,"rank":63,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.39490644491672056,"rank":61,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.38726933988675744,"rank":64,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3923029206256148,"rank":63,"remainingConfigurations":398}]},"glm-5.3-flash--effort-max":{"score":0.39031487577235063,"rank":64,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.39011456128331595,"rank":57,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4059633683554416,"rank":64,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2726159578072232,"rank":87,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3905452763937884,"rank":63,"remainingConfigurations":398},{"removed":"Scale","score":0.4049989956803682,"rank":62,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.38733629414994186,"rank":66,"remainingConfigurations":398},{"removed":"Cognition","score":0.40997970804811074,"rank":61,"remainingConfigurations":398},{"removed":"LiveBench","score":0.40236738120941457,"rank":60,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3855455447711409,"rank":64,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.43989431890040787,"rank":50,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3906239912877096,"rank":60,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.39029943769427783,"rank":64,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3891772112620943,"rank":64,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.39058397654814736,"rank":63,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.39031487577235063,"rank":64,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3894152156147231,"rank":64,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.39035695774213325,"rank":64,"remainingConfigurations":398},{"removed":"briefcase","score":0.39026592905718355,"rank":63,"remainingConfigurations":398},{"removed":"aime","score":0.38153257271624846,"rank":67,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3908064563557219,"rank":64,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3903151472878607,"rank":63,"remainingConfigurations":398},{"removed":"automationbench","score":0.3894930408972697,"rank":63,"remainingConfigurations":398},{"removed":"critpt","score":0.39076373144994747,"rank":64,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3903419640013334,"rank":64,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3914523108656555,"rank":62,"remainingConfigurations":398},{"removed":"gdpval","score":0.3902367403822899,"rank":64,"remainingConfigurations":398},{"removed":"gmmlu","score":0.39043702666275726,"rank":64,"remainingConfigurations":398},{"removed":"gpqa","score":0.37809380089920236,"rank":67,"remainingConfigurations":398},{"removed":"harvey","score":0.38282971047804204,"rank":65,"remainingConfigurations":398},{"removed":"hle","score":0.39525881619109576,"rank":62,"remainingConfigurations":398},{"removed":"ifbench","score":0.38912314608868726,"rank":62,"remainingConfigurations":398},{"removed":"itbench","score":0.3898394674367407,"rank":64,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3906421324479867,"rank":63,"remainingConfigurations":398},{"removed":"math500","score":0.39040194398795053,"rank":64,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.4018389111827501,"rank":60,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.40019670522587497,"rank":63,"remainingConfigurations":398},{"removed":"omniscience","score":0.39063275280898185,"rank":65,"remainingConfigurations":398},{"removed":"scicode","score":0.39072559907736365,"rank":63,"remainingConfigurations":398},{"removed":"tau-bench","score":0.38862356371807744,"rank":63,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.39310282112351697,"rank":65,"remainingConfigurations":398},{"removed":"arc-agi","score":0.40492739131685,"rank":65,"remainingConfigurations":398},{"removed":"deepswe","score":0.27280401270734267,"rank":87,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3904115272129561,"rank":64,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3890615749869215,"rank":64,"remainingConfigurations":398},{"removed":"frontiercode","score":0.40997970804811074,"rank":61,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3911101857365631,"rank":63,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.38803424624911886,"rank":64,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3901502009768325,"rank":64,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3897709208671471,"rank":63,"remainingConfigurations":398},{"removed":"livebench-math","score":0.39087992683444583,"rank":64,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3894994163656195,"rank":64,"remainingConfigurations":398},{"removed":"livebench-language","score":0.39152778990539283,"rank":64,"remainingConfigurations":398},{"removed":"livebench-data","score":0.39228757444722223,"rank":64,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3873806254321844,"rank":63,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.38920083073179096,"rank":64,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.39142132614024305,"rank":63,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3855455447711409,"rank":64,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.4057161152869087,"rank":55,"remainingConfigurations":398},{"removed":"frontiermath","score":0.39257962839388677,"rank":64,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3928810803158695,"rank":63,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3789855325388149,"rank":67,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3945667700179904,"rank":62,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.37900275139048095,"rank":66,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.39291788039389236,"rank":62,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3972900154401804,"rank":61,"remainingConfigurations":398}]},"gpt-5.4--effort-xhigh":{"score":0.38312804209091134,"rank":65,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.41176365569882095,"rank":52,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.37963123303838797,"rank":72,"remainingConfigurations":398},{"removed":"Datacurve","score":0.37123251729953183,"rank":59,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.38295493746047987,"rank":65,"remainingConfigurations":398},{"removed":"Scale","score":0.40442357563898385,"rank":63,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.384468391667925,"rank":67,"remainingConfigurations":398},{"removed":"Cognition","score":0.3944587452658444,"rank":64,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3656631627858498,"rank":69,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.37817803554233526,"rank":65,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.38550233782107046,"rank":67,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3918981524768501,"rank":58,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.38312978026589367,"rank":65,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3864368646941414,"rank":65,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3831026228552967,"rank":65,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.38312804209091134,"rank":65,"remainingConfigurations":398},{"removed":"All provider reports","score":0.38642154125077655,"rank":65,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3831460065923166,"rank":65,"remainingConfigurations":398},{"removed":"briefcase","score":0.3845172450295979,"rank":64,"remainingConfigurations":398},{"removed":"aime","score":0.38224412476423436,"rank":65,"remainingConfigurations":398},{"removed":"apex-agents","score":0.38119449076777895,"rank":66,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.38151454484190644,"rank":66,"remainingConfigurations":398},{"removed":"automationbench","score":0.3840992960811016,"rank":65,"remainingConfigurations":398},{"removed":"critpt","score":0.3826294243652713,"rank":65,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3836354631164944,"rank":65,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.38429063337443253,"rank":65,"remainingConfigurations":398},{"removed":"gdpval","score":0.38426190086196305,"rank":65,"remainingConfigurations":398},{"removed":"gmmlu","score":0.38311295102355913,"rank":65,"remainingConfigurations":398},{"removed":"gpqa","score":0.3801741456955912,"rank":66,"remainingConfigurations":398},{"removed":"harvey","score":0.39066796334079773,"rank":63,"remainingConfigurations":398},{"removed":"hle","score":0.3848682900515148,"rank":66,"remainingConfigurations":398},{"removed":"ifbench","score":0.38218938093819893,"rank":65,"remainingConfigurations":398},{"removed":"itbench","score":0.38430038079246104,"rank":65,"remainingConfigurations":398},{"removed":"livecodebench","score":0.38278513605441516,"rank":65,"remainingConfigurations":398},{"removed":"math500","score":0.383062183106278,"rank":65,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3843288959995732,"rank":67,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.40174824954735566,"rank":62,"remainingConfigurations":398},{"removed":"omniscience","score":0.3833380539650597,"rank":66,"remainingConfigurations":398},{"removed":"scicode","score":0.3836410693849579,"rank":65,"remainingConfigurations":398},{"removed":"tau-bench","score":0.38248735889999724,"rank":65,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.42024720021275086,"rank":53,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3783966926867354,"rank":72,"remainingConfigurations":398},{"removed":"deepswe","score":0.37100410862076005,"rank":59,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3820001009459144,"rank":66,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3822801720317901,"rank":65,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3944587452658444,"rank":64,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.38445036180178027,"rank":65,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.38511906152793296,"rank":65,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.38378785449332936,"rank":65,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3796299923119337,"rank":66,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3851398232233261,"rank":65,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3850824461840016,"rank":65,"remainingConfigurations":398},{"removed":"livebench-language","score":0.38309196970194664,"rank":66,"remainingConfigurations":398},{"removed":"livebench-data","score":0.37933667542169763,"rank":67,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3812148304531624,"rank":66,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.382523491603745,"rank":65,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3855110522905043,"rank":65,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.37817803554233526,"rank":65,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3789009053302385,"rank":65,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3841843932525432,"rank":66,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3874587355810541,"rank":66,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.38086489418681063,"rank":65,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3812033052514681,"rank":66,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.38127310615886234,"rank":65,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3817879905859031,"rank":66,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3813633732646802,"rank":65,"remainingConfigurations":398}]},"claude-opus-4-7--effort-xhigh":{"score":0.38240451476925225,"rank":66,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3829493294134286,"rank":59,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3834320580531141,"rank":70,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3545954140895095,"rank":65,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3826822680915137,"rank":66,"remainingConfigurations":398},{"removed":"Scale","score":0.3927895150150196,"rank":66,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.37871011737136734,"rank":69,"remainingConfigurations":398},{"removed":"Cognition","score":0.46107471744017503,"rank":47,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3624682915047454,"rank":72,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3766755695135034,"rank":66,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3916209143808711,"rank":64,"remainingConfigurations":381},{"removed":"Vals AI","score":0.37146672516811224,"rank":67,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.38215396499837384,"rank":66,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.38233227479283,"rank":66,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.38189738553300584,"rank":66,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.38240451476925225,"rank":66,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3815587078858937,"rank":66,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.38239793612852896,"rank":66,"remainingConfigurations":398},{"removed":"briefcase","score":0.3821025567256208,"rank":66,"remainingConfigurations":398},{"removed":"aime","score":0.3833827857204895,"rank":64,"remainingConfigurations":398},{"removed":"apex-agents","score":0.38278412572224113,"rank":65,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.382419141253143,"rank":65,"remainingConfigurations":398},{"removed":"automationbench","score":0.38245395450829345,"rank":66,"remainingConfigurations":398},{"removed":"critpt","score":0.382599291018985,"rank":66,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.38221617174985795,"rank":66,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3834541005531349,"rank":66,"remainingConfigurations":398},{"removed":"gdpval","score":0.38235317842860717,"rank":66,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3824687575586494,"rank":66,"remainingConfigurations":398},{"removed":"gpqa","score":0.38429044001258905,"rank":65,"remainingConfigurations":398},{"removed":"harvey","score":0.38037193774076844,"rank":67,"remainingConfigurations":398},{"removed":"hle","score":0.38807331077640367,"rank":64,"remainingConfigurations":398},{"removed":"ifbench","score":0.3806206362217283,"rank":66,"remainingConfigurations":398},{"removed":"itbench","score":0.3821326168506822,"rank":66,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3826258093336652,"rank":66,"remainingConfigurations":398},{"removed":"math500","score":0.38242025279621145,"rank":66,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3865068286175754,"rank":66,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3929465966075034,"rank":66,"remainingConfigurations":398},{"removed":"omniscience","score":0.3826070669475797,"rank":67,"remainingConfigurations":398},{"removed":"scicode","score":0.38288852796816153,"rank":66,"remainingConfigurations":398},{"removed":"tau-bench","score":0.38112058643265606,"rank":66,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3799830427375279,"rank":69,"remainingConfigurations":398},{"removed":"arc-agi","score":0.38145073147556197,"rank":71,"remainingConfigurations":398},{"removed":"deepswe","score":0.3547886462155348,"rank":65,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3824887583518171,"rank":65,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3813553525177769,"rank":66,"remainingConfigurations":398},{"removed":"frontiercode","score":0.46107471744017503,"rank":47,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3831341952462932,"rank":66,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.37991963888698566,"rank":66,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.38211328160906083,"rank":66,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.38099515851368304,"rank":65,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3752899663466933,"rank":67,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3686974550742302,"rank":69,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3972089182081778,"rank":61,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3816908938912224,"rank":66,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3870019055600024,"rank":64,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.37738353519305706,"rank":67,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3897156381837798,"rank":64,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3766755695135034,"rank":66,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3884994072443864,"rank":61,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3852710144896006,"rank":65,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3713951991526634,"rank":70,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3808155738809867,"rank":66,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.38248618040642923,"rank":65,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3818043869798751,"rank":64,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3822134332477587,"rank":65,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3808415892437087,"rank":66,"remainingConfigurations":398}]},"claude-sonnet-5--effort-max":{"score":0.38026735724676114,"rank":67,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3727993176326357,"rank":61,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.39462623583318535,"rank":68,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3419194653059054,"rank":69,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3801177850940318,"rank":67,"remainingConfigurations":398},{"removed":"Scale","score":0.39404790421779107,"rank":65,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.41367464669521636,"rank":55,"remainingConfigurations":398},{"removed":"Cognition","score":0.3650042905685891,"rank":75,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3904711432394587,"rank":65,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3762570625486114,"rank":67,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.43473704411324504,"rank":52,"remainingConfigurations":381},{"removed":"Vals AI","score":0.33006659982783804,"rank":76,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3801141560584746,"rank":67,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3791499997558055,"rank":67,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3801717350796563,"rank":67,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.38026735724676114,"rank":67,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3788921257282281,"rank":67,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3779725717343351,"rank":67,"remainingConfigurations":398},{"removed":"briefcase","score":0.3795011178216556,"rank":67,"remainingConfigurations":398},{"removed":"aime","score":0.381901123761228,"rank":66,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3810444566073301,"rank":67,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3782159149190014,"rank":67,"remainingConfigurations":398},{"removed":"automationbench","score":0.3806684578187454,"rank":67,"remainingConfigurations":398},{"removed":"critpt","score":0.3812944886289296,"rank":67,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.37952098246266003,"rank":67,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3826759086618628,"rank":67,"remainingConfigurations":398},{"removed":"gdpval","score":0.3800137354241045,"rank":67,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3804171756366945,"rank":67,"remainingConfigurations":398},{"removed":"gpqa","score":0.3915694091408877,"rank":62,"remainingConfigurations":398},{"removed":"harvey","score":0.3818878966963646,"rank":66,"remainingConfigurations":398},{"removed":"hle","score":0.38505881703530137,"rank":65,"remainingConfigurations":398},{"removed":"ifbench","score":0.37883190384393234,"rank":67,"remainingConfigurations":398},{"removed":"itbench","score":0.379857508863964,"rank":67,"remainingConfigurations":398},{"removed":"livecodebench","score":0.380225362472237,"rank":67,"remainingConfigurations":398},{"removed":"math500","score":0.38034493774190153,"rank":67,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3897808309382351,"rank":65,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3926922051325417,"rank":67,"remainingConfigurations":398},{"removed":"omniscience","score":0.38253782827022964,"rank":68,"remainingConfigurations":398},{"removed":"scicode","score":0.380805728894224,"rank":67,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3785917287609761,"rank":67,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.4125917296466028,"rank":57,"remainingConfigurations":398},{"removed":"arc-agi","score":0.39333312604078086,"rank":68,"remainingConfigurations":398},{"removed":"deepswe","score":0.3423986284207929,"rank":69,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.38032277742631654,"rank":67,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3789888681201372,"rank":67,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3650042905685891,"rank":75,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3813050527321146,"rank":67,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3777684843033759,"rank":67,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.38001828402604726,"rank":67,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.37926206599773327,"rank":67,"remainingConfigurations":398},{"removed":"livebench-math","score":0.38011683221258147,"rank":66,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3779488358921277,"rank":66,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3820808365738038,"rank":67,"remainingConfigurations":398},{"removed":"livebench-data","score":0.38226102298148174,"rank":65,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.37739649281742654,"rank":67,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3789501793426955,"rank":66,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3831238929968703,"rank":67,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3762570625486114,"rank":67,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.37223403938934574,"rank":66,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3699330521119415,"rank":69,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3880576394278192,"rank":65,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.38219364189759414,"rank":64,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3776283573602719,"rank":67,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.37645581663731953,"rank":67,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.377830771344642,"rank":67,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3746922541211079,"rank":67,"remainingConfigurations":398}]},"grok-4.5--effort-high":{"score":0.37280852725243996,"rank":68,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3594569890050095,"rank":63,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4144906573501457,"rank":60,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3247923418241348,"rank":73,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.37272396412211695,"rank":68,"remainingConfigurations":398},{"removed":"Scale","score":0.3858351419313308,"rank":68,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3971049568437793,"rank":63,"remainingConfigurations":398},{"removed":"Cognition","score":0.3812223968559207,"rank":67,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3799138457810438,"rank":66,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.35753120693922663,"rank":72,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.37912628964967193,"rank":69,"remainingConfigurations":381},{"removed":"Vals AI","score":0.36455929563435907,"rank":68,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3727202318356993,"rank":68,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.37213357331830554,"rank":68,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3730526491992124,"rank":68,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.37280852725243996,"rank":68,"remainingConfigurations":398},{"removed":"All provider reports","score":0.37226537761589995,"rank":68,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.37398979964242923,"rank":68,"remainingConfigurations":398},{"removed":"briefcase","score":0.37185572548419016,"rank":68,"remainingConfigurations":398},{"removed":"aime","score":0.368334919098049,"rank":68,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3736158589156286,"rank":68,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3740803697600194,"rank":68,"remainingConfigurations":398},{"removed":"automationbench","score":0.3706828917802755,"rank":68,"remainingConfigurations":398},{"removed":"critpt","score":0.37374202476211743,"rank":68,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3734084507874112,"rank":68,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.37346403438728615,"rank":69,"remainingConfigurations":398},{"removed":"gdpval","score":0.3724845446964968,"rank":68,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3730012525772857,"rank":68,"remainingConfigurations":398},{"removed":"gpqa","score":0.36685553200596716,"rank":69,"remainingConfigurations":398},{"removed":"harvey","score":0.3604263910999441,"rank":72,"remainingConfigurations":398},{"removed":"hle","score":0.37886010670961273,"rank":67,"remainingConfigurations":398},{"removed":"ifbench","score":0.3712471176905701,"rank":68,"remainingConfigurations":398},{"removed":"itbench","score":0.372468846352432,"rank":68,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3728580194075651,"rank":68,"remainingConfigurations":398},{"removed":"math500","score":0.37289253451477394,"rank":68,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.37430981106748207,"rank":69,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.38342098675460695,"rank":68,"remainingConfigurations":398},{"removed":"omniscience","score":0.3737155882311813,"rank":69,"remainingConfigurations":398},{"removed":"scicode","score":0.37328657215083955,"rank":69,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3708000669045995,"rank":68,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.40125874074691525,"rank":59,"remainingConfigurations":398},{"removed":"arc-agi","score":0.40707016320900485,"rank":64,"remainingConfigurations":398},{"removed":"deepswe","score":0.32488189230985454,"rank":73,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3728754365918611,"rank":68,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3686386704944867,"rank":69,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3812223968559207,"rank":67,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.37269861820528777,"rank":68,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.37050264173850866,"rank":68,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3725889768178064,"rank":68,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.37178418631397725,"rank":68,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3732484810742478,"rank":68,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.37138726241467657,"rank":67,"remainingConfigurations":398},{"removed":"livebench-language","score":0.37450155632212184,"rank":68,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3739086574827273,"rank":68,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3699915685234667,"rank":68,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3716230022547757,"rank":68,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.37499500036089656,"rank":68,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.35753120693922663,"rank":72,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3683889827182342,"rank":67,"remainingConfigurations":398},{"removed":"frontiermath","score":0.37808577122604675,"rank":67,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3816289765167367,"rank":68,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.37667857154994344,"rank":68,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3717987803066895,"rank":68,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.37160811877243244,"rank":68,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3767654042537875,"rank":68,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3730831052553015,"rank":68,"remainingConfigurations":398}]},"deepseek-v4-flash--effort-max":{"score":0.3708350243210516,"rank":69,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.36693776578216103,"rank":62,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3833333619458877,"rank":71,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3428926767622871,"rank":68,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.37073526622801606,"rank":69,"remainingConfigurations":398},{"removed":"Scale","score":0.3860531450455793,"rank":67,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3692390098721307,"rank":71,"remainingConfigurations":398},{"removed":"Cognition","score":0.3777595615086889,"rank":69,"remainingConfigurations":398},{"removed":"LiveBench","score":0.37743827699774113,"rank":67,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3668038551466805,"rank":68,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3870482841293708,"rank":66,"remainingConfigurations":381},{"removed":"Vals AI","score":0.36384521330701913,"rank":69,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3708212658535526,"rank":69,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.36964877093137005,"rank":70,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.37143768676482125,"rank":69,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3708350243210516,"rank":69,"remainingConfigurations":398},{"removed":"All provider reports","score":0.37021546010344103,"rank":70,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3711140350185153,"rank":69,"remainingConfigurations":398},{"removed":"briefcase","score":0.3689083828098902,"rank":69,"remainingConfigurations":398},{"removed":"aime","score":0.36657711238459595,"rank":70,"remainingConfigurations":398},{"removed":"apex-agents","score":0.37175202496005105,"rank":69,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.37152634644385074,"rank":69,"remainingConfigurations":398},{"removed":"automationbench","score":0.3680676470942263,"rank":70,"remainingConfigurations":398},{"removed":"critpt","score":0.3701894736234195,"rank":69,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.37068872770945477,"rank":69,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.37550194240962814,"rank":68,"remainingConfigurations":398},{"removed":"gdpval","score":0.3693702074343969,"rank":69,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3709966954986503,"rank":69,"remainingConfigurations":398},{"removed":"gpqa","score":0.362598315354521,"rank":70,"remainingConfigurations":398},{"removed":"harvey","score":0.36821859252822026,"rank":68,"remainingConfigurations":398},{"removed":"hle","score":0.37694278985143487,"rank":68,"remainingConfigurations":398},{"removed":"ifbench","score":0.3687969500174019,"rank":69,"remainingConfigurations":398},{"removed":"itbench","score":0.37050069479282605,"rank":69,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3709187206666848,"rank":69,"remainingConfigurations":398},{"removed":"math500","score":0.3709589704795566,"rank":69,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3755266941815689,"rank":68,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.38111585584753277,"rank":69,"remainingConfigurations":398},{"removed":"omniscience","score":0.3723522527646949,"rank":70,"remainingConfigurations":398},{"removed":"scicode","score":0.3737571574555423,"rank":68,"remainingConfigurations":398},{"removed":"tau-bench","score":0.367320606908637,"rank":70,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3695505058404698,"rank":71,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3836586951455148,"rank":69,"remainingConfigurations":398},{"removed":"deepswe","score":0.3430891051834431,"rank":68,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3709124853409733,"rank":69,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3696144363809435,"rank":68,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3777595615086889,"rank":69,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3716393952426584,"rank":70,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.36855315323283167,"rank":69,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.37054995596128365,"rank":69,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.36985725702242006,"rank":69,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3712461914650859,"rank":69,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3694933961291445,"rank":68,"remainingConfigurations":398},{"removed":"livebench-language","score":0.37260906462845816,"rank":69,"remainingConfigurations":398},{"removed":"livebench-data","score":0.37184498009262984,"rank":69,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3679567201295913,"rank":69,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3696583045875434,"rank":69,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3730109171200377,"rank":69,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3668038551466805,"rank":68,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3569724893471699,"rank":72,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3754516716863768,"rank":68,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3900581943062251,"rank":64,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.36948623880815185,"rank":70,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.37081760717872075,"rank":69,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3697668109168242,"rank":69,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3707782300151779,"rank":69,"remainingConfigurations":398},{"removed":"vibe-code","score":0.36980688115847454,"rank":69,"remainingConfigurations":398}]},"claude-opus-4-7--effort-high":{"score":0.36866718089711087,"rank":70,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3458833860206589,"rank":66,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3734019587458475,"rank":75,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3520312259679444,"rank":66,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.368894222586398,"rank":70,"remainingConfigurations":398},{"removed":"Scale","score":0.3799657073442506,"rank":70,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.36034025778940904,"rank":73,"remainingConfigurations":398},{"removed":"Cognition","score":0.41825970630351567,"rank":56,"remainingConfigurations":398},{"removed":"LiveBench","score":0.374312439883602,"rank":68,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.32975547080981954,"rank":77,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3841052013971551,"rank":68,"remainingConfigurations":381},{"removed":"Vals AI","score":0.35875108270721406,"rank":70,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3686537668356582,"rank":70,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.370935950763599,"rank":69,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3681578457452504,"rank":70,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.36866718089711087,"rank":70,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3703744173377497,"rank":69,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.36880895311238304,"rank":70,"remainingConfigurations":398},{"removed":"briefcase","score":0.36854839823354607,"rank":70,"remainingConfigurations":398},{"removed":"aime","score":0.3651348546968359,"rank":71,"remainingConfigurations":398},{"removed":"apex-agents","score":0.36954446987382744,"rank":70,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.368963887306619,"rank":70,"remainingConfigurations":398},{"removed":"automationbench","score":0.36882161796236446,"rank":69,"remainingConfigurations":398},{"removed":"critpt","score":0.36813788468319436,"rank":70,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.36856663692055586,"rank":70,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.369627060669933,"rank":70,"remainingConfigurations":398},{"removed":"gdpval","score":0.3680031312772703,"rank":70,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3689222155007974,"rank":70,"remainingConfigurations":398},{"removed":"gpqa","score":0.3683183640054561,"rank":68,"remainingConfigurations":398},{"removed":"harvey","score":0.3662656919659955,"rank":69,"remainingConfigurations":398},{"removed":"hle","score":0.37508495923249424,"rank":69,"remainingConfigurations":398},{"removed":"ifbench","score":0.3673106803056582,"rank":70,"remainingConfigurations":398},{"removed":"itbench","score":0.3683078024769834,"rank":70,"remainingConfigurations":398},{"removed":"livecodebench","score":0.368971178074802,"rank":70,"remainingConfigurations":398},{"removed":"math500","score":0.3687263922240062,"rank":70,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3734631795238695,"rank":70,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3793899718787514,"rank":70,"remainingConfigurations":398},{"removed":"omniscience","score":0.3675885044755663,"rank":71,"remainingConfigurations":398},{"removed":"scicode","score":0.3697573478099064,"rank":70,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3676477104816515,"rank":69,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.36164035095650676,"rank":73,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3744803218582364,"rank":74,"remainingConfigurations":398},{"removed":"deepswe","score":0.35198084883318703,"rank":66,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.36864535073943777,"rank":70,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3677364296265641,"rank":70,"remainingConfigurations":398},{"removed":"frontiercode","score":0.41825970630351567,"rank":56,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3722155783658528,"rank":69,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.36200722652166156,"rank":71,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.36892074357303356,"rank":70,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.367835721609392,"rank":70,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3689333293820222,"rank":70,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3662236298690691,"rank":70,"remainingConfigurations":398},{"removed":"livebench-language","score":0.37020873988756836,"rank":70,"remainingConfigurations":398},{"removed":"livebench-data","score":0.369642391747177,"rank":70,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3661826018977859,"rank":71,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3668068609878292,"rank":70,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3726634847372072,"rank":70,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.32975547080981954,"rank":77,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3655433821890211,"rank":68,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3684471206200748,"rank":70,"remainingConfigurations":398},{"removed":"simpleqa","score":0.37419753869809336,"rank":69,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3694925084022486,"rank":69,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3682217891612616,"rank":70,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.36772263367124153,"rank":70,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.36811435734671355,"rank":70,"remainingConfigurations":398},{"removed":"vibe-code","score":0.36757669254031494,"rank":70,"remainingConfigurations":398}]},"kimi-k3--effort-high":{"score":0.364230262068402,"rank":71,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3471070817427879,"rank":65,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4609963572166876,"rank":51,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3251672048597571,"rank":72,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.365787164114642,"rank":71,"remainingConfigurations":398},{"removed":"Scale","score":0.3781172996060839,"rank":71,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3629292358417681,"rank":72,"remainingConfigurations":398},{"removed":"Cognition","score":0.3806806399551568,"rank":68,"remainingConfigurations":398},{"removed":"LiveBench","score":0.36477309962296517,"rank":70,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3619478781314622,"rank":69,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3447876146082752,"rank":74,"remainingConfigurations":381},{"removed":"Vals AI","score":0.35455515615087546,"rank":71,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3642055828870001,"rank":71,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3640281119280928,"rank":71,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3640294550384911,"rank":71,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.364230262068402,"rank":71,"remainingConfigurations":398},{"removed":"All provider reports","score":0.36377700858960177,"rank":71,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3645686743870551,"rank":71,"remainingConfigurations":398},{"removed":"briefcase","score":0.3640012441517504,"rank":71,"remainingConfigurations":398},{"removed":"aime","score":0.3642253830956272,"rank":72,"remainingConfigurations":398},{"removed":"apex-agents","score":0.365216876882179,"rank":71,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.36388758673190164,"rank":71,"remainingConfigurations":398},{"removed":"automationbench","score":0.36391037778294516,"rank":71,"remainingConfigurations":398},{"removed":"critpt","score":0.36216427492152986,"rank":72,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3642419667223496,"rank":71,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.36521312862251043,"rank":71,"remainingConfigurations":398},{"removed":"gdpval","score":0.3643184804526938,"rank":71,"remainingConfigurations":398},{"removed":"gmmlu","score":0.36436744249976005,"rank":71,"remainingConfigurations":398},{"removed":"gpqa","score":0.3525637474157323,"rank":74,"remainingConfigurations":398},{"removed":"harvey","score":0.3619822962779542,"rank":71,"remainingConfigurations":398},{"removed":"hle","score":0.3708053096258424,"rank":71,"remainingConfigurations":398},{"removed":"ifbench","score":0.36243631964570716,"rank":71,"remainingConfigurations":398},{"removed":"itbench","score":0.3639860588816663,"rank":71,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3658662354463775,"rank":71,"remainingConfigurations":398},{"removed":"math500","score":0.36439307527566717,"rank":71,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.36912501290431426,"rank":71,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.37509700015517383,"rank":71,"remainingConfigurations":398},{"removed":"omniscience","score":0.3616201450977963,"rank":73,"remainingConfigurations":398},{"removed":"scicode","score":0.3657736718553461,"rank":71,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3628249914429624,"rank":71,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3634782309534226,"rank":72,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4617538788390277,"rank":51,"remainingConfigurations":398},{"removed":"deepswe","score":0.32527548786431304,"rank":72,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3642723971490509,"rank":71,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3644731344226608,"rank":71,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3806806399551568,"rank":68,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.36394726044471604,"rank":71,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.36195200438212405,"rank":72,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.36366073984138964,"rank":71,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.36318651128948726,"rank":72,"remainingConfigurations":398},{"removed":"livebench-math","score":0.36454630756264345,"rank":71,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3626767847253291,"rank":72,"remainingConfigurations":398},{"removed":"livebench-language","score":0.36608895574554773,"rank":71,"remainingConfigurations":398},{"removed":"livebench-data","score":0.364506521718968,"rank":71,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.36142800284968385,"rank":72,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.36310391303469425,"rank":72,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3672072595875693,"rank":71,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3619478781314622,"rank":69,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.36166889514139716,"rank":71,"remainingConfigurations":398},{"removed":"frontiermath","score":0.36774589265572555,"rank":71,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3702182565283793,"rank":71,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.36342260507671104,"rank":72,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.36357109660388076,"rank":71,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3634960961673302,"rank":71,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.36392810120087876,"rank":71,"remainingConfigurations":398},{"removed":"vibe-code","score":0.36294296025619016,"rank":72,"remainingConfigurations":398}]},"gemini-3.1-pro--effort-high":{"score":0.36232959944541454,"rank":72,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3351620206154422,"rank":68,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.37645822012141056,"rank":74,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3959389954951387,"rank":52,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3621132930731677,"rank":72,"remainingConfigurations":398},{"removed":"Scale","score":0.3349972292827195,"rank":80,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.38244251414144914,"rank":68,"remainingConfigurations":398},{"removed":"Cognition","score":0.36812394598181103,"rank":74,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3526443933101024,"rank":74,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.36104592466038415,"rank":70,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.33578611832491473,"rank":77,"remainingConfigurations":381},{"removed":"Vals AI","score":0.37332208609483697,"rank":66,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3623127892783616,"rank":72,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3623853819842891,"rank":72,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3623245197973344,"rank":72,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.36232959944541454,"rank":72,"remainingConfigurations":398},{"removed":"All provider reports","score":0.36241106941316836,"rank":72,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3623761892250306,"rank":72,"remainingConfigurations":398},{"removed":"briefcase","score":0.36322449979049726,"rank":72,"remainingConfigurations":398},{"removed":"aime","score":0.3677353355690664,"rank":69,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3612529696505949,"rank":72,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3615830618227727,"rank":72,"remainingConfigurations":398},{"removed":"automationbench","score":0.36312065882074673,"rank":72,"remainingConfigurations":398},{"removed":"critpt","score":0.36257674967338627,"rank":71,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3627217674792267,"rank":72,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.36285964649834707,"rank":72,"remainingConfigurations":398},{"removed":"gdpval","score":0.3624995186159668,"rank":72,"remainingConfigurations":398},{"removed":"gmmlu","score":0.36242858136936956,"rank":72,"remainingConfigurations":398},{"removed":"gpqa","score":0.36076094693287136,"rank":73,"remainingConfigurations":398},{"removed":"harvey","score":0.36470340142602975,"rank":70,"remainingConfigurations":398},{"removed":"hle","score":0.349958924349687,"rank":76,"remainingConfigurations":398},{"removed":"ifbench","score":0.3613113747953423,"rank":73,"remainingConfigurations":398},{"removed":"itbench","score":0.3632033897163715,"rank":72,"remainingConfigurations":398},{"removed":"livecodebench","score":0.36252995268892635,"rank":72,"remainingConfigurations":398},{"removed":"math500","score":0.3625020793600891,"rank":72,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.35604020146484316,"rank":73,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.34646208994569583,"rank":76,"remainingConfigurations":398},{"removed":"omniscience","score":0.3628670335804884,"rank":72,"remainingConfigurations":398},{"removed":"scicode","score":0.36201195411567294,"rank":72,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3608209164732177,"rank":72,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3830058388404503,"rank":68,"remainingConfigurations":398},{"removed":"arc-agi","score":0.37442955009357,"rank":75,"remainingConfigurations":398},{"removed":"deepswe","score":0.3958868318485565,"rank":52,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.36227416535327556,"rank":72,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.36139824162486617,"rank":72,"remainingConfigurations":398},{"removed":"frontiercode","score":0.36812394598181103,"rank":74,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.36132661070079225,"rank":72,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.36251890389677327,"rank":70,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3614821434173403,"rank":72,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3637300311495948,"rank":71,"remainingConfigurations":398},{"removed":"livebench-math","score":0.36200180408082194,"rank":72,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.36545982812872363,"rank":71,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3596187776898255,"rank":72,"remainingConfigurations":398},{"removed":"livebench-data","score":0.36097255939297845,"rank":72,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.36633755719270616,"rank":70,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3644571481914228,"rank":71,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3575047354264112,"rank":74,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.36104592466038415,"rank":70,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.36229629078693254,"rank":70,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3652089047582933,"rank":72,"remainingConfigurations":398},{"removed":"simpleqa","score":0.35594493010295564,"rank":74,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3635109626033423,"rank":71,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3633901289830361,"rank":72,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.36331486858953754,"rank":72,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.36337965244526377,"rank":72,"remainingConfigurations":398},{"removed":"vibe-code","score":0.36388271136785605,"rank":71,"remainingConfigurations":398}]},"claude-opus-4-7--effort-max":{"score":0.3578778505154514,"rank":73,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3525323036363306,"rank":64,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3709478419040253,"rank":76,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3297711182656955,"rank":71,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3576191437910892,"rank":73,"remainingConfigurations":398},{"removed":"Scale","score":0.37197569771911027,"rank":72,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.37486540922305406,"rank":70,"remainingConfigurations":398},{"removed":"Cognition","score":0.36269191581973964,"rank":76,"remainingConfigurations":398},{"removed":"LiveBench","score":0.36449269195424344,"rank":71,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.35898835723280725,"rank":71,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3920486816087789,"rank":62,"remainingConfigurations":381},{"removed":"Vals AI","score":0.31520314588151327,"rank":81,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3577813636200451,"rank":73,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3585958597983781,"rank":73,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3576282061287516,"rank":73,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3578778505154514,"rank":73,"remainingConfigurations":398},{"removed":"All provider reports","score":0.35822707854579144,"rank":73,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.35558842612687197,"rank":73,"remainingConfigurations":398},{"removed":"briefcase","score":0.35663026464827247,"rank":73,"remainingConfigurations":398},{"removed":"aime","score":0.3584936332104535,"rank":73,"remainingConfigurations":398},{"removed":"apex-agents","score":0.35868932279980564,"rank":73,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3582626347606472,"rank":73,"remainingConfigurations":398},{"removed":"automationbench","score":0.3578332186613795,"rank":73,"remainingConfigurations":398},{"removed":"critpt","score":0.35850317330294096,"rank":73,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3579142062070377,"rank":73,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3594153413861898,"rank":73,"remainingConfigurations":398},{"removed":"gdpval","score":0.35733780070532384,"rank":73,"remainingConfigurations":398},{"removed":"gmmlu","score":0.35811007104017595,"rank":73,"remainingConfigurations":398},{"removed":"gpqa","score":0.36195985145195236,"rank":71,"remainingConfigurations":398},{"removed":"harvey","score":0.3572441007135845,"rank":73,"remainingConfigurations":398},{"removed":"hle","score":0.36220565600464366,"rank":72,"remainingConfigurations":398},{"removed":"ifbench","score":0.3613629906703259,"rank":72,"remainingConfigurations":398},{"removed":"itbench","score":0.35408514727584833,"rank":74,"remainingConfigurations":398},{"removed":"livecodebench","score":0.35777203551559883,"rank":73,"remainingConfigurations":398},{"removed":"math500","score":0.3579733285054006,"rank":73,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.35444777948876555,"rank":74,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.367494793447615,"rank":72,"remainingConfigurations":398},{"removed":"omniscience","score":0.3579687179314222,"rank":74,"remainingConfigurations":398},{"removed":"scicode","score":0.358890347745068,"rank":73,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3571059404296079,"rank":73,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3776208832785059,"rank":70,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3702938887147404,"rank":77,"remainingConfigurations":398},{"removed":"deepswe","score":0.3298617776563898,"rank":71,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.35788284978666596,"rank":73,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3565942447357757,"rank":73,"remainingConfigurations":398},{"removed":"frontiercode","score":0.36269191581973964,"rank":76,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.35773468778894685,"rank":73,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3564906186437113,"rank":73,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3579500264230751,"rank":73,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3562491091987401,"rank":73,"remainingConfigurations":398},{"removed":"livebench-math","score":0.35819667339620737,"rank":73,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.356104249154487,"rank":73,"remainingConfigurations":398},{"removed":"livebench-language","score":0.35948565445416286,"rank":73,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3588401425028265,"rank":73,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.35549976400137845,"rank":73,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.356725025028293,"rank":73,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3602795209476158,"rank":72,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.35898835723280725,"rank":71,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.36483614190526154,"rank":69,"remainingConfigurations":398},{"removed":"frontiermath","score":0.34282973243711384,"rank":76,"remainingConfigurations":398},{"removed":"simpleqa","score":0.36219678594798904,"rank":72,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.35953042140734515,"rank":73,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3542603829557936,"rank":74,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3596639598214075,"rank":73,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.356247498385794,"rank":73,"remainingConfigurations":398},{"removed":"vibe-code","score":0.35950962680587223,"rank":73,"remainingConfigurations":398}]},"claude-opus-4-8--effort-low":{"score":0.35490510389127344,"rank":74,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3450147739070588,"rank":67,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.33373418946643146,"rank":85,"remainingConfigurations":398},{"removed":"Datacurve","score":0.35978642051632814,"rank":64,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.355245879823689,"rank":74,"remainingConfigurations":398},{"removed":"Scale","score":0.3679945452156291,"rank":73,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.35005334862645704,"rank":74,"remainingConfigurations":398},{"removed":"Cognition","score":0.3768125626489384,"rank":70,"remainingConfigurations":398},{"removed":"LiveBench","score":0.35747050108259515,"rank":73,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3497431478390891,"rank":74,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3694493971431421,"rank":71,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3419908286131422,"rank":72,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3549560855901192,"rank":74,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3543345455031481,"rank":74,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3549090086694849,"rank":74,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.35490510389127344,"rank":74,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3543660057918289,"rank":74,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3550759928093026,"rank":74,"remainingConfigurations":398},{"removed":"briefcase","score":0.3543975733040927,"rank":75,"remainingConfigurations":398},{"removed":"aime","score":0.34327403138922064,"rank":75,"remainingConfigurations":398},{"removed":"apex-agents","score":0.35575051781248385,"rank":74,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.35493337720703927,"rank":74,"remainingConfigurations":398},{"removed":"automationbench","score":0.35459706175088423,"rank":74,"remainingConfigurations":398},{"removed":"critpt","score":0.3544415581889097,"rank":74,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.35481540321299065,"rank":74,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3557361982624663,"rank":74,"remainingConfigurations":398},{"removed":"gdpval","score":0.3547728868399032,"rank":74,"remainingConfigurations":398},{"removed":"gmmlu","score":0.355030902234714,"rank":74,"remainingConfigurations":398},{"removed":"gpqa","score":0.3609665545883744,"rank":72,"remainingConfigurations":398},{"removed":"harvey","score":0.35283397979237135,"rank":74,"remainingConfigurations":398},{"removed":"hle","score":0.36183959255260656,"rank":73,"remainingConfigurations":398},{"removed":"ifbench","score":0.3536589738112748,"rank":74,"remainingConfigurations":398},{"removed":"itbench","score":0.354506430471147,"rank":73,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3552779522565161,"rank":74,"remainingConfigurations":398},{"removed":"math500","score":0.354957336129615,"rank":74,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3596284473067248,"rank":72,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.36550502187881956,"rank":73,"remainingConfigurations":398},{"removed":"omniscience","score":0.35403015894524925,"rank":76,"remainingConfigurations":398},{"removed":"scicode","score":0.3559432770185919,"rank":75,"remainingConfigurations":398},{"removed":"tau-bench","score":0.35358070012759574,"rank":74,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.35047789981544236,"rank":74,"remainingConfigurations":398},{"removed":"arc-agi","score":0.33518435619751236,"rank":84,"remainingConfigurations":398},{"removed":"deepswe","score":0.3599449854977233,"rank":64,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3549575725685315,"rank":74,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.35389159247882535,"rank":74,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3768125626489384,"rank":70,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.35519852133408913,"rank":74,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3526234752663022,"rank":74,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3545745538889143,"rank":74,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3531195232666791,"rank":74,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3551373009661258,"rank":74,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.35258252097137754,"rank":74,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3569867307882926,"rank":74,"remainingConfigurations":398},{"removed":"livebench-data","score":0.35571647492743685,"rank":74,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3522305335025653,"rank":74,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.35336123675131814,"rank":74,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.35829702275663067,"rank":73,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3497431478390891,"rank":74,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.35660446331814133,"rank":73,"remainingConfigurations":398},{"removed":"frontiermath","score":0.35570485849351785,"rank":73,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3602322221746192,"rank":73,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.35413823641069003,"rank":74,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.35431243424379016,"rank":73,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3539607134663487,"rank":74,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3544505153889583,"rank":74,"remainingConfigurations":398},{"removed":"vibe-code","score":0.35376114338106973,"rank":74,"remainingConfigurations":398}]},"deepseek-v4-pro-0424--effort-max":{"score":0.34866729963022186,"rank":75,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3839890672178124,"rank":69,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3142640216078288,"rank":74,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3471750224236987,"rank":75,"remainingConfigurations":398},{"removed":"Scale","score":0.3639689743212393,"rank":74,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.34941487496586227,"rank":75,"remainingConfigurations":398},{"removed":"Cognition","score":0.3550276143954676,"rank":77,"remainingConfigurations":398},{"removed":"LiveBench","score":0.35122770871911474,"rank":75,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3527353832494758,"rank":73,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3475324880316488,"rank":72,"remainingConfigurations":381},{"removed":"Vals AI","score":0.34023841167236335,"rank":74,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.34866943201583256,"rank":75,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.34823484271584876,"rank":75,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3481221335319311,"rank":75,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.34866729963022186,"rank":75,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3476636761195205,"rank":75,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3550023757882232,"rank":75,"remainingConfigurations":398},{"removed":"briefcase","score":0.35578874830460117,"rank":74,"remainingConfigurations":398},{"removed":"aime","score":0.3484527138163516,"rank":74,"remainingConfigurations":398},{"removed":"apex-agents","score":0.35565765946208927,"rank":75,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.34495774988671823,"rank":75,"remainingConfigurations":398},{"removed":"automationbench","score":0.33653042968327346,"rank":76,"remainingConfigurations":398},{"removed":"critpt","score":0.34956672018681334,"rank":75,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3519274512279174,"rank":75,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.35217288529581614,"rank":75,"remainingConfigurations":398},{"removed":"gdpval","score":0.3502672445207173,"rank":75,"remainingConfigurations":398},{"removed":"gmmlu","score":0.34915111316279207,"rank":75,"remainingConfigurations":398},{"removed":"gpqa","score":0.34503009678471613,"rank":75,"remainingConfigurations":398},{"removed":"harvey","score":0.34441382412541954,"rank":75,"remainingConfigurations":398},{"removed":"hle","score":0.3542957411210375,"rank":74,"remainingConfigurations":398},{"removed":"ifbench","score":0.34250167862144903,"rank":75,"remainingConfigurations":398},{"removed":"itbench","score":0.34552925938388346,"rank":75,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3473882770520101,"rank":75,"remainingConfigurations":398},{"removed":"math500","score":0.34852083056885524,"rank":75,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3526720201768667,"rank":75,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.35845567559412234,"rank":75,"remainingConfigurations":398},{"removed":"omniscience","score":0.35405509651989897,"rank":75,"remainingConfigurations":398},{"removed":"scicode","score":0.3507691948708936,"rank":76,"remainingConfigurations":398},{"removed":"tau-bench","score":0.34611466125372514,"rank":75,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.34746725463214095,"rank":75,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3832932643643321,"rank":70,"remainingConfigurations":398},{"removed":"deepswe","score":0.31445870043838897,"rank":74,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.348722018393173,"rank":75,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.34686305768294456,"rank":75,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3550276143954676,"rank":77,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.34870257019852297,"rank":75,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3466067355803264,"rank":75,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3481942835222543,"rank":75,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3476476739766993,"rank":75,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3489568867411769,"rank":75,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3474409018531191,"rank":75,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3508621140913224,"rank":75,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3489834069723608,"rank":75,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.34574754716480305,"rank":75,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3475412510432782,"rank":75,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3510841480487646,"rank":75,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3527353832494758,"rank":73,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.34044128686145897,"rank":75,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3504724535259884,"rank":74,"remainingConfigurations":398},{"removed":"simpleqa","score":0.355655027149922,"rank":75,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.34780269348579046,"rank":75,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3480950324734626,"rank":75,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.34785965098057287,"rank":75,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3485194719762034,"rank":75,"remainingConfigurations":398},{"removed":"vibe-code","score":0.34739228306337794,"rank":75,"remainingConfigurations":398}]},"qwen3.8-27b--effort-xhigh":{"score":0.3417091383203576,"rank":76,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.37902395137588374,"rank":73,"remainingConfigurations":398},{"removed":"Datacurve","score":0.31148329100468425,"rank":75,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.34013991711322705,"rank":76,"remainingConfigurations":398},{"removed":"Scale","score":0.3578465480032733,"rank":75,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3439437421846494,"rank":76,"remainingConfigurations":398},{"removed":"Cognition","score":0.3505545450195972,"rank":78,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3464747085917122,"rank":76,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3461881449964848,"rank":75,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.34208186848209876,"rank":75,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3365562224889999,"rank":75,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3417391945340911,"rank":76,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3413426102135609,"rank":76,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3413258042697905,"rank":76,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3417091383203576,"rank":76,"remainingConfigurations":398},{"removed":"All provider reports","score":0.34096128831338834,"rank":76,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3436061913917234,"rank":76,"remainingConfigurations":398},{"removed":"briefcase","score":0.33164029998322925,"rank":79,"remainingConfigurations":398},{"removed":"aime","score":0.3387732726457398,"rank":76,"remainingConfigurations":398},{"removed":"apex-agents","score":0.34521143816951794,"rank":76,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.32152850339948397,"rank":80,"remainingConfigurations":398},{"removed":"automationbench","score":0.3386576254224451,"rank":75,"remainingConfigurations":398},{"removed":"critpt","score":0.3466193483162607,"rank":76,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3148495318257116,"rank":81,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.34098162004219845,"rank":76,"remainingConfigurations":398},{"removed":"gdpval","score":0.33812716399707754,"rank":77,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3413469828476116,"rank":76,"remainingConfigurations":398},{"removed":"gpqa","score":0.3345509038642049,"rank":76,"remainingConfigurations":398},{"removed":"harvey","score":0.341804354724024,"rank":77,"remainingConfigurations":398},{"removed":"hle","score":0.35022886009131377,"rank":75,"remainingConfigurations":398},{"removed":"ifbench","score":0.3333247821171485,"rank":76,"remainingConfigurations":398},{"removed":"itbench","score":0.34294543838794334,"rank":76,"remainingConfigurations":398},{"removed":"livecodebench","score":0.33741914842256193,"rank":76,"remainingConfigurations":398},{"removed":"math500","score":0.34008986194387064,"rank":76,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3424722862855682,"rank":76,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.35856046112510814,"rank":74,"remainingConfigurations":398},{"removed":"omniscience","score":0.41645406730162277,"rank":54,"remainingConfigurations":398},{"removed":"scicode","score":0.3565041477312148,"rank":74,"remainingConfigurations":398},{"removed":"tau-bench","score":0.32817747262684754,"rank":77,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.34009056619994943,"rank":76,"remainingConfigurations":398},{"removed":"arc-agi","score":0.37770410024861495,"rank":73,"remainingConfigurations":398},{"removed":"deepswe","score":0.3116610123138652,"rank":75,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.34176967427892907,"rank":76,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.33986774607119735,"rank":76,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3505545450195972,"rank":78,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3418496681002905,"rank":76,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.33957768191577414,"rank":76,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.34127830897040234,"rank":76,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.34081027586675056,"rank":76,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3420045590069251,"rank":76,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.34041620573579223,"rank":76,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3439042295631994,"rank":76,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3420819357662863,"rank":76,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3387633435110871,"rank":76,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3405430925660773,"rank":76,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3441981018923072,"rank":76,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3461881449964848,"rank":75,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.332923393784712,"rank":76,"remainingConfigurations":398},{"removed":"frontiermath","score":0.34354912400098153,"rank":75,"remainingConfigurations":398},{"removed":"simpleqa","score":0.34871169261622303,"rank":76,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3408335712617155,"rank":76,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3411438460838885,"rank":76,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.34087886481202573,"rank":76,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.34159678615097494,"rank":76,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3403883731698611,"rank":76,"remainingConfigurations":398}]},"claude-opus-4-6--effort-high":{"score":0.33226081076280295,"rank":77,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.31528111549796767,"rank":70,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3073524569121455,"rank":91,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3109434279300381,"rank":76,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.33258886520211983,"rank":77,"remainingConfigurations":398},{"removed":"Scale","score":0.34775265929872073,"rank":76,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.33119246174317546,"rank":77,"remainingConfigurations":398},{"removed":"Cognition","score":0.41370785521846604,"rank":58,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3206818767428955,"rank":80,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.30987177791620796,"rank":85,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.34640295307314867,"rank":73,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3240107604720916,"rank":77,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.33223341527215366,"rank":77,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.33306542829942093,"rank":77,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.33170837487636873,"rank":77,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.33226081076280295,"rank":77,"remainingConfigurations":398},{"removed":"All provider reports","score":0.33245713807776806,"rank":77,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3323685894011483,"rank":77,"remainingConfigurations":398},{"removed":"briefcase","score":0.3324794381362171,"rank":78,"remainingConfigurations":398},{"removed":"aime","score":0.32992272501418946,"rank":77,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3330424163941605,"rank":77,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3316936621966691,"rank":76,"remainingConfigurations":398},{"removed":"automationbench","score":0.33220486225423324,"rank":77,"remainingConfigurations":398},{"removed":"critpt","score":0.33148062732763295,"rank":77,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.332189825151226,"rank":76,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3331742615171271,"rank":77,"remainingConfigurations":398},{"removed":"gdpval","score":0.33216904777746875,"rank":78,"remainingConfigurations":398},{"removed":"gmmlu","score":0.33233193348142837,"rank":77,"remainingConfigurations":398},{"removed":"gpqa","score":0.33204172807932447,"rank":77,"remainingConfigurations":398},{"removed":"harvey","score":0.3305595001901569,"rank":78,"remainingConfigurations":398},{"removed":"hle","score":0.33851707603141806,"rank":77,"remainingConfigurations":398},{"removed":"ifbench","score":0.3305021980668443,"rank":77,"remainingConfigurations":398},{"removed":"itbench","score":0.33201114259209064,"rank":78,"remainingConfigurations":398},{"removed":"livecodebench","score":0.33263370770040107,"rank":77,"remainingConfigurations":398},{"removed":"math500","score":0.3323599913312704,"rank":77,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3368647067257235,"rank":77,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.343151823449533,"rank":77,"remainingConfigurations":398},{"removed":"omniscience","score":0.3302526752066786,"rank":77,"remainingConfigurations":398},{"removed":"scicode","score":0.3334009463195285,"rank":77,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3324138545150674,"rank":76,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.332176885232591,"rank":77,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3067070962985275,"rank":89,"remainingConfigurations":398},{"removed":"deepswe","score":0.3109933426604839,"rank":76,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3322947063911787,"rank":77,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.33357214188821177,"rank":77,"remainingConfigurations":398},{"removed":"frontiercode","score":0.41370785521846604,"rank":58,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3340668909641063,"rank":77,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3283679403454183,"rank":77,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.33221290319980085,"rank":77,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.33130378823440826,"rank":77,"remainingConfigurations":398},{"removed":"livebench-math","score":0.33210944586116714,"rank":77,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3299142568635283,"rank":77,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3287540137771638,"rank":77,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3335068364388301,"rank":77,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.3316236153010287,"rank":77,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.32687749929403465,"rank":77,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.34308944133962016,"rank":77,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.30987177791620796,"rank":85,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.32842244461620873,"rank":77,"remainingConfigurations":398},{"removed":"frontiermath","score":0.33248571871672555,"rank":77,"remainingConfigurations":398},{"removed":"simpleqa","score":0.33765786004280135,"rank":77,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3313018846439823,"rank":77,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.33180280405502643,"rank":77,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.33162301171400405,"rank":77,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.33174541263107543,"rank":77,"remainingConfigurations":398},{"removed":"vibe-code","score":0.33089583901602504,"rank":77,"remainingConfigurations":398}]},"grok-4.5--effort-medium":{"score":0.32618923151353835,"rank":78,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3163689665851907,"rank":69,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.4241774511141057,"rank":59,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2882102807192782,"rank":80,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.32671053506109005,"rank":78,"remainingConfigurations":398},{"removed":"Scale","score":0.3407079012773,"rank":77,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3193084690550017,"rank":80,"remainingConfigurations":398},{"removed":"Cognition","score":0.3167760918327183,"rank":84,"remainingConfigurations":398},{"removed":"LiveBench","score":0.33076528455781523,"rank":77,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.32274028456321885,"rank":81,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3278702002442408,"rank":78,"remainingConfigurations":381},{"removed":"Vals AI","score":0.31557911875108985,"rank":80,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3261929316744417,"rank":78,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3256568951496931,"rank":78,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3260854067630432,"rank":78,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.32618923151353835,"rank":78,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3255279821162912,"rank":78,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.32673423029602044,"rank":78,"remainingConfigurations":398},{"removed":"briefcase","score":0.3249182098602319,"rank":80,"remainingConfigurations":398},{"removed":"aime","score":0.324869404404309,"rank":78,"remainingConfigurations":398},{"removed":"apex-agents","score":0.32718401306149697,"rank":78,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.326203845455029,"rank":77,"remainingConfigurations":398},{"removed":"automationbench","score":0.3243578651405408,"rank":78,"remainingConfigurations":398},{"removed":"critpt","score":0.32609999046505145,"rank":78,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.326218865531054,"rank":77,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3262469531871952,"rank":79,"remainingConfigurations":398},{"removed":"gdpval","score":0.32576309673973797,"rank":79,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3262348696901037,"rank":78,"remainingConfigurations":398},{"removed":"gpqa","score":0.3250470356728022,"rank":78,"remainingConfigurations":398},{"removed":"harvey","score":0.32360061177554406,"rank":79,"remainingConfigurations":398},{"removed":"hle","score":0.3342738586483858,"rank":78,"remainingConfigurations":398},{"removed":"ifbench","score":0.3245911997298038,"rank":79,"remainingConfigurations":398},{"removed":"itbench","score":0.32597762993007223,"rank":79,"remainingConfigurations":398},{"removed":"livecodebench","score":0.32664204382908696,"rank":78,"remainingConfigurations":398},{"removed":"math500","score":0.3262189695271547,"rank":78,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3310362842830207,"rank":78,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3368173764937484,"rank":78,"remainingConfigurations":398},{"removed":"omniscience","score":0.3252541708835137,"rank":78,"remainingConfigurations":398},{"removed":"scicode","score":0.3273367524953055,"rank":78,"remainingConfigurations":398},{"removed":"tau-bench","score":0.32574935710826375,"rank":79,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.31961280786284213,"rank":81,"remainingConfigurations":398},{"removed":"arc-agi","score":0.4028785594866509,"rank":66,"remainingConfigurations":398},{"removed":"deepswe","score":0.28823259120815964,"rank":80,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.32623184612451606,"rank":78,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3269974845185715,"rank":78,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3167760918327183,"rank":84,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.32581213288796984,"rank":78,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.32401348054601226,"rank":78,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3258446947638033,"rank":78,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.32527960239946535,"rank":78,"remainingConfigurations":398},{"removed":"livebench-math","score":0.32652098284829173,"rank":78,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3246746186072628,"rank":78,"remainingConfigurations":398},{"removed":"livebench-language","score":0.32801363481722123,"rank":78,"remainingConfigurations":398},{"removed":"livebench-data","score":0.32657765204642825,"rank":78,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.32341691426115954,"rank":79,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.32499839497807675,"rank":78,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3291111992388782,"rank":78,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.32274028456321885,"rank":81,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3209596046111603,"rank":78,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3267893010240246,"rank":78,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3334527339445296,"rank":78,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3261221898998492,"rank":78,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.32537674823186524,"rank":78,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3251281170965534,"rank":78,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.32627795153720757,"rank":78,"remainingConfigurations":398},{"removed":"vibe-code","score":0.325116264456053,"rank":78,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-low":{"score":0.32434955725295717,"rank":79,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.3113148614422374,"rank":71,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3506343754633574,"rank":81,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2966764239836292,"rank":78,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.32415750733215704,"rank":79,"remainingConfigurations":398},{"removed":"Scale","score":0.3392374274053376,"rank":79,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.32303745490275076,"rank":79,"remainingConfigurations":398},{"removed":"Cognition","score":0.3479125635061635,"rank":79,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3293704139828767,"rank":78,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3205703325932661,"rank":82,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3151192173301484,"rank":82,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3172339715268031,"rank":78,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.32442983015369603,"rank":79,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3244473439554559,"rank":79,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3242931698792532,"rank":79,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.32434955725295717,"rank":79,"remainingConfigurations":398},{"removed":"All provider reports","score":0.32444308699041313,"rank":79,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3248498270686779,"rank":79,"remainingConfigurations":398},{"removed":"briefcase","score":0.3241747808740929,"rank":81,"remainingConfigurations":398},{"removed":"aime","score":0.3209448429973145,"rank":80,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3256204984582208,"rank":79,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3250426464579276,"rank":78,"remainingConfigurations":398},{"removed":"automationbench","score":0.32293678485209165,"rank":79,"remainingConfigurations":398},{"removed":"critpt","score":0.32398432086374696,"rank":79,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3246233530456885,"rank":78,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3219424639052675,"rank":80,"remainingConfigurations":398},{"removed":"gdpval","score":0.32372386287105875,"rank":80,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3246828800887176,"rank":79,"remainingConfigurations":398},{"removed":"gpqa","score":0.3217153668719286,"rank":79,"remainingConfigurations":398},{"removed":"harvey","score":0.3227950146215988,"rank":80,"remainingConfigurations":398},{"removed":"hle","score":0.33133366897566496,"rank":79,"remainingConfigurations":398},{"removed":"ifbench","score":0.3266084829997379,"rank":78,"remainingConfigurations":398},{"removed":"itbench","score":0.3241838183257267,"rank":80,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3243298771019766,"rank":79,"remainingConfigurations":398},{"removed":"math500","score":0.32443245735100873,"rank":79,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.32950590130526497,"rank":79,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3340541282824468,"rank":79,"remainingConfigurations":398},{"removed":"omniscience","score":0.32278157314570544,"rank":80,"remainingConfigurations":398},{"removed":"scicode","score":0.3229490121554455,"rank":79,"remainingConfigurations":398},{"removed":"tau-bench","score":0.32610983331940496,"rank":78,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3231772705623562,"rank":79,"remainingConfigurations":398},{"removed":"arc-agi","score":0.37415775878477153,"rank":76,"remainingConfigurations":398},{"removed":"deepswe","score":0.2966980070077201,"rank":78,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.32438699275257604,"rank":79,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.30721568847366415,"rank":84,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3479125635061635,"rank":79,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.32485866810833613,"rank":79,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3219381125644785,"rank":79,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3240891807049429,"rank":79,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3232338111972078,"rank":79,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3247888028911919,"rank":79,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.32274163262287403,"rank":79,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3263229325073409,"rank":79,"remainingConfigurations":398},{"removed":"livebench-data","score":0.32455995150672806,"rank":79,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.32158866378867124,"rank":80,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.32313587125428644,"rank":79,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.32728732756859213,"rank":79,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3205703325932661,"rank":82,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.32065242460917504,"rank":79,"remainingConfigurations":398},{"removed":"frontiermath","score":0.32558680064378387,"rank":79,"remainingConfigurations":398},{"removed":"simpleqa","score":0.33091391955098054,"rank":79,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3234863040411413,"rank":79,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3236434572896005,"rank":79,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.32360700003157195,"rank":79,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.323910943271791,"rank":79,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3231102443377561,"rank":79,"remainingConfigurations":398}]},"gemini-3.1-pro--effort-reasoning":{"score":0.3237873276130345,"rank":80,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.359950838870216,"rank":78,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2918240672756686,"rank":79,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.32224833299774464,"rank":80,"remainingConfigurations":398},{"removed":"Scale","score":0.3394721518359836,"rank":78,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3252807350630188,"rank":78,"remainingConfigurations":398},{"removed":"Cognition","score":0.3319988248830406,"rank":80,"remainingConfigurations":398},{"removed":"LiveBench","score":0.32731757482334745,"rank":79,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3284447859116664,"rank":79,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3242921371629695,"rank":80,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3168742810730316,"rank":79,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3237954958838073,"rank":80,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.32340817953050377,"rank":80,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3232690586368347,"rank":80,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3237873276130345,"rank":80,"remainingConfigurations":398},{"removed":"All provider reports","score":0.32287071497472014,"rank":80,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3164942394944066,"rank":82,"remainingConfigurations":398},{"removed":"briefcase","score":0.3494090522704016,"rank":76,"remainingConfigurations":398},{"removed":"aime","score":0.32399909355857676,"rank":79,"remainingConfigurations":398},{"removed":"apex-agents","score":0.31720597173294246,"rank":81,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.31774907028994637,"rank":81,"remainingConfigurations":398},{"removed":"automationbench","score":0.3228458364667233,"rank":80,"remainingConfigurations":398},{"removed":"critpt","score":0.32133506078064433,"rank":80,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.32032904403618145,"rank":79,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.31855296465803484,"rank":82,"remainingConfigurations":398},{"removed":"gdpval","score":0.3410466551186179,"rank":76,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3212229698046985,"rank":80,"remainingConfigurations":398},{"removed":"gpqa","score":0.312210087717131,"rank":81,"remainingConfigurations":398},{"removed":"harvey","score":0.3439308183556233,"rank":76,"remainingConfigurations":398},{"removed":"hle","score":0.3245783219726015,"rank":80,"remainingConfigurations":398},{"removed":"ifbench","score":0.31692372024217036,"rank":81,"remainingConfigurations":398},{"removed":"itbench","score":0.339717494674924,"rank":77,"remainingConfigurations":398},{"removed":"livecodebench","score":0.32279196324151366,"rank":80,"remainingConfigurations":398},{"removed":"math500","score":0.3241124542046799,"rank":80,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.32808835591250785,"rank":80,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.32867173155423096,"rank":80,"remainingConfigurations":398},{"removed":"omniscience","score":0.32102649343042217,"rank":81,"remainingConfigurations":398},{"removed":"scicode","score":0.3128102848891011,"rank":84,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3232828461937136,"rank":81,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3234509861081727,"rank":78,"remainingConfigurations":398},{"removed":"arc-agi","score":0.358725544575863,"rank":79,"remainingConfigurations":398},{"removed":"deepswe","score":0.29200840215479623,"rank":79,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3238421942614818,"rank":80,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.32204867197679826,"rank":79,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3319988248830406,"rank":80,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3237597839000775,"rank":80,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3217821755689288,"rank":80,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.32334480708055574,"rank":80,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3228198351895137,"rank":80,"remainingConfigurations":398},{"removed":"livebench-math","score":0.32408127047832097,"rank":80,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3225707598608291,"rank":80,"remainingConfigurations":398},{"removed":"livebench-language","score":0.32594460230520567,"rank":80,"remainingConfigurations":398},{"removed":"livebench-data","score":0.32409249093766745,"rank":80,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.32090658404272987,"rank":81,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3226711294140992,"rank":80,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.32619775148624297,"rank":80,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3284447859116664,"rank":79,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3155409326369399,"rank":81,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3255535316656491,"rank":80,"remainingConfigurations":398},{"removed":"simpleqa","score":0.33080908427665473,"rank":80,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3229193281299765,"rank":80,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.32321461177512667,"rank":80,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.32300309181019005,"rank":80,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.323628970771141,"rank":80,"remainingConfigurations":398},{"removed":"vibe-code","score":0.32253330993297075,"rank":80,"remainingConfigurations":398}]},"gemini-3.5-flash--effort-medium":{"score":0.3160782905658032,"rank":81,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3579849594364459,"rank":80,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2864592754786146,"rank":81,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3143626769177364,"rank":82,"remainingConfigurations":398},{"removed":"Scale","score":0.33348953552310606,"rank":82,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3176333650339791,"rank":81,"remainingConfigurations":398},{"removed":"Cognition","score":0.32588225675887594,"rank":81,"remainingConfigurations":398},{"removed":"LiveBench","score":0.31964570414366195,"rank":82,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.32336758541964244,"rank":80,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.31607458735420707,"rank":81,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3106914586522755,"rank":82,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.31608769320631713,"rank":81,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.31582382926264757,"rank":81,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3156361839593536,"rank":81,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3160782905658032,"rank":81,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3153633963497729,"rank":81,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3166380106470085,"rank":81,"remainingConfigurations":398},{"removed":"briefcase","score":0.34025691740507186,"rank":77,"remainingConfigurations":398},{"removed":"aime","score":0.31559123307182935,"rank":81,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3185950183389401,"rank":80,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3234575403331542,"rank":79,"remainingConfigurations":398},{"removed":"automationbench","score":0.31560665658429005,"rank":82,"remainingConfigurations":398},{"removed":"critpt","score":0.31334951806329,"rank":82,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3163746762048206,"rank":80,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.31861484078128743,"rank":81,"remainingConfigurations":398},{"removed":"gdpval","score":0.3166984710697115,"rank":81,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3181558631362707,"rank":81,"remainingConfigurations":398},{"removed":"gpqa","score":0.3040084457506467,"rank":84,"remainingConfigurations":398},{"removed":"harvey","score":0.3140311628002827,"rank":81,"remainingConfigurations":398},{"removed":"hle","score":0.3176904795344815,"rank":83,"remainingConfigurations":398},{"removed":"ifbench","score":0.3173672975472145,"rank":80,"remainingConfigurations":398},{"removed":"itbench","score":0.31610751473004495,"rank":81,"remainingConfigurations":398},{"removed":"livecodebench","score":0.31359247599289863,"rank":82,"remainingConfigurations":398},{"removed":"math500","score":0.3148705033689306,"rank":81,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3183914069227202,"rank":82,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3140130047088981,"rank":85,"remainingConfigurations":398},{"removed":"omniscience","score":0.3045520605251128,"rank":84,"remainingConfigurations":398},{"removed":"scicode","score":0.3204357076694859,"rank":80,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3158111182068834,"rank":84,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.32315831931173716,"rank":80,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3567976561756234,"rank":81,"remainingConfigurations":398},{"removed":"deepswe","score":0.2866131483944529,"rank":81,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.31613470603646476,"rank":81,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.31423215521360065,"rank":80,"remainingConfigurations":398},{"removed":"frontiercode","score":0.32588225675887594,"rank":81,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3161429955899547,"rank":81,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3141320361479984,"rank":81,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3156474520844532,"rank":81,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.31517501951968224,"rank":81,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3163852184884366,"rank":81,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3147951268365476,"rank":81,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3181866936230594,"rank":81,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3163662725720243,"rank":81,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.31323922029023304,"rank":82,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.314940427321033,"rank":81,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.31858360458975554,"rank":81,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.32336758541964244,"rank":80,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.30749124208231776,"rank":83,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3182435330930503,"rank":81,"remainingConfigurations":398},{"removed":"simpleqa","score":0.32316186308327904,"rank":81,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3152165401723886,"rank":81,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.315491201121049,"rank":81,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.31531862597065774,"rank":81,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.31589668027266415,"rank":81,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3148417995834673,"rank":81,"remainingConfigurations":398}]},"claude-sonnet-5--effort-high":{"score":0.3145273975549942,"rank":82,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.30867390046094145,"rank":72,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3180465805793817,"rank":87,"remainingConfigurations":398},{"removed":"Datacurve","score":0.28509374912337715,"rank":82,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.3144080826463171,"rank":81,"remainingConfigurations":398},{"removed":"Scale","score":0.3339731168836923,"rank":81,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3132462550869149,"rank":83,"remainingConfigurations":398},{"removed":"Cognition","score":0.281242275732817,"rank":92,"remainingConfigurations":398},{"removed":"LiveBench","score":0.31973624421805236,"rank":81,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.33691827249724643,"rank":76,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.33891051426284563,"rank":76,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3052919074056855,"rank":84,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3145324748138409,"rank":82,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3144189648107449,"rank":82,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3145144488204717,"rank":82,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3145273975549942,"rank":82,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3143859030901444,"rank":82,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.3147014838446837,"rank":83,"remainingConfigurations":398},{"removed":"briefcase","score":0.31289088295251044,"rank":83,"remainingConfigurations":398},{"removed":"aime","score":0.3109218899115631,"rank":84,"remainingConfigurations":398},{"removed":"apex-agents","score":0.31563767249918867,"rank":83,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.31540979301304484,"rank":82,"remainingConfigurations":398},{"removed":"automationbench","score":0.3142837802101332,"rank":83,"remainingConfigurations":398},{"removed":"critpt","score":0.3140434084021987,"rank":81,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.31460664844190245,"rank":82,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.31764179378011964,"rank":83,"remainingConfigurations":398},{"removed":"gdpval","score":0.31351967655623486,"rank":83,"remainingConfigurations":398},{"removed":"gmmlu","score":0.31475835630005566,"rank":82,"remainingConfigurations":398},{"removed":"gpqa","score":0.31459212839340117,"rank":80,"remainingConfigurations":398},{"removed":"harvey","score":0.31250764796675007,"rank":82,"remainingConfigurations":398},{"removed":"hle","score":0.3212367976682498,"rank":81,"remainingConfigurations":398},{"removed":"ifbench","score":0.31340002648005383,"rank":82,"remainingConfigurations":398},{"removed":"itbench","score":0.31403531349560027,"rank":82,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3143772509141149,"rank":81,"remainingConfigurations":398},{"removed":"math500","score":0.31448849617048397,"rank":82,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3181852206787071,"rank":83,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.32495900395736294,"rank":81,"remainingConfigurations":398},{"removed":"omniscience","score":0.3154323789975526,"rank":82,"remainingConfigurations":398},{"removed":"scicode","score":0.3133599796565209,"rank":83,"remainingConfigurations":398},{"removed":"tau-bench","score":0.31352590643452977,"rank":85,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3136194167016807,"rank":83,"remainingConfigurations":398},{"removed":"arc-agi","score":0.32084520779147846,"rank":86,"remainingConfigurations":398},{"removed":"deepswe","score":0.28520354282679955,"rank":82,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3145730796812258,"rank":82,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.31274347052710555,"rank":81,"remainingConfigurations":398},{"removed":"frontiercode","score":0.281242275732817,"rank":92,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3146774484163625,"rank":82,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3132655268630648,"rank":82,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.31529881722969755,"rank":82,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.31134790661340034,"rank":83,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3147143907769863,"rank":82,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.31235120122865934,"rank":83,"remainingConfigurations":398},{"removed":"livebench-language","score":0.31642866998174835,"rank":82,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3153639392516904,"rank":82,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.31208750872470564,"rank":83,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3130238949812625,"rank":82,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3177287259513926,"rank":82,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.33691827249724643,"rank":76,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.318198839555859,"rank":80,"remainingConfigurations":398},{"removed":"frontiermath","score":0.31325637020245306,"rank":84,"remainingConfigurations":398},{"removed":"simpleqa","score":0.31917106063088624,"rank":83,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.31414162497430376,"rank":82,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3136963454875828,"rank":82,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.31380470021109585,"rank":82,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3141166778686979,"rank":82,"remainingConfigurations":398},{"removed":"vibe-code","score":0.31367137678796037,"rank":82,"remainingConfigurations":398}]},"qwen3.7-max--effort-reasoning":{"score":0.31394630742662916,"rank":83,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.34900269171390774,"rank":82,"remainingConfigurations":398},{"removed":"Datacurve","score":0.28143402927822,"rank":83,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.31242690212923496,"rank":83,"remainingConfigurations":398},{"removed":"Scale","score":0.33004341729493963,"rank":83,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3148959557802636,"rank":82,"remainingConfigurations":398},{"removed":"Cognition","score":0.3213221167950834,"rank":83,"remainingConfigurations":398},{"removed":"LiveBench","score":0.31757725568752104,"rank":83,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.318697503054222,"rank":83,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.313939572956586,"rank":83,"remainingConfigurations":381},{"removed":"Vals AI","score":0.30651607088057825,"rank":83,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.3139547591575044,"rank":83,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3135930845277665,"rank":83,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.31343466625406163,"rank":83,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.31394630742662916,"rank":83,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3130624348681103,"rank":83,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.31714828399193845,"rank":80,"remainingConfigurations":398},{"removed":"briefcase","score":0.31798614027868816,"rank":82,"remainingConfigurations":398},{"removed":"aime","score":0.31399507430190515,"rank":82,"remainingConfigurations":398},{"removed":"apex-agents","score":0.31665918051088565,"rank":82,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3100099451503302,"rank":83,"remainingConfigurations":398},{"removed":"automationbench","score":0.3177080377707735,"rank":81,"remainingConfigurations":398},{"removed":"critpt","score":0.31246829747518184,"rank":83,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3010433326558179,"rank":86,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3284808564390718,"rank":78,"remainingConfigurations":398},{"removed":"gdpval","score":0.31439832856890715,"rank":82,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3144924952792139,"rank":83,"remainingConfigurations":398},{"removed":"gpqa","score":0.30426909052190587,"rank":83,"remainingConfigurations":398},{"removed":"harvey","score":0.31235844571167604,"rank":83,"remainingConfigurations":398},{"removed":"hle","score":0.3172979498644746,"rank":84,"remainingConfigurations":398},{"removed":"ifbench","score":0.3043286905236477,"rank":84,"remainingConfigurations":398},{"removed":"itbench","score":0.30122018889682795,"rank":86,"remainingConfigurations":398},{"removed":"livecodebench","score":0.31287938705698587,"rank":83,"remainingConfigurations":398},{"removed":"math500","score":0.31414740636630945,"rank":83,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.31812879329679106,"rank":84,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3241626128131629,"rank":82,"remainingConfigurations":398},{"removed":"omniscience","score":0.32450494728174073,"rank":79,"remainingConfigurations":398},{"removed":"scicode","score":0.3186792125584536,"rank":81,"remainingConfigurations":398},{"removed":"tau-bench","score":0.32226088058909286,"rank":82,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.31438776177414657,"rank":82,"remainingConfigurations":398},{"removed":"arc-agi","score":0.34793344584149916,"rank":82,"remainingConfigurations":398},{"removed":"deepswe","score":0.28161019156556216,"rank":83,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3140041972329958,"rank":83,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.31222822487666124,"rank":82,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3213221167950834,"rank":83,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3140809372782649,"rank":83,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3119601486608585,"rank":83,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.31351884943468117,"rank":83,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.31291621852235024,"rank":82,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3142384035343434,"rank":83,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3127076118910946,"rank":82,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3160915200223407,"rank":83,"remainingConfigurations":398},{"removed":"livebench-data","score":0.31427769254873034,"rank":83,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.31107533611853555,"rank":84,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.31282487835925643,"rank":84,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.31636565892943547,"rank":83,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.318697503054222,"rank":83,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3056947878606339,"rank":85,"remainingConfigurations":398},{"removed":"frontiermath","score":0.31569077071929513,"rank":82,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3207629039045376,"rank":82,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.31308537132978953,"rank":83,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.313379089781809,"rank":83,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.31316767899366943,"rank":83,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.313795263953085,"rank":83,"remainingConfigurations":398},{"removed":"vibe-code","score":0.31269547377866197,"rank":83,"remainingConfigurations":398}]},"gpt-5.2--effort-xhigh":{"score":0.31173074518937355,"rank":84,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2814778508152553,"rank":75,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3666184585118777,"rank":77,"remainingConfigurations":398},{"removed":"Datacurve","score":0.27809037787675067,"rank":85,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.31199576245893373,"rank":84,"remainingConfigurations":398},{"removed":"Scale","score":0.3277088619547308,"rank":84,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.31137647044690225,"rank":84,"remainingConfigurations":398},{"removed":"Cognition","score":0.32450690256925385,"rank":82,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3085327136879397,"rank":84,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.30528451436125276,"rank":86,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.31270932129453693,"rank":84,"remainingConfigurations":381},{"removed":"Vals AI","score":0.3034847526302087,"rank":85,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.31173518315660703,"rank":84,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3113537815843535,"rank":84,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3114429746655936,"rank":84,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.31173074518937355,"rank":84,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3110452558079943,"rank":85,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.31214240009336885,"rank":84,"remainingConfigurations":398},{"removed":"briefcase","score":0.3126100537157408,"rank":84,"remainingConfigurations":398},{"removed":"aime","score":0.31112767126967317,"rank":83,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3133300824838594,"rank":84,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.3063270648029857,"rank":85,"remainingConfigurations":398},{"removed":"automationbench","score":0.3120430997601164,"rank":84,"remainingConfigurations":398},{"removed":"critpt","score":0.3101969851140592,"rank":84,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.31207929753247415,"rank":83,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.31301637132548193,"rank":84,"remainingConfigurations":398},{"removed":"gdpval","score":0.3124786842883169,"rank":84,"remainingConfigurations":398},{"removed":"gmmlu","score":0.31167504547780395,"rank":84,"remainingConfigurations":398},{"removed":"gpqa","score":0.3081812290204526,"rank":82,"remainingConfigurations":398},{"removed":"harvey","score":0.3099552210254007,"rank":84,"remainingConfigurations":398},{"removed":"hle","score":0.31780048086640234,"rank":82,"remainingConfigurations":398},{"removed":"ifbench","score":0.3074234304393029,"rank":83,"remainingConfigurations":398},{"removed":"itbench","score":0.311910940421908,"rank":83,"remainingConfigurations":398},{"removed":"livecodebench","score":0.3128016185759053,"rank":84,"remainingConfigurations":398},{"removed":"math500","score":0.3116592540009287,"rank":84,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3185251302618194,"rank":81,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3226368459634666,"rank":83,"remainingConfigurations":398},{"removed":"omniscience","score":0.304858638352765,"rank":83,"remainingConfigurations":398},{"removed":"scicode","score":0.3149215591466137,"rank":82,"remainingConfigurations":398},{"removed":"tau-bench","score":0.3179076141664964,"rank":83,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.3121069770874903,"rank":85,"remainingConfigurations":398},{"removed":"arc-agi","score":0.365046336035705,"rank":78,"remainingConfigurations":398},{"removed":"deepswe","score":0.278204226851921,"rank":85,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.31177589953627377,"rank":84,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.31203185195002786,"rank":83,"remainingConfigurations":398},{"removed":"frontiercode","score":0.32450690256925385,"rank":82,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.311682350241742,"rank":84,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.3096420969548146,"rank":84,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.3112716142042046,"rank":84,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3108107295549958,"rank":84,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3120046098780077,"rank":84,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3103706954792081,"rank":84,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3134426270232085,"rank":84,"remainingConfigurations":398},{"removed":"livebench-data","score":0.31202964640828185,"rank":84,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.30904024909072847,"rank":85,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3104428725063763,"rank":85,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.31473875124766004,"rank":85,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.30528451436125276,"rank":86,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3065276290273438,"rank":84,"remainingConfigurations":398},{"removed":"frontiermath","score":0.31360612717443864,"rank":83,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3182678011894493,"rank":84,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3108919555617754,"rank":84,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3111099472351205,"rank":84,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.311079349907259,"rank":84,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.31140845527189936,"rank":84,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3104218110093859,"rank":84,"remainingConfigurations":398}]},"gemini-3-flash-preview--effort-reasoning":{"score":0.30545878840274493,"rank":85,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.34607610018406126,"rank":83,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2751642701278771,"rank":86,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.30375474177761425,"rank":85,"remainingConfigurations":398},{"removed":"Scale","score":0.3216963931958337,"rank":85,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.3069027908061645,"rank":85,"remainingConfigurations":398},{"removed":"Cognition","score":0.31500475551730084,"rank":85,"remainingConfigurations":398},{"removed":"LiveBench","score":0.3081738919021469,"rank":85,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.3113971982099432,"rank":84,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3033389027485402,"rank":85,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2990791171204847,"rank":86,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.30546538605894624,"rank":85,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.30520080651463033,"rank":86,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.30505858363453264,"rank":85,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.30545878840274493,"rank":85,"remainingConfigurations":398},{"removed":"All provider reports","score":0.30477924358181635,"rank":86,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.30614184785194115,"rank":85,"remainingConfigurations":398},{"removed":"briefcase","score":0.3056563211829974,"rank":85,"remainingConfigurations":398},{"removed":"aime","score":0.3068620457687052,"rank":85,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2987808621321428,"rank":86,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.30678083638492215,"rank":84,"remainingConfigurations":398},{"removed":"automationbench","score":0.3054127592418598,"rank":85,"remainingConfigurations":398},{"removed":"critpt","score":0.3051183282006678,"rank":85,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.3058350149828714,"rank":84,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3080769876920036,"rank":85,"remainingConfigurations":398},{"removed":"gdpval","score":0.3073949115991151,"rank":85,"remainingConfigurations":398},{"removed":"gmmlu","score":0.3016335425997511,"rank":86,"remainingConfigurations":398},{"removed":"gpqa","score":0.29942194314684173,"rank":86,"remainingConfigurations":398},{"removed":"harvey","score":0.303836949435546,"rank":85,"remainingConfigurations":398},{"removed":"hle","score":0.3116882290035085,"rank":85,"remainingConfigurations":398},{"removed":"ifbench","score":0.2982782980835012,"rank":86,"remainingConfigurations":398},{"removed":"itbench","score":0.3057430689967711,"rank":84,"remainingConfigurations":398},{"removed":"livecodebench","score":0.30498936031640306,"rank":85,"remainingConfigurations":398},{"removed":"math500","score":0.3046662846295727,"rank":85,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.31102031050080875,"rank":85,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3107839276903722,"rank":87,"remainingConfigurations":398},{"removed":"omniscience","score":0.2934373315300732,"rank":88,"remainingConfigurations":398},{"removed":"scicode","score":0.30917301652030754,"rank":85,"remainingConfigurations":398},{"removed":"tau-bench","score":0.32501794824386426,"rank":80,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.31216909983377134,"rank":84,"remainingConfigurations":398},{"removed":"arc-agi","score":0.34476879876700145,"rank":83,"remainingConfigurations":398},{"removed":"deepswe","score":0.2753233217030662,"rank":86,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.305508865556245,"rank":85,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3036886333142759,"rank":85,"remainingConfigurations":398},{"removed":"frontiercode","score":0.31500475551730084,"rank":85,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3053929462134322,"rank":85,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.30351962436029956,"rank":85,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.30502902105182944,"rank":85,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.30454646614299813,"rank":85,"remainingConfigurations":398},{"removed":"livebench-math","score":0.3057655869447914,"rank":85,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.3042254564725261,"rank":85,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3075377065726174,"rank":85,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3056925341934726,"rank":85,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.30266869214989006,"rank":86,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.30435408284793003,"rank":86,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3079194783850566,"rank":86,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.3113971982099432,"rank":84,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.29629748087564173,"rank":86,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3076671748968314,"rank":85,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3124432826623162,"rank":85,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.30459792584594836,"rank":85,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.30487193040071164,"rank":85,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.3047090366796348,"rank":85,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.30526063961655,"rank":85,"remainingConfigurations":398},{"removed":"vibe-code","score":0.30425384050326426,"rank":85,"remainingConfigurations":398}]},"claude-sonnet-5--effort-medium":{"score":0.3020807740351314,"rank":86,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.30290782524121546,"rank":73,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.29817803003457594,"rank":95,"remainingConfigurations":398},{"removed":"Datacurve","score":0.3075615207456493,"rank":77,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.301932898340955,"rank":86,"remainingConfigurations":398},{"removed":"Scale","score":0.31440856997772754,"rank":86,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2957231263885833,"rank":86,"remainingConfigurations":398},{"removed":"Cognition","score":0.241609985385033,"rank":111,"remainingConfigurations":398},{"removed":"LiveBench","score":0.30666742920499895,"rank":86,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2987218581511679,"rank":87,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3245931005130777,"rank":79,"remainingConfigurations":381},{"removed":"Vals AI","score":0.28884315481969286,"rank":88,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.30216224817069987,"rank":86,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3017630618064608,"rank":87,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.3020364891422767,"rank":86,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.3020807740351314,"rank":86,"remainingConfigurations":398},{"removed":"All provider reports","score":0.3017777016104691,"rank":87,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.30236475330257445,"rank":86,"remainingConfigurations":398},{"removed":"briefcase","score":0.30061439871422363,"rank":86,"remainingConfigurations":398},{"removed":"aime","score":0.2977981990575597,"rank":86,"remainingConfigurations":398},{"removed":"apex-agents","score":0.3032372215438925,"rank":85,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.30374693108854245,"rank":86,"remainingConfigurations":398},{"removed":"automationbench","score":0.30249577711769077,"rank":86,"remainingConfigurations":398},{"removed":"critpt","score":0.3017439724459985,"rank":86,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.30204375959578933,"rank":85,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.3034332694208012,"rank":86,"remainingConfigurations":398},{"removed":"gdpval","score":0.3014346347059063,"rank":86,"remainingConfigurations":398},{"removed":"gmmlu","score":0.30230958315785056,"rank":85,"remainingConfigurations":398},{"removed":"gpqa","score":0.30190354404057607,"rank":85,"remainingConfigurations":398},{"removed":"harvey","score":0.30028615610158904,"rank":86,"remainingConfigurations":398},{"removed":"hle","score":0.3097928236431129,"rank":86,"remainingConfigurations":398},{"removed":"ifbench","score":0.30009567144595056,"rank":85,"remainingConfigurations":398},{"removed":"itbench","score":0.3018204719608413,"rank":85,"remainingConfigurations":398},{"removed":"livecodebench","score":0.30172485459609477,"rank":86,"remainingConfigurations":398},{"removed":"math500","score":0.30191766974710466,"rank":86,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.3058216573637123,"rank":86,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3123523428089049,"rank":86,"remainingConfigurations":398},{"removed":"omniscience","score":0.3033674177014764,"rank":85,"remainingConfigurations":398},{"removed":"scicode","score":0.3008991321121656,"rank":86,"remainingConfigurations":398},{"removed":"tau-bench","score":0.30061169878304017,"rank":86,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.29628936033652575,"rank":87,"remainingConfigurations":398},{"removed":"arc-agi","score":0.30019642413717124,"rank":94,"remainingConfigurations":398},{"removed":"deepswe","score":0.3077812449737923,"rank":77,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.3021367124453905,"rank":86,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.3012197848387417,"rank":86,"remainingConfigurations":398},{"removed":"frontiercode","score":0.241609985385033,"rank":111,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.3032305453075659,"rank":86,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.29915244661507784,"rank":86,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.30198769167358325,"rank":86,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.3003478299701773,"rank":86,"remainingConfigurations":398},{"removed":"livebench-math","score":0.30218506168629133,"rank":86,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2995194808422628,"rank":86,"remainingConfigurations":398},{"removed":"livebench-language","score":0.3042219178661166,"rank":86,"remainingConfigurations":398},{"removed":"livebench-data","score":0.3028515929921339,"rank":86,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.29986023008684515,"rank":87,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.3004459230433001,"rank":87,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.30547833706659494,"rank":87,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2987218581511679,"rank":87,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.3086105661221727,"rank":82,"remainingConfigurations":398},{"removed":"frontiermath","score":0.3015712625586647,"rank":86,"remainingConfigurations":398},{"removed":"simpleqa","score":0.30719525755755184,"rank":86,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.3013610693731103,"rank":86,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.3014666050588607,"rank":86,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.30119407572420603,"rank":86,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.3016006262806026,"rank":86,"remainingConfigurations":398},{"removed":"vibe-code","score":0.3010165120465384,"rank":86,"remainingConfigurations":398}]},"claude-opus-4-5-20251101--effort-thinking-64k":{"score":0.2932907782775482,"rank":87,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.29640865797224586,"rank":74,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3091854784863184,"rank":90,"remainingConfigurations":398},{"removed":"Datacurve","score":0.26774216722337757,"rank":89,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2935244409629965,"rank":87,"remainingConfigurations":398},{"removed":"Scale","score":0.30470388619681926,"rank":88,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2956280720845667,"rank":87,"remainingConfigurations":398},{"removed":"Cognition","score":0.31414834575617484,"rank":86,"remainingConfigurations":398},{"removed":"LiveBench","score":null,"rank":null,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.28630804504576207,"rank":91,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2985787960207636,"rank":87,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2913963804314257,"rank":87,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2932190911156509,"rank":87,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.29387678852534715,"rank":88,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2911267792925788,"rank":88,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2932907782775482,"rank":87,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2916212430831658,"rank":88,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2932502953960343,"rank":87,"remainingConfigurations":398},{"removed":"briefcase","score":0.2935795234891969,"rank":88,"remainingConfigurations":398},{"removed":"aime","score":0.2916994323487245,"rank":88,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2932488639156633,"rank":87,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2931863636201851,"rank":88,"remainingConfigurations":398},{"removed":"automationbench","score":0.2932032798797719,"rank":89,"remainingConfigurations":398},{"removed":"critpt","score":0.2932803375527105,"rank":87,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.29319519836615854,"rank":87,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2939490356700593,"rank":88,"remainingConfigurations":398},{"removed":"gdpval","score":0.2933351420985282,"rank":87,"remainingConfigurations":398},{"removed":"gmmlu","score":0.29339338713619284,"rank":87,"remainingConfigurations":398},{"removed":"gpqa","score":0.2924648081606598,"rank":87,"remainingConfigurations":398},{"removed":"harvey","score":0.2919742543655884,"rank":87,"remainingConfigurations":398},{"removed":"hle","score":0.2975859769633003,"rank":87,"remainingConfigurations":398},{"removed":"ifbench","score":0.2916136458105543,"rank":87,"remainingConfigurations":398},{"removed":"itbench","score":0.2933265620261125,"rank":88,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2935677790985409,"rank":87,"remainingConfigurations":398},{"removed":"math500","score":0.2933632569548482,"rank":87,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.297204383449087,"rank":88,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.303272685241164,"rank":88,"remainingConfigurations":398},{"removed":"omniscience","score":0.29347184486990247,"rank":87,"remainingConfigurations":398},{"removed":"scicode","score":0.29330521319772496,"rank":87,"remainingConfigurations":398},{"removed":"tau-bench","score":0.29233421249390223,"rank":87,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.29827732032333587,"rank":86,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3059845075428398,"rank":90,"remainingConfigurations":398},{"removed":"deepswe","score":0.2677763856735118,"rank":89,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2934276052475275,"rank":87,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.292843924936228,"rank":87,"remainingConfigurations":398},{"removed":"frontiercode","score":0.31414834575617484,"rank":86,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2941756835298071,"rank":87,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2916779594344397,"rank":87,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2931541285402058,"rank":87,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.29280015773879703,"rank":87,"remainingConfigurations":398},{"removed":"livebench-math","score":0.27565286922262067,"rank":92,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2585644132756018,"rank":95,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2739281052702492,"rank":93,"remainingConfigurations":398},{"removed":"livebench-data","score":0.28981536807496616,"rank":88,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.32867534461482123,"rank":78,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.31284756709411377,"rank":83,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3156657456993405,"rank":84,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.28630804504576207,"rank":91,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2907730251618577,"rank":88,"remainingConfigurations":398},{"removed":"frontiermath","score":0.29440015658053437,"rank":87,"remainingConfigurations":398},{"removed":"simpleqa","score":0.292346559056207,"rank":88,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2907956777988102,"rank":88,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2938939412926664,"rank":87,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2934497972296764,"rank":87,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2931369873905461,"rank":87,"remainingConfigurations":398},{"removed":"vibe-code","score":0.29157924294589904,"rank":88,"remainingConfigurations":398}]},"glm-5.2--effort-max":{"score":0.29149981365172783,"rank":88,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.27906870154065605,"rank":77,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3147680626368009,"rank":88,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2781418017396448,"rank":84,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2911554847867141,"rank":88,"remainingConfigurations":398},{"removed":"Scale","score":0.3065682154986982,"rank":87,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2913122534914005,"rank":89,"remainingConfigurations":398},{"removed":"Cognition","score":0.2984290746755769,"rank":88,"remainingConfigurations":398},{"removed":"LiveBench","score":0.29944835475160003,"rank":87,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2890206853913205,"rank":89,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.3005041968079276,"rank":86,"remainingConfigurations":381},{"removed":"Vals AI","score":0.274283047113654,"rank":91,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.29153517673054,"rank":88,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.3110752199653872,"rank":85,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2914516628494717,"rank":87,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.29149981365172783,"rank":88,"remainingConfigurations":398},{"removed":"All provider reports","score":0.31107874747217346,"rank":84,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.29174324025604786,"rank":88,"remainingConfigurations":398},{"removed":"briefcase","score":0.2903928955461786,"rank":89,"remainingConfigurations":398},{"removed":"aime","score":0.2924621802629584,"rank":87,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2892417831080709,"rank":88,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2932829484026844,"rank":87,"remainingConfigurations":398},{"removed":"automationbench","score":0.29445955068926105,"rank":87,"remainingConfigurations":398},{"removed":"critpt","score":0.29106420945761696,"rank":88,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.29031677184924304,"rank":89,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2949000047793129,"rank":87,"remainingConfigurations":398},{"removed":"gdpval","score":0.2909970309693471,"rank":88,"remainingConfigurations":398},{"removed":"gmmlu","score":0.29176448673120475,"rank":88,"remainingConfigurations":398},{"removed":"gpqa","score":0.27886415420969873,"rank":91,"remainingConfigurations":398},{"removed":"harvey","score":0.2794960340700469,"rank":91,"remainingConfigurations":398},{"removed":"hle","score":0.29510063116664004,"rank":88,"remainingConfigurations":398},{"removed":"ifbench","score":0.29105569377561574,"rank":88,"remainingConfigurations":398},{"removed":"itbench","score":0.2885068779211056,"rank":89,"remainingConfigurations":398},{"removed":"livecodebench","score":0.29136525730862006,"rank":88,"remainingConfigurations":398},{"removed":"math500","score":0.29162217362069537,"rank":88,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2981098627919915,"rank":87,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.29997487163848363,"rank":89,"remainingConfigurations":398},{"removed":"omniscience","score":0.29667624582399094,"rank":86,"remainingConfigurations":398},{"removed":"scicode","score":0.2923813558420418,"rank":88,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2893690656571337,"rank":88,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.29512815218154076,"rank":88,"remainingConfigurations":398},{"removed":"arc-agi","score":0.31399570552423267,"rank":87,"remainingConfigurations":398},{"removed":"deepswe","score":0.2814702772189806,"rank":84,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.29141149665719607,"rank":88,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2904727948897499,"rank":88,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2984290746755769,"rank":88,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2925637323053476,"rank":88,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2894184583045799,"rank":88,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2910682843555043,"rank":88,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2905329721517715,"rank":88,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2918565076882053,"rank":87,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.28957374845770184,"rank":88,"remainingConfigurations":398},{"removed":"livebench-language","score":0.293377448802816,"rank":87,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2926199864790516,"rank":87,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2890144656627759,"rank":88,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.29025681150851784,"rank":88,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.29380769658806,"rank":89,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2890206853913205,"rank":89,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2908146003770817,"rank":87,"remainingConfigurations":398},{"removed":"frontiermath","score":0.28595425057059726,"rank":91,"remainingConfigurations":398},{"removed":"simpleqa","score":0.3028684034686084,"rank":87,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.29233730752336334,"rank":87,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.28773030594468774,"rank":88,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2917534732965231,"rank":88,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2926864150528406,"rank":88,"remainingConfigurations":398},{"removed":"vibe-code","score":0.29293424232720694,"rank":87,"remainingConfigurations":398}]},"kimi-k2.6--effort-reasoning":{"score":0.28766887287931425,"rank":89,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.31303597523486437,"rank":89,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2708834346727638,"rank":88,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2866746530573031,"rank":90,"remainingConfigurations":398},{"removed":"Scale","score":0.29521189693496,"rank":90,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2919472054240179,"rank":88,"remainingConfigurations":398},{"removed":"Cognition","score":0.2945436475613848,"rank":89,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2859959013117697,"rank":88,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.28987384673233657,"rank":88,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2830962693222611,"rank":90,"remainingConfigurations":381},{"removed":"Vals AI","score":0.285843341996392,"rank":89,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2876742867735278,"rank":89,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.28816107864606205,"rank":89,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.28735310789041857,"rank":89,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.28766887287931425,"rank":89,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2876675386147725,"rank":89,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.28793244968900034,"rank":89,"remainingConfigurations":398},{"removed":"briefcase","score":0.29385420209101404,"rank":87,"remainingConfigurations":398},{"removed":"aime","score":0.28863723874672154,"rank":89,"remainingConfigurations":398},{"removed":"apex-agents","score":0.28258043460085064,"rank":90,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2825636416074167,"rank":90,"remainingConfigurations":398},{"removed":"automationbench","score":0.29414708766396463,"rank":88,"remainingConfigurations":398},{"removed":"critpt","score":0.28793588231113026,"rank":89,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2905469067375787,"rank":88,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2878605929651146,"rank":89,"remainingConfigurations":398},{"removed":"gdpval","score":0.2898486704853313,"rank":89,"remainingConfigurations":398},{"removed":"gmmlu","score":0.28821396686238915,"rank":89,"remainingConfigurations":398},{"removed":"gpqa","score":0.28191644600556187,"rank":90,"remainingConfigurations":398},{"removed":"harvey","score":0.2852346229510077,"rank":88,"remainingConfigurations":398},{"removed":"hle","score":0.28854340904371617,"rank":90,"remainingConfigurations":398},{"removed":"ifbench","score":0.28259113814822207,"rank":90,"remainingConfigurations":398},{"removed":"itbench","score":0.29562975187989143,"rank":87,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2870902026376589,"rank":90,"remainingConfigurations":398},{"removed":"math500","score":0.2877710742542275,"rank":89,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.28940500034713235,"rank":90,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.3224102785264205,"rank":84,"remainingConfigurations":398},{"removed":"omniscience","score":0.29146494239600157,"rank":89,"remainingConfigurations":398},{"removed":"scicode","score":0.285452305877201,"rank":90,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2847234232106409,"rank":90,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2481099714494018,"rank":98,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3118166063810312,"rank":88,"remainingConfigurations":398},{"removed":"deepswe","score":0.2709623408082626,"rank":88,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2875658278894427,"rank":89,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2863899207267799,"rank":89,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2945436475613848,"rank":89,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.28767169796302555,"rank":89,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2867028731309834,"rank":89,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2873239488427455,"rank":89,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.286919167112424,"rank":89,"remainingConfigurations":398},{"removed":"livebench-math","score":0.28802538709153164,"rank":88,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.28766408787687486,"rank":89,"remainingConfigurations":398},{"removed":"livebench-language","score":0.28854532599902777,"rank":88,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2871800809750204,"rank":89,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.28634660104121407,"rank":89,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2872675476461074,"rank":90,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.28862313925265376,"rank":90,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.28987384673233657,"rank":88,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2819124768968844,"rank":90,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2894244185883815,"rank":88,"remainingConfigurations":398},{"removed":"simpleqa","score":0.291381630424806,"rank":89,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.28706389788600833,"rank":89,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2872735425372137,"rank":89,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.28714800869761736,"rank":89,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2875943137958904,"rank":89,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2869612390665576,"rank":89,"remainingConfigurations":398}]},"gpt-5.2--effort-high":{"score":0.2863072577355285,"rank":90,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2810417870561221,"rank":76,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.30712024770617774,"rank":92,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2550992417582259,"rank":90,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2881936517361567,"rank":89,"remainingConfigurations":398},{"removed":"Scale","score":0.30008646001349026,"rank":89,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2865831525390181,"rank":90,"remainingConfigurations":398},{"removed":"Cognition","score":0.3033995534273383,"rank":87,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2830252003076006,"rank":89,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.28356502807956663,"rank":92,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.286997749623386,"rank":89,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2813986956404901,"rank":90,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.28627617955309154,"rank":90,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2862810337870325,"rank":90,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.28523298747303266,"rank":90,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2863072577355285,"rank":90,"remainingConfigurations":398},{"removed":"All provider reports","score":0.28515756586073243,"rank":90,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2864549051118133,"rank":90,"remainingConfigurations":398},{"removed":"briefcase","score":0.28632102719052555,"rank":90,"remainingConfigurations":398},{"removed":"aime","score":0.28550719217254217,"rank":90,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2867625396740035,"rank":89,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2859339629755366,"rank":89,"remainingConfigurations":398},{"removed":"automationbench","score":0.28603033583671483,"rank":90,"remainingConfigurations":398},{"removed":"critpt","score":0.2860859089467756,"rank":90,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.28624505934093397,"rank":90,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.28696853145824475,"rank":90,"remainingConfigurations":398},{"removed":"gdpval","score":0.2865961624932415,"rank":90,"remainingConfigurations":398},{"removed":"gmmlu","score":0.28629806326367585,"rank":90,"remainingConfigurations":398},{"removed":"gpqa","score":0.28613058406971065,"rank":88,"remainingConfigurations":398},{"removed":"harvey","score":0.2845759023162372,"rank":89,"remainingConfigurations":398},{"removed":"hle","score":0.29232828877244016,"rank":89,"remainingConfigurations":398},{"removed":"ifbench","score":0.28425104835772175,"rank":89,"remainingConfigurations":398},{"removed":"itbench","score":0.28621630305132806,"rank":90,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2881004894155775,"rank":89,"remainingConfigurations":398},{"removed":"math500","score":0.2863998979008103,"rank":90,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.29072772792614426,"rank":89,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2967091620932013,"rank":90,"remainingConfigurations":398},{"removed":"omniscience","score":0.2844581712324085,"rank":91,"remainingConfigurations":398},{"removed":"scicode","score":0.28701873956697904,"rank":89,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2859956481844386,"rank":89,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.28855157064729275,"rank":89,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3038487333644581,"rank":92,"remainingConfigurations":398},{"removed":"deepswe","score":0.2551599203028943,"rank":90,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2863901182723644,"rank":90,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2852409288629328,"rank":90,"remainingConfigurations":398},{"removed":"frontiercode","score":0.3033995534273383,"rank":87,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2866815012852097,"rank":90,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2845199928747513,"rank":90,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.28599064210421565,"rank":90,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2854288084182285,"rank":90,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2822713289507983,"rank":89,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.28967471450250853,"rank":87,"remainingConfigurations":398},{"removed":"livebench-language","score":0.28465077800167615,"rank":89,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2744241081433139,"rank":92,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2796553500134418,"rank":90,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.28937393186646937,"rank":89,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.3044493349179291,"rank":88,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.28356502807956663,"rank":92,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2775405721970201,"rank":91,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2880428625743326,"rank":89,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2897950106537794,"rank":90,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2847273681973935,"rank":90,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.28622414623809295,"rank":90,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.28609505038499033,"rank":90,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2860012044491769,"rank":90,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2847986776234945,"rank":90,"remainingConfigurations":398}]},"gemini-3-flash-preview--effort-high":{"score":0.2795032932263614,"rank":91,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2748684515299062,"rank":78,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3276580453742723,"rank":86,"remainingConfigurations":398},{"removed":"Datacurve","score":0.24362358909734008,"rank":92,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.28021795314524195,"rank":91,"remainingConfigurations":398},{"removed":"Scale","score":0.2932400770384555,"rank":91,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.27866758589054536,"rank":91,"remainingConfigurations":398},{"removed":"Cognition","score":0.29086799861161194,"rank":90,"remainingConfigurations":398},{"removed":"LiveBench","score":0.28109122600408143,"rank":90,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2765966354307356,"rank":93,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.20359506721918427,"rank":118,"remainingConfigurations":381},{"removed":"Vals AI","score":0.34118990001308,"rank":73,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.27939139451292583,"rank":91,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2790422591858013,"rank":91,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.279356536504373,"rank":91,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2795032932263614,"rank":91,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2787682368622657,"rank":91,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.279754583793631,"rank":91,"remainingConfigurations":398},{"removed":"briefcase","score":0.2792775946106813,"rank":91,"remainingConfigurations":398},{"removed":"aime","score":0.27831656815313394,"rank":92,"remainingConfigurations":398},{"removed":"apex-agents","score":0.28011984111143107,"rank":91,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2793081579103707,"rank":91,"remainingConfigurations":398},{"removed":"automationbench","score":0.279253317565472,"rank":91,"remainingConfigurations":398},{"removed":"critpt","score":0.2791521743700429,"rank":91,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2795372048821639,"rank":91,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.28045437269620865,"rank":91,"remainingConfigurations":398},{"removed":"gdpval","score":0.279435391988973,"rank":91,"remainingConfigurations":398},{"removed":"gmmlu","score":0.2796219809193327,"rank":91,"remainingConfigurations":398},{"removed":"gpqa","score":0.28303266479950234,"rank":89,"remainingConfigurations":398},{"removed":"harvey","score":0.27996180193010917,"rank":90,"remainingConfigurations":398},{"removed":"hle","score":0.2861623986181557,"rank":91,"remainingConfigurations":398},{"removed":"ifbench","score":0.2783458902540566,"rank":91,"remainingConfigurations":398},{"removed":"itbench","score":0.2790722064893366,"rank":91,"remainingConfigurations":398},{"removed":"livecodebench","score":0.28033278853913307,"rank":91,"remainingConfigurations":398},{"removed":"math500","score":0.27962963296222065,"rank":91,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.268587572067404,"rank":95,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.28965069071720634,"rank":91,"remainingConfigurations":398},{"removed":"omniscience","score":0.27846266792367047,"rank":92,"remainingConfigurations":398},{"removed":"scicode","score":0.2804287962561678,"rank":91,"remainingConfigurations":398},{"removed":"tau-bench","score":0.27816806623820195,"rank":92,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.28199652099024775,"rank":90,"remainingConfigurations":398},{"removed":"arc-agi","score":0.32643845218842227,"rank":85,"remainingConfigurations":398},{"removed":"deepswe","score":0.24379727213039062,"rank":92,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2795608046925279,"rank":91,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2770858166112858,"rank":92,"remainingConfigurations":398},{"removed":"frontiercode","score":0.29086799861161194,"rank":90,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.27967285629576766,"rank":91,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2776718595199257,"rank":91,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2791526529991974,"rank":91,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2780025324648759,"rank":91,"remainingConfigurations":398},{"removed":"livebench-math","score":0.27992511695970407,"rank":90,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.27801112126449784,"rank":90,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2813958580362125,"rank":90,"remainingConfigurations":398},{"removed":"livebench-data","score":0.28018597244953697,"rank":90,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2767578149066532,"rank":91,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.27850368114104634,"rank":91,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.28172423657897644,"rank":91,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2765966354307356,"rank":93,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.28902698064423066,"rank":89,"remainingConfigurations":398},{"removed":"frontiermath","score":0.28792639694711003,"rank":90,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2579925643567605,"rank":97,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.28023014992643663,"rank":91,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2830761166596543,"rank":91,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.27747148015831474,"rank":91,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.281952669270452,"rank":91,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2821228695202478,"rank":91,"remainingConfigurations":398}]},"gpt-5.2--effort-medium":{"score":0.27568279262350615,"rank":92,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.26910872320733853,"rank":79,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3585895017491058,"rank":79,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2437686148298497,"rank":91,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2759382742088876,"rank":92,"remainingConfigurations":398},{"removed":"Scale","score":0.29169686176845816,"rank":92,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.27500977885061006,"rank":92,"remainingConfigurations":398},{"removed":"Cognition","score":0.2833952870728013,"rank":91,"remainingConfigurations":398},{"removed":"LiveBench","score":0.27011964354328866,"rank":93,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.21607183245153885,"rank":117,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.27499252036775323,"rank":92,"remainingConfigurations":381},{"removed":"Vals AI","score":0.267850873009289,"rank":92,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2756876698075272,"rank":92,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2755233897952545,"rank":92,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2753906250871511,"rank":92,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.27568279262350615,"rank":92,"remainingConfigurations":398},{"removed":"All provider reports","score":0.27521061223700344,"rank":92,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.27597477226091954,"rank":92,"remainingConfigurations":398},{"removed":"briefcase","score":0.27607352518597794,"rank":92,"remainingConfigurations":398},{"removed":"aime","score":0.2742834268359429,"rank":93,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2769466700367953,"rank":92,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.27538797088333405,"rank":92,"remainingConfigurations":398},{"removed":"automationbench","score":0.2753127821821616,"rank":92,"remainingConfigurations":398},{"removed":"critpt","score":0.2734253007666171,"rank":92,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.27568952865774937,"rank":92,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.27659847047593944,"rank":92,"remainingConfigurations":398},{"removed":"gdpval","score":0.2759819770298406,"rank":92,"remainingConfigurations":398},{"removed":"gmmlu","score":0.27526863681937414,"rank":92,"remainingConfigurations":398},{"removed":"gpqa","score":0.27332259248322655,"rank":92,"remainingConfigurations":398},{"removed":"harvey","score":0.27367892715507863,"rank":92,"remainingConfigurations":398},{"removed":"hle","score":0.28340514225909474,"rank":92,"remainingConfigurations":398},{"removed":"ifbench","score":0.27465657614045785,"rank":94,"remainingConfigurations":398},{"removed":"itbench","score":0.2755723985142211,"rank":92,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2755043741344639,"rank":92,"remainingConfigurations":398},{"removed":"math500","score":0.27604138276904616,"rank":92,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.28105975372722286,"rank":91,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.28838917903975997,"rank":92,"remainingConfigurations":398},{"removed":"omniscience","score":0.2681101403505752,"rank":96,"remainingConfigurations":398},{"removed":"scicode","score":0.2778161149744062,"rank":92,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2804868763332459,"rank":91,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.274109214834516,"rank":91,"remainingConfigurations":398},{"removed":"arc-agi","score":0.35761199923017145,"rank":80,"remainingConfigurations":398},{"removed":"deepswe","score":0.24386178657202415,"rank":91,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.27572212458145656,"rank":92,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.27026889712600227,"rank":93,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2833952870728013,"rank":91,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.27589324527206155,"rank":92,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2734737632658013,"rank":92,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2753209677870247,"rank":92,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2748859011687694,"rank":92,"remainingConfigurations":398},{"removed":"livebench-math","score":0.27593164693453176,"rank":91,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2743104239872461,"rank":91,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2771431971525681,"rank":91,"remainingConfigurations":398},{"removed":"livebench-data","score":0.27601222751077875,"rank":91,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.273168682765409,"rank":92,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2742829892301106,"rank":92,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.27890128878248255,"rank":92,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.21607183245153885,"rank":117,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2682382412128707,"rank":93,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2774885251583898,"rank":92,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2819617173907391,"rank":91,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2748755694707134,"rank":92,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.27508385174284644,"rank":92,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.27505556799454256,"rank":92,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.27534907170139644,"rank":92,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2744347924037691,"rank":92,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-high":{"score":0.2725304479967569,"rank":93,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.24473028795775775,"rank":80,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.33713664821361866,"rank":84,"remainingConfigurations":398},{"removed":"Datacurve","score":0.23507219323926287,"rank":94,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.27248721124241176,"rank":93,"remainingConfigurations":398},{"removed":"Scale","score":0.28685585962145727,"rank":93,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2696374508326562,"rank":93,"remainingConfigurations":398},{"removed":"Cognition","score":0.2552999497310087,"rank":102,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2780793198782872,"rank":91,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2676817385298473,"rank":96,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.28018597996232103,"rank":91,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2651550960971096,"rank":93,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2726013189655516,"rank":93,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2726406521039514,"rank":93,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2724793485036756,"rank":93,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2725304479967569,"rank":93,"remainingConfigurations":398},{"removed":"All provider reports","score":0.27262935297899854,"rank":93,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.27309321098414224,"rank":93,"remainingConfigurations":398},{"removed":"briefcase","score":0.27139193766147157,"rank":94,"remainingConfigurations":398},{"removed":"aime","score":0.2712802158919352,"rank":94,"remainingConfigurations":398},{"removed":"apex-agents","score":0.27384425236424303,"rank":93,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2724445706106788,"rank":93,"remainingConfigurations":398},{"removed":"automationbench","score":0.271556996472953,"rank":93,"remainingConfigurations":398},{"removed":"critpt","score":0.272064445712079,"rank":93,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2729076479338929,"rank":93,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.26926324556174047,"rank":94,"remainingConfigurations":398},{"removed":"gdpval","score":0.2717907615803175,"rank":93,"remainingConfigurations":398},{"removed":"gmmlu","score":0.272897348625505,"rank":93,"remainingConfigurations":398},{"removed":"gpqa","score":0.271449374645427,"rank":93,"remainingConfigurations":398},{"removed":"harvey","score":0.2712218368769378,"rank":93,"remainingConfigurations":398},{"removed":"hle","score":0.28056365994312915,"rank":93,"remainingConfigurations":398},{"removed":"ifbench","score":0.2716576040569094,"rank":95,"remainingConfigurations":398},{"removed":"itbench","score":0.27249500460907544,"rank":93,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2726186012498311,"rank":93,"remainingConfigurations":398},{"removed":"math500","score":0.2725855234902691,"rank":93,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.27660136685966125,"rank":92,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2832945572910223,"rank":93,"remainingConfigurations":398},{"removed":"omniscience","score":0.27232086101073866,"rank":93,"remainingConfigurations":398},{"removed":"scicode","score":0.27252133573070136,"rank":94,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2731657185962765,"rank":93,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.27035274298934403,"rank":92,"remainingConfigurations":398},{"removed":"arc-agi","score":0.29164388006085673,"rank":96,"remainingConfigurations":398},{"removed":"deepswe","score":0.2350272251037704,"rank":94,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2725779084347548,"rank":93,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2814738785988241,"rank":91,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2552999497310087,"rank":102,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.27272861465433446,"rank":93,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.27011493121271934,"rank":93,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2723772275577642,"rank":93,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.27166224047428505,"rank":93,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2728996509256206,"rank":93,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.27115679900813244,"rank":92,"remainingConfigurations":398},{"removed":"livebench-language","score":0.27432594851010006,"rank":92,"remainingConfigurations":398},{"removed":"livebench-data","score":0.272740783812036,"rank":93,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.269876101537229,"rank":93,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.27136946755843755,"rank":93,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.275345662399005,"rank":93,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2676817385298473,"rank":96,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.26887353862145885,"rank":92,"remainingConfigurations":398},{"removed":"frontiermath","score":0.27313805789201573,"rank":93,"remainingConfigurations":398},{"removed":"simpleqa","score":0.27888886112679684,"rank":92,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.27175035597871827,"rank":93,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2718706715896753,"rank":93,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2718354300076474,"rank":93,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.27210381134003436,"rank":93,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2713262814007085,"rank":93,"remainingConfigurations":398}]},"kimi-k2.7-code--effort-reasoning":{"score":0.2686351695641198,"rank":94,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3019341090115492,"rank":94,"remainingConfigurations":398},{"removed":"Datacurve","score":0.23835132717721683,"rank":93,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.26711675199870694,"rank":94,"remainingConfigurations":398},{"removed":"Scale","score":0.2842421904263457,"rank":94,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.269222349272192,"rank":94,"remainingConfigurations":398},{"removed":"Cognition","score":0.27530345699761744,"rank":93,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2719435257037451,"rank":92,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2729484661792552,"rank":94,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.26903676271414945,"rank":93,"remainingConfigurations":381},{"removed":"Vals AI","score":0.26182918226947943,"rank":94,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.26864643549200395,"rank":94,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2683763619564707,"rank":94,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.26820439075623076,"rank":94,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2686351695641198,"rank":94,"remainingConfigurations":398},{"removed":"All provider reports","score":0.26793025414489086,"rank":94,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.269696491317078,"rank":94,"remainingConfigurations":398},{"removed":"briefcase","score":0.2743082196956624,"rank":93,"remainingConfigurations":398},{"removed":"aime","score":0.2687810472035034,"rank":95,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2711224112047489,"rank":94,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2609385498016965,"rank":94,"remainingConfigurations":398},{"removed":"automationbench","score":0.2679497427613959,"rank":95,"remainingConfigurations":398},{"removed":"critpt","score":0.2663185896713271,"rank":95,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2673794114037554,"rank":94,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2711904488959221,"rank":93,"remainingConfigurations":398},{"removed":"gdpval","score":0.27055576117622937,"rank":94,"remainingConfigurations":398},{"removed":"gmmlu","score":0.269295997297704,"rank":94,"remainingConfigurations":398},{"removed":"gpqa","score":0.26163909613159947,"rank":94,"remainingConfigurations":398},{"removed":"harvey","score":0.2564688983841224,"rank":96,"remainingConfigurations":398},{"removed":"hle","score":0.27345122265632377,"rank":94,"remainingConfigurations":398},{"removed":"ifbench","score":0.2778926889419225,"rank":92,"remainingConfigurations":398},{"removed":"itbench","score":0.2688752500973671,"rank":94,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2676513915164056,"rank":94,"remainingConfigurations":398},{"removed":"math500","score":0.2689079815394872,"rank":94,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.27277491548676003,"rank":93,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2786021950645012,"rank":94,"remainingConfigurations":398},{"removed":"omniscience","score":0.268399888379712,"rank":95,"remainingConfigurations":398},{"removed":"scicode","score":0.27358439831184184,"rank":93,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2699001901342239,"rank":94,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2679934660471395,"rank":94,"remainingConfigurations":398},{"removed":"arc-agi","score":0.30098380710047073,"rank":93,"remainingConfigurations":398},{"removed":"deepswe","score":0.23850587226799433,"rank":93,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2686914436499853,"rank":94,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2671130275825348,"rank":94,"remainingConfigurations":398},{"removed":"frontiercode","score":0.27530345699761744,"rank":93,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.26872874904035793,"rank":94,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2667949206087502,"rank":94,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.26826454557642887,"rank":94,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2676664949458885,"rank":94,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2689189726660471,"rank":94,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2674203389229818,"rank":93,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2706764427064254,"rank":94,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2689617950804878,"rank":94,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.26590040965046424,"rank":94,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2675484371912092,"rank":94,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.27099418961339666,"rank":94,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2729484661792552,"rank":94,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.26085252564453715,"rank":94,"remainingConfigurations":398},{"removed":"frontiermath","score":0.27028090815156625,"rank":94,"remainingConfigurations":398},{"removed":"simpleqa","score":0.27514465095531376,"rank":93,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.26779530424641185,"rank":94,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.26809021161208174,"rank":94,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2678983031375857,"rank":94,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2684803135997264,"rank":94,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2674384081739868,"rank":94,"remainingConfigurations":398}]},"hy3--effort-reasoning":{"score":0.2644613199363198,"rank":95,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2970427691064605,"rank":96,"remainingConfigurations":398},{"removed":"Datacurve","score":0.23395956906287138,"rank":95,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2630759114202361,"rank":95,"remainingConfigurations":398},{"removed":"Scale","score":0.28019048664097074,"rank":95,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.26486240991441196,"rank":95,"remainingConfigurations":398},{"removed":"Cognition","score":0.27013431268083626,"rank":95,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2676702228876892,"rank":94,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.26901444649746825,"rank":95,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.264527583825474,"rank":94,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2576303644104973,"rank":95,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.26445991795503404,"rank":95,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.26421059060278407,"rank":95,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.26403793872984765,"rank":95,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2644613199363198,"rank":95,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2637595467190457,"rank":95,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.26522314156578525,"rank":95,"remainingConfigurations":398},{"removed":"briefcase","score":0.2618094537031041,"rank":95,"remainingConfigurations":398},{"removed":"aime","score":0.26470593062506215,"rank":96,"remainingConfigurations":398},{"removed":"apex-agents","score":0.26694625001817074,"rank":95,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2569678808123078,"rank":95,"remainingConfigurations":398},{"removed":"automationbench","score":0.2704234129423388,"rank":94,"remainingConfigurations":398},{"removed":"critpt","score":0.2666177397569333,"rank":94,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2644423984523086,"rank":95,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.26676220812499957,"rank":95,"remainingConfigurations":398},{"removed":"gdpval","score":0.2640686180386815,"rank":95,"remainingConfigurations":398},{"removed":"gmmlu","score":0.265409588159855,"rank":95,"remainingConfigurations":398},{"removed":"gpqa","score":0.25560363047490936,"rank":95,"remainingConfigurations":398},{"removed":"harvey","score":0.26280414507029143,"rank":94,"remainingConfigurations":398},{"removed":"hle","score":0.2699946346998801,"rank":95,"remainingConfigurations":398},{"removed":"ifbench","score":0.2594309656278111,"rank":96,"remainingConfigurations":398},{"removed":"itbench","score":0.2643392298758728,"rank":96,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2637174119643933,"rank":95,"remainingConfigurations":398},{"removed":"math500","score":0.26458824981526213,"rank":95,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.26861267592036625,"rank":94,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2741885604133651,"rank":95,"remainingConfigurations":398},{"removed":"omniscience","score":0.27106914729676346,"rank":94,"remainingConfigurations":398},{"removed":"scicode","score":0.26662842588413793,"rank":96,"remainingConfigurations":398},{"removed":"tau-bench","score":0.26053564283085195,"rank":95,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.26921778298282034,"rank":93,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2966113382665135,"rank":95,"remainingConfigurations":398},{"removed":"deepswe","score":0.23410137435162892,"rank":95,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2645207541295136,"rank":95,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2629230926182599,"rank":95,"remainingConfigurations":398},{"removed":"frontiercode","score":0.27013431268083626,"rank":95,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2645508331862352,"rank":95,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.26261785041727864,"rank":95,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.26410166992094014,"rank":95,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2635391668644799,"rank":95,"remainingConfigurations":398},{"removed":"livebench-math","score":0.26475332765208504,"rank":95,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2632251490409548,"rank":94,"remainingConfigurations":398},{"removed":"livebench-language","score":0.26647958270446215,"rank":95,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2648050637552164,"rank":95,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2617390523573963,"rank":95,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.26336726695912377,"rank":95,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2668360943402896,"rank":95,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.26901444649746825,"rank":95,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2565739483357103,"rank":95,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2660981315100515,"rank":95,"remainingConfigurations":398},{"removed":"simpleqa","score":0.270968948559186,"rank":94,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2636166080608651,"rank":95,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.26392489149747733,"rank":95,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2637375326312024,"rank":95,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.26430298598363294,"rank":95,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2632744189536658,"rank":95,"remainingConfigurations":398}]},"deepseek-v4-flash-0424--effort-max":{"score":0.2571209544923257,"rank":96,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.28945832137476496,"rank":97,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2265487678683968,"rank":97,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2557757517853077,"rank":96,"remainingConfigurations":398},{"removed":"Scale","score":0.27261586395728216,"rank":96,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.25748745959820607,"rank":96,"remainingConfigurations":398},{"removed":"Cognition","score":0.26252549763855487,"rank":97,"remainingConfigurations":398},{"removed":"LiveBench","score":0.26046994741720986,"rank":95,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.26131739641338947,"rank":97,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2573283805580738,"rank":95,"remainingConfigurations":381},{"removed":"Vals AI","score":0.25010500498408067,"rank":96,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2571328825640123,"rank":96,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.25683415583765556,"rank":96,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.25671118047877356,"rank":96,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2571209544923257,"rank":96,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2564095693963555,"rank":96,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.24675478801422215,"rank":98,"remainingConfigurations":398},{"removed":"briefcase","score":0.26170195519015954,"rank":96,"remainingConfigurations":398},{"removed":"aime","score":0.25730138242023665,"rank":97,"remainingConfigurations":398},{"removed":"apex-agents","score":0.25973041030719324,"rank":96,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2543985841676641,"rank":96,"remainingConfigurations":398},{"removed":"automationbench","score":0.25461802944399076,"rank":96,"remainingConfigurations":398},{"removed":"critpt","score":0.2571154606805519,"rank":96,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2567293396749946,"rank":97,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.26108355982692943,"rank":97,"remainingConfigurations":398},{"removed":"gdpval","score":0.2575754291272078,"rank":96,"remainingConfigurations":398},{"removed":"gmmlu","score":0.25825244085286597,"rank":96,"remainingConfigurations":398},{"removed":"gpqa","score":0.2502570465399821,"rank":96,"remainingConfigurations":398},{"removed":"harvey","score":0.26209921635642147,"rank":95,"remainingConfigurations":398},{"removed":"hle","score":0.26152942323356393,"rank":96,"remainingConfigurations":398},{"removed":"ifbench","score":0.24762237164204107,"rank":98,"remainingConfigurations":398},{"removed":"itbench","score":0.2652764919716147,"rank":95,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2564489508098757,"rank":96,"remainingConfigurations":398},{"removed":"math500","score":0.2571113221101567,"rank":96,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2612835714752744,"rank":96,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2673797199477639,"rank":96,"remainingConfigurations":398},{"removed":"omniscience","score":0.26029162841857995,"rank":97,"remainingConfigurations":398},{"removed":"scicode","score":0.26448649833738297,"rank":97,"remainingConfigurations":398},{"removed":"tau-bench","score":0.25095478513255703,"rank":99,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.25845368834442545,"rank":96,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2889651235157095,"rank":97,"remainingConfigurations":398},{"removed":"deepswe","score":0.22670147440016167,"rank":97,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2571704100810215,"rank":96,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2556780603595648,"rank":96,"remainingConfigurations":398},{"removed":"frontiercode","score":0.26252549763855487,"rank":97,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.25717115543509106,"rank":96,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.25535219726910363,"rank":96,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.25675778069017535,"rank":96,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2562375787642582,"rank":96,"remainingConfigurations":398},{"removed":"livebench-math","score":0.25738905573510246,"rank":96,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2559221495696619,"rank":96,"remainingConfigurations":398},{"removed":"livebench-language","score":0.25912355317283214,"rank":96,"remainingConfigurations":398},{"removed":"livebench-data","score":0.25742077890683385,"rank":96,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2544523699357958,"rank":96,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2560626825175693,"rank":96,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2594549307749708,"rank":96,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.26131739641338947,"rank":97,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.24981741977609553,"rank":96,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2587190086803146,"rank":96,"remainingConfigurations":398},{"removed":"simpleqa","score":0.26355270251450125,"rank":95,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.25632965891647,"rank":96,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2565667221454417,"rank":96,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2563971727375816,"rank":96,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2569334318887406,"rank":96,"remainingConfigurations":398},{"removed":"vibe-code","score":0.25597648487705177,"rank":96,"remainingConfigurations":398}]},"agnes-2.5-pro-alpha--effort-reasoning":{"score":0.25190007320345986,"rank":97,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2839407536182344,"rank":98,"remainingConfigurations":398},{"removed":"Datacurve","score":0.22248979854547976,"rank":98,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.25054824516265106,"rank":97,"remainingConfigurations":398},{"removed":"Scale","score":0.2673873122838257,"rank":97,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2522702099232723,"rank":97,"remainingConfigurations":398},{"removed":"Cognition","score":0.2579824639696731,"rank":100,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2551328302209989,"rank":96,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2562932085256772,"rank":98,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2523658494371625,"rank":98,"remainingConfigurations":381},{"removed":"Vals AI","score":0.24541548828615148,"rank":97,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2518997993110397,"rank":97,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2516624333898021,"rank":97,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2514959328895414,"rank":97,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.25190007320345986,"rank":97,"remainingConfigurations":398},{"removed":"All provider reports","score":0.251232136270692,"rank":97,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2527557428234049,"rank":97,"remainingConfigurations":398},{"removed":"briefcase","score":0.23955155662999852,"rank":101,"remainingConfigurations":398},{"removed":"aime","score":0.2519743053928454,"rank":98,"remainingConfigurations":398},{"removed":"apex-agents","score":0.25413714931836695,"rank":97,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.24988566010301724,"rank":97,"remainingConfigurations":398},{"removed":"automationbench","score":0.2429257904900798,"rank":100,"remainingConfigurations":398},{"removed":"critpt","score":0.24551702686490837,"rank":98,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2517975017906362,"rank":98,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.26144466975597297,"rank":96,"remainingConfigurations":398},{"removed":"gdpval","score":0.25541629019169293,"rank":97,"remainingConfigurations":398},{"removed":"gmmlu","score":0.25261114735812157,"rank":97,"remainingConfigurations":398},{"removed":"gpqa","score":0.24659499285382971,"rank":97,"remainingConfigurations":398},{"removed":"harvey","score":0.25001154463484276,"rank":97,"remainingConfigurations":398},{"removed":"hle","score":0.25563696249797446,"rank":97,"remainingConfigurations":398},{"removed":"ifbench","score":0.2466434437976787,"rank":99,"remainingConfigurations":398},{"removed":"itbench","score":0.2518252287847211,"rank":97,"remainingConfigurations":398},{"removed":"livecodebench","score":0.25103465323191515,"rank":97,"remainingConfigurations":398},{"removed":"math500","score":0.2519646166872817,"rank":97,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.25583296334633304,"rank":97,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.26124694704134416,"rank":97,"remainingConfigurations":398},{"removed":"omniscience","score":0.2553444568106662,"rank":100,"remainingConfigurations":398},{"removed":"scicode","score":0.2704872395253625,"rank":95,"remainingConfigurations":398},{"removed":"tau-bench","score":0.260441405792527,"rank":96,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2478531083905314,"rank":99,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2833617851234198,"rank":98,"remainingConfigurations":398},{"removed":"deepswe","score":0.22262684816908843,"rank":98,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.25195770759223585,"rank":97,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2504249477178728,"rank":97,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2579824639696731,"rank":100,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2519964474974489,"rank":97,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.25011280837001,"rank":97,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2515558270977948,"rank":97,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2509963063665465,"rank":97,"remainingConfigurations":398},{"removed":"livebench-math","score":0.25218630640756995,"rank":97,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.25068183083840256,"rank":97,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2538770418505883,"rank":97,"remainingConfigurations":398},{"removed":"livebench-data","score":0.25223604583443565,"rank":97,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.24923446471916125,"rank":97,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2508260299430494,"rank":97,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2542399632676896,"rank":97,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2562932085256772,"rank":98,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.24426116526489428,"rank":97,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2534925281602444,"rank":97,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2582833789203713,"rank":96,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.25107269977911906,"rank":97,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.25137070406487705,"rank":97,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.25119207355119527,"rank":97,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.25173711864481696,"rank":97,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2507402561811026,"rank":97,"remainingConfigurations":398}]},"minimax-m3--effort-reasoning":{"score":0.2511354611563794,"rank":98,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.283875884386071,"rank":100,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2223867823529536,"rank":99,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.24968238480383417,"rank":98,"remainingConfigurations":398},{"removed":"Scale","score":0.2668532100568935,"rank":98,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.251698778196544,"rank":98,"remainingConfigurations":398},{"removed":"Cognition","score":0.25794319003082106,"rank":101,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2547390744060057,"rank":97,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2557893243730977,"rank":99,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2526852292583628,"rank":97,"remainingConfigurations":381},{"removed":"Vals AI","score":0.24525230007325072,"rank":98,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.25114566461486715,"rank":98,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2508659008456327,"rank":98,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.25072330745624977,"rank":98,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2511354611563794,"rank":98,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2504381621071888,"rank":98,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.26188851868574997,"rank":96,"remainingConfigurations":398},{"removed":"briefcase","score":0.24395850921775608,"rank":97,"remainingConfigurations":398},{"removed":"aime","score":0.251201528694921,"rank":99,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2535128702137598,"rank":98,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2400013522220914,"rank":101,"remainingConfigurations":398},{"removed":"automationbench","score":0.2511142144409362,"rank":97,"remainingConfigurations":398},{"removed":"critpt","score":0.25430966844419317,"rank":97,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2585381373642985,"rank":96,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2570538419658821,"rank":98,"remainingConfigurations":398},{"removed":"gdpval","score":0.2454124625304485,"rank":100,"remainingConfigurations":398},{"removed":"gmmlu","score":0.2516039548395421,"rank":98,"remainingConfigurations":398},{"removed":"gpqa","score":0.2388915662662678,"rank":100,"remainingConfigurations":398},{"removed":"harvey","score":0.23611191190894956,"rank":104,"remainingConfigurations":398},{"removed":"hle","score":0.25307255581251215,"rank":98,"remainingConfigurations":398},{"removed":"ifbench","score":0.23892205595722393,"rank":103,"remainingConfigurations":398},{"removed":"itbench","score":0.25095948536362367,"rank":98,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2501891275183613,"rank":98,"remainingConfigurations":398},{"removed":"math500","score":0.2514161446673132,"rank":98,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.25513014463507383,"rank":98,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.25824941234286514,"rank":98,"remainingConfigurations":398},{"removed":"omniscience","score":0.28655913284464957,"rank":90,"remainingConfigurations":398},{"removed":"scicode","score":0.25544220843869764,"rank":98,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2535642786983668,"rank":97,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.25010117894813727,"rank":97,"remainingConfigurations":398},{"removed":"arc-agi","score":0.28280365167207433,"rank":99,"remainingConfigurations":398},{"removed":"deepswe","score":0.2225345812035945,"rank":99,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.25118828160950923,"rank":98,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.24969517831328134,"rank":98,"remainingConfigurations":398},{"removed":"frontiercode","score":0.25794319003082106,"rank":101,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.25126374671785046,"rank":98,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.24937345873015884,"rank":98,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.25078867410787836,"rank":98,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2503529772754047,"rank":98,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2514097596085965,"rank":98,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.24994925822096534,"rank":98,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2531119184587009,"rank":98,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2514520934423763,"rank":98,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2484820909016627,"rank":98,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2500815685824779,"rank":98,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.25344263839812137,"rank":98,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2557893243730977,"rank":99,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2436781437544492,"rank":98,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2526849409987472,"rank":98,"remainingConfigurations":398},{"removed":"simpleqa","score":0.25750469506598167,"rank":98,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.25032891632266807,"rank":98,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.25059802124974834,"rank":98,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2504213212697242,"rank":98,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.25096404913272513,"rank":98,"remainingConfigurations":398},{"removed":"vibe-code","score":0.24998285989043248,"rank":98,"remainingConfigurations":398}]},"glm-5.1--effort-reasoning":{"score":0.24292302856539486,"rank":99,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.27466791616367875,"rank":102,"remainingConfigurations":398},{"removed":"Datacurve","score":0.21420925355118844,"rank":101,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.24154182201972296,"rank":100,"remainingConfigurations":398},{"removed":"Scale","score":0.258546469765806,"rank":99,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.24327102966137082,"rank":99,"remainingConfigurations":398},{"removed":"Cognition","score":0.24927033362376907,"rank":103,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24614139646300495,"rank":99,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.24750478030627943,"rank":100,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.24352449653860056,"rank":101,"remainingConfigurations":381},{"removed":"Vals AI","score":0.23669012040099938,"rank":99,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.24292620617042535,"rank":99,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.24270300368568412,"rank":99,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.24254161305291413,"rank":99,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.24292302856539486,"rank":99,"remainingConfigurations":398},{"removed":"All provider reports","score":0.24229849299652964,"rank":99,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.24379524101071334,"rank":99,"remainingConfigurations":398},{"removed":"briefcase","score":0.23700825812107962,"rank":107,"remainingConfigurations":398},{"removed":"aime","score":0.2428025555918176,"rank":100,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2458523754662816,"rank":99,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.24172898927557232,"rank":99,"remainingConfigurations":398},{"removed":"automationbench","score":0.2433467549227261,"rank":99,"remainingConfigurations":398},{"removed":"critpt","score":0.24348552507207313,"rank":100,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.24345568991837882,"rank":99,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2530489073628062,"rank":99,"remainingConfigurations":398},{"removed":"gdpval","score":0.23926824127852828,"rank":103,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24390259700427763,"rank":99,"remainingConfigurations":398},{"removed":"gpqa","score":0.238079379121475,"rank":101,"remainingConfigurations":398},{"removed":"harvey","score":0.24173937158183548,"rank":98,"remainingConfigurations":398},{"removed":"hle","score":0.24845756570507782,"rank":101,"remainingConfigurations":398},{"removed":"ifbench","score":0.23400081537642373,"rank":106,"remainingConfigurations":398},{"removed":"itbench","score":0.22761654269595152,"rank":114,"remainingConfigurations":398},{"removed":"livecodebench","score":0.24184291132467448,"rank":99,"remainingConfigurations":398},{"removed":"math500","score":0.24282863841526536,"rank":99,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2466296266039093,"rank":100,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.25299351309711066,"rank":99,"remainingConfigurations":398},{"removed":"omniscience","score":0.2575105997402059,"rank":99,"remainingConfigurations":398},{"removed":"scicode","score":0.2531712677508252,"rank":99,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2420851541372863,"rank":102,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.241694291384974,"rank":102,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2738623291626265,"rank":103,"remainingConfigurations":398},{"removed":"deepswe","score":0.21434665269199682,"rank":101,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.24297675340122646,"rank":99,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.24151309528931633,"rank":100,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24927033362376907,"rank":103,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.24303340509421775,"rank":99,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2412111058540444,"rank":99,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2425917569227215,"rank":99,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2420785716104871,"rank":99,"remainingConfigurations":398},{"removed":"livebench-math","score":0.24320103252777533,"rank":99,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2417424673722162,"rank":99,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2448697468644354,"rank":99,"remainingConfigurations":398},{"removed":"livebench-data","score":0.24321885480380476,"rank":99,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.24031616837132716,"rank":99,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.24187692143483175,"rank":99,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24521947675537084,"rank":99,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.24750478030627943,"rank":100,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.23559049621700767,"rank":101,"remainingConfigurations":398},{"removed":"frontiermath","score":0.24447222108531955,"rank":99,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24922624039709326,"rank":99,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.24211890650155743,"rank":100,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2423892293396163,"rank":99,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.24223206921905893,"rank":100,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.24274742008035075,"rank":99,"remainingConfigurations":398},{"removed":"vibe-code","score":0.24180115804526262,"rank":99,"remainingConfigurations":398}]},"qwen3.7-plus--effort-reasoning":{"score":0.24249494004637548,"rank":100,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.273512036933851,"rank":104,"remainingConfigurations":398},{"removed":"Datacurve","score":0.21400813231016344,"rank":103,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.24107589807655225,"rank":101,"remainingConfigurations":398},{"removed":"Scale","score":0.2577755155140131,"rank":100,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.24304003209429226,"rank":100,"remainingConfigurations":398},{"removed":"Cognition","score":0.24901449197733658,"rank":105,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24522862654630131,"rank":100,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.24706751117998552,"rank":101,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.24359695661791061,"rank":100,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2363208358355693,"rank":100,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.24250634091360546,"rank":100,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2422665179902568,"rank":100,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2420985778474616,"rank":100,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.24249494004637548,"rank":100,"remainingConfigurations":398},{"removed":"All provider reports","score":0.24185546402354238,"rank":100,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2430084288223223,"rank":100,"remainingConfigurations":398},{"removed":"briefcase","score":0.24206457013522906,"rank":98,"remainingConfigurations":398},{"removed":"aime","score":0.24260521109015495,"rank":101,"remainingConfigurations":398},{"removed":"apex-agents","score":0.24330832224014412,"rank":100,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.24373198275067384,"rank":98,"remainingConfigurations":398},{"removed":"automationbench","score":0.2453020527970057,"rank":98,"remainingConfigurations":398},{"removed":"critpt","score":0.24003774194407124,"rank":103,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2368700731252058,"rank":106,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.24128159050080977,"rank":102,"remainingConfigurations":398},{"removed":"gdpval","score":0.2537565702925957,"rank":98,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24295703344237216,"rank":100,"remainingConfigurations":398},{"removed":"gpqa","score":0.23418606342120465,"rank":103,"remainingConfigurations":398},{"removed":"harvey","score":0.2406845975071339,"rank":99,"remainingConfigurations":398},{"removed":"hle","score":0.24570929179279857,"rank":104,"remainingConfigurations":398},{"removed":"ifbench","score":0.2323990486137142,"rank":109,"remainingConfigurations":398},{"removed":"itbench","score":0.2422708201754913,"rank":99,"remainingConfigurations":398},{"removed":"livecodebench","score":0.24162884983170962,"rank":101,"remainingConfigurations":398},{"removed":"math500","score":0.2427808663987435,"rank":100,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.24650096511700417,"rank":101,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24512241095139312,"rank":107,"remainingConfigurations":398},{"removed":"omniscience","score":0.25847613642948314,"rank":98,"remainingConfigurations":398},{"removed":"scicode","score":0.24792168165907036,"rank":101,"remainingConfigurations":398},{"removed":"tau-bench","score":0.24118721595701398,"rank":104,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.24239267258937813,"rank":101,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2725033027279353,"rank":105,"remainingConfigurations":398},{"removed":"deepswe","score":0.21415361032358618,"rank":103,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.24254503502219418,"rank":100,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.24110486529651565,"rank":101,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24901449197733658,"rank":105,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.24255383483788215,"rank":100,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2407794559249187,"rank":100,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.24215374720124605,"rank":100,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.24167988267372822,"rank":100,"remainingConfigurations":398},{"removed":"livebench-math","score":0.24276602764730995,"rank":100,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2413401925910232,"rank":100,"remainingConfigurations":398},{"removed":"livebench-language","score":0.24444779320334034,"rank":100,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2427783070137383,"rank":100,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23989054857278383,"rank":100,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.24145917693727648,"rank":100,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24476643687368263,"rank":100,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.24706751117998552,"rank":101,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2352373066530443,"rank":103,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2440206845534624,"rank":100,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24873920122564638,"rank":100,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2416911382256208,"rank":101,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.24196209375893807,"rank":100,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.24179628127641428,"rank":101,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.24232322104461654,"rank":100,"remainingConfigurations":398},{"removed":"vibe-code","score":0.24136725715776056,"rank":100,"remainingConfigurations":398}]},"grok-4.3--effort-medium":{"score":0.24117507149820527,"rank":101,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2768471328438344,"rank":101,"remainingConfigurations":398},{"removed":"Datacurve","score":0.21410132476029123,"rank":102,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23966818033685452,"rank":103,"remainingConfigurations":398},{"removed":"Scale","score":0.2575957681159055,"rank":101,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.24199559710281707,"rank":101,"remainingConfigurations":398},{"removed":"Cognition","score":0.24909706038728374,"rank":104,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24421760586535932,"rank":102,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.24565172601681518,"rank":102,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.24098501717176865,"rank":102,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2357961211032944,"rank":101,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.24118536365741375,"rank":101,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.24097941255871236,"rank":101,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.24082764668273396,"rank":101,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.24117507149820527,"rank":101,"remainingConfigurations":398},{"removed":"All provider reports","score":0.24061651702876788,"rank":101,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2418208529435343,"rank":101,"remainingConfigurations":398},{"removed":"briefcase","score":0.2401206219861793,"rank":100,"remainingConfigurations":398},{"removed":"aime","score":0.24174045946591624,"rank":102,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2431665879733098,"rank":101,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.23800109406501027,"rank":104,"remainingConfigurations":398},{"removed":"automationbench","score":0.24058018416759044,"rank":101,"remainingConfigurations":398},{"removed":"critpt","score":0.2382563726218548,"rank":104,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.24104224713356406,"rank":100,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.24306819307726654,"rank":100,"remainingConfigurations":398},{"removed":"gdpval","score":0.242082833512982,"rank":101,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24287580772412354,"rank":101,"remainingConfigurations":398},{"removed":"gpqa","score":0.23067525252546386,"rank":108,"remainingConfigurations":398},{"removed":"harvey","score":0.23904377937293497,"rank":100,"remainingConfigurations":398},{"removed":"hle","score":0.24704665707578768,"rank":102,"remainingConfigurations":398},{"removed":"ifbench","score":0.223670571229139,"rank":114,"remainingConfigurations":398},{"removed":"itbench","score":0.241302913461631,"rank":100,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23988587122499913,"rank":103,"remainingConfigurations":398},{"removed":"math500","score":0.24064197297928533,"rank":102,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.24408782260227657,"rank":103,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.25003095359335265,"rank":103,"remainingConfigurations":398},{"removed":"omniscience","score":0.24574655786461796,"rank":102,"remainingConfigurations":398},{"removed":"scicode","score":0.24461004980298437,"rank":102,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2447994167192075,"rank":101,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.26114654253793423,"rank":95,"remainingConfigurations":398},{"removed":"arc-agi","score":0.275866347744862,"rank":102,"remainingConfigurations":398},{"removed":"deepswe","score":0.21422821005979073,"rank":102,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.24122311121436837,"rank":101,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23967069740426503,"rank":102,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24909706038728374,"rank":104,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.24123524978488978,"rank":101,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23949385545763782,"rank":101,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.24082903632933628,"rank":101,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.24040076442365388,"rank":101,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2414562592401457,"rank":101,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2399682238939623,"rank":101,"remainingConfigurations":398},{"removed":"livebench-language","score":0.24307321555367375,"rank":101,"remainingConfigurations":398},{"removed":"livebench-data","score":0.24144484597927507,"rank":102,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23861161074398887,"rank":101,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.24013453081493785,"rank":101,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24351633620411658,"rank":101,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.24565172601681518,"rank":102,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.23298498389412245,"rank":107,"remainingConfigurations":398},{"removed":"frontiermath","score":0.242912552961285,"rank":101,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2475915527526097,"rank":101,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2403811450339983,"rank":102,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.24063028006430176,"rank":101,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.24049813351862503,"rank":102,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.24096406230832665,"rank":101,"remainingConfigurations":398},{"removed":"vibe-code","score":0.24006625739035511,"rank":101,"remainingConfigurations":398}]},"deepseek-v4-flash--effort-high":{"score":0.2406782058095042,"rank":102,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.24139410232195624,"rank":81,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1907813068371503,"rank":149,"remainingConfigurations":398},{"removed":"Datacurve","score":0.19456853652471548,"rank":113,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.24172976949965078,"rank":99,"remainingConfigurations":398},{"removed":"Scale","score":0.25587098257694735,"rank":102,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23912246590636302,"rank":104,"remainingConfigurations":398},{"removed":"Cognition","score":0.38836414709103934,"rank":66,"remainingConfigurations":398},{"removed":"LiveBench","score":0.25022469620754056,"rank":98,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23800573435655903,"rank":107,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.24640136557969358,"rank":99,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18368040451890186,"rank":128,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.24062820440642932,"rank":102,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.24018461370410601,"rank":102,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2404014237203618,"rank":102,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2406782058095042,"rank":102,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2398424386203812,"rank":102,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.24078703736454932,"rank":102,"remainingConfigurations":398},{"removed":"briefcase","score":0.24066198960021135,"rank":99,"remainingConfigurations":398},{"removed":"aime","score":0.23963109386663017,"rank":104,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2412536340057172,"rank":104,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.24045231561594635,"rank":100,"remainingConfigurations":398},{"removed":"automationbench","score":0.2400948707096946,"rank":102,"remainingConfigurations":398},{"removed":"critpt","score":0.2410285876703504,"rank":102,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.24068429304990727,"rank":101,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.24138783087517143,"rank":101,"remainingConfigurations":398},{"removed":"gdpval","score":0.24092066329106165,"rank":102,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24066735952162446,"rank":103,"remainingConfigurations":398},{"removed":"gpqa","score":0.23902129310231568,"rank":99,"remainingConfigurations":398},{"removed":"harvey","score":0.22840301366535032,"rank":111,"remainingConfigurations":398},{"removed":"hle","score":0.2467813779120226,"rank":103,"remainingConfigurations":398},{"removed":"ifbench","score":0.23914851430574038,"rank":102,"remainingConfigurations":398},{"removed":"itbench","score":0.2403094024425587,"rank":101,"remainingConfigurations":398},{"removed":"livecodebench","score":0.24166134090433786,"rank":100,"remainingConfigurations":398},{"removed":"math500","score":0.24074279473784918,"rank":101,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2523496491835922,"rank":99,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.250271376829198,"rank":102,"remainingConfigurations":398},{"removed":"omniscience","score":0.23949638167315637,"rank":103,"remainingConfigurations":398},{"removed":"scicode","score":0.24115235702493187,"rank":105,"remainingConfigurations":398},{"removed":"tau-bench","score":0.24025080322550038,"rank":105,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.24412794760293657,"rank":100,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18946429123123565,"rank":147,"remainingConfigurations":398},{"removed":"deepswe","score":0.1946963748450404,"rank":113,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.24073654737074426,"rank":102,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.24231505773684572,"rank":99,"remainingConfigurations":398},{"removed":"frontiercode","score":0.38836414709103934,"rank":66,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2411015053550862,"rank":102,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23899752656586706,"rank":102,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2404350241447287,"rank":102,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2401356557979338,"rank":102,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2411281472870456,"rank":102,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2398666450452754,"rank":102,"remainingConfigurations":398},{"removed":"livebench-language","score":0.24186968955393992,"rank":102,"remainingConfigurations":398},{"removed":"livebench-data","score":0.241890061933311,"rank":101,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23810852300970373,"rank":102,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2397656953533136,"rank":102,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24211691656036016,"rank":104,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23800573435655903,"rank":107,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2352769635190309,"rank":102,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2424421181888828,"rank":102,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24491102960890374,"rank":104,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.24247000568458613,"rank":99,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.23634932319287383,"rank":106,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.24434363151391292,"rank":99,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.24052910966893937,"rank":102,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23501165995677384,"rank":106,"remainingConfigurations":398}]},"grok-4.6--effort-low":{"score":0.24011946975121745,"rank":103,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.20587878154096997,"rank":90,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.24918749013935648,"rank":113,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2067717792276124,"rank":107,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.24036293498839,"rank":102,"remainingConfigurations":398},{"removed":"Scale","score":0.25476452786178877,"rank":104,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23763797626580865,"rank":105,"remainingConfigurations":398},{"removed":"Cognition","score":0.26196470312692627,"rank":98,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24426926945638772,"rank":101,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2350032170793802,"rank":109,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.24088393468066968,"rank":103,"remainingConfigurations":381},{"removed":"Vals AI","score":0.23012709613190382,"rank":104,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2401639642784004,"rank":103,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23975741536174444,"rank":103,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2400831898296469,"rank":103,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.24011946975121745,"rank":103,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23974190515385937,"rank":103,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2407445818319307,"rank":103,"remainingConfigurations":398},{"removed":"briefcase","score":0.23760112986191181,"rank":104,"remainingConfigurations":398},{"removed":"aime","score":0.2391274210104888,"rank":105,"remainingConfigurations":398},{"removed":"apex-agents","score":0.24137691257165017,"rank":103,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2390515085570338,"rank":103,"remainingConfigurations":398},{"removed":"automationbench","score":0.23743771679412226,"rank":105,"remainingConfigurations":398},{"removed":"critpt","score":0.2411981477538818,"rank":101,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2405374402400373,"rank":102,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23930328160480366,"rank":105,"remainingConfigurations":398},{"removed":"gdpval","score":0.23858028611952778,"rank":104,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24040582388340273,"rank":104,"remainingConfigurations":398},{"removed":"gpqa","score":0.23967094336750408,"rank":98,"remainingConfigurations":398},{"removed":"harvey","score":0.2379041105862589,"rank":101,"remainingConfigurations":398},{"removed":"hle","score":0.24953764520006538,"rank":100,"remainingConfigurations":398},{"removed":"ifbench","score":0.23855478403169872,"rank":104,"remainingConfigurations":398},{"removed":"itbench","score":0.24011479338606026,"rank":102,"remainingConfigurations":398},{"removed":"livecodebench","score":0.24049872105295053,"rank":102,"remainingConfigurations":398},{"removed":"math500","score":0.24021762653952114,"rank":103,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.24446197641709877,"rank":102,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2504052732105531,"rank":101,"remainingConfigurations":398},{"removed":"omniscience","score":0.23934596913801542,"rank":104,"remainingConfigurations":398},{"removed":"scicode","score":0.24206584322749045,"rank":104,"remainingConfigurations":398},{"removed":"tau-bench","score":0.23882878853077594,"rank":106,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.23851535331113402,"rank":105,"remainingConfigurations":398},{"removed":"arc-agi","score":0.28206659203512635,"rank":101,"remainingConfigurations":398},{"removed":"deepswe","score":0.20683939616752986,"rank":107,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2401680379132918,"rank":103,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23782281871984645,"rank":104,"remainingConfigurations":398},{"removed":"frontiercode","score":0.26196470312692627,"rank":98,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.24044460269737203,"rank":103,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2382196915200614,"rank":104,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23991504335210104,"rank":103,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23920111020793633,"rank":103,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2404221045223449,"rank":103,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23879687589699972,"rank":103,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2418280496821614,"rank":104,"remainingConfigurations":398},{"removed":"livebench-data","score":0.24054160831159757,"rank":103,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2375576268545637,"rank":103,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23905585769181817,"rank":103,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24263847096077437,"rank":102,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2350032170793802,"rank":109,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2341117158709374,"rank":105,"remainingConfigurations":398},{"removed":"frontiermath","score":0.24140412317584126,"rank":104,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24622654899417817,"rank":103,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2396734710280787,"rank":103,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.23954911660430978,"rank":102,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23938332988321157,"rank":103,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.24011876308431465,"rank":103,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2391222208732301,"rank":102,"remainingConfigurations":398}]},"qwen3.6-plus--effort-reasoning":{"score":0.23993675456903749,"rank":104,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2741670183866259,"rank":103,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2124537503790492,"rank":104,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23851339156230297,"rank":105,"remainingConfigurations":398},{"removed":"Scale","score":0.255813606775455,"rank":103,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.24064181583859579,"rank":102,"remainingConfigurations":398},{"removed":"Cognition","score":0.2473997627425005,"rank":107,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24291105599216703,"rank":103,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2442910180019309,"rank":103,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23947064094166917,"rank":104,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2341357083126602,"rank":102,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2399446059209663,"rank":104,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.239735387174297,"rank":104,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23957321000610973,"rank":104,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23993675456903749,"rank":104,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23935405729287443,"rank":104,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.24028618857716097,"rank":104,"remainingConfigurations":398},{"removed":"briefcase","score":0.2383535014766978,"rank":103,"remainingConfigurations":398},{"removed":"aime","score":0.24052846026276523,"rank":103,"remainingConfigurations":398},{"removed":"apex-agents","score":0.24186830624181932,"rank":102,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.23162046451631024,"rank":109,"remainingConfigurations":398},{"removed":"automationbench","score":0.2385383223662134,"rank":104,"remainingConfigurations":398},{"removed":"critpt","score":0.2451930022524478,"rank":99,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2397658249250345,"rank":103,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.24105861489978167,"rank":103,"remainingConfigurations":398},{"removed":"gdpval","score":0.24774315941593147,"rank":99,"remainingConfigurations":398},{"removed":"gmmlu","score":0.24139967819871022,"rank":102,"remainingConfigurations":398},{"removed":"gpqa","score":0.23301643936503866,"rank":105,"remainingConfigurations":398},{"removed":"harvey","score":0.23781755747341604,"rank":102,"remainingConfigurations":398},{"removed":"hle","score":0.2510136128034446,"rank":99,"remainingConfigurations":398},{"removed":"ifbench","score":0.23355929876451176,"rank":107,"remainingConfigurations":398},{"removed":"itbench","score":0.23966708712250828,"rank":103,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23910889029253457,"rank":105,"remainingConfigurations":398},{"removed":"math500","score":0.2400199504051821,"rank":104,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.24364794006925097,"rank":104,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2468824159415464,"rank":105,"remainingConfigurations":398},{"removed":"omniscience","score":0.25033905001590084,"rank":101,"remainingConfigurations":398},{"removed":"scicode","score":0.24218827317921718,"rank":103,"remainingConfigurations":398},{"removed":"tau-bench","score":0.23222249181574325,"rank":110,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.23936240841781045,"rank":103,"remainingConfigurations":398},{"removed":"arc-agi","score":0.27315263116759003,"rank":104,"remainingConfigurations":398},{"removed":"deepswe","score":0.2125813205208219,"rank":104,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23998642033047765,"rank":104,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23847226582629677,"rank":103,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2473997627425005,"rank":107,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.24000927686226206,"rank":104,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23825645437999823,"rank":103,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23959682669894464,"rank":104,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23914471325044503,"rank":104,"remainingConfigurations":398},{"removed":"livebench-math","score":0.24021944269811848,"rank":104,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2387397155157409,"rank":104,"remainingConfigurations":398},{"removed":"livebench-language","score":0.24183752015176627,"rank":103,"remainingConfigurations":398},{"removed":"livebench-data","score":0.24022130757801916,"rank":104,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2373685733470372,"rank":104,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23889653199644956,"rank":104,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2422560364620748,"rank":103,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2442910180019309,"rank":103,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2318283835127852,"rank":108,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2417186136225468,"rank":103,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2462799915632673,"rank":102,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.23914037549584286,"rank":104,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.23939904037620865,"rank":103,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23925548725880832,"rank":104,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2397405040256291,"rank":104,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2388272575265715,"rank":103,"remainingConfigurations":398}]},"glm-5.2--effort-low":{"score":0.23881777869766804,"rank":105,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.23060023834231444,"rank":83,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2708390622856896,"rank":106,"remainingConfigurations":398},{"removed":"Datacurve","score":0.2079614366178635,"rank":106,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2383444692766754,"rank":106,"remainingConfigurations":398},{"removed":"Scale","score":0.2525624363147945,"rank":106,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23921043964672448,"rank":103,"remainingConfigurations":398},{"removed":"Cognition","score":0.24886804800575213,"rank":106,"remainingConfigurations":398},{"removed":"LiveBench","score":0.23973337197049657,"rank":105,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.24065954816835153,"rank":104,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.23170151565372518,"rank":103,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2388160499369877,"rank":105,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23838896769869236,"rank":105,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23865835436822372,"rank":105,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23881777869766804,"rank":105,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23820688827179246,"rank":105,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23918245233854826,"rank":105,"remainingConfigurations":398},{"removed":"briefcase","score":0.23863499670701036,"rank":102,"remainingConfigurations":398},{"removed":"aime","score":0.27952045939611675,"rank":91,"remainingConfigurations":398},{"removed":"apex-agents","score":0.24002124652571535,"rank":105,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.23930496445425162,"rank":102,"remainingConfigurations":398},{"removed":"automationbench","score":0.23867053499692914,"rank":103,"remainingConfigurations":398},{"removed":"critpt","score":0.23823857079029528,"rank":105,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23899555858494634,"rank":104,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23976947193084244,"rank":104,"remainingConfigurations":398},{"removed":"gdpval","score":0.23816004432812923,"rank":105,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23946964561855863,"rank":105,"remainingConfigurations":398},{"removed":"gpqa","score":0.20713051236271784,"rank":118,"remainingConfigurations":398},{"removed":"harvey","score":0.23691199158061546,"rank":103,"remainingConfigurations":398},{"removed":"hle","score":0.2437677055042471,"rank":106,"remainingConfigurations":398},{"removed":"ifbench","score":0.2396876822371373,"rank":101,"remainingConfigurations":398},{"removed":"itbench","score":0.23855478632396274,"rank":104,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23896550379854672,"rank":106,"remainingConfigurations":398},{"removed":"math500","score":0.2391233369376254,"rank":105,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.24361302286632472,"rank":105,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2487160434883584,"rank":104,"remainingConfigurations":398},{"removed":"omniscience","score":0.23840845640103928,"rank":105,"remainingConfigurations":398},{"removed":"scicode","score":0.24043575362020184,"rank":106,"remainingConfigurations":398},{"removed":"tau-bench","score":0.23352355370415737,"rank":109,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2386094811187447,"rank":104,"remainingConfigurations":398},{"removed":"arc-agi","score":0.27033890827071855,"rank":106,"remainingConfigurations":398},{"removed":"deepswe","score":0.20808570799917592,"rank":106,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23885637102589086,"rank":105,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2377709569332452,"rank":105,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24886804800575213,"rank":106,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2394058445326891,"rank":105,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23664097578845375,"rank":105,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23856060894628173,"rank":105,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23819410691384027,"rank":105,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23927428968637018,"rank":105,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23704731593792114,"rank":105,"remainingConfigurations":398},{"removed":"livebench-language","score":0.24061239569849724,"rank":105,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2393331733770339,"rank":105,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23647938278262126,"rank":105,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23771768326272588,"rank":105,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24123747961331543,"rank":105,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.24065954816835153,"rank":104,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2240185352978781,"rank":112,"remainingConfigurations":398},{"removed":"frontiermath","score":0.22247959838364506,"rank":115,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2424667905411996,"rank":106,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2380218965896699,"rank":105,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.23839906080742948,"rank":104,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23794880688535172,"rank":105,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2386217774130723,"rank":105,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23787986113228088,"rank":104,"remainingConfigurations":398}]},"gpt-5.4--effort-low":{"score":0.23748306937651487,"rank":106,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2361859660192398,"rank":82,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2839235052329812,"rank":99,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20657187374116215,"rank":108,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23906373633008923,"rank":104,"remainingConfigurations":398},{"removed":"Scale","score":0.2532203338251859,"rank":105,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2367504795431977,"rank":106,"remainingConfigurations":398},{"removed":"Cognition","score":0.24388672980301931,"rank":108,"remainingConfigurations":398},{"removed":"LiveBench","score":0.24040274986249824,"rank":104,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23960596493297828,"rank":105,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23036974382257738,"rank":110,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2293703641108419,"rank":106,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2374890571821183,"rank":106,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2371187873585182,"rank":106,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2372395257768339,"rank":106,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23748306937651487,"rank":106,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23685801388707994,"rank":106,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23783003889910861,"rank":106,"remainingConfigurations":398},{"removed":"briefcase","score":0.23701925564773382,"rank":106,"remainingConfigurations":398},{"removed":"aime","score":0.2377228078240147,"rank":107,"remainingConfigurations":398},{"removed":"apex-agents","score":0.23869632488181405,"rank":106,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.23497751078373164,"rank":106,"remainingConfigurations":398},{"removed":"automationbench","score":0.2370500104621932,"rank":106,"remainingConfigurations":398},{"removed":"critpt","score":0.23505392145742965,"rank":106,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23743673625741382,"rank":105,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2386272273311675,"rank":106,"remainingConfigurations":398},{"removed":"gdpval","score":0.23813287577923525,"rank":106,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23812449335594235,"rank":106,"remainingConfigurations":398},{"removed":"gpqa","score":0.2357330818776935,"rank":102,"remainingConfigurations":398},{"removed":"harvey","score":0.2354250794720152,"rank":105,"remainingConfigurations":398},{"removed":"hle","score":0.24390192833094312,"rank":105,"remainingConfigurations":398},{"removed":"ifbench","score":0.2407963797417708,"rank":100,"remainingConfigurations":398},{"removed":"itbench","score":0.23726327255977686,"rank":105,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23911045079117457,"rank":104,"remainingConfigurations":398},{"removed":"math500","score":0.2375068969380374,"rank":106,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.241612901851044,"rank":106,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24559737537995596,"rank":106,"remainingConfigurations":398},{"removed":"omniscience","score":0.2280873441031981,"rank":110,"remainingConfigurations":398},{"removed":"scicode","score":0.2395745247684421,"rank":107,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2472832506546098,"rank":100,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2363464444625036,"rank":106,"remainingConfigurations":398},{"removed":"arc-agi","score":0.28274825115062535,"rank":100,"remainingConfigurations":398},{"removed":"deepswe","score":0.2066683502145065,"rank":108,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23752694136394012,"rank":106,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2317786295858406,"rank":108,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24388672980301931,"rank":108,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23742977867932835,"rank":106,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2357882178521535,"rank":106,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23710805755006434,"rank":106,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2367204791968568,"rank":106,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23770812845528658,"rank":106,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23628332489962955,"rank":106,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2392406422363982,"rank":106,"remainingConfigurations":398},{"removed":"livebench-data","score":0.23763956120107524,"rank":106,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23492070730628664,"rank":106,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2365119884563741,"rank":106,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.24006005733765887,"rank":106,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23960596493297828,"rank":105,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2260779890418371,"rank":110,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23967181462233852,"rank":105,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24348756739867514,"rank":105,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.23670609809348642,"rank":106,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.236891761833096,"rank":105,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23693586324342722,"rank":106,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23715582209885225,"rank":106,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23629809328989013,"rank":105,"remainingConfigurations":398}]},"claude-opus-4-5-20251101--effort-reasoning":{"score":0.23493920596936355,"rank":107,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.27107288050401923,"rank":105,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20846356651019246,"rank":105,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23335361608009142,"rank":107,"remainingConfigurations":398},{"removed":"Scale","score":0.25122668035233,"rank":107,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23581113788270205,"rank":107,"remainingConfigurations":398},{"removed":"Cognition","score":0.2432201191481059,"rank":110,"remainingConfigurations":398},{"removed":"LiveBench","score":0.238003446736466,"rank":106,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23936366409899512,"rank":106,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23437791066522887,"rank":107,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22970415146311218,"rank":105,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.23494921773374164,"rank":107,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23474813721355717,"rank":107,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23460523162573263,"rank":107,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23493920596936355,"rank":107,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2343987773121534,"rank":107,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2353545496702971,"rank":107,"remainingConfigurations":398},{"removed":"briefcase","score":0.234152422593666,"rank":108,"remainingConfigurations":398},{"removed":"aime","score":0.23852819254013288,"rank":106,"remainingConfigurations":398},{"removed":"apex-agents","score":0.23652102391260674,"rank":107,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.22900664586768996,"rank":111,"remainingConfigurations":398},{"removed":"automationbench","score":0.23431291913473404,"rank":107,"remainingConfigurations":398},{"removed":"critpt","score":0.2342239497772323,"rank":107,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23485614622438736,"rank":107,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23664499956522267,"rank":107,"remainingConfigurations":398},{"removed":"gdpval","score":0.23568270471510522,"rank":107,"remainingConfigurations":398},{"removed":"gmmlu","score":0.22981522751836092,"rank":113,"remainingConfigurations":398},{"removed":"gpqa","score":0.23188293032492838,"rank":106,"remainingConfigurations":398},{"removed":"harvey","score":0.23277436721625133,"rank":106,"remainingConfigurations":398},{"removed":"hle","score":0.24106315847042828,"rank":107,"remainingConfigurations":398},{"removed":"ifbench","score":0.25248763002355906,"rank":97,"remainingConfigurations":398},{"removed":"itbench","score":0.23466279520229263,"rank":106,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23427715346633501,"rank":107,"remainingConfigurations":398},{"removed":"math500","score":0.23465040274684837,"rank":107,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.23623670099813865,"rank":109,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.25134634786763627,"rank":100,"remainingConfigurations":398},{"removed":"omniscience","score":0.2193547104732009,"rank":115,"remainingConfigurations":398},{"removed":"scicode","score":0.23778109819845641,"rank":108,"remainingConfigurations":398},{"removed":"tau-bench","score":0.23838363212077138,"rank":107,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2318122340788045,"rank":108,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2699914665567657,"rank":107,"remainingConfigurations":398},{"removed":"deepswe","score":0.20858838316891695,"rank":105,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23498647494018876,"rank":107,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23345719110606342,"rank":106,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2432201191481059,"rank":110,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23495760176762595,"rank":107,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23326677261835668,"rank":107,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23459795215720078,"rank":107,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2341902990693109,"rank":107,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23521814044528208,"rank":107,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23374433010900678,"rank":107,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23681250289386693,"rank":107,"remainingConfigurations":398},{"removed":"livebench-data","score":0.235199037022687,"rank":107,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23240854135094532,"rank":107,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23391259204658685,"rank":107,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23726042669728706,"rank":107,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23936366409899512,"rank":106,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.22660863357363606,"rank":109,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23694350685064905,"rank":106,"remainingConfigurations":398},{"removed":"simpleqa","score":0.24133270119507136,"rank":107,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2341581228651046,"rank":107,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.23439793965907565,"rank":107,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2342702836639824,"rank":107,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23472928333147328,"rank":107,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23384870239061195,"rank":107,"remainingConfigurations":398}]},"gpt-5.5--effort-low":{"score":0.23302707532263278,"rank":108,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2181797750911654,"rank":86,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.25619052017884264,"rank":111,"remainingConfigurations":398},{"removed":"Datacurve","score":0.22206691128074615,"rank":100,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23301225761847044,"rank":108,"remainingConfigurations":398},{"removed":"Scale","score":0.24720786472538261,"rank":109,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23188383868586224,"rank":110,"remainingConfigurations":398},{"removed":"Cognition","score":0.2434331345855633,"rank":109,"remainingConfigurations":398},{"removed":"LiveBench","score":0.23651507073304853,"rank":108,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23214790847571762,"rank":111,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.220278447473371,"rank":113,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22549936809697033,"rank":108,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.23307081834001567,"rank":108,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23273164093640186,"rank":108,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23297734068365575,"rank":108,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23302707532263278,"rank":108,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2327003975312403,"rank":108,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2333955941900471,"rank":108,"remainingConfigurations":398},{"removed":"briefcase","score":0.23272846242171155,"rank":109,"remainingConfigurations":398},{"removed":"aime","score":0.23743621120317301,"rank":108,"remainingConfigurations":398},{"removed":"apex-agents","score":0.234077353010089,"rank":108,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2321010204658213,"rank":108,"remainingConfigurations":398},{"removed":"automationbench","score":0.23254134051647865,"rank":109,"remainingConfigurations":398},{"removed":"critpt","score":0.23227245856369483,"rank":110,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23316484906554114,"rank":108,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23338687252565302,"rank":109,"remainingConfigurations":398},{"removed":"gdpval","score":0.23353734437587192,"rank":108,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23344860642575715,"rank":107,"remainingConfigurations":398},{"removed":"gpqa","score":0.2311714143858384,"rank":107,"remainingConfigurations":398},{"removed":"harvey","score":0.2314589995364229,"rank":107,"remainingConfigurations":398},{"removed":"hle","score":0.2397222548131196,"rank":109,"remainingConfigurations":398},{"removed":"ifbench","score":0.2348936321353887,"rank":105,"remainingConfigurations":398},{"removed":"itbench","score":0.2328054687180654,"rank":107,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23326803452366718,"rank":108,"remainingConfigurations":398},{"removed":"math500","score":0.23315441776505755,"rank":108,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2377486434769732,"rank":107,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24169572697045005,"rank":110,"remainingConfigurations":398},{"removed":"omniscience","score":0.22955317584114496,"rank":109,"remainingConfigurations":398},{"removed":"scicode","score":0.23437485365895197,"rank":110,"remainingConfigurations":398},{"removed":"tau-bench","score":0.23366706210335897,"rank":108,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.23172242547499708,"rank":109,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2544695699629507,"rank":112,"remainingConfigurations":398},{"removed":"deepswe","score":0.222101150761673,"rank":100,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2330800639985969,"rank":108,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23210340132961838,"rank":107,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2434331345855633,"rank":109,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23321680146871018,"rank":108,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23100505367295712,"rank":108,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23287275977031272,"rank":108,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23218708467966068,"rank":108,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23340892284870376,"rank":108,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23163937911018073,"rank":108,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23477854293312614,"rank":108,"remainingConfigurations":398},{"removed":"livebench-data","score":0.23316642485584083,"rank":108,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.23054696303333477,"rank":108,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23199900199379878,"rank":108,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23564993424503947,"rank":108,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23214790847571762,"rank":111,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2203301930723196,"rank":116,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23473614116033267,"rank":107,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2384572696045781,"rank":108,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2321839283979703,"rank":109,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2324469396233058,"rank":108,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2323984423810697,"rank":108,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23261652522952256,"rank":108,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23190019404184473,"rank":109,"remainingConfigurations":398}]},"claude-sonnet-4-6--effort-max":{"score":0.2322996393999656,"rank":109,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.21672822472643016,"rank":87,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21269761153150976,"rank":132,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20435272505230961,"rank":111,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23230631748218236,"rank":109,"remainingConfigurations":398},{"removed":"Scale","score":0.24637399845640115,"rank":110,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23195389663444343,"rank":109,"remainingConfigurations":398},{"removed":"Cognition","score":0.2729451798196827,"rank":94,"remainingConfigurations":398},{"removed":"LiveBench","score":0.23711925162518263,"rank":107,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23071261923881256,"rank":112,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2896803900297999,"rank":88,"remainingConfigurations":381},{"removed":"Vals AI","score":0.20150198059639657,"rank":118,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.23227155781912956,"rank":109,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23200096393188574,"rank":109,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2322455216290494,"rank":109,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2322996393999656,"rank":109,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23190090981080605,"rank":109,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23233887650742005,"rank":110,"remainingConfigurations":398},{"removed":"briefcase","score":0.23149013710067864,"rank":110,"remainingConfigurations":398},{"removed":"aime","score":0.22762642876992836,"rank":113,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2327143525186545,"rank":110,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.23024843756080685,"rank":110,"remainingConfigurations":398},{"removed":"automationbench","score":0.23292125259385055,"rank":108,"remainingConfigurations":398},{"removed":"critpt","score":0.2333258531947516,"rank":108,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2322760576621502,"rank":109,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23204610884833274,"rank":113,"remainingConfigurations":398},{"removed":"gdpval","score":0.23191600291620343,"rank":111,"remainingConfigurations":398},{"removed":"gmmlu","score":0.2326139282814017,"rank":108,"remainingConfigurations":398},{"removed":"gpqa","score":0.2332978395160142,"rank":104,"remainingConfigurations":398},{"removed":"harvey","score":0.2281892567741902,"rank":112,"remainingConfigurations":398},{"removed":"hle","score":0.23820641331616318,"rank":110,"remainingConfigurations":398},{"removed":"ifbench","score":0.2332086236266976,"rank":108,"remainingConfigurations":398},{"removed":"itbench","score":0.2310424089300082,"rank":109,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2324339261458351,"rank":109,"remainingConfigurations":398},{"removed":"math500","score":0.2324069207493751,"rank":109,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2372075536636186,"rank":108,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24337100082204868,"rank":108,"remainingConfigurations":398},{"removed":"omniscience","score":0.23173834110879735,"rank":106,"remainingConfigurations":398},{"removed":"scicode","score":0.2333883885798583,"rank":111,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2318095013911895,"rank":111,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.23620507442860808,"rank":107,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21182507428180997,"rank":131,"remainingConfigurations":398},{"removed":"deepswe","score":0.2045168466949779,"rank":111,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2323510764046418,"rank":109,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23174559490389054,"rank":109,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2729451798196827,"rank":94,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23285355969628518,"rank":109,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.23046250893365391,"rank":109,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2320738901427175,"rank":109,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23138526667807138,"rank":109,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23255326200892926,"rank":109,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.23069468348855382,"rank":109,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23412000846323341,"rank":109,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2329943557133668,"rank":109,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.22979265205922692,"rank":109,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.23120419408198611,"rank":109,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2347370099040229,"rank":109,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23071261923881256,"rank":112,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2349805764594712,"rank":104,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23102474316152866,"rank":112,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23806330233624176,"rank":109,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2327417537688643,"rank":108,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.22787196160618714,"rank":114,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.22988989924286837,"rank":111,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23042685753049855,"rank":111,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23379932420559904,"rank":108,"remainingConfigurations":398}]},"claude-opus-4-7--effort-non-reasoning":{"score":0.2314570699319134,"rank":110,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.266547741099669,"rank":107,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20550574185651327,"rank":110,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2299676359630515,"rank":112,"remainingConfigurations":398},{"removed":"Scale","score":0.24721128740985632,"rank":108,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23223468757941934,"rank":108,"remainingConfigurations":398},{"removed":"Cognition","score":0.23964195487094772,"rank":114,"remainingConfigurations":398},{"removed":"LiveBench","score":0.23482761008202843,"rank":110,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23620816992395788,"rank":108,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23015624382615996,"rank":111,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2266386072973893,"rank":107,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2314654361136338,"rank":110,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23126142412284947,"rank":110,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23113063063831296,"rank":111,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2314570699319134,"rank":110,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23091808570457795,"rank":111,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23236723047771193,"rank":109,"remainingConfigurations":398},{"removed":"briefcase","score":0.22362543074464303,"rank":113,"remainingConfigurations":398},{"removed":"aime","score":0.23100931882157041,"rank":110,"remainingConfigurations":398},{"removed":"apex-agents","score":0.23366782065315547,"rank":109,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2111537637083478,"rank":117,"remainingConfigurations":398},{"removed":"automationbench","score":0.2320328069669052,"rank":110,"remainingConfigurations":398},{"removed":"critpt","score":0.2272827426584644,"rank":114,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2320367687340162,"rank":110,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23451829077953135,"rank":108,"remainingConfigurations":398},{"removed":"gdpval","score":0.23258278467052076,"rank":109,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23234162323736707,"rank":109,"remainingConfigurations":398},{"removed":"gpqa","score":0.22199882409738822,"rank":113,"remainingConfigurations":398},{"removed":"harvey","score":0.22999520244670524,"rank":108,"remainingConfigurations":398},{"removed":"hle","score":0.2334012698082054,"rank":113,"remainingConfigurations":398},{"removed":"ifbench","score":0.27789172451531313,"rank":93,"remainingConfigurations":398},{"removed":"itbench","score":0.23181330097228114,"rank":108,"remainingConfigurations":398},{"removed":"livecodebench","score":0.22947109018571457,"rank":113,"remainingConfigurations":398},{"removed":"math500","score":0.23107211183529955,"rank":111,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2338228648786358,"rank":113,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.23737773317477143,"rank":114,"remainingConfigurations":398},{"removed":"omniscience","score":0.21748266524305634,"rank":117,"remainingConfigurations":398},{"removed":"scicode","score":0.23587735317688815,"rank":109,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2510171638205314,"rank":98,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2231940381135342,"rank":114,"remainingConfigurations":398},{"removed":"arc-agi","score":0.26520744180514155,"rank":108,"remainingConfigurations":398},{"removed":"deepswe","score":0.2056313341089787,"rank":110,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23150507326284916,"rank":110,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.23004974859512628,"rank":111,"remainingConfigurations":398},{"removed":"frontiercode","score":0.23964195487094772,"rank":114,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23159625549462703,"rank":111,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.22983778424883547,"rank":110,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.23113182311136463,"rank":111,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.23074300470979495,"rank":110,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2317307242532715,"rank":110,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2302719090623506,"rank":110,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23332672408601055,"rank":110,"remainingConfigurations":398},{"removed":"livebench-data","score":0.23173556581124388,"rank":111,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.22893506699927332,"rank":111,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2304323573805107,"rank":110,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23375207146990862,"rank":111,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23620816992395788,"rank":108,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.22310562992467198,"rank":114,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2331689611602343,"rank":108,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23772193096388985,"rank":110,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.23067760814618665,"rank":110,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2309262008839307,"rank":109,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23078247540278818,"rank":109,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23125629932005767,"rank":109,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23036403729420263,"rank":110,"remainingConfigurations":398}]},"claude-sonnet-5--effort-low":{"score":0.23129981769488142,"rank":111,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.23030667468245866,"rank":84,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22958544194513017,"rank":119,"remainingConfigurations":398},{"removed":"Datacurve","score":0.226572540227393,"rank":96,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.23113342201472875,"rank":110,"remainingConfigurations":398},{"removed":"Scale","score":0.24429474809712204,"rank":113,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2270924622929845,"rank":114,"remainingConfigurations":398},{"removed":"Cognition","score":0.1908781860841755,"rank":136,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2364318521011066,"rank":109,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.22588843581295096,"rank":114,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2551846468368691,"rank":96,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22138809117740577,"rank":112,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.23136589821172238,"rank":111,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2310754010527459,"rank":111,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.23124249617389922,"rank":110,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23129981769488142,"rank":111,"remainingConfigurations":398},{"removed":"All provider reports","score":0.23106329406922366,"rank":110,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23156643241187325,"rank":111,"remainingConfigurations":398},{"removed":"briefcase","score":0.22994802391232785,"rank":111,"remainingConfigurations":398},{"removed":"aime","score":0.22760505941795373,"rank":114,"remainingConfigurations":398},{"removed":"apex-agents","score":0.23239712548790467,"rank":111,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2344246355442202,"rank":107,"remainingConfigurations":398},{"removed":"automationbench","score":0.2315209217354358,"rank":111,"remainingConfigurations":398},{"removed":"critpt","score":0.23081362870580424,"rank":112,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23128287391721544,"rank":111,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23336789018121218,"rank":110,"remainingConfigurations":398},{"removed":"gdpval","score":0.23019742646327676,"rank":113,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23153050850113752,"rank":110,"remainingConfigurations":398},{"removed":"gpqa","score":0.23058277154893747,"rank":109,"remainingConfigurations":398},{"removed":"harvey","score":0.229631381153354,"rank":109,"remainingConfigurations":398},{"removed":"hle","score":0.2398042855161778,"rank":108,"remainingConfigurations":398},{"removed":"ifbench","score":0.22938730004770402,"rank":111,"remainingConfigurations":398},{"removed":"itbench","score":0.23099382853040898,"rank":110,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23105370965631647,"rank":110,"remainingConfigurations":398},{"removed":"math500","score":0.23123823743210856,"rank":110,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.23489582170843504,"rank":110,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24085697496181654,"rank":111,"remainingConfigurations":398},{"removed":"omniscience","score":0.23026498218391103,"rank":107,"remainingConfigurations":398},{"removed":"scicode","score":0.2303584759387237,"rank":113,"remainingConfigurations":398},{"removed":"tau-bench","score":0.22987084359537824,"rank":112,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.22694395121393618,"rank":113,"remainingConfigurations":398},{"removed":"arc-agi","score":0.23078877684925422,"rank":119,"remainingConfigurations":398},{"removed":"deepswe","score":0.2267484091821299,"rank":96,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23134896165990967,"rank":111,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2307591057612306,"rank":110,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1908781860841755,"rank":136,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23209680591393286,"rank":110,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.22887920568816755,"rank":111,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.231225375039095,"rank":110,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.22999322570843997,"rank":111,"remainingConfigurations":398},{"removed":"livebench-math","score":0.2314464940088343,"rank":111,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.22901081022922778,"rank":111,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2332280679112707,"rank":111,"remainingConfigurations":398},{"removed":"livebench-data","score":0.23192242427308085,"rank":110,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.22929678640436904,"rank":110,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.22983922951034294,"rank":111,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23436658152257203,"rank":110,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.22588843581295096,"rank":114,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.23813370319022822,"rank":100,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23095934155822395,"rank":113,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23615345420086054,"rank":112,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2306242338690664,"rank":111,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2307272058304136,"rank":110,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.23052698112768466,"rank":110,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.23087126763140162,"rank":110,"remainingConfigurations":398},{"removed":"vibe-code","score":0.23034379895691526,"rank":111,"remainingConfigurations":398}]},"gpt-5.3-codex--effort-xhigh":{"score":0.23025253409883203,"rank":112,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.047784817639114165,"rank":144,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22562437618133882,"rank":122,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20628008282411667,"rank":109,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.22940611066543273,"rank":113,"remainingConfigurations":398},{"removed":"Scale","score":0.24636008295588155,"rank":111,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.23033066185559803,"rank":111,"remainingConfigurations":398},{"removed":"Cognition","score":0.24014370417542455,"rank":112,"remainingConfigurations":398},{"removed":"LiveBench","score":0.228489624286117,"rank":113,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.329654044929141,"rank":78,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2329829968950012,"rank":108,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22516043517570306,"rank":109,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2302599007907947,"rank":112,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.23035916985736846,"rank":112,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.22991019853687036,"rank":112,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.23025253409883203,"rank":112,"remainingConfigurations":398},{"removed":"All provider reports","score":0.229997911833712,"rank":112,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2309204297921228,"rank":112,"remainingConfigurations":398},{"removed":"briefcase","score":0.2375611982833924,"rank":105,"remainingConfigurations":398},{"removed":"aime","score":0.23032587825490572,"rank":111,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2321136022787881,"rank":112,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.22131472141976868,"rank":113,"remainingConfigurations":398},{"removed":"automationbench","score":0.23047250816744605,"rank":112,"remainingConfigurations":398},{"removed":"critpt","score":0.2255052867507503,"rank":115,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.23056556917585738,"rank":112,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23243336390448002,"rank":111,"remainingConfigurations":398},{"removed":"gdpval","score":0.23130655076066683,"rank":112,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23107345929651038,"rank":112,"remainingConfigurations":398},{"removed":"gpqa","score":0.2246271559937413,"rank":112,"remainingConfigurations":398},{"removed":"harvey","score":0.22861333867851208,"rank":110,"remainingConfigurations":398},{"removed":"hle","score":0.23259666855296487,"rank":114,"remainingConfigurations":398},{"removed":"ifbench","score":0.22941145976501656,"rank":110,"remainingConfigurations":398},{"removed":"itbench","score":0.23024563288320496,"rank":111,"remainingConfigurations":398},{"removed":"livecodebench","score":0.22989210282178899,"rank":112,"remainingConfigurations":398},{"removed":"math500","score":0.23060834362528362,"rank":112,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2342216343340581,"rank":111,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.24171655949404472,"rank":109,"remainingConfigurations":398},{"removed":"omniscience","score":0.2212285012888788,"rank":113,"remainingConfigurations":398},{"removed":"scicode","score":0.23331755102564286,"rank":112,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2419922626310461,"rank":103,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.22961634026246802,"rank":110,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2247924253143904,"rank":122,"remainingConfigurations":398},{"removed":"deepswe","score":0.2063702354963722,"rank":109,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.23029002420548014,"rank":112,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2288820007930732,"rank":112,"remainingConfigurations":398},{"removed":"frontiercode","score":0.24014370417542455,"rank":112,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.2307387506269157,"rank":112,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.22807298047597654,"rank":113,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2300028813925099,"rank":112,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2297633483393815,"rank":112,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23049503120800932,"rank":112,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.22897153516968186,"rank":112,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23171557629496373,"rank":113,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2306045253521428,"rank":112,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.22789151368489757,"rank":112,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.22895500255673704,"rank":112,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23312600001727649,"rank":112,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.329654044929141,"rank":78,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.22313895746900725,"rank":113,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23169375112429794,"rank":111,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23632464970572567,"rank":111,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.22950410831343648,"rank":112,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.22971918789754484,"rank":111,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2296021657020968,"rank":112,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.22999736576034932,"rank":112,"remainingConfigurations":398},{"removed":"vibe-code","score":0.22915372122241282,"rank":112,"remainingConfigurations":398}]},"deepseek-v4-flash-0424--effort-high":{"score":0.2299105425604798,"rank":113,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.26051316005308095,"rank":109,"remainingConfigurations":398},{"removed":"Datacurve","score":0.20154176494026663,"rank":112,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.22859062700488922,"rank":114,"remainingConfigurations":398},{"removed":"Scale","score":0.24530593439452444,"rank":112,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2302437623921456,"rank":112,"remainingConfigurations":398},{"removed":"Cognition","score":0.23474365566137032,"rank":115,"remainingConfigurations":398},{"removed":"LiveBench","score":0.233039178786167,"rank":111,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.23457211906461173,"rank":110,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2316772265730105,"rank":109,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22407069728285275,"rank":110,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.22991473513382987,"rank":113,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.22970480108599567,"rank":113,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.22956371091370045,"rank":113,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.2299105425604798,"rank":113,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2293369844072061,"rank":113,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.23060603739504373,"rank":113,"remainingConfigurations":398},{"removed":"briefcase","score":0.2224296132810343,"rank":114,"remainingConfigurations":398},{"removed":"aime","score":0.23031008902249642,"rank":112,"remainingConfigurations":398},{"removed":"apex-agents","score":0.23199501126113675,"rank":113,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2361175402453636,"rank":105,"remainingConfigurations":398},{"removed":"automationbench","score":0.22462675020847625,"rank":114,"remainingConfigurations":398},{"removed":"critpt","score":0.23143884676226598,"rank":111,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.22979079775737934,"rank":113,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.23232141610554302,"rank":112,"remainingConfigurations":398},{"removed":"gdpval","score":0.23200517720154398,"rank":110,"remainingConfigurations":398},{"removed":"gmmlu","score":0.23143268576682288,"rank":111,"remainingConfigurations":398},{"removed":"gpqa","score":0.22486078090873418,"rank":111,"remainingConfigurations":398},{"removed":"harvey","score":0.2279383853067377,"rank":113,"remainingConfigurations":398},{"removed":"hle","score":0.23411915020301513,"rank":112,"remainingConfigurations":398},{"removed":"ifbench","score":0.22471669173575748,"rank":113,"remainingConfigurations":398},{"removed":"itbench","score":0.22981954262688264,"rank":112,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2292472533946386,"rank":114,"remainingConfigurations":398},{"removed":"math500","score":0.22987101089699805,"rank":113,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.23374801538863169,"rank":114,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.23967576397530518,"rank":112,"remainingConfigurations":398},{"removed":"omniscience","score":0.2297639669239229,"rank":108,"remainingConfigurations":398},{"removed":"scicode","score":0.24909073754430586,"rank":100,"remainingConfigurations":398},{"removed":"tau-bench","score":0.21982583634779665,"rank":115,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.22918723211754197,"rank":111,"remainingConfigurations":398},{"removed":"arc-agi","score":0.26030772843939526,"rank":110,"remainingConfigurations":398},{"removed":"deepswe","score":0.2016679898973596,"rank":112,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2299627538928903,"rank":113,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.22855288111130911,"rank":113,"remainingConfigurations":398},{"removed":"frontiercode","score":0.23474365566137032,"rank":115,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.23002678038530364,"rank":113,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.22824560890266266,"rank":112,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.22959445661456335,"rank":113,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.22911838769337503,"rank":113,"remainingConfigurations":398},{"removed":"livebench-math","score":0.23018268169432765,"rank":113,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.22872399495404275,"rank":113,"remainingConfigurations":398},{"removed":"livebench-language","score":0.23179688124513909,"rank":112,"remainingConfigurations":398},{"removed":"livebench-data","score":0.23022219802565314,"rank":113,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2273710075279115,"rank":113,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.22887827313761755,"rank":113,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23218742528124162,"rank":113,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.23457211906461173,"rank":110,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.22293217634255133,"rank":115,"remainingConfigurations":398},{"removed":"frontiermath","score":0.23169597985897086,"rank":110,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23607768212957006,"rank":113,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2291261936318263,"rank":113,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.22939048062277353,"rank":112,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.22923393948356044,"rank":113,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.22973019838052447,"rank":113,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2288103231963017,"rank":113,"remainingConfigurations":398}]},"gemini-3.6-flash--effort-low":{"score":0.22889990862315232,"rank":114,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.22243463467920643,"rank":85,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2382103334595678,"rank":116,"remainingConfigurations":398},{"removed":"Datacurve","score":0.18799310352338783,"rank":116,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2299814466528692,"rank":111,"remainingConfigurations":398},{"removed":"Scale","score":0.2433212641275386,"rank":114,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.22727633620480692,"rank":113,"remainingConfigurations":398},{"removed":"Cognition","score":0.259583819888864,"rank":99,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2324638479539448,"rank":112,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.22719156137189536,"rank":113,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.21609208466860838,"rank":115,"remainingConfigurations":381},{"removed":"Vals AI","score":0.22395476745276824,"rank":111,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2288838871457197,"rank":114,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.22843607502758667,"rank":114,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2287596467086641,"rank":114,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.22889990862315232,"rank":114,"remainingConfigurations":398},{"removed":"All provider reports","score":0.22825952857152068,"rank":114,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.22912161448882928,"rank":114,"remainingConfigurations":398},{"removed":"briefcase","score":0.2287669776725353,"rank":112,"remainingConfigurations":398},{"removed":"aime","score":0.23292869279047534,"rank":109,"remainingConfigurations":398},{"removed":"apex-agents","score":0.22974255696656432,"rank":114,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2287652602640201,"rank":112,"remainingConfigurations":398},{"removed":"automationbench","score":0.22841922094862943,"rank":113,"remainingConfigurations":398},{"removed":"critpt","score":0.2288012606156231,"rank":113,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.22887676176347335,"rank":114,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2295885334208406,"rank":114,"remainingConfigurations":398},{"removed":"gdpval","score":0.22898006128493975,"rank":114,"remainingConfigurations":398},{"removed":"gmmlu","score":0.22901689137369452,"rank":114,"remainingConfigurations":398},{"removed":"gpqa","score":0.22782192364958223,"rank":110,"remainingConfigurations":398},{"removed":"harvey","score":0.22620287928907193,"rank":114,"remainingConfigurations":398},{"removed":"hle","score":0.23549161416025208,"rank":111,"remainingConfigurations":398},{"removed":"ifbench","score":0.2275761769059673,"rank":112,"remainingConfigurations":398},{"removed":"itbench","score":0.2286331967585993,"rank":113,"remainingConfigurations":398},{"removed":"livecodebench","score":0.23004225466964365,"rank":111,"remainingConfigurations":398},{"removed":"math500","score":0.2290240377308299,"rank":114,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.23387304156412056,"rank":112,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.23859231324322785,"rank":113,"remainingConfigurations":398},{"removed":"omniscience","score":0.22715076337969317,"rank":111,"remainingConfigurations":398},{"removed":"scicode","score":0.2298389029272114,"rank":114,"remainingConfigurations":398},{"removed":"tau-bench","score":0.22769946264214913,"rank":113,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.22813246440576243,"rank":112,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2379385737873746,"rank":116,"remainingConfigurations":398},{"removed":"deepswe","score":0.18809784668390864,"rank":116,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.22894138566177913,"rank":114,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2260827747992059,"rank":114,"remainingConfigurations":398},{"removed":"frontiercode","score":0.259583819888864,"rank":99,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.22919951187865895,"rank":114,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.22716179048482973,"rank":114,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.22860226780467974,"rank":114,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.22820148969974477,"rank":114,"remainingConfigurations":398},{"removed":"livebench-math","score":0.22918936431146109,"rank":114,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.22768733764948001,"rank":114,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2304180970435864,"rank":114,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2295593194309231,"rank":114,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.22641805536098417,"rank":114,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.22788213577138106,"rank":114,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.23113669631116016,"rank":114,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.22719156137189536,"rank":113,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.21379681484089483,"rank":117,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2321813004528117,"rank":109,"remainingConfigurations":398},{"removed":"simpleqa","score":0.23431905480468465,"rank":114,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.22784049756314742,"rank":114,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.22846035387474664,"rank":113,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.2282073731050277,"rank":114,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.22870189828080054,"rank":114,"remainingConfigurations":398},{"removed":"vibe-code","score":0.22786070141609271,"rank":114,"remainingConfigurations":398}]},"claude-opus-4-8--effort-non-reasoning":{"score":0.21954898014263957,"rank":115,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.2151292554685816,"rank":88,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2505074261972006,"rank":112,"remainingConfigurations":398},{"removed":"Datacurve","score":0.19055162484721644,"rank":114,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.21912182262458435,"rank":115,"remainingConfigurations":398},{"removed":"Scale","score":0.23285397447219716,"rank":115,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.2200121744812703,"rank":115,"remainingConfigurations":398},{"removed":"Cognition","score":0.23305930528157306,"rank":116,"remainingConfigurations":398},{"removed":"LiveBench","score":0.22161512614542458,"rank":114,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2205381904532283,"rank":115,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.21182550999559244,"rank":113,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.21953249305747527,"rank":115,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.21921944314001407,"rank":115,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.21938690264405283,"rank":115,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.21954898014263957,"rank":115,"remainingConfigurations":398},{"removed":"All provider reports","score":0.21902127315446532,"rank":115,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.21990826383405482,"rank":115,"remainingConfigurations":398},{"removed":"briefcase","score":0.21935109538554418,"rank":115,"remainingConfigurations":398},{"removed":"aime","score":0.1835266574973139,"rank":132,"remainingConfigurations":398},{"removed":"apex-agents","score":0.2206747073876897,"rank":116,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.22009093596259946,"rank":114,"remainingConfigurations":398},{"removed":"automationbench","score":0.2194596835845125,"rank":115,"remainingConfigurations":398},{"removed":"critpt","score":0.21780723685561185,"rank":116,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2197018270740616,"rank":115,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.22051125116851358,"rank":116,"remainingConfigurations":398},{"removed":"gdpval","score":0.218785917131608,"rank":116,"remainingConfigurations":398},{"removed":"gmmlu","score":0.22031567152264878,"rank":115,"remainingConfigurations":398},{"removed":"gpqa","score":0.21904385860678965,"rank":114,"remainingConfigurations":398},{"removed":"harvey","score":0.2175961245066431,"rank":115,"remainingConfigurations":398},{"removed":"hle","score":0.22493859010664782,"rank":116,"remainingConfigurations":398},{"removed":"ifbench","score":0.21967712179599375,"rank":115,"remainingConfigurations":398},{"removed":"itbench","score":0.21924244783042357,"rank":115,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2197341204253407,"rank":115,"remainingConfigurations":398},{"removed":"math500","score":0.21982610998368537,"rank":115,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.22423094676148028,"rank":115,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2289496777939171,"rank":115,"remainingConfigurations":398},{"removed":"omniscience","score":0.21940195926320685,"rank":114,"remainingConfigurations":398},{"removed":"scicode","score":0.2210247155757521,"rank":115,"remainingConfigurations":398},{"removed":"tau-bench","score":0.21466492826520622,"rank":117,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.22003567445524572,"rank":115,"remainingConfigurations":398},{"removed":"arc-agi","score":0.25107113076355914,"rank":113,"remainingConfigurations":398},{"removed":"deepswe","score":0.19069831976004167,"rank":114,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2195887650821,"rank":115,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.2183948447702635,"rank":115,"remainingConfigurations":398},{"removed":"frontiercode","score":0.23305930528157306,"rank":116,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.22004258903323803,"rank":115,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.2177670992095657,"rank":115,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.2192691441266185,"rank":115,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.21887621007629376,"rank":115,"remainingConfigurations":398},{"removed":"livebench-math","score":0.22002825746404187,"rank":115,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.21774654551171038,"rank":115,"remainingConfigurations":398},{"removed":"livebench-language","score":0.22131064187068863,"rank":115,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2200159738318698,"rank":115,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.21732577706062758,"rank":115,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2184602899257909,"rank":115,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.22193698482286686,"rank":115,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2205381904532283,"rank":115,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.24112125307627705,"rank":99,"remainingConfigurations":398},{"removed":"frontiermath","score":0.22186705193730785,"rank":116,"remainingConfigurations":398},{"removed":"simpleqa","score":0.22323427349192684,"rank":115,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2188134438434044,"rank":115,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.21912124812406555,"rank":115,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.21871604833640443,"rank":115,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.21938568717293652,"rank":115,"remainingConfigurations":398},{"removed":"vibe-code","score":0.21868144181686067,"rank":115,"remainingConfigurations":398}]},"gpt-5.1--effort-high":{"score":0.21731156620193237,"rank":116,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.20290995322290648,"rank":91,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2620735423720463,"rank":108,"remainingConfigurations":398},{"removed":"Datacurve","score":0.18844631134378523,"rank":115,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.21835534934968517,"rank":116,"remainingConfigurations":398},{"removed":"Scale","score":0.23258507748413246,"rank":116,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.21682362073725858,"rank":116,"remainingConfigurations":398},{"removed":"Cognition","score":0.22345589849015277,"rank":117,"remainingConfigurations":398},{"removed":"LiveBench","score":0.2197347583509802,"rank":115,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2190496093439124,"rank":116,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.21264438249304166,"rank":116,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2099614728871221,"rank":115,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.21731825026596288,"rank":116,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.21702190857778705,"rank":116,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2170661826092998,"rank":116,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.21731156620193237,"rank":116,"remainingConfigurations":398},{"removed":"All provider reports","score":0.2167605293121223,"rank":116,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.21766238932821302,"rank":116,"remainingConfigurations":398},{"removed":"briefcase","score":0.21698286576653092,"rank":116,"remainingConfigurations":398},{"removed":"aime","score":0.21792349974255598,"rank":115,"remainingConfigurations":398},{"removed":"apex-agents","score":0.21857936420225552,"rank":118,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2118666038105058,"rank":116,"remainingConfigurations":398},{"removed":"automationbench","score":0.2169427513702563,"rank":116,"remainingConfigurations":398},{"removed":"critpt","score":0.21653947253974026,"rank":117,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2173213602841513,"rank":116,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.21855057736211134,"rank":117,"remainingConfigurations":398},{"removed":"gdpval","score":0.22304131295359708,"rank":115,"remainingConfigurations":398},{"removed":"gmmlu","score":0.2153672862211959,"rank":116,"remainingConfigurations":398},{"removed":"gpqa","score":0.2150286747611753,"rank":116,"remainingConfigurations":398},{"removed":"harvey","score":0.2154375417589355,"rank":116,"remainingConfigurations":398},{"removed":"hle","score":0.22520999815702888,"rank":115,"remainingConfigurations":398},{"removed":"ifbench","score":0.21400181816781794,"rank":116,"remainingConfigurations":398},{"removed":"itbench","score":0.21713832483674303,"rank":116,"remainingConfigurations":398},{"removed":"livecodebench","score":0.21883880575461753,"rank":116,"remainingConfigurations":398},{"removed":"math500","score":0.21760409112881418,"rank":116,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2219072200509901,"rank":116,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.22715327469257673,"rank":116,"remainingConfigurations":398},{"removed":"omniscience","score":0.21183133134843402,"rank":120,"remainingConfigurations":398},{"removed":"scicode","score":0.21933471724769207,"rank":116,"remainingConfigurations":398},{"removed":"tau-bench","score":0.22051586842173862,"rank":114,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.21846414728029814,"rank":116,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2610114649136513,"rank":109,"remainingConfigurations":398},{"removed":"deepswe","score":0.1885424967437137,"rank":115,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.21735293283608306,"rank":116,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.21257574509935082,"rank":116,"remainingConfigurations":398},{"removed":"frontiercode","score":0.22345589849015277,"rank":117,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.21731575630090727,"rank":116,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.21570871330519348,"rank":116,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.21698074912754092,"rank":116,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.21659275234998962,"rank":116,"remainingConfigurations":398},{"removed":"livebench-math","score":0.21754455448631974,"rank":116,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.21616739689439435,"rank":116,"remainingConfigurations":398},{"removed":"livebench-language","score":0.21902096644931277,"rank":116,"remainingConfigurations":398},{"removed":"livebench-data","score":0.2174834533440845,"rank":116,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.21485980730893328,"rank":116,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.21636527609502476,"rank":116,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.21972997428424912,"rank":116,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2190496093439124,"rank":116,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.20714499914296647,"rank":119,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2192545508182848,"rank":117,"remainingConfigurations":398},{"removed":"simpleqa","score":0.22311591336274295,"rank":116,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.21655767427665465,"rank":116,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2167520571718967,"rank":116,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.21676068317666838,"rank":116,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2170202440628853,"rank":116,"remainingConfigurations":398},{"removed":"vibe-code","score":0.21619297685562167,"rank":116,"remainingConfigurations":398}]},"claude-opus-4-5-20251101--effort-thinking-32k":{"score":0.210410723714046,"rank":117,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.20737393281935468,"rank":89,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21561448178460343,"rank":129,"remainingConfigurations":398},{"removed":"Datacurve","score":0.17959985957318306,"rank":119,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.21192059859604795,"rank":117,"remainingConfigurations":398},{"removed":"Scale","score":0.22295831829326865,"rank":117,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.20971650479840823,"rank":117,"remainingConfigurations":398},{"removed":"Cognition","score":0.22012187631443955,"rank":119,"remainingConfigurations":398},{"removed":"LiveBench","score":0.21313959936649288,"rank":116,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.20957920332471888,"rank":119,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.2023350963928355,"rank":116,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.2102867452700762,"rank":117,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2101080486740096,"rank":117,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.21114971951556238,"rank":117,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.210410723714046,"rank":117,"remainingConfigurations":398},{"removed":"All provider reports","score":0.21070163433213876,"rank":117,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.21065930090596655,"rank":117,"remainingConfigurations":398},{"removed":"briefcase","score":0.21014607542325428,"rank":117,"remainingConfigurations":398},{"removed":"aime","score":0.21581056697695353,"rank":116,"remainingConfigurations":398},{"removed":"apex-agents","score":0.21108611982411787,"rank":119,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.21042095073668596,"rank":118,"remainingConfigurations":398},{"removed":"automationbench","score":0.21018141586528774,"rank":117,"remainingConfigurations":398},{"removed":"critpt","score":0.21149001120285213,"rank":119,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.21040096763472235,"rank":117,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.21124962078653073,"rank":118,"remainingConfigurations":398},{"removed":"gdpval","score":0.21015443889017962,"rank":117,"remainingConfigurations":398},{"removed":"gmmlu","score":0.21048784073083174,"rank":117,"remainingConfigurations":398},{"removed":"gpqa","score":0.19640173515086237,"rank":121,"remainingConfigurations":398},{"removed":"harvey","score":0.2081700925226285,"rank":118,"remainingConfigurations":398},{"removed":"hle","score":0.21502014756744944,"rank":119,"remainingConfigurations":398},{"removed":"ifbench","score":0.20972757271395004,"rank":117,"remainingConfigurations":398},{"removed":"itbench","score":0.21007341311168037,"rank":117,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2119609716557506,"rank":117,"remainingConfigurations":398},{"removed":"math500","score":0.21052823549174174,"rank":117,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.21452278935483385,"rank":117,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.22005555569933566,"rank":117,"remainingConfigurations":398},{"removed":"omniscience","score":0.20908851057646868,"rank":121,"remainingConfigurations":398},{"removed":"scicode","score":0.21146557966591548,"rank":117,"remainingConfigurations":398},{"removed":"tau-bench","score":0.2087524757601138,"rank":119,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.21062207145453582,"rank":118,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21571508969496975,"rank":127,"remainingConfigurations":398},{"removed":"deepswe","score":0.1797600097137028,"rank":119,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.21043807489392133,"rank":117,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.20704207558262933,"rank":117,"remainingConfigurations":398},{"removed":"frontiercode","score":0.22012187631443955,"rank":119,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.21033737304602076,"rank":117,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.20880035731297905,"rank":117,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.21007979028182855,"rank":117,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.20984149793665355,"rank":117,"remainingConfigurations":398},{"removed":"livebench-math","score":0.21045197926114087,"rank":117,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2086125106979834,"rank":117,"remainingConfigurations":398},{"removed":"livebench-language","score":0.21253162883832546,"rank":117,"remainingConfigurations":398},{"removed":"livebench-data","score":0.21099546559906648,"rank":117,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.20823106898879787,"rank":117,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.2093462653693817,"rank":117,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.2126941890191413,"rank":117,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.20957920332471888,"rank":119,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.23300748590588974,"rank":106,"remainingConfigurations":398},{"removed":"frontiermath","score":0.22902456352766987,"rank":114,"remainingConfigurations":398},{"removed":"simpleqa","score":0.2025025008522342,"rank":121,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.20948482897863605,"rank":117,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.21014889012112525,"rank":117,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.20965139497132587,"rank":117,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2103275506610085,"rank":117,"remainingConfigurations":398},{"removed":"vibe-code","score":0.2094045264224087,"rank":117,"remainingConfigurations":398}]},"mimo-v2.5-pro--effort-reasoning":{"score":0.20787716378710128,"rank":118,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2367784102712549,"rank":117,"remainingConfigurations":398},{"removed":"Datacurve","score":0.18204754090672046,"rank":118,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2066574716748335,"rank":118,"remainingConfigurations":398},{"removed":"Scale","score":0.2224162497727875,"rank":118,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.20805021693191808,"rank":118,"remainingConfigurations":398},{"removed":"Cognition","score":0.21389074355846485,"rank":120,"remainingConfigurations":398},{"removed":"LiveBench","score":0.21087110607511572,"rank":117,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.21165460153263102,"rank":118,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.20899203187961732,"rank":117,"remainingConfigurations":381},{"removed":"Vals AI","score":0.20214326085062514,"rank":117,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.20788027028708933,"rank":118,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2076702246143224,"rank":118,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.20752529698743816,"rank":118,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.20787716378710128,"rank":118,"remainingConfigurations":398},{"removed":"All provider reports","score":0.20729689475766264,"rank":118,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2016549898895077,"rank":120,"remainingConfigurations":398},{"removed":"briefcase","score":0.20587095796870816,"rank":118,"remainingConfigurations":398},{"removed":"aime","score":0.20778389956969678,"rank":119,"remainingConfigurations":398},{"removed":"apex-agents","score":0.22529223143927238,"rank":115,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.2026899720758061,"rank":120,"remainingConfigurations":398},{"removed":"automationbench","score":0.20969181787943003,"rank":118,"remainingConfigurations":398},{"removed":"critpt","score":0.2076115047833348,"rank":121,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.20804885423638897,"rank":118,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.22067910578231287,"rank":115,"remainingConfigurations":398},{"removed":"gdpval","score":0.20289461488909832,"rank":119,"remainingConfigurations":398},{"removed":"gmmlu","score":0.20848678216349206,"rank":118,"remainingConfigurations":398},{"removed":"gpqa","score":0.20279185245434272,"rank":119,"remainingConfigurations":398},{"removed":"harvey","score":0.20932975353536398,"rank":117,"remainingConfigurations":398},{"removed":"hle","score":0.20943196589129742,"rank":120,"remainingConfigurations":398},{"removed":"ifbench","score":0.19683970435955003,"rank":119,"remainingConfigurations":398},{"removed":"itbench","score":0.19951362464215303,"rank":121,"remainingConfigurations":398},{"removed":"livecodebench","score":0.20711345585576058,"rank":118,"remainingConfigurations":398},{"removed":"math500","score":0.20800063630558288,"rank":118,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.21159516634540967,"rank":118,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.21707096465802,"rank":118,"remainingConfigurations":398},{"removed":"omniscience","score":0.21815975639754695,"rank":116,"remainingConfigurations":398},{"removed":"scicode","score":0.2023497407370987,"rank":122,"remainingConfigurations":398},{"removed":"tau-bench","score":0.21088468208923739,"rank":118,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.2113573722213484,"rank":117,"remainingConfigurations":398},{"removed":"arc-agi","score":0.23580005237016888,"rank":117,"remainingConfigurations":398},{"removed":"deepswe","score":0.18217737221890626,"rank":118,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.20792209670708708,"rank":118,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.20667260275830615,"rank":118,"remainingConfigurations":398},{"removed":"frontiercode","score":0.21389074355846485,"rank":120,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.20797284647175884,"rank":118,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.20635111842766285,"rank":118,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.20758079137260585,"rank":118,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2071782748574881,"rank":118,"remainingConfigurations":398},{"removed":"livebench-math","score":0.20812639925270296,"rank":118,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.20679518312373046,"rank":118,"remainingConfigurations":398},{"removed":"livebench-language","score":0.20967817215572615,"rank":118,"remainingConfigurations":398},{"removed":"livebench-data","score":0.20813151308321545,"rank":118,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.2054795587996858,"rank":118,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.20691991695293796,"rank":118,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.21000578475690942,"rank":118,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.21165460153263102,"rank":118,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2010469168437797,"rank":121,"remainingConfigurations":398},{"removed":"frontiermath","score":0.2092048821034206,"rank":119,"remainingConfigurations":398},{"removed":"simpleqa","score":0.21371274207182067,"rank":117,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.20714610389075291,"rank":118,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2073701756554173,"rank":118,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.20723808039017114,"rank":118,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2076879515414283,"rank":118,"remainingConfigurations":398},{"removed":"vibe-code","score":0.20685893446402245,"rank":118,"remainingConfigurations":398}]},"kimi-k3--effort-low":{"score":0.20513417721002192,"rank":119,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14668909337447175,"rank":108,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2588306550569193,"rank":110,"remainingConfigurations":398},{"removed":"Datacurve","score":0.17764547550169654,"rank":120,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.2050817906603979,"rank":119,"remainingConfigurations":398},{"removed":"Scale","score":0.2194687862965522,"rank":119,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.20459512046679726,"rank":119,"remainingConfigurations":398},{"removed":"Cognition","score":0.21264295729423602,"rank":121,"remainingConfigurations":398},{"removed":"LiveBench","score":0.20734399921376698,"rank":118,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.20644273652037057,"rank":120,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23911293607881481,"rank":105,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1986652609469177,"rank":119,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.20513858762674675,"rank":119,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.20501629590173043,"rank":119,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2049078899397687,"rank":119,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.20513417721002192,"rank":119,"remainingConfigurations":398},{"removed":"All provider reports","score":0.20477178811909513,"rank":119,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.20566488282957918,"rank":118,"remainingConfigurations":398},{"removed":"briefcase","score":0.20448410052238838,"rank":119,"remainingConfigurations":398},{"removed":"aime","score":0.21255098023583083,"rank":117,"remainingConfigurations":398},{"removed":"apex-agents","score":0.20653165271569918,"rank":120,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.20435242204954818,"rank":119,"remainingConfigurations":398},{"removed":"automationbench","score":0.20228257182171996,"rank":119,"remainingConfigurations":398},{"removed":"critpt","score":0.20801303719468808,"rank":120,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.20543441526539485,"rank":119,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.20262020157373417,"rank":120,"remainingConfigurations":398},{"removed":"gdpval","score":0.2057002508157314,"rank":118,"remainingConfigurations":398},{"removed":"gmmlu","score":0.2055666201044255,"rank":119,"remainingConfigurations":398},{"removed":"gpqa","score":0.19656411065727433,"rank":120,"remainingConfigurations":398},{"removed":"harvey","score":0.20359928302415883,"rank":119,"remainingConfigurations":398},{"removed":"hle","score":0.21524062180456235,"rank":118,"remainingConfigurations":398},{"removed":"ifbench","score":0.20313223500883462,"rank":118,"remainingConfigurations":398},{"removed":"itbench","score":0.20507819257339135,"rank":118,"remainingConfigurations":398},{"removed":"livecodebench","score":0.2055082108318117,"rank":119,"remainingConfigurations":398},{"removed":"math500","score":0.20537914422571002,"rank":119,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.20944431549483478,"rank":119,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2150916811094734,"rank":120,"remainingConfigurations":398},{"removed":"omniscience","score":0.2037603290882295,"rank":124,"remainingConfigurations":398},{"removed":"scicode","score":0.2043695227916783,"rank":118,"remainingConfigurations":398},{"removed":"tau-bench","score":0.20134622316175788,"rank":120,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.20289866731554249,"rank":119,"remainingConfigurations":398},{"removed":"arc-agi","score":0.25830686903238026,"rank":111,"remainingConfigurations":398},{"removed":"deepswe","score":0.17773981332390543,"rank":120,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.20517424262583195,"rank":119,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.20183367083948292,"rank":119,"remainingConfigurations":398},{"removed":"frontiercode","score":0.21264295729423602,"rank":121,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.20530801626033782,"rank":119,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.20351998782202008,"rank":119,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.20484634030988377,"rank":119,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.2045516959003025,"rank":119,"remainingConfigurations":398},{"removed":"livebench-math","score":0.20542377197306186,"rank":119,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.20387850429406543,"rank":119,"remainingConfigurations":398},{"removed":"livebench-language","score":0.20679640205049532,"rank":119,"remainingConfigurations":398},{"removed":"livebench-data","score":0.20540803823783163,"rank":119,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.20280668240583077,"rank":119,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.20418651913662786,"rank":119,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.20743465289185373,"rank":119,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.20644273652037057,"rank":120,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.20206206642115934,"rank":120,"remainingConfigurations":398},{"removed":"frontiermath","score":0.20540913160429744,"rank":120,"remainingConfigurations":398},{"removed":"simpleqa","score":0.20982362236445226,"rank":118,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.20439995938724018,"rank":119,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.20461290636189433,"rank":119,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.20452929898259675,"rank":119,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.20489343288342024,"rank":119,"remainingConfigurations":398},{"removed":"vibe-code","score":0.204102741597908,"rank":119,"remainingConfigurations":398}]},"glm-5--effort-reasoning":{"score":0.20164072839157446,"rank":120,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.23186320470637864,"rank":118,"remainingConfigurations":398},{"removed":"Datacurve","score":0.17726187773797045,"rank":121,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.20034421144197476,"rank":120,"remainingConfigurations":398},{"removed":"Scale","score":0.21608249469477347,"rank":120,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.20214790879962896,"rank":120,"remainingConfigurations":398},{"removed":"Cognition","score":0.20848773654507358,"rank":122,"remainingConfigurations":398},{"removed":"LiveBench","score":0.20375384286336728,"rank":119,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.20604794142337532,"rank":121,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.20349347727596442,"rank":119,"remainingConfigurations":381},{"removed":"Vals AI","score":0.196096725412139,"rank":120,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.20164915499747713,"rank":120,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.2014853369818945,"rank":120,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.2013473546356439,"rank":120,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.20164072839157446,"rank":120,"remainingConfigurations":398},{"removed":"All provider reports","score":0.20117604642217488,"rank":120,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.2020942489655373,"rank":119,"remainingConfigurations":398},{"removed":"briefcase","score":0.20102120563394144,"rank":120,"remainingConfigurations":398},{"removed":"aime","score":0.20228858759599497,"rank":120,"remainingConfigurations":398},{"removed":"apex-agents","score":0.21859703453437274,"rank":117,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.19467768882969494,"rank":122,"remainingConfigurations":398},{"removed":"automationbench","score":0.20096683690153824,"rank":120,"remainingConfigurations":398},{"removed":"critpt","score":0.2032180083228854,"rank":124,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.20102767224970688,"rank":120,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.20299023625138743,"rank":119,"remainingConfigurations":398},{"removed":"gdpval","score":0.20188372265230903,"rank":120,"remainingConfigurations":398},{"removed":"gmmlu","score":0.20301486514821832,"rank":120,"remainingConfigurations":398},{"removed":"gpqa","score":0.2099645179555952,"rank":117,"remainingConfigurations":398},{"removed":"harvey","score":0.19930537151077177,"rank":120,"remainingConfigurations":398},{"removed":"hle","score":0.20312554911231187,"rank":122,"remainingConfigurations":398},{"removed":"ifbench","score":0.19679587117701722,"rank":120,"remainingConfigurations":398},{"removed":"itbench","score":0.2012561127747152,"rank":119,"remainingConfigurations":398},{"removed":"livecodebench","score":0.20089318597052977,"rank":120,"remainingConfigurations":398},{"removed":"math500","score":0.20161550657878366,"rank":120,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2049714884582827,"rank":120,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.21036202893873146,"rank":121,"remainingConfigurations":398},{"removed":"omniscience","score":0.20613314181734632,"rank":123,"remainingConfigurations":398},{"removed":"scicode","score":0.20357225272969545,"rank":120,"remainingConfigurations":398},{"removed":"tau-bench","score":0.19000083968552176,"rank":124,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.19623743504765792,"rank":123,"remainingConfigurations":398},{"removed":"arc-agi","score":0.23085698867641877,"rank":118,"remainingConfigurations":398},{"removed":"deepswe","score":0.17737967104309146,"rank":121,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.2016808813875546,"rank":120,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.20038711590907451,"rank":121,"remainingConfigurations":398},{"removed":"frontiercode","score":0.20848773654507358,"rank":122,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.20169653611470453,"rank":120,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.20016912506588913,"rank":120,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.201338706298169,"rank":120,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.20097639697778738,"rank":120,"remainingConfigurations":398},{"removed":"livebench-math","score":0.20189381091948652,"rank":120,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.2005490127977866,"rank":120,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2033835606342943,"rank":120,"remainingConfigurations":398},{"removed":"livebench-data","score":0.20186294437952565,"rank":120,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.19930938214034935,"rank":120,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.20069485231484907,"rank":120,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.20378690741934,"rank":120,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.20604794142337532,"rank":121,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.19518042497441992,"rank":122,"remainingConfigurations":398},{"removed":"frontiermath","score":0.203614559032268,"rank":121,"remainingConfigurations":398},{"removed":"simpleqa","score":0.20749095883220084,"rank":119,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.2009207868775281,"rank":120,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.2011323806619519,"rank":120,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.20102044952985273,"rank":120,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.20143344035690067,"rank":120,"remainingConfigurations":398},{"removed":"vibe-code","score":0.20064947365433908,"rank":120,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-non-reasoning":{"score":0.20026107192215636,"rank":121,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22957519584049915,"rank":120,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1758329789782959,"rank":122,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1989982021648984,"rank":121,"remainingConfigurations":398},{"removed":"Scale","score":0.21458187825392863,"rank":121,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.20061420419221343,"rank":121,"remainingConfigurations":398},{"removed":"Cognition","score":0.20611742754097043,"rank":123,"remainingConfigurations":398},{"removed":"LiveBench","score":0.203408381618535,"rank":120,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.2043367242039027,"rank":122,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2007952358189838,"rank":120,"remainingConfigurations":381},{"removed":"Vals AI","score":0.19541046546730081,"rank":121,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.20026665619545883,"rank":121,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.20007949993419058,"rank":121,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.19994787525450017,"rank":121,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.20026107192215636,"rank":121,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1997484044159744,"rank":121,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.20123799555385033,"rank":121,"remainingConfigurations":398},{"removed":"briefcase","score":0.19214606691312494,"rank":122,"remainingConfigurations":398},{"removed":"aime","score":0.20069118673793274,"rank":121,"remainingConfigurations":398},{"removed":"apex-agents","score":0.20212397632666476,"rank":121,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.21703282172495694,"rank":115,"remainingConfigurations":398},{"removed":"automationbench","score":0.1998705862625886,"rank":121,"remainingConfigurations":398},{"removed":"critpt","score":0.19129784453149132,"rank":128,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.2004324074045193,"rank":121,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.20216862724295784,"rank":121,"remainingConfigurations":398},{"removed":"gdpval","score":0.18925856990090165,"rank":124,"remainingConfigurations":398},{"removed":"gmmlu","score":0.20101754028740182,"rank":121,"remainingConfigurations":398},{"removed":"gpqa","score":0.2157855628673203,"rank":115,"remainingConfigurations":398},{"removed":"harvey","score":0.19865420346179405,"rank":121,"remainingConfigurations":398},{"removed":"hle","score":0.21818342805724575,"rank":117,"remainingConfigurations":398},{"removed":"ifbench","score":0.19588968706218157,"rank":121,"remainingConfigurations":398},{"removed":"itbench","score":0.200170554630879,"rank":120,"remainingConfigurations":398},{"removed":"livecodebench","score":0.19943195232289698,"rank":121,"remainingConfigurations":398},{"removed":"math500","score":0.2000039582202149,"rank":121,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.2033981339626053,"rank":121,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.21675712853965948,"rank":119,"remainingConfigurations":398},{"removed":"omniscience","score":0.182286678996462,"rank":132,"remainingConfigurations":398},{"removed":"scicode","score":0.2034518357843829,"rank":121,"remainingConfigurations":398},{"removed":"tau-bench","score":0.19723552776413625,"rank":121,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.195189769026045,"rank":124,"remainingConfigurations":398},{"removed":"arc-agi","score":0.22877690926285,"rank":120,"remainingConfigurations":398},{"removed":"deepswe","score":0.17594553369149266,"rank":122,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.20030621864013157,"rank":121,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.19902216377795354,"rank":122,"remainingConfigurations":398},{"removed":"frontiercode","score":0.20611742754097043,"rank":123,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.20036236974138602,"rank":121,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.19874650233532973,"rank":121,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.19997462741481373,"rank":121,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1996311696969141,"rank":121,"remainingConfigurations":398},{"removed":"livebench-math","score":0.20051655742456856,"rank":121,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.19914372876421182,"rank":121,"remainingConfigurations":398},{"removed":"livebench-language","score":0.2019987332526029,"rank":121,"remainingConfigurations":398},{"removed":"livebench-data","score":0.20053902295857087,"rank":121,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.19791682801259017,"rank":121,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1993025952679696,"rank":121,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.20240799300769285,"rank":121,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.2043367242039027,"rank":122,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.19310442256854765,"rank":124,"remainingConfigurations":398},{"removed":"frontiermath","score":0.20160813039762204,"rank":122,"remainingConfigurations":398},{"removed":"simpleqa","score":0.20607127634197686,"rank":120,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.19953318392116956,"rank":121,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.19976949086354348,"rank":121,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.19964116937204568,"rank":121,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.2000702651345233,"rank":121,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1992513218676851,"rank":121,"remainingConfigurations":398}]},"qwen3.5-397b-a17b--effort-reasoning":{"score":0.19414030196475654,"rank":122,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22185322396261511,"rank":124,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16959909697004308,"rank":123,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1929917653652514,"rank":122,"remainingConfigurations":398},{"removed":"Scale","score":0.20825366251831287,"rank":122,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.19434975686201525,"rank":122,"remainingConfigurations":398},{"removed":"Cognition","score":0.19985920370911103,"rank":125,"remainingConfigurations":398},{"removed":"LiveBench","score":0.19645362945296344,"rank":121,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.19818803203003418,"rank":123,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.19559543031655283,"rank":122,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18860204691781216,"rank":122,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1941505108596501,"rank":122,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1939661521407565,"rank":122,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.19381908655973515,"rank":122,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.19414030196475654,"rank":122,"remainingConfigurations":398},{"removed":"All provider reports","score":0.19363113643074914,"rank":122,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.194550155570156,"rank":122,"remainingConfigurations":398},{"removed":"briefcase","score":0.2004455952649015,"rank":121,"remainingConfigurations":398},{"removed":"aime","score":0.19469125287983569,"rank":122,"remainingConfigurations":398},{"removed":"apex-agents","score":0.19468279705871352,"rank":122,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18867446407839508,"rank":125,"remainingConfigurations":398},{"removed":"automationbench","score":0.1970687153548714,"rank":122,"remainingConfigurations":398},{"removed":"critpt","score":0.1956686812619858,"rank":126,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.19819645878866762,"rank":122,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.19041587116883138,"rank":125,"remainingConfigurations":398},{"removed":"gdpval","score":0.19939546194890148,"rank":121,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1923418451452792,"rank":124,"remainingConfigurations":398},{"removed":"gpqa","score":0.18681082016995174,"rank":123,"remainingConfigurations":398},{"removed":"harvey","score":0.19668204214499574,"rank":122,"remainingConfigurations":398},{"removed":"hle","score":0.19825151075557468,"rank":125,"remainingConfigurations":398},{"removed":"ifbench","score":0.1842877590360751,"rank":129,"remainingConfigurations":398},{"removed":"itbench","score":0.19163814276091032,"rank":123,"remainingConfigurations":398},{"removed":"livecodebench","score":0.19400540542452746,"rank":122,"remainingConfigurations":398},{"removed":"math500","score":0.19445446523052579,"rank":122,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.19826439235690538,"rank":123,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.2000663914842212,"rank":123,"remainingConfigurations":398},{"removed":"omniscience","score":0.194333247504246,"rank":125,"remainingConfigurations":398},{"removed":"scicode","score":0.1979614290181724,"rank":123,"remainingConfigurations":398},{"removed":"tau-bench","score":0.19156526931767326,"rank":122,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.19931653563635884,"rank":121,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2208785926830925,"rank":124,"remainingConfigurations":398},{"removed":"deepswe","score":0.16972155231990393,"rank":123,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.19418305341592523,"rank":122,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.19298570551601582,"rank":124,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19985920370911103,"rank":125,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1942156925379742,"rank":122,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.19268986319983358,"rank":122,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1938598662576536,"rank":122,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1934339385154307,"rank":122,"remainingConfigurations":398},{"removed":"livebench-math","score":0.19437978005949585,"rank":122,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.19309503768489145,"rank":122,"remainingConfigurations":398},{"removed":"livebench-language","score":0.19588143037025751,"rank":122,"remainingConfigurations":398},{"removed":"livebench-data","score":0.19437642913920147,"rank":122,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.19183131762947295,"rank":122,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1932147753794418,"rank":122,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.19620371217941765,"rank":122,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.19818803203003418,"rank":123,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18788762362339198,"rank":125,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1954277721118399,"rank":123,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19976060521410646,"rank":122,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.19343058967900953,"rank":122,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.19365120086634413,"rank":122,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.19352611623088523,"rank":122,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1939605694942151,"rank":122,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1931560955016677,"rank":122,"remainingConfigurations":398}]},"glm-4.7--effort-reasoning":{"score":0.19277907822065013,"rank":123,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22312807829321402,"rank":123,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16906056220946739,"rank":124,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1914566828182355,"rank":124,"remainingConfigurations":398},{"removed":"Scale","score":0.20748195815470602,"rank":123,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.19319797141736453,"rank":123,"remainingConfigurations":398},{"removed":"Cognition","score":0.19946327728603197,"rank":126,"remainingConfigurations":398},{"removed":"LiveBench","score":0.19557346016165625,"rank":122,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.19673892635884238,"rank":124,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1938221795937959,"rank":123,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18791841980100657,"rank":123,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.19278593865325078,"rank":123,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.19261457333812962,"rank":123,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.19249059929204493,"rank":123,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.19277907822065013,"rank":123,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1923098472832844,"rank":123,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.19315215793531318,"rank":123,"remainingConfigurations":398},{"removed":"briefcase","score":0.19187504145972958,"rank":123,"remainingConfigurations":398},{"removed":"aime","score":0.19109527536862717,"rank":127,"remainingConfigurations":398},{"removed":"apex-agents","score":0.19436319330217974,"rank":123,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.19318684995115612,"rank":123,"remainingConfigurations":398},{"removed":"automationbench","score":0.19206430918479445,"rank":124,"remainingConfigurations":398},{"removed":"critpt","score":0.19335788399392786,"rank":127,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1926891407053951,"rank":123,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1942225916517182,"rank":123,"remainingConfigurations":398},{"removed":"gdpval","score":0.18812588985781634,"rank":125,"remainingConfigurations":398},{"removed":"gmmlu","score":0.19429009015304957,"rank":122,"remainingConfigurations":398},{"removed":"gpqa","score":0.18735244184373992,"rank":122,"remainingConfigurations":398},{"removed":"harvey","score":0.19084035265182406,"rank":123,"remainingConfigurations":398},{"removed":"hle","score":0.19951109463617267,"rank":123,"remainingConfigurations":398},{"removed":"ifbench","score":0.1917420293661688,"rank":123,"remainingConfigurations":398},{"removed":"itbench","score":0.19240388094816266,"rank":122,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18912712507175825,"rank":126,"remainingConfigurations":398},{"removed":"math500","score":0.19288553156936383,"rank":123,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.19828368372385852,"rank":122,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.20236192552133078,"rank":122,"remainingConfigurations":398},{"removed":"omniscience","score":0.1899371385826103,"rank":127,"remainingConfigurations":398},{"removed":"scicode","score":0.1951942092475802,"rank":125,"remainingConfigurations":398},{"removed":"tau-bench","score":0.19125308934858784,"rank":123,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.20220402149182556,"rank":120,"remainingConfigurations":398},{"removed":"arc-agi","score":0.22218390832033508,"rank":123,"remainingConfigurations":398},{"removed":"deepswe","score":0.16916912091640468,"rank":124,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.19282279818273787,"rank":123,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.19155251507844628,"rank":125,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19946327728603197,"rank":126,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.19286052110545185,"rank":123,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1913142106588369,"rank":123,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.19250313393700927,"rank":123,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.19211391588148044,"rank":123,"remainingConfigurations":398},{"removed":"livebench-math","score":0.19303109867451215,"rank":123,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.19168479344235603,"rank":123,"remainingConfigurations":398},{"removed":"livebench-language","score":0.19447307335579408,"rank":123,"remainingConfigurations":398},{"removed":"livebench-data","score":0.19304015771956465,"rank":123,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.19049206065091792,"rank":123,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.19184380826957345,"rank":123,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.19488793687049033,"rank":123,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.19673892635884238,"rank":124,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18576805032438837,"rank":126,"remainingConfigurations":398},{"removed":"frontiermath","score":0.19438924678814604,"rank":124,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19848669724299006,"rank":123,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.19206947917213832,"rank":123,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.19229289587920959,"rank":123,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.19217434578858394,"rank":123,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.19258674387007893,"rank":123,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1917939757460634,"rank":123,"remainingConfigurations":398}]},"qwen3.5-27b--effort-reasoning":{"score":0.19129066917485602,"rank":124,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22111709389466613,"rank":126,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1678002620714508,"rank":125,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18998838486963052,"rank":125,"remainingConfigurations":398},{"removed":"Scale","score":0.2057286059007798,"rank":124,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.19172687192269386,"rank":124,"remainingConfigurations":398},{"removed":"Cognition","score":0.19815340701169817,"rank":129,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1943026861889254,"rank":123,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1951557974589813,"rank":125,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1919201026453705,"rank":126,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18664247681921886,"rank":124,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.19129923594645448,"rank":124,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1911339875705482,"rank":124,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.19100296637092054,"rank":124,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.19129066917485602,"rank":124,"remainingConfigurations":398},{"removed":"All provider reports","score":0.19083125125864853,"rank":124,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.19151906579314307,"rank":125,"remainingConfigurations":398},{"removed":"briefcase","score":0.19071693711280477,"rank":124,"remainingConfigurations":398},{"removed":"aime","score":0.1916986219615409,"rank":125,"remainingConfigurations":398},{"removed":"apex-agents","score":0.19313302234364196,"rank":124,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1818526799369058,"rank":132,"remainingConfigurations":398},{"removed":"automationbench","score":0.19061117446341336,"rank":125,"remainingConfigurations":398},{"removed":"critpt","score":0.20210053431822073,"rank":125,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.19149730393224215,"rank":124,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1926735752078139,"rank":124,"remainingConfigurations":398},{"removed":"gdpval","score":0.19163679249563167,"rank":122,"remainingConfigurations":398},{"removed":"gmmlu","score":0.19397766031276334,"rank":123,"remainingConfigurations":398},{"removed":"gpqa","score":0.18568250488106464,"rank":125,"remainingConfigurations":398},{"removed":"harvey","score":0.1896965595218698,"rank":124,"remainingConfigurations":398},{"removed":"hle","score":0.19898245774688397,"rank":124,"remainingConfigurations":398},{"removed":"ifbench","score":0.1802782888984852,"rank":132,"remainingConfigurations":398},{"removed":"itbench","score":0.18226626602562734,"rank":133,"remainingConfigurations":398},{"removed":"livecodebench","score":0.19027367990497254,"rank":125,"remainingConfigurations":398},{"removed":"math500","score":0.1911504863577432,"rank":124,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.19412643288367945,"rank":125,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19857663057141647,"rank":125,"remainingConfigurations":398},{"removed":"omniscience","score":0.20751900880700835,"rank":122,"remainingConfigurations":398},{"removed":"scicode","score":0.19345138071058676,"rank":126,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18646914004759288,"rank":126,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.19632246251306942,"rank":122,"remainingConfigurations":398},{"removed":"arc-agi","score":0.22013513121298645,"rank":125,"remainingConfigurations":398},{"removed":"deepswe","score":0.1679103322204544,"rank":125,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1913312017218264,"rank":124,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.19008066254666525,"rank":126,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19815340701169817,"rank":129,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.19134813247686777,"rank":124,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18986234995410234,"rank":124,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.19100939259623592,"rank":124,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.19066875323567833,"rank":124,"remainingConfigurations":398},{"removed":"livebench-math","score":0.19153574805659213,"rank":124,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1902178611864029,"rank":124,"remainingConfigurations":398},{"removed":"livebench-language","score":0.19298043076554283,"rank":124,"remainingConfigurations":398},{"removed":"livebench-data","score":0.19151809545016987,"rank":124,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18902754674763736,"rank":124,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.19036943289906852,"rank":124,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.19338466590247505,"rank":124,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1951557974589813,"rank":125,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18439021630100152,"rank":129,"remainingConfigurations":398},{"removed":"frontiermath","score":0.19267618180011606,"rank":125,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1969715313443967,"rank":124,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1905952134282003,"rank":124,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.19079472053029653,"rank":124,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.19069416839751838,"rank":124,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.19108378928162048,"rank":124,"remainingConfigurations":398},{"removed":"vibe-code","score":0.19032984061996652,"rank":124,"remainingConfigurations":398}]},"solar-pro4-260806--effort-reasoning":{"score":0.19112944096219342,"rank":125,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21890227692475808,"rank":127,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16640171432024253,"rank":128,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18990195851014888,"rank":126,"remainingConfigurations":398},{"removed":"Scale","score":0.20526164810907552,"rank":125,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.19129138388032674,"rank":125,"remainingConfigurations":398},{"removed":"Cognition","score":0.1962281970482417,"rank":131,"remainingConfigurations":398},{"removed":"LiveBench","score":0.193906045918988,"rank":124,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.19477655062409993,"rank":126,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.19220019269597408,"rank":125,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1857850569438381,"rank":125,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.19113315265521283,"rank":125,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.19095309794323034,"rank":125,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.19082110055937385,"rank":125,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.19112944096219342,"rank":125,"remainingConfigurations":398},{"removed":"All provider reports","score":0.19062551245323647,"rank":125,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.19163054142721425,"rank":124,"remainingConfigurations":398},{"removed":"briefcase","score":0.18979823305131602,"rank":125,"remainingConfigurations":398},{"removed":"aime","score":0.19116272546633492,"rank":126,"remainingConfigurations":398},{"removed":"apex-agents","score":0.19288674119924387,"rank":125,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18663423094158274,"rank":127,"remainingConfigurations":398},{"removed":"automationbench","score":0.19558475638516684,"rank":123,"remainingConfigurations":398},{"removed":"critpt","score":0.18428476501749347,"rank":132,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1909108272878098,"rank":125,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.2011544361525025,"rank":122,"remainingConfigurations":398},{"removed":"gdpval","score":0.18128931530375061,"rank":135,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1920468468889566,"rank":125,"remainingConfigurations":398},{"removed":"gpqa","score":0.17941595896927334,"rank":131,"remainingConfigurations":398},{"removed":"harvey","score":0.1892315680984836,"rank":125,"remainingConfigurations":398},{"removed":"hle","score":0.19232660582918024,"rank":128,"remainingConfigurations":398},{"removed":"ifbench","score":0.18628364745254603,"rank":127,"remainingConfigurations":398},{"removed":"itbench","score":0.1907398139841225,"rank":124,"remainingConfigurations":398},{"removed":"livecodebench","score":0.19033668119338312,"rank":124,"remainingConfigurations":398},{"removed":"math500","score":0.1911167670549203,"rank":125,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.19457910400197242,"rank":124,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19934740207745263,"rank":124,"remainingConfigurations":398},{"removed":"omniscience","score":0.22143959209229733,"rank":112,"remainingConfigurations":398},{"removed":"scicode","score":0.1972058717388937,"rank":124,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18275537338398226,"rank":130,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.19256871774284148,"rank":125,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21843607238001095,"rank":126,"remainingConfigurations":398},{"removed":"deepswe","score":0.16651127670131158,"rank":128,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.19117647563993892,"rank":125,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.18996549793902165,"rank":127,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1962281970482417,"rank":131,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.19122714344935962,"rank":125,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1896578802013784,"rank":125,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1908609121305499,"rank":125,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1904095663873223,"rank":125,"remainingConfigurations":398},{"removed":"livebench-math","score":0.19137789539021557,"rank":125,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.19004184681144617,"rank":125,"remainingConfigurations":398},{"removed":"livebench-language","score":0.19283750784572343,"rank":125,"remainingConfigurations":398},{"removed":"livebench-data","score":0.19141738554988721,"rank":125,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18882986014178038,"rank":125,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.19019041891716382,"rank":125,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.19321399195455569,"rank":125,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.19477655062409993,"rank":126,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18446147122159695,"rank":128,"remainingConfigurations":398},{"removed":"frontiermath","score":0.19247880730967037,"rank":126,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19672348801449566,"rank":125,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1904148128191591,"rank":125,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.19065585896779866,"rank":125,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1905206834125719,"rank":125,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1909547079424568,"rank":125,"remainingConfigurations":398},{"removed":"vibe-code","score":0.19013767060698292,"rank":125,"remainingConfigurations":398}]},"claude-sonnet-4-5-20250929--effort-thinking-32k":{"score":0.1893336140090298,"rank":126,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.18092643338474257,"rank":97,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1966676509809516,"rank":144,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16022102120258083,"rank":131,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1917731508733381,"rank":123,"remainingConfigurations":398},{"removed":"Scale","score":0.20266411226557382,"rank":126,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18814197309687675,"rank":127,"remainingConfigurations":398},{"removed":"Cognition","score":0.19645734248499938,"rank":130,"remainingConfigurations":398},{"removed":"LiveBench","score":0.19180615333221737,"rank":125,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18900235181471056,"rank":130,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.19332568504356618,"rank":124,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18079883566655053,"rank":130,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18928854611827617,"rank":126,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1890284946497293,"rank":126,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18951278865599033,"rank":126,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1893336140090298,"rank":126,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18914302065095231,"rank":126,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1895760339161804,"rank":126,"remainingConfigurations":398},{"removed":"briefcase","score":0.18912545094792862,"rank":126,"remainingConfigurations":398},{"removed":"aime","score":0.19307386880960156,"rank":124,"remainingConfigurations":398},{"removed":"apex-agents","score":0.190040254903847,"rank":126,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18913261037416507,"rank":124,"remainingConfigurations":398},{"removed":"automationbench","score":0.18906076736849367,"rank":126,"remainingConfigurations":398},{"removed":"critpt","score":0.19016151553441588,"rank":129,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18933602000659522,"rank":126,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18999602191666287,"rank":126,"remainingConfigurations":398},{"removed":"gdpval","score":0.18936531080913774,"rank":123,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18934295246783175,"rank":127,"remainingConfigurations":398},{"removed":"gpqa","score":0.1761779346017569,"rank":138,"remainingConfigurations":398},{"removed":"harvey","score":0.18744739288337206,"rank":126,"remainingConfigurations":398},{"removed":"hle","score":0.19511980598982726,"rank":126,"remainingConfigurations":398},{"removed":"ifbench","score":0.18814814590286696,"rank":125,"remainingConfigurations":398},{"removed":"itbench","score":0.18907669211105624,"rank":125,"remainingConfigurations":398},{"removed":"livecodebench","score":0.19170790017497483,"rank":123,"remainingConfigurations":398},{"removed":"math500","score":0.18944573877653936,"rank":126,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.19343332450399595,"rank":126,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19852619713981853,"rank":126,"remainingConfigurations":398},{"removed":"omniscience","score":0.1872249499551127,"rank":128,"remainingConfigurations":398},{"removed":"scicode","score":0.19039169673493828,"rank":127,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18855531800338063,"rank":125,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18919200132381453,"rank":127,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19673073583387837,"rank":141,"remainingConfigurations":398},{"removed":"deepswe","score":0.16032867637250084,"rank":131,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18936187366197765,"rank":126,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.18490550538254036,"rank":130,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19645734248499938,"rank":130,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18931800227712947,"rank":126,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18786419586695516,"rank":126,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18903174176324478,"rank":126,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1887658340377456,"rank":126,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18948759178580318,"rank":126,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18797380549065443,"rank":126,"remainingConfigurations":398},{"removed":"livebench-language","score":0.19101744243181792,"rank":126,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18967080068494244,"rank":126,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1871569532841337,"rank":126,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1884367862851727,"rank":126,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.19158959954381616,"rank":126,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18900235181471056,"rank":130,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.15941341296000391,"rank":151,"remainingConfigurations":398},{"removed":"frontiermath","score":0.21686318862217865,"rank":118,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19134519631000746,"rank":128,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.188553622883512,"rank":126,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1889127022385495,"rank":126,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18875902945885328,"rank":126,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18908834837695324,"rank":126,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1883263194994417,"rank":126,"remainingConfigurations":398}]},"qwen3.8-27b--effort-medium":{"score":0.18783269631008784,"rank":127,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21634441241834157,"rank":128,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16673878619853866,"rank":127,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18654739091524467,"rank":128,"remainingConfigurations":398},{"removed":"Scale","score":0.20221776164781222,"rank":127,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18857202728607733,"rank":126,"remainingConfigurations":398},{"removed":"Cognition","score":0.1956124489771043,"rank":132,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1915933135031409,"rank":126,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.19218058522837297,"rank":127,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.18948325970658417,"rank":127,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18414220084389352,"rank":127,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18783774041383464,"rank":127,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18765977947667237,"rank":127,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18752991324837578,"rank":127,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18783269631008784,"rank":127,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18733922465828298,"rank":127,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18893862254949048,"rank":127,"remainingConfigurations":398},{"removed":"briefcase","score":0.17084770213987058,"rank":145,"remainingConfigurations":398},{"removed":"aime","score":0.18616550708021362,"rank":129,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18990832891037704,"rank":127,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.17538327345283408,"rank":140,"remainingConfigurations":398},{"removed":"automationbench","score":0.17768211171857232,"rank":137,"remainingConfigurations":398},{"removed":"critpt","score":0.23250154616147914,"rank":109,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18877475091165696,"rank":127,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1833895847554168,"rank":131,"remainingConfigurations":398},{"removed":"gdpval","score":0.1778141703573213,"rank":139,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18766859879112605,"rank":128,"remainingConfigurations":398},{"removed":"gpqa","score":0.18363595037476063,"rank":126,"remainingConfigurations":398},{"removed":"harvey","score":0.18698761812255912,"rank":127,"remainingConfigurations":398},{"removed":"hle","score":0.20445254672850655,"rank":121,"remainingConfigurations":398},{"removed":"ifbench","score":0.18154634898225785,"rank":130,"remainingConfigurations":398},{"removed":"itbench","score":0.18803797315840334,"rank":126,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18518259780756655,"rank":128,"remainingConfigurations":398},{"removed":"math500","score":0.18686659412875997,"rank":128,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18921403334509432,"rank":128,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1955714957417148,"rank":127,"remainingConfigurations":398},{"removed":"omniscience","score":0.2144047372392833,"rank":119,"remainingConfigurations":398},{"removed":"scicode","score":0.20394870851211444,"rank":119,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17264235029438613,"rank":141,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1811673305098478,"rank":134,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21505447161027266,"rank":128,"remainingConfigurations":398},{"removed":"deepswe","score":0.1668469575469488,"rank":127,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18787822228727338,"rank":127,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1866832509557693,"rank":129,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1956124489771043,"rank":132,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18800521863624767,"rank":127,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18639113192053677,"rank":127,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18757030174384348,"rank":127,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18728681626688584,"rank":127,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18807660337809326,"rank":127,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18674788857274824,"rank":127,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1895203131385851,"rank":127,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18811583125255082,"rank":127,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18556292193968424,"rank":127,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18690139066310904,"rank":127,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1899076409239732,"rank":127,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.19218058522837297,"rank":127,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18087111752561943,"rank":130,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18908449600317564,"rank":127,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19345197237577602,"rank":127,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18712902799656175,"rank":127,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18736069726462926,"rank":127,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18723244643466808,"rank":127,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18765076178062923,"rank":127,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18685557784881693,"rank":127,"remainingConfigurations":398}]},"claude-sonnet-4-6--effort-high":{"score":0.1871136302154405,"rank":128,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1815385097709243,"rank":96,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12297399334876873,"rank":188,"remainingConfigurations":398},{"removed":"Datacurve","score":0.18606443304879763,"rank":117,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1874474541755674,"rank":127,"remainingConfigurations":398},{"removed":"Scale","score":0.19965019879241866,"rank":129,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18587621781865896,"rank":129,"remainingConfigurations":398},{"removed":"Cognition","score":0.2231048073106722,"rank":118,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18952923486254655,"rank":127,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18309686866274333,"rank":135,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.2258842496347392,"rank":112,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17896061980753974,"rank":132,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18719656036255652,"rank":128,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18666854703910304,"rank":128,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18729434436519887,"rank":128,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1871136302154405,"rank":128,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18691478976522427,"rank":128,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18724029598926187,"rank":128,"remainingConfigurations":398},{"removed":"briefcase","score":0.18679663390906667,"rank":127,"remainingConfigurations":398},{"removed":"aime","score":0.1839371290036119,"rank":131,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1877409382845767,"rank":128,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1872184318119814,"rank":126,"remainingConfigurations":398},{"removed":"automationbench","score":0.1868194592237077,"rank":128,"remainingConfigurations":398},{"removed":"critpt","score":0.18710479821776674,"rank":131,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18706687654357448,"rank":129,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1876270798467716,"rank":127,"remainingConfigurations":398},{"removed":"gdpval","score":0.1870150415356401,"rank":126,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18721476978522997,"rank":129,"remainingConfigurations":398},{"removed":"gpqa","score":0.18321553858063755,"rank":127,"remainingConfigurations":398},{"removed":"harvey","score":0.1855220063873959,"rank":128,"remainingConfigurations":398},{"removed":"hle","score":0.19262024569884936,"rank":127,"remainingConfigurations":398},{"removed":"ifbench","score":0.18632757128246072,"rank":126,"remainingConfigurations":398},{"removed":"itbench","score":0.1868138074980875,"rank":127,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18747161443240615,"rank":127,"remainingConfigurations":398},{"removed":"math500","score":0.18716443431259502,"rank":127,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1908488603290933,"rank":127,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19550516319139966,"rank":128,"remainingConfigurations":398},{"removed":"omniscience","score":0.18630775905085414,"rank":129,"remainingConfigurations":398},{"removed":"scicode","score":0.1877889881933148,"rank":128,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18631203899788892,"rank":127,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1864608890291716,"rank":130,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12277805238709237,"rank":189,"remainingConfigurations":398},{"removed":"deepswe","score":0.1861649849004614,"rank":117,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18716107400680182,"rank":128,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.18753448672683884,"rank":128,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2231048073106722,"rank":118,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1875736561842923,"rank":128,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1854690045500721,"rank":128,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18709311260199565,"rank":128,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18583650248799763,"rank":128,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1873291160328022,"rank":128,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18561591007562214,"rank":128,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1886466660919197,"rank":128,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18773433624198,"rank":128,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18496923416758024,"rank":128,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18603398756721892,"rank":128,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18948078358002415,"rank":128,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18309686866274333,"rank":135,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.19380979281247476,"rank":123,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18572230818509472,"rank":131,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19087875767247597,"rank":130,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18629760103233686,"rank":128,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18679466978663264,"rank":128,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18646301909013963,"rank":128,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18679517626817863,"rank":128,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18627794814699628,"rank":128,"remainingConfigurations":398}]},"glm-5-turbo--effort-reasoning":{"score":0.18564205501975964,"rank":129,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21527490950978392,"rank":130,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16287534417350732,"rank":129,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18433258118927845,"rank":129,"remainingConfigurations":398},{"removed":"Scale","score":0.20015301150021822,"rank":128,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18610785950803466,"rank":128,"remainingConfigurations":398},{"removed":"Cognition","score":0.19261575286087237,"rank":134,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18837302374298523,"rank":128,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18952186105481617,"rank":129,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.18591426931871627,"rank":129,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18101909217177223,"rank":129,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18565106929835437,"rank":129,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18549177989317775,"rank":129,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18536650773992217,"rank":129,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18564205501975964,"rank":129,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1852025370287501,"rank":129,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1859367982340369,"rank":130,"remainingConfigurations":398},{"removed":"briefcase","score":0.18467723994232363,"rank":128,"remainingConfigurations":398},{"removed":"aime","score":0.18647701183771567,"rank":128,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18707617690025746,"rank":129,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18572677213243108,"rank":129,"remainingConfigurations":398},{"removed":"automationbench","score":0.18481652045407496,"rank":129,"remainingConfigurations":398},{"removed":"critpt","score":0.2120170464154927,"rank":118,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18553496365089794,"rank":130,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18687279013627647,"rank":128,"remainingConfigurations":398},{"removed":"gdpval","score":0.18579835527303032,"rank":127,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1870322928053906,"rank":130,"remainingConfigurations":398},{"removed":"gpqa","score":0.18183087538794837,"rank":130,"remainingConfigurations":398},{"removed":"harvey","score":0.18363266588745442,"rank":129,"remainingConfigurations":398},{"removed":"hle","score":0.18978554779879034,"rank":130,"remainingConfigurations":398},{"removed":"ifbench","score":0.17595862820638597,"rank":138,"remainingConfigurations":398},{"removed":"itbench","score":0.1852386095562811,"rank":128,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18510965259250012,"rank":129,"remainingConfigurations":398},{"removed":"math500","score":0.18578831286420364,"rank":129,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18905365605429156,"rank":129,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19466229433563242,"rank":129,"remainingConfigurations":398},{"removed":"omniscience","score":0.1818179664569759,"rank":134,"remainingConfigurations":398},{"removed":"scicode","score":0.18767884160021933,"rank":129,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16986790691329692,"rank":143,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1899604090927101,"rank":126,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21422080674977606,"rank":129,"remainingConfigurations":398},{"removed":"deepswe","score":0.1629801695047682,"rank":129,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1856835400127523,"rank":129,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.184454524450409,"rank":131,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19261575286087237,"rank":134,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18572603628370976,"rank":129,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18425073921784865,"rank":129,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18536843091413766,"rank":129,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18501751675204112,"rank":129,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18588727916791092,"rank":129,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18456415875156681,"rank":129,"remainingConfigurations":398},{"removed":"livebench-language","score":0.18729480889542924,"rank":129,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18589384056343253,"rank":129,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18341167696934876,"rank":129,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18472660142284572,"rank":129,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1877175019557522,"rank":129,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18952186105481617,"rank":129,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.17862416865929598,"rank":131,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18721772499230224,"rank":129,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19123067264677418,"rank":129,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18495220050251512,"rank":130,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18516186325469716,"rank":129,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18505224123190844,"rank":129,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1854448202250184,"rank":130,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18468504206761474,"rank":130,"remainingConfigurations":398}]},"grok-4.3--effort-high":{"score":0.18441296084940173,"rank":130,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.19942697989869393,"rank":92,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.20179937087250452,"rank":137,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15612724219235277,"rank":135,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18401940416147175,"rank":130,"remainingConfigurations":398},{"removed":"Scale","score":0.19643935133322354,"rank":132,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1840639484923953,"rank":131,"remainingConfigurations":398},{"removed":"Cognition","score":0.19137661620129073,"rank":135,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18685368167850513,"rank":130,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18453734676967867,"rank":132,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1523060950521554,"rank":157,"remainingConfigurations":381},{"removed":"Vals AI","score":0.20998963682659144,"rank":114,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18436943723928087,"rank":130,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1842194100851299,"rank":130,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1842663979629319,"rank":130,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18441296084940173,"rank":130,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1840139831695171,"rank":130,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1870453356785856,"rank":129,"remainingConfigurations":398},{"removed":"briefcase","score":0.1844628952830332,"rank":129,"remainingConfigurations":398},{"removed":"aime","score":0.17926184798083536,"rank":137,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18493512695216796,"rank":132,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18317552360945466,"rank":131,"remainingConfigurations":398},{"removed":"automationbench","score":0.18838208630203201,"rank":127,"remainingConfigurations":398},{"removed":"critpt","score":0.18263107377863974,"rank":134,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18811045175737032,"rank":128,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18680564293254842,"rank":129,"remainingConfigurations":398},{"removed":"gdpval","score":0.18453529818975012,"rank":128,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1846905699531659,"rank":132,"remainingConfigurations":398},{"removed":"gpqa","score":0.17528857983938537,"rank":140,"remainingConfigurations":398},{"removed":"harvey","score":0.17982224675887612,"rank":134,"remainingConfigurations":398},{"removed":"hle","score":0.1874841861328647,"rank":133,"remainingConfigurations":398},{"removed":"ifbench","score":0.17996168435598583,"rank":133,"remainingConfigurations":398},{"removed":"itbench","score":0.18372565277252065,"rank":131,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1843938924955618,"rank":130,"remainingConfigurations":398},{"removed":"math500","score":0.18461206738662386,"rank":130,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1869297939419198,"rank":132,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1912704976968179,"rank":132,"remainingConfigurations":398},{"removed":"omniscience","score":0.1834445794843179,"rank":131,"remainingConfigurations":398},{"removed":"scicode","score":0.18407086050530805,"rank":132,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18188274220546152,"rank":131,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18801515912693514,"rank":128,"remainingConfigurations":398},{"removed":"arc-agi","score":0.20099576695686036,"rank":135,"remainingConfigurations":398},{"removed":"deepswe","score":0.15628093633863585,"rank":135,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18445836419610326,"rank":130,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.18347858837391087,"rank":132,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19137661620129073,"rank":135,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18444554377263914,"rank":130,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18303244535904015,"rank":130,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1841850086999224,"rank":130,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18351712853266441,"rank":131,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18479687997472427,"rank":130,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18320121851111168,"rank":130,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1860377621020428,"rank":130,"remainingConfigurations":398},{"removed":"livebench-data","score":0.184912605357988,"rank":130,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1821799092584047,"rank":130,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18361003976161225,"rank":130,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18615336433733276,"rank":132,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18453734676967867,"rank":132,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.17702662465010985,"rank":134,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18858606884758208,"rank":128,"remainingConfigurations":398},{"removed":"simpleqa","score":0.19654201471660424,"rank":126,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18568822322333658,"rank":129,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18387154762877847,"rank":130,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18231484870209103,"rank":132,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18581998462694727,"rank":129,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18568901727439868,"rank":129,"remainingConfigurations":398}]},"hy3-preview--effort-reasoning":{"score":0.18419490612655157,"rank":131,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.21300395799333008,"rank":131,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16135147122841378,"rank":130,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18287793023715823,"rank":132,"remainingConfigurations":398},{"removed":"Scale","score":0.19870228440610863,"rank":130,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18460307774408993,"rank":130,"remainingConfigurations":398},{"removed":"Cognition","score":0.19066087746817117,"rank":137,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18691793640455645,"rank":129,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18753596617533308,"rank":131,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.18593424792102356,"rank":128,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1795689270866242,"rank":131,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1842035951648597,"rank":131,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18404432525765446,"rank":131,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18392192866037707,"rank":132,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18419490612655157,"rank":131,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1837574456352754,"rank":132,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1845265900519567,"rank":131,"remainingConfigurations":398},{"removed":"briefcase","score":0.18305314985350543,"rank":130,"remainingConfigurations":398},{"removed":"aime","score":0.18510782719340113,"rank":130,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18563524944758547,"rank":130,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.19507768770528597,"rank":121,"remainingConfigurations":398},{"removed":"automationbench","score":0.18330034927553893,"rank":130,"remainingConfigurations":398},{"removed":"critpt","score":0.1759031049226625,"rank":143,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18398704028740956,"rank":132,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18533576926686846,"rank":130,"remainingConfigurations":398},{"removed":"gdpval","score":0.18425317801337807,"rank":129,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1859409190797088,"rank":131,"remainingConfigurations":398},{"removed":"gpqa","score":0.17410532258626177,"rank":143,"remainingConfigurations":398},{"removed":"harvey","score":0.18213499712597123,"rank":131,"remainingConfigurations":398},{"removed":"hle","score":0.18796077743721193,"rank":132,"remainingConfigurations":398},{"removed":"ifbench","score":0.19246991126872529,"rank":122,"remainingConfigurations":398},{"removed":"itbench","score":0.1838153135067806,"rank":130,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18350450559316367,"rank":132,"remainingConfigurations":398},{"removed":"math500","score":0.1841201818341899,"rank":132,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18736308317563566,"rank":131,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19342277524908247,"rank":130,"remainingConfigurations":398},{"removed":"omniscience","score":0.18158806822156903,"rank":135,"remainingConfigurations":398},{"removed":"scicode","score":0.1863522929463497,"rank":130,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17904935819422638,"rank":136,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18718361583715692,"rank":129,"remainingConfigurations":398},{"removed":"arc-agi","score":0.21208646182500798,"rank":130,"remainingConfigurations":398},{"removed":"deepswe","score":0.16145534203949138,"rank":130,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18423611172035434,"rank":131,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.18300906686921778,"rank":133,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19066087746817117,"rank":137,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18425817294327862,"rank":132,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1827865707129738,"rank":131,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1839243137675762,"rank":131,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18357861856588678,"rank":130,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1844386359483909,"rank":131,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18312007856861678,"rank":131,"remainingConfigurations":398},{"removed":"livebench-language","score":0.18583951052762093,"rank":131,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18444572089894887,"rank":131,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1819757248321684,"rank":131,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18328338098124264,"rank":131,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.186263244299674,"rank":131,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18753596617533308,"rank":131,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.17737035267574178,"rank":133,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1855937433834299,"rank":132,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18976638144143307,"rank":131,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18350868866525485,"rank":131,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.183716795302003,"rank":131,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18360804696212998,"rank":130,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.183997189896969,"rank":131,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18324237841163085,"rank":131,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-low":{"score":0.1840047266994124,"rank":132,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1650509642609715,"rank":100,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22116802714415104,"rank":125,"remainingConfigurations":398},{"removed":"Datacurve","score":0.16737431468705463,"rank":126,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18384155399247892,"rank":131,"remainingConfigurations":398},{"removed":"Scale","score":0.19714304129147484,"rank":131,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18362533742886575,"rank":132,"remainingConfigurations":398},{"removed":"Cognition","score":0.2007465567318295,"rank":124,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18670349360225102,"rank":131,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1819057165959335,"rank":136,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.16577191274176906,"rank":146,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17716615865766994,"rank":134,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1840426187971025,"rank":132,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18401523624419358,"rank":132,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18392889955633318,"rank":131,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1840047266994124,"rank":132,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18395395094385256,"rank":131,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18443192006237988,"rank":132,"remainingConfigurations":398},{"removed":"briefcase","score":0.1828193847372478,"rank":131,"remainingConfigurations":398},{"removed":"aime","score":0.18185165639307566,"rank":133,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18510516333688742,"rank":131,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1849462504120053,"rank":130,"remainingConfigurations":398},{"removed":"automationbench","score":0.1825347711231754,"rank":131,"remainingConfigurations":398},{"removed":"critpt","score":0.18299233083457622,"rank":133,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1842851140726335,"rank":131,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18181652055847064,"rank":134,"remainingConfigurations":398},{"removed":"gdpval","score":0.18340424637507013,"rank":130,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18444886710750644,"rank":133,"remainingConfigurations":398},{"removed":"gpqa","score":0.18271540305478337,"rank":128,"remainingConfigurations":398},{"removed":"harvey","score":0.18275895547808685,"rank":130,"remainingConfigurations":398},{"removed":"hle","score":0.18999466675249543,"rank":129,"remainingConfigurations":398},{"removed":"ifbench","score":0.18529783961131088,"rank":128,"remainingConfigurations":398},{"removed":"itbench","score":0.18389492037965036,"rank":129,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18422304558824232,"rank":131,"remainingConfigurations":398},{"removed":"math500","score":0.18419509461058023,"rank":131,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18813062933147415,"rank":130,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.19222420639946877,"rank":131,"remainingConfigurations":398},{"removed":"omniscience","score":0.1820735614126691,"rank":133,"remainingConfigurations":398},{"removed":"scicode","score":0.1842313257409426,"rank":131,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18513077606802128,"rank":129,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18358771009445882,"rank":133,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1889974751762027,"rank":148,"remainingConfigurations":398},{"removed":"deepswe","score":0.1673936378651567,"rank":126,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1840422580355541,"rank":132,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.19761254599991893,"rank":123,"remainingConfigurations":398},{"removed":"frontiercode","score":0.2007465567318295,"rank":124,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18430654757808695,"rank":131,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18230407531925683,"rank":132,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18386259462328014,"rank":132,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18340088924130438,"rank":132,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18434885847289365,"rank":132,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18271760563971737,"rank":132,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1855612036774548,"rank":132,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1841819286586109,"rank":132,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1818463176034438,"rank":132,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18310517730925283,"rank":132,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18628592253772694,"rank":130,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1819057165959335,"rank":136,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1778851236220198,"rank":132,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1860932719596633,"rank":130,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18895097263600505,"rank":132,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18332123116568474,"rank":132,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18352499576135886,"rank":132,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1834616153695021,"rank":131,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18369520337238876,"rank":132,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1830605571978363,"rank":132,"remainingConfigurations":398}]},"gemini-3.5-flash--effort-minimal":{"score":0.1825754715658124,"rank":133,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1844048763754519,"rank":95,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.24829604697128463,"rank":114,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15949802166925348,"rank":132,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.18258883560329484,"rank":133,"remainingConfigurations":398},{"removed":"Scale","score":0.19625843578142999,"rank":133,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1824801845808691,"rank":133,"remainingConfigurations":398},{"removed":"Cognition","score":0.1931660115544782,"rank":133,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18494511072326855,"rank":133,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18336175865638552,"rank":134,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15296516263909346,"rank":156,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17748729472723476,"rank":133,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18258034769728035,"rank":133,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18227549099018184,"rank":133,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18239744624499743,"rank":133,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1825754715658124,"rank":133,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18208269891666673,"rank":133,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18287602455305776,"rank":133,"remainingConfigurations":398},{"removed":"briefcase","score":0.18217785553055835,"rank":132,"remainingConfigurations":398},{"removed":"aime","score":0.19368131570028088,"rank":123,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18358769648743614,"rank":133,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18586236152224125,"rank":128,"remainingConfigurations":398},{"removed":"automationbench","score":0.1821763330215861,"rank":132,"remainingConfigurations":398},{"removed":"critpt","score":0.18203656030423523,"rank":135,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1826053008394702,"rank":133,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.183354872933134,"rank":132,"remainingConfigurations":398},{"removed":"gdpval","score":0.18253935180942593,"rank":132,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18293682447488654,"rank":134,"remainingConfigurations":398},{"removed":"gpqa","score":0.18241306199493068,"rank":129,"remainingConfigurations":398},{"removed":"harvey","score":0.18085470982295573,"rank":133,"remainingConfigurations":398},{"removed":"hle","score":0.18804702541316975,"rank":131,"remainingConfigurations":398},{"removed":"ifbench","score":0.18828087636338187,"rank":124,"remainingConfigurations":398},{"removed":"itbench","score":0.18233110544079742,"rank":132,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1828010087241666,"rank":133,"remainingConfigurations":398},{"removed":"math500","score":0.1827375899226491,"rank":133,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18636095897957086,"rank":133,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18566502928598996,"rank":140,"remainingConfigurations":398},{"removed":"omniscience","score":0.1753139108387272,"rank":140,"remainingConfigurations":398},{"removed":"scicode","score":0.18400017320975315,"rank":133,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18617734505333708,"rank":128,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1794157513843981,"rank":138,"remainingConfigurations":398},{"removed":"arc-agi","score":0.24758906865884864,"rank":114,"remainingConfigurations":398},{"removed":"deepswe","score":0.1595881847265513,"rank":132,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18260898671837655,"rank":133,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1810392378663371,"rank":134,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1931660115544782,"rank":133,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1828204751047544,"rank":133,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.18112420616187971,"rank":133,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.18231247238251405,"rank":133,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18195406549147897,"rank":133,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1828605880960584,"rank":133,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1813527954477089,"rank":134,"remainingConfigurations":398},{"removed":"livebench-language","score":0.18412505631656062,"rank":133,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1828232713753252,"rank":133,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.18041199120501325,"rank":133,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18168127079941773,"rank":134,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1847751260261891,"rank":134,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18336175865638552,"rank":134,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1613876765906358,"rank":149,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18541116597626514,"rank":133,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18861819672660862,"rank":133,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18190991269402668,"rank":133,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1820915992772284,"rank":133,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18200191794732812,"rank":133,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.18231157934048214,"rank":133,"remainingConfigurations":398},{"removed":"vibe-code","score":0.18162223775706646,"rank":133,"remainingConfigurations":398}]},"solar-open2-250b--effort-reasoning":{"score":0.18109179394027441,"rank":134,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.20849351849517214,"rank":135,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15753527725219388,"rank":134,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17986908859504178,"rank":136,"remainingConfigurations":398},{"removed":"Scale","score":0.19500996877708757,"rank":134,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.18128165256539464,"rank":134,"remainingConfigurations":398},{"removed":"Cognition","score":0.18629067466568663,"rank":139,"remainingConfigurations":398},{"removed":"LiveBench","score":0.183911302441741,"rank":135,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.18446472435368413,"rank":133,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.18188835822820518,"rank":132,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17609082328621853,"rank":135,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1810967784933225,"rank":134,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.18092929735606864,"rank":134,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18080693758781075,"rank":134,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18109179394027441,"rank":134,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18062709629409232,"rank":134,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18145885667736159,"rank":134,"remainingConfigurations":398},{"removed":"briefcase","score":0.18010071462743704,"rank":134,"remainingConfigurations":398},{"removed":"aime","score":0.18106564574282394,"rank":134,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18273651458394435,"rank":134,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.18059591142451878,"rank":134,"remainingConfigurations":398},{"removed":"automationbench","score":0.18035389289394285,"rank":133,"remainingConfigurations":398},{"removed":"critpt","score":0.16931421274174277,"rank":149,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18120855953475448,"rank":134,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1825203132826474,"rank":133,"remainingConfigurations":398},{"removed":"gdpval","score":0.1830793019004033,"rank":131,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1821065405628788,"rank":135,"remainingConfigurations":398},{"removed":"gpqa","score":0.17412339581147307,"rank":142,"remainingConfigurations":398},{"removed":"harvey","score":0.17949109016455836,"rank":135,"remainingConfigurations":398},{"removed":"hle","score":0.18097705836400682,"rank":145,"remainingConfigurations":398},{"removed":"ifbench","score":0.17683699912013542,"rank":137,"remainingConfigurations":398},{"removed":"itbench","score":0.18083087500435954,"rank":134,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18008914603176987,"rank":137,"remainingConfigurations":398},{"removed":"math500","score":0.1810836593661589,"rank":134,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18414114881255608,"rank":136,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18986464989142857,"rank":134,"remainingConfigurations":398},{"removed":"omniscience","score":0.2166812370814624,"rank":118,"remainingConfigurations":398},{"removed":"scicode","score":0.17531452249793733,"rank":145,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1733182741324277,"rank":140,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18631317794993185,"rank":131,"remainingConfigurations":398},{"removed":"arc-agi","score":0.20791329298223496,"rank":133,"remainingConfigurations":398},{"removed":"deepswe","score":0.1576383629546434,"rank":134,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18113535169164172,"rank":134,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1799582752540688,"rank":136,"remainingConfigurations":398},{"removed":"frontiercode","score":0.18629067466568663,"rank":139,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18117851449214284,"rank":134,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17968209288287804,"rank":134,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1808335566544198,"rank":134,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.18043316636287768,"rank":134,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1813339420789498,"rank":135,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18003027253655027,"rank":135,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1827332975662547,"rank":134,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1813632076577476,"rank":134,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17887807511565154,"rank":134,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18018374372665746,"rank":135,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18312518825025806,"rank":135,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.18446472435368413,"rank":133,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.17427767578095685,"rank":136,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1824146141161953,"rank":134,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18653867779624167,"rank":134,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.18040363889511776,"rank":134,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.18062798299269603,"rank":134,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.18050555950242517,"rank":135,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1809106278465209,"rank":134,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1801389780049906,"rank":134,"remainingConfigurations":398}]},"gpt-5.4-mini--effort-xhigh":{"score":0.18043351828200482,"rank":135,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.16449810333509784,"rank":101,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1928986533019655,"rank":147,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1549017108023577,"rank":137,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1804669322179855,"rank":135,"remainingConfigurations":398},{"removed":"Scale","score":0.19232979877077136,"rank":137,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1802267131262727,"rank":135,"remainingConfigurations":398},{"removed":"Cognition","score":0.19937299864479097,"rank":127,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1857294458941121,"rank":132,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1794544616790059,"rank":139,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1834310321773738,"rank":130,"remainingConfigurations":381},{"removed":"Vals AI","score":0.18540768185158352,"rank":126,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18044967236532417,"rank":135,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1805528285922635,"rank":135,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.18025311578381706,"rank":135,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18043351828200482,"rank":135,"remainingConfigurations":398},{"removed":"All provider reports","score":0.18036923019402432,"rank":135,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.18111083408292383,"rank":135,"remainingConfigurations":398},{"removed":"briefcase","score":0.18126826916762093,"rank":133,"remainingConfigurations":398},{"removed":"aime","score":0.17978554530033722,"rank":136,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1797527574239821,"rank":137,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1807402035376475,"rank":133,"remainingConfigurations":398},{"removed":"automationbench","score":0.17970286141115865,"rank":135,"remainingConfigurations":398},{"removed":"critpt","score":0.1800871380133766,"rank":138,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18076034725102522,"rank":135,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17984184238580977,"rank":136,"remainingConfigurations":398},{"removed":"gdpval","score":0.18056291001226069,"rank":136,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18065038931942223,"rank":136,"remainingConfigurations":398},{"removed":"gpqa","score":0.17901415208499824,"rank":133,"remainingConfigurations":398},{"removed":"harvey","score":0.18204399226432685,"rank":132,"remainingConfigurations":398},{"removed":"hle","score":0.18584642535795626,"rank":136,"remainingConfigurations":398},{"removed":"ifbench","score":0.1788209508667882,"rank":134,"remainingConfigurations":398},{"removed":"itbench","score":0.1801135159492976,"rank":135,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1805620394140457,"rank":136,"remainingConfigurations":398},{"removed":"math500","score":0.1805440466864543,"rank":136,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18603701683310878,"rank":134,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18953985342136237,"rank":135,"remainingConfigurations":398},{"removed":"omniscience","score":0.17953698899058798,"rank":136,"remainingConfigurations":398},{"removed":"scicode","score":0.17969913328722542,"rank":137,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18026212111469,"rank":133,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18022040210477894,"rank":137,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19015894116179768,"rank":146,"remainingConfigurations":398},{"removed":"deepswe","score":0.15494217763008336,"rank":137,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18049002458266383,"rank":135,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1800072877360032,"rank":135,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19937299864479097,"rank":127,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.18065290958674488,"rank":135,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1790078032443415,"rank":135,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1802758755943782,"rank":135,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17971509057763402,"rank":135,"remainingConfigurations":398},{"removed":"livebench-math","score":0.18188537570076355,"rank":134,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.18191958506707273,"rank":133,"remainingConfigurations":398},{"removed":"livebench-language","score":0.18228505818094717,"rank":135,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1723382175916953,"rank":143,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1772476479897115,"rank":137,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.18228706972574715,"rank":133,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1851420800197571,"rank":133,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1794544616790059,"rank":139,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.17626186886832354,"rank":135,"remainingConfigurations":398},{"removed":"frontiermath","score":0.18110158283117206,"rank":136,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18464266360571346,"rank":137,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17867435556628083,"rank":137,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1802091257107076,"rank":135,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1815920750460426,"rank":134,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17907952301218077,"rank":137,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17732240570441204,"rank":137,"remainingConfigurations":398}]},"gpt-5--effort-high":{"score":0.18014945378150696,"rank":136,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14405725300175223,"rank":109,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.22686162404224772,"rank":121,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15512943232221174,"rank":136,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1806572126670826,"rank":134,"remainingConfigurations":398},{"removed":"Scale","score":0.19427543804330638,"rank":135,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17954482189387236,"rank":136,"remainingConfigurations":398},{"removed":"Cognition","score":0.18720865177024174,"rank":138,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1811801166611863,"rank":136,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1919925960425918,"rank":128,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1764450227737809,"rank":134,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17361285874791646,"rank":137,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.18015679594898074,"rank":136,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1799019752758955,"rank":136,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17994962177597232,"rank":136,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.18014945378150696,"rank":136,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17968899734451074,"rank":136,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.180453237800182,"rank":136,"remainingConfigurations":398},{"removed":"briefcase","score":0.18003108997525877,"rank":135,"remainingConfigurations":398},{"removed":"aime","score":0.1803209582672034,"rank":135,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18122683821588095,"rank":135,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1771565003128647,"rank":138,"remainingConfigurations":398},{"removed":"automationbench","score":0.17996814379498763,"rank":134,"remainingConfigurations":398},{"removed":"critpt","score":0.17869890679846256,"rank":139,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18019494687554746,"rank":136,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.18124680902539658,"rank":135,"remainingConfigurations":398},{"removed":"gdpval","score":0.1822224844732447,"rank":133,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17787337916001325,"rank":138,"remainingConfigurations":398},{"removed":"gpqa","score":0.1793635994893805,"rank":132,"remainingConfigurations":398},{"removed":"harvey","score":0.17849349107858312,"rank":137,"remainingConfigurations":398},{"removed":"hle","score":0.18708984463855835,"rank":134,"remainingConfigurations":398},{"removed":"ifbench","score":0.17691746351251283,"rank":136,"remainingConfigurations":398},{"removed":"itbench","score":0.1799680515866692,"rank":136,"remainingConfigurations":398},{"removed":"livecodebench","score":0.18180398246525734,"rank":135,"remainingConfigurations":398},{"removed":"math500","score":0.18089995525704997,"rank":135,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18433161019318703,"rank":135,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18996632275376135,"rank":133,"remainingConfigurations":398},{"removed":"omniscience","score":0.1743613048658832,"rank":142,"remainingConfigurations":398},{"removed":"scicode","score":0.18196418085827726,"rank":135,"remainingConfigurations":398},{"removed":"tau-bench","score":0.18003901897083155,"rank":134,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18402696809658647,"rank":132,"remainingConfigurations":398},{"removed":"arc-agi","score":0.22579618703788454,"rank":121,"remainingConfigurations":398},{"removed":"deepswe","score":0.15520941528359578,"rank":136,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.18018555878428896,"rank":136,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17656699626650116,"rank":137,"remainingConfigurations":398},{"removed":"frontiercode","score":0.18720865177024174,"rank":138,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1802051379990456,"rank":136,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17876077546991032,"rank":136,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17987523152362242,"rank":136,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1795401039124843,"rank":136,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1803646065450085,"rank":136,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1790971034970313,"rank":136,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1816715632121736,"rank":136,"remainingConfigurations":398},{"removed":"livebench-data","score":0.18032019540078367,"rank":135,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1779604556620581,"rank":135,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17927654680011407,"rank":136,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18235800658684945,"rank":136,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1919925960425918,"rank":128,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1720894894035863,"rank":138,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1818467738982853,"rank":135,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1853271740021464,"rank":135,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1794716502295656,"rank":135,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17964357962197922,"rank":136,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17966281792333524,"rank":136,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1798722538686711,"rank":135,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17914202994710415,"rank":135,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-medium":{"score":0.17966497894323227,"rank":137,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14187022277533554,"rank":110,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2104180115048826,"rank":134,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15888656984006186,"rank":133,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17952192467542114,"rank":137,"remainingConfigurations":398},{"removed":"Scale","score":0.19283966408412714,"rank":136,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17889729752077543,"rank":137,"remainingConfigurations":398},{"removed":"Cognition","score":0.16453356638308814,"rank":157,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18476940914344908,"rank":134,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17922136042022327,"rank":140,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.21614840846125305,"rank":114,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1748503065033601,"rank":136,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17971144692183275,"rank":137,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.179721002419469,"rank":137,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17959371440424435,"rank":137,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17966497894323227,"rank":137,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17967246979824134,"rank":137,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1801747251042036,"rank":137,"remainingConfigurations":398},{"removed":"briefcase","score":0.1787942044738824,"rank":136,"remainingConfigurations":398},{"removed":"aime","score":0.1780295736747629,"rank":138,"remainingConfigurations":398},{"removed":"apex-agents","score":0.18085728450696267,"rank":136,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.17987479016898586,"rank":135,"remainingConfigurations":398},{"removed":"automationbench","score":0.1783549353489432,"rank":136,"remainingConfigurations":398},{"removed":"critpt","score":0.1783994549607204,"rank":140,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.18004612336876522,"rank":137,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.177703396262579,"rank":139,"remainingConfigurations":398},{"removed":"gdpval","score":0.17848035454752853,"rank":137,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18010492620719487,"rank":137,"remainingConfigurations":398},{"removed":"gpqa","score":0.17627140104100636,"rank":137,"remainingConfigurations":398},{"removed":"harvey","score":0.1786169024745294,"rank":136,"remainingConfigurations":398},{"removed":"hle","score":0.18569443720070936,"rank":137,"remainingConfigurations":398},{"removed":"ifbench","score":0.1812175481371828,"rank":131,"remainingConfigurations":398},{"removed":"itbench","score":0.1796704594919153,"rank":137,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1798873942141734,"rank":138,"remainingConfigurations":398},{"removed":"math500","score":0.17986558002246203,"rank":137,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1837981577275356,"rank":137,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1879478534049626,"rank":136,"remainingConfigurations":398},{"removed":"omniscience","score":0.17792506147964374,"rank":137,"remainingConfigurations":398},{"removed":"scicode","score":0.17988428633018172,"rank":136,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1805729464677163,"rank":132,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1793078907587912,"rank":139,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18054445432342048,"rank":155,"remainingConfigurations":398},{"removed":"deepswe","score":0.15888878391575192,"rank":133,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17970165469388136,"rank":137,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.20107315407120074,"rank":120,"remainingConfigurations":398},{"removed":"frontiercode","score":0.16453356638308814,"rank":157,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17998412893516227,"rank":137,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1778929845414461,"rank":137,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17955113862852237,"rank":137,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1791047826615804,"rank":137,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17998674727813535,"rank":137,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17844781135261176,"rank":137,"remainingConfigurations":398},{"removed":"livebench-language","score":0.18118966174166984,"rank":137,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17980140322840463,"rank":136,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17752629720214597,"rank":136,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17878719794820974,"rank":137,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.18193317625322983,"rank":137,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17922136042022327,"rank":140,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.20854720963931975,"rank":118,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17632501805978582,"rank":143,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18464694905285373,"rank":136,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17898635395872012,"rank":136,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17917741454532934,"rank":137,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17916448885048528,"rank":137,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17933411644182387,"rank":136,"remainingConfigurations":398},{"removed":"vibe-code","score":0.178706703340765,"rank":136,"remainingConfigurations":398}]},"gpt-5--effort-medium":{"score":0.17753577888774363,"rank":138,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.17027583384477482,"rank":99,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.24660845423061029,"rank":115,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15274922571082247,"rank":141,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17808735445127735,"rank":138,"remainingConfigurations":398},{"removed":"Scale","score":0.19156381603904116,"rank":138,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17692394964218774,"rank":140,"remainingConfigurations":398},{"removed":"Cognition","score":0.18469237930339555,"rank":141,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17852729356591715,"rank":139,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1640218203998581,"rank":155,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.172186691629138,"rank":138,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1710861923136351,"rank":139,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17754215018308453,"rank":138,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17729133168928443,"rank":138,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1773355770618407,"rank":138,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17753577888774363,"rank":138,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1770771887797958,"rank":138,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17781682362707754,"rank":138,"remainingConfigurations":398},{"removed":"briefcase","score":0.17723770737384484,"rank":137,"remainingConfigurations":398},{"removed":"aime","score":0.176700668188439,"rank":140,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17855749145359245,"rank":138,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.17374806627366168,"rank":141,"remainingConfigurations":398},{"removed":"automationbench","score":0.17714043148493522,"rank":138,"remainingConfigurations":398},{"removed":"critpt","score":0.18964542914411361,"rank":130,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17754319705723384,"rank":138,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1783792762289044,"rank":137,"remainingConfigurations":398},{"removed":"gdpval","score":0.17793257389431485,"rank":138,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17471185665130828,"rank":143,"remainingConfigurations":398},{"removed":"gpqa","score":0.17643608253800971,"rank":136,"remainingConfigurations":398},{"removed":"harvey","score":0.17587496570737116,"rank":138,"remainingConfigurations":398},{"removed":"hle","score":0.18375626033714945,"rank":138,"remainingConfigurations":398},{"removed":"ifbench","score":0.1742705106204719,"rank":140,"remainingConfigurations":398},{"removed":"itbench","score":0.1773502751686811,"rank":138,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1824455077888002,"rank":134,"remainingConfigurations":398},{"removed":"math500","score":0.17775734457280812,"rank":138,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18041440902598538,"rank":139,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1862057392484364,"rank":139,"remainingConfigurations":398},{"removed":"omniscience","score":0.16974252181363078,"rank":147,"remainingConfigurations":398},{"removed":"scicode","score":0.17910315078521136,"rank":139,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17760596149481814,"rank":137,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1761737561114348,"rank":144,"remainingConfigurations":398},{"removed":"arc-agi","score":0.24555478291512378,"rank":115,"remainingConfigurations":398},{"removed":"deepswe","score":0.15282638184399835,"rank":141,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17757051685199887,"rank":138,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1739473575822995,"rank":141,"remainingConfigurations":398},{"removed":"frontiercode","score":0.18469237930339555,"rank":141,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17758848140737168,"rank":138,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1761592323123243,"rank":138,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17726192000586297,"rank":138,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17694081489326077,"rank":138,"remainingConfigurations":398},{"removed":"livebench-math","score":0.177746415425718,"rank":138,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1764859821335656,"rank":138,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17903778281708946,"rank":138,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1777001710556274,"rank":137,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17537038387453396,"rank":139,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17667085113790593,"rank":138,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17974166765718824,"rank":138,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1640218203998581,"rank":155,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16939896609095673,"rank":140,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17926703118800225,"rank":137,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18267308937244378,"rank":138,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1768672921752156,"rank":138,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17702985096561183,"rank":138,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17705896746300867,"rank":138,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17725130552465052,"rank":138,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1765369672711967,"rank":138,"remainingConfigurations":398}]},"gpt-5.6-sol--effort-none":{"score":0.17683188883068016,"rank":139,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1601915682158816,"rank":102,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1990617777151301,"rank":140,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15401774563052506,"rank":139,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17638609733713018,"rank":140,"remainingConfigurations":398},{"removed":"Scale","score":0.19046778211736948,"rank":141,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1769249615645511,"rank":139,"remainingConfigurations":398},{"removed":"Cognition","score":0.1846771969891828,"rank":142,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17601495865243488,"rank":141,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1797970388326404,"rank":137,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.170870683300394,"rank":140,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17683821222684862,"rank":139,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17661580818676084,"rank":139,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17668770459611813,"rank":139,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17683188883068016,"rank":139,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1764596943400042,"rank":139,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1771448684443763,"rank":139,"remainingConfigurations":398},{"removed":"briefcase","score":0.17670556384389505,"rank":139,"remainingConfigurations":398},{"removed":"aime","score":0.21140910943115257,"rank":118,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17788474384600525,"rank":139,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1772652765684671,"rank":137,"remainingConfigurations":398},{"removed":"automationbench","score":0.1767655936659216,"rank":139,"remainingConfigurations":398},{"removed":"critpt","score":0.1753227415936587,"rank":144,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17697919592579878,"rank":139,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17761004679343237,"rank":140,"remainingConfigurations":398},{"removed":"gdpval","score":0.17614440040369747,"rank":143,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17742730076586535,"rank":139,"remainingConfigurations":398},{"removed":"gpqa","score":0.17449821981511213,"rank":141,"remainingConfigurations":398},{"removed":"harvey","score":0.17521341356160514,"rank":139,"remainingConfigurations":398},{"removed":"hle","score":0.18187282884980246,"rank":142,"remainingConfigurations":398},{"removed":"ifbench","score":0.17749033796141958,"rank":135,"remainingConfigurations":398},{"removed":"itbench","score":0.17661407185855058,"rank":139,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17692600875226647,"rank":140,"remainingConfigurations":398},{"removed":"math500","score":0.17710409716844547,"rank":139,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18103382022558157,"rank":138,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18533436095223035,"rank":141,"remainingConfigurations":398},{"removed":"omniscience","score":0.17664299043113532,"rank":138,"remainingConfigurations":398},{"removed":"scicode","score":0.17823106066290598,"rank":142,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17238888855144255,"rank":142,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17648770514070986,"rank":143,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19791705372013926,"rank":138,"remainingConfigurations":398},{"removed":"deepswe","score":0.15413210797819596,"rank":139,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17686508282995725,"rank":139,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17619691939561874,"rank":139,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1846771969891828,"rank":142,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17736045547649235,"rank":139,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17503988335191265,"rank":142,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17664988242588278,"rank":139,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17633723541413918,"rank":139,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17721604412761652,"rank":139,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17532850446507617,"rank":142,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17836709634926828,"rank":139,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17724285339322574,"rank":138,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17484442866906413,"rank":140,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17588970198523024,"rank":139,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.178933844245026,"rank":139,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1797970388326404,"rank":137,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.11224449937058227,"rank":181,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1771655196781172,"rank":142,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17996461176660009,"rank":142,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17616292049760043,"rank":140,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17644258464759932,"rank":139,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1761320038708747,"rank":140,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17665242899458602,"rank":139,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1760375502127105,"rank":139,"remainingConfigurations":398}]},"o4-mini--effort-high":{"score":0.17672216851847145,"rank":140,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.18909054117264132,"rank":94,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1364214949130427,"rank":178,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15232543199946022,"rank":142,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12076494584090712,"rank":179,"remainingConfigurations":398},{"removed":"Scale","score":0.19081932306363836,"rank":139,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17610353597698877,"rank":141,"remainingConfigurations":398},{"removed":"Cognition","score":0.1850375589088661,"rank":140,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17846510442549277,"rank":140,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17717687389962097,"rank":141,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17259345494641654,"rank":137,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17032632245878895,"rank":142,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17673073987310314,"rank":140,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17645614607228077,"rank":140,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17653337623279222,"rank":140,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17672216851847145,"rank":140,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17625609239722698,"rank":140,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17701536782651375,"rank":140,"remainingConfigurations":398},{"removed":"briefcase","score":0.17645686547761172,"rank":140,"remainingConfigurations":398},{"removed":"aime","score":0.17460684796828171,"rank":142,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17771160907592173,"rank":141,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.17775280832897655,"rank":136,"remainingConfigurations":398},{"removed":"automationbench","score":0.17634323802853058,"rank":140,"remainingConfigurations":398},{"removed":"critpt","score":0.17763234891050206,"rank":141,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17671087334596644,"rank":140,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17751439257782511,"rank":141,"remainingConfigurations":398},{"removed":"gdpval","score":0.1771865014255853,"rank":140,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1769326585707595,"rank":141,"remainingConfigurations":398},{"removed":"gpqa","score":0.17710179914650426,"rank":134,"remainingConfigurations":398},{"removed":"harvey","score":0.17506126558754062,"rank":140,"remainingConfigurations":398},{"removed":"hle","score":0.18358744968974294,"rank":139,"remainingConfigurations":398},{"removed":"ifbench","score":0.17232883110106947,"rank":142,"remainingConfigurations":398},{"removed":"itbench","score":0.17653866447330743,"rank":140,"remainingConfigurations":398},{"removed":"livecodebench","score":0.11831881734705713,"rank":180,"remainingConfigurations":398},{"removed":"math500","score":0.17481851144075333,"rank":142,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.18013268970676488,"rank":141,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18639265273466896,"rank":137,"remainingConfigurations":398},{"removed":"omniscience","score":0.17236854582652564,"rank":144,"remainingConfigurations":398},{"removed":"scicode","score":0.17815279160461261,"rank":143,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17960679480996133,"rank":135,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.18107185532303097,"rank":135,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1355952708347531,"rank":181,"remainingConfigurations":398},{"removed":"deepswe","score":0.15240161632035712,"rank":142,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.176756715212489,"rank":140,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17327424674756178,"rank":142,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1850375589088661,"rank":140,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17676626789237157,"rank":140,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17536936084482793,"rank":139,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1764547931294983,"rank":140,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17611082784344204,"rank":140,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17693873422951037,"rank":140,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17567981535203492,"rank":139,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17823247255300886,"rank":140,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1768709280267903,"rank":139,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17455121897492665,"rank":141,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1758880860844958,"rank":140,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17889525392450636,"rank":140,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17717687389962097,"rank":141,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16745162494670063,"rank":141,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17854481165709202,"rank":138,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18183051450941243,"rank":141,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1760485157664029,"rank":141,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17620915779385127,"rank":140,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1762631481535432,"rank":139,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17642468788693236,"rank":141,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17571319913233716,"rank":140,"remainingConfigurations":398}]},"grok-4.5--effort-low":{"score":0.17654588924074235,"rank":141,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15598949555339608,"rank":105,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08060513699841783,"rank":237,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14135050979969513,"rank":153,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17711632712146988,"rank":139,"remainingConfigurations":398},{"removed":"Scale","score":0.18955307682502429,"rank":142,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17418098583355265,"rank":142,"remainingConfigurations":398},{"removed":"Cognition","score":0.26827687863462424,"rank":96,"remainingConfigurations":398},{"removed":"LiveBench","score":0.18050970986370915,"rank":137,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17525204797124283,"rank":144,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1819883393894629,"rank":131,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17052575279753315,"rank":141,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17655910798140528,"rank":141,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17625017330857828,"rank":142,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17646484475620908,"rank":141,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17654588924074235,"rank":141,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17616076580943574,"rank":141,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17690840706932365,"rank":141,"remainingConfigurations":398},{"removed":"briefcase","score":0.17568742270002494,"rank":142,"remainingConfigurations":398},{"removed":"aime","score":0.17579218080781142,"rank":141,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17733929638681992,"rank":142,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1764318303602517,"rank":139,"remainingConfigurations":398},{"removed":"automationbench","score":0.17537543365164318,"rank":142,"remainingConfigurations":398},{"removed":"critpt","score":0.1769332131157053,"rank":142,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17659851057191278,"rank":141,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17643389620525374,"rank":142,"remainingConfigurations":398},{"removed":"gdpval","score":0.17626468474112703,"rank":142,"remainingConfigurations":398},{"removed":"gmmlu","score":0.176583860106997,"rank":142,"remainingConfigurations":398},{"removed":"gpqa","score":0.17605014572617664,"rank":139,"remainingConfigurations":398},{"removed":"harvey","score":0.1747637964230696,"rank":141,"remainingConfigurations":398},{"removed":"hle","score":0.1833049445065262,"rank":140,"remainingConfigurations":398},{"removed":"ifbench","score":0.1754234443085094,"rank":139,"remainingConfigurations":398},{"removed":"itbench","score":0.17638353084862743,"rank":141,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17705263215177588,"rank":139,"remainingConfigurations":398},{"removed":"math500","score":0.17658987753949637,"rank":141,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1804015162320055,"rank":140,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18511368205217663,"rank":142,"remainingConfigurations":398},{"removed":"omniscience","score":0.1752526738678916,"rank":141,"remainingConfigurations":398},{"removed":"scicode","score":0.177436309105247,"rank":144,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17647181168554762,"rank":138,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17454688180248393,"rank":145,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1865812980231141,"rank":151,"remainingConfigurations":398},{"removed":"deepswe","score":0.1413777896219346,"rank":153,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1765788144705729,"rank":142,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17621055004942077,"rank":138,"remainingConfigurations":398},{"removed":"frontiercode","score":0.26827687863462424,"rank":96,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17667356879140628,"rank":141,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17506423581655772,"rank":141,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17635679504260662,"rank":141,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1759591268770914,"rank":141,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17679732545202856,"rank":141,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17537808075964112,"rank":141,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17798906787327717,"rank":142,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17680636516842452,"rank":140,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1744100321002601,"rank":142,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1756521653360816,"rank":142,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17881307275020628,"rank":141,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17525204797124283,"rank":144,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1726390460824283,"rank":137,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1775561346452439,"rank":141,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1818350120526975,"rank":140,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1762304428939171,"rank":139,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17596057748762153,"rank":142,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17589331967833585,"rank":142,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1764393948623905,"rank":140,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17566511967878554,"rank":141,"remainingConfigurations":398}]},"minimax-m2.5--effort-reasoning":{"score":0.1765418685653942,"rank":142,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2044399392408708,"rank":136,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15459778336011223,"rank":138,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1753475989517377,"rank":141,"remainingConfigurations":398},{"removed":"Scale","score":0.190640104538083,"rank":140,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17694815788486082,"rank":138,"remainingConfigurations":398},{"removed":"Cognition","score":0.18336128475292204,"rank":143,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1792087913790326,"rank":138,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1797895033557968,"rank":138,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17679695833750034,"rank":133,"remainingConfigurations":381},{"removed":"Vals AI","score":0.17206341618050172,"rank":138,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17655039524807592,"rank":142,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17639660685948447,"rank":141,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17627830521605684,"rank":142,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1765418685653942,"rank":142,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17611954581998168,"rank":142,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1768436617816702,"rank":142,"remainingConfigurations":398},{"removed":"briefcase","score":0.17573961530682888,"rank":141,"remainingConfigurations":398},{"removed":"aime","score":0.17728319612704024,"rank":139,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17787029864616488,"rank":140,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1719665248260243,"rank":142,"remainingConfigurations":398},{"removed":"automationbench","score":0.17584061507241996,"rank":141,"remainingConfigurations":398},{"removed":"critpt","score":0.18067910096574238,"rank":136,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1764227674143172,"rank":142,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17774638535057855,"rank":138,"remainingConfigurations":398},{"removed":"gdpval","score":0.1768475592461166,"rank":141,"remainingConfigurations":398},{"removed":"gmmlu","score":0.18992285680254226,"rank":126,"remainingConfigurations":398},{"removed":"gpqa","score":0.17155829985737658,"rank":145,"remainingConfigurations":398},{"removed":"harvey","score":0.17468820511269686,"rank":142,"remainingConfigurations":398},{"removed":"hle","score":0.1867109180118138,"rank":135,"remainingConfigurations":398},{"removed":"ifbench","score":0.1697968253888801,"rank":145,"remainingConfigurations":398},{"removed":"itbench","score":0.17615543005198311,"rank":142,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17603713075991786,"rank":141,"remainingConfigurations":398},{"removed":"math500","score":0.17665077327037793,"rank":140,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17982003015319248,"rank":142,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18502178043863157,"rank":143,"remainingConfigurations":398},{"removed":"omniscience","score":0.17575328810716925,"rank":139,"remainingConfigurations":398},{"removed":"scicode","score":0.17855129056521649,"rank":140,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16651836077436868,"rank":150,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1769841285369875,"rank":141,"remainingConfigurations":398},{"removed":"arc-agi","score":0.20338562498272664,"rank":134,"remainingConfigurations":398},{"removed":"deepswe","score":0.15469845631836496,"rank":138,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1765819364035017,"rank":141,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17539996674348712,"rank":140,"remainingConfigurations":398},{"removed":"frontiercode","score":0.18336128475292204,"rank":143,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1766056542860526,"rank":142,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17520135335891027,"rank":140,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17627717618866576,"rank":142,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17594760067842927,"rank":142,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17678014120097488,"rank":142,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1754935775905744,"rank":140,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17814360821855402,"rank":141,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17678443537336133,"rank":141,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1743800271107208,"rank":143,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17565431682822183,"rank":141,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1785613413665995,"rank":142,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1797895033557968,"rank":138,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16963820242463798,"rank":139,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17808174645219096,"rank":139,"remainingConfigurations":398},{"removed":"simpleqa","score":0.18196197170872522,"rank":139,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17587262078361054,"rank":142,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17607436731445403,"rank":141,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1759707430294941,"rank":141,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1763464111848064,"rank":142,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17561483278839507,"rank":142,"remainingConfigurations":398}]},"gemini-3.5-flash-lite--effort-reasoning":{"score":0.17298964905674763,"rank":143,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19968911019004168,"rank":138,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15054826143065533,"rank":143,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17188156898709261,"rank":142,"remainingConfigurations":398},{"removed":"Scale","score":0.18641871537693222,"rank":143,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1732576975862216,"rank":143,"remainingConfigurations":398},{"removed":"Cognition","score":0.17843529238077804,"rank":144,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1760103644075971,"rank":142,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1768713379677267,"rank":142,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17501161330960868,"rank":135,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16861051343870534,"rank":143,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1729975531671456,"rank":143,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17282550762436366,"rank":143,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17271697705047365,"rank":143,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17298964905674763,"rank":143,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17253889090041752,"rank":143,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17394893543108395,"rank":143,"remainingConfigurations":398},{"removed":"briefcase","score":0.17688065815877504,"rank":138,"remainingConfigurations":398},{"removed":"aime","score":0.17317413611691668,"rank":143,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1751705445848022,"rank":143,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16948046336488443,"rank":144,"remainingConfigurations":398},{"removed":"automationbench","score":0.1656985014392236,"rank":152,"remainingConfigurations":398},{"removed":"critpt","score":0.20566352310346322,"rank":122,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16103186009237344,"rank":156,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16422640318134782,"rank":153,"remainingConfigurations":398},{"removed":"gdpval","score":0.17221222116963017,"rank":144,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17373830771413568,"rank":144,"remainingConfigurations":398},{"removed":"gpqa","score":0.17065336473973378,"rank":146,"remainingConfigurations":398},{"removed":"harvey","score":0.1722616807367553,"rank":143,"remainingConfigurations":398},{"removed":"hle","score":0.1819041030793959,"rank":141,"remainingConfigurations":398},{"removed":"ifbench","score":0.1693293707210339,"rank":146,"remainingConfigurations":398},{"removed":"itbench","score":0.1733123491935149,"rank":143,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17253135812553536,"rank":142,"remainingConfigurations":398},{"removed":"math500","score":0.17327966742738035,"rank":143,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17654786254789365,"rank":143,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17145335189761388,"rank":153,"remainingConfigurations":398},{"removed":"omniscience","score":0.17209763645292073,"rank":145,"remainingConfigurations":398},{"removed":"scicode","score":0.18256756680465772,"rank":134,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1692934201286451,"rank":145,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17191860644085258,"rank":148,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19878253869165116,"rank":136,"remainingConfigurations":398},{"removed":"deepswe","score":0.1506527213836312,"rank":143,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17303273099372932,"rank":143,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1719406717865444,"rank":143,"remainingConfigurations":398},{"removed":"frontiercode","score":0.17843529238077804,"rank":144,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1730887014211494,"rank":143,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.17162054878584912,"rank":143,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1727510956905377,"rank":143,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17234132490972834,"rank":143,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17321903233088054,"rank":144,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17197377375819797,"rank":143,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17460428352649474,"rank":143,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1732550664703519,"rank":142,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17082489454725705,"rank":144,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.17210777440061845,"rank":143,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17495123424428818,"rank":144,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1768713379677267,"rank":142,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16698030027030755,"rank":142,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1742008047870303,"rank":144,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17823643284246313,"rank":143,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17232026110538945,"rank":143,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1725397993006841,"rank":143,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1724130868541688,"rank":143,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17282320033334755,"rank":143,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1720547719758639,"rank":143,"remainingConfigurations":398}]},"qwen3.6-27b--effort-reasoning":{"score":0.17190312125583818,"rank":144,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19818089589655777,"rank":142,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1494538922405697,"rank":145,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17076182398214038,"rank":144,"remainingConfigurations":398},{"removed":"Scale","score":0.18550585194518956,"rank":144,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17203201824538153,"rank":144,"remainingConfigurations":398},{"removed":"Cognition","score":0.17720979848072257,"rank":146,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17492836501289208,"rank":143,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17547698536672682,"rank":143,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17357107512467274,"rank":136,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16740417999317816,"rank":145,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17190880261086453,"rank":144,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17174794186346184,"rank":144,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17159627244770534,"rank":144,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17190312125583818,"rank":144,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1714249120910484,"rank":144,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1725760750252423,"rank":144,"remainingConfigurations":398},{"removed":"briefcase","score":0.17096236728276507,"rank":144,"remainingConfigurations":398},{"removed":"aime","score":0.17208328141203214,"rank":145,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17364437894553553,"rank":144,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1649255062764146,"rank":149,"remainingConfigurations":398},{"removed":"automationbench","score":0.17242920778026707,"rank":143,"remainingConfigurations":398},{"removed":"critpt","score":0.17426477937651152,"rank":145,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17219786733729578,"rank":143,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1681523964798575,"rank":150,"remainingConfigurations":398},{"removed":"gdpval","score":0.17113946026338803,"rank":147,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17272654470373583,"rank":145,"remainingConfigurations":398},{"removed":"gpqa","score":0.16880789206777935,"rank":148,"remainingConfigurations":398},{"removed":"harvey","score":0.1635424021517273,"rank":152,"remainingConfigurations":398},{"removed":"hle","score":0.1778381803331527,"rank":148,"remainingConfigurations":398},{"removed":"ifbench","score":0.16814964388204723,"rank":147,"remainingConfigurations":398},{"removed":"itbench","score":0.17175373562483565,"rank":144,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1713720549262565,"rank":145,"remainingConfigurations":398},{"removed":"math500","score":0.17206516723840237,"rank":144,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17533902597623333,"rank":145,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1788530620467084,"rank":147,"remainingConfigurations":398},{"removed":"omniscience","score":0.18387004177198082,"rank":130,"remainingConfigurations":398},{"removed":"scicode","score":0.1792297720950252,"rank":138,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1667785015344522,"rank":149,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17657107855544,"rank":142,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19742459289726158,"rank":140,"remainingConfigurations":398},{"removed":"deepswe","score":0.14955754513047073,"rank":145,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17194521253718187,"rank":144,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17085401316404877,"rank":145,"remainingConfigurations":398},{"removed":"frontiercode","score":0.17720979848072257,"rank":146,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17203193680444784,"rank":145,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1705559995655068,"rank":144,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1716563843056715,"rank":144,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1712702515668387,"rank":144,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17213042640963536,"rank":145,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1708913040032324,"rank":144,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17350577928919475,"rank":144,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17215997596369378,"rank":144,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1697571805205642,"rank":145,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1710284450824724,"rank":144,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17385684451549832,"rank":145,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17547698536672682,"rank":143,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16590915881163468,"rank":143,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17318771850795442,"rank":145,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17715290136752013,"rank":144,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.17123711946879192,"rank":144,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17145277995301492,"rank":144,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17133751366776226,"rank":144,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17172669823758727,"rank":144,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1709825199705912,"rank":144,"remainingConfigurations":398}]},"claude-sonnet-4-6--effort-medium":{"score":0.17140037618560014,"rank":145,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.17188217062698785,"rank":98,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.17592569516528642,"rank":160,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1531900123485743,"rank":140,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17143170975936114,"rank":143,"remainingConfigurations":398},{"removed":"Scale","score":0.18347744354291193,"rank":149,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17137239785260794,"rank":146,"remainingConfigurations":398},{"removed":"Cognition","score":0.23966134111568635,"rank":113,"remainingConfigurations":398},{"removed":"LiveBench","score":0.12360508790099896,"rank":178,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1682388051502993,"rank":151,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.19693026470014896,"rank":121,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16818799766332684,"rank":144,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17140074998218516,"rank":146,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17137008292237751,"rank":145,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.17094722985130892,"rank":146,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17140037618560014,"rank":145,"remainingConfigurations":398},{"removed":"All provider reports","score":0.17090251967166778,"rank":146,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17147100215778102,"rank":146,"remainingConfigurations":398},{"removed":"briefcase","score":0.1711954499111689,"rank":143,"remainingConfigurations":398},{"removed":"aime","score":0.16003399371157004,"rank":154,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1718987297611324,"rank":147,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.17162642755399382,"rank":143,"remainingConfigurations":398},{"removed":"automationbench","score":0.17135257559258568,"rank":144,"remainingConfigurations":398},{"removed":"critpt","score":0.17090374878939527,"rank":147,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17135676428366398,"rank":144,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17201630737602105,"rank":144,"remainingConfigurations":398},{"removed":"gdpval","score":0.17116997870818515,"rank":146,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1716141105975508,"rank":147,"remainingConfigurations":398},{"removed":"gpqa","score":0.17039627139591132,"rank":147,"remainingConfigurations":398},{"removed":"harvey","score":0.17017438615057648,"rank":144,"remainingConfigurations":398},{"removed":"hle","score":0.17622816891797244,"rank":150,"remainingConfigurations":398},{"removed":"ifbench","score":0.17070868056206165,"rank":143,"remainingConfigurations":398},{"removed":"itbench","score":0.171200866987416,"rank":145,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17154892656533827,"rank":143,"remainingConfigurations":398},{"removed":"math500","score":0.17146334502220642,"rank":145,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1748018762053426,"rank":146,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17965739014046553,"rank":145,"remainingConfigurations":398},{"removed":"omniscience","score":0.17128245416510543,"rank":146,"remainingConfigurations":398},{"removed":"scicode","score":0.171935770590283,"rank":149,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1698540105217717,"rank":144,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17200158563679072,"rank":147,"remainingConfigurations":398},{"removed":"arc-agi","score":0.17479257055521616,"rank":161,"remainingConfigurations":398},{"removed":"deepswe","score":0.15329444503173079,"rank":140,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1714541698371932,"rank":145,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1710182144162453,"rank":144,"remainingConfigurations":398},{"removed":"frontiercode","score":0.23966134111568635,"rank":113,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17233781454767327,"rank":144,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16974249927447385,"rank":146,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1713032144663733,"rank":145,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17096177692623696,"rank":145,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17479302094854798,"rank":143,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16168295423114332,"rank":152,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17325208210385568,"rank":145,"remainingConfigurations":398},{"removed":"livebench-data","score":0.16896695738529047,"rank":150,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.17558652056711554,"rank":138,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16797270800361938,"rank":150,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17768135665959794,"rank":143,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1682388051502993,"rank":151,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.18544013142700755,"rank":127,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17101263693227053,"rank":149,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17465687474925795,"rank":148,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1704866796131401,"rank":146,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17120086976527968,"rank":145,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1709686998780461,"rank":145,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17108820122389892,"rank":146,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17038490761447952,"rank":146,"remainingConfigurations":398}]},"o3--effort-reasoning":{"score":0.17139439586952887,"rank":146,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1996112826977772,"rank":139,"remainingConfigurations":398},{"removed":"Datacurve","score":0.15004033998257546,"rank":144,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.17003772397014102,"rank":145,"remainingConfigurations":398},{"removed":"Scale","score":0.1853012955079355,"rank":145,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17178928430023824,"rank":145,"remainingConfigurations":398},{"removed":"Cognition","score":0.17831107523232018,"rank":145,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17408255749929832,"rank":144,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17475952021448035,"rank":145,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17093529817179554,"rank":140,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16716332471159567,"rank":146,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17140290112297007,"rank":145,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17124934298312675,"rank":146,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1711312874034002,"rank":145,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17139439586952887,"rank":146,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1709731979733606,"rank":145,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17172027165996018,"rank":145,"remainingConfigurations":398},{"removed":"briefcase","score":0.1708182113247508,"rank":146,"remainingConfigurations":398},{"removed":"aime","score":0.17280019968329866,"rank":144,"remainingConfigurations":398},{"removed":"apex-agents","score":0.172727994694,"rank":146,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16533946338641262,"rank":148,"remainingConfigurations":398},{"removed":"automationbench","score":0.17097588834165464,"rank":145,"remainingConfigurations":398},{"removed":"critpt","score":0.17331083432153097,"rank":146,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17131988246835195,"rank":145,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1727995995759104,"rank":143,"remainingConfigurations":398},{"removed":"gdpval","score":0.17196397774087635,"rank":145,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17225934974414905,"rank":146,"remainingConfigurations":398},{"removed":"gpqa","score":0.17186669575043426,"rank":144,"remainingConfigurations":398},{"removed":"harvey","score":0.16961987199219183,"rank":145,"remainingConfigurations":398},{"removed":"hle","score":0.18088793407716688,"rank":146,"remainingConfigurations":398},{"removed":"ifbench","score":0.16588770366134584,"rank":148,"remainingConfigurations":398},{"removed":"itbench","score":0.17108620290740872,"rank":146,"remainingConfigurations":398},{"removed":"livecodebench","score":0.17137343305250394,"rank":144,"remainingConfigurations":398},{"removed":"math500","score":0.17115983222545614,"rank":146,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17567785469270666,"rank":144,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18631750861654894,"rank":138,"remainingConfigurations":398},{"removed":"omniscience","score":0.15742364567849879,"rank":157,"remainingConfigurations":398},{"removed":"scicode","score":0.17362491169573166,"rank":146,"remainingConfigurations":398},{"removed":"tau-bench","score":0.17582037492625327,"rank":139,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16951159028405635,"rank":149,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19847362661858592,"rank":137,"remainingConfigurations":398},{"removed":"deepswe","score":0.15013822369411592,"rank":144,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1714334984691064,"rank":146,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.17026996584911522,"rank":146,"remainingConfigurations":398},{"removed":"frontiercode","score":0.17831107523232018,"rank":145,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1714537661807438,"rank":146,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1700554996651503,"rank":145,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.17114306305658789,"rank":146,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.17082044946031824,"rank":146,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17162745156854642,"rank":146,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.170366637753088,"rank":145,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17296590867039296,"rank":146,"remainingConfigurations":398},{"removed":"livebench-data","score":0.171631790032561,"rank":145,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16927339060531424,"rank":146,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1705228909227353,"rank":145,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1733783914254873,"rank":146,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17475952021448035,"rank":145,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16434145826453112,"rank":144,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1729056615086889,"rank":146,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17674439273606524,"rank":145,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1707360318712773,"rank":145,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.17093523145404313,"rank":146,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.17083634763481867,"rank":146,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17119946006213024,"rank":145,"remainingConfigurations":398},{"removed":"vibe-code","score":0.17048408100905832,"rank":145,"remainingConfigurations":398}]},"grok-4.3--effort-low":{"score":0.17019850024176839,"rank":147,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19851165411592842,"rank":141,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14872941309475332,"rank":146,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16900724540598955,"rank":146,"remainingConfigurations":398},{"removed":"Scale","score":0.1841877767562435,"rank":147,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1705326685481893,"rank":147,"remainingConfigurations":398},{"removed":"Cognition","score":0.17645999150134975,"rank":147,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1729892611277,"rank":145,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17398373350084986,"rank":146,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17072874812490413,"rank":141,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16600876420181265,"rank":147,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17020683733560635,"rank":147,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17005432316169097,"rank":147,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16993734195579027,"rank":147,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.17019850024176839,"rank":147,"remainingConfigurations":398},{"removed":"All provider reports","score":0.16977992724738764,"rank":147,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17061140996717147,"rank":148,"remainingConfigurations":398},{"removed":"briefcase","score":0.16912324717279104,"rank":148,"remainingConfigurations":398},{"removed":"aime","score":0.17120258152102355,"rank":146,"remainingConfigurations":398},{"removed":"apex-agents","score":0.17159440559748865,"rank":148,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16266022983446837,"rank":151,"remainingConfigurations":398},{"removed":"automationbench","score":0.16941414460196114,"rank":148,"remainingConfigurations":398},{"removed":"critpt","score":0.18062343082418683,"rank":137,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.17002781050290947,"rank":146,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17133135396972918,"rank":146,"remainingConfigurations":398},{"removed":"gdpval","score":0.1707012980231258,"rank":148,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17119433692601363,"rank":149,"remainingConfigurations":398},{"removed":"gpqa","score":0.1670355160222449,"rank":150,"remainingConfigurations":398},{"removed":"harvey","score":0.16829151411043153,"rank":146,"remainingConfigurations":398},{"removed":"hle","score":0.1818339789112148,"rank":143,"remainingConfigurations":398},{"removed":"ifbench","score":0.15188176891686586,"rank":161,"remainingConfigurations":398},{"removed":"itbench","score":0.1698849046027632,"rank":147,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1698931306461381,"rank":146,"remainingConfigurations":398},{"removed":"math500","score":0.17031073167301872,"rank":148,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17343752486744746,"rank":148,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1789353766654751,"rank":146,"remainingConfigurations":398},{"removed":"omniscience","score":0.1680594278186394,"rank":150,"remainingConfigurations":398},{"removed":"scicode","score":0.17238698794334417,"rank":147,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16815653595529775,"rank":146,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1809469647198579,"rank":136,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19760539382588968,"rank":139,"remainingConfigurations":398},{"removed":"deepswe","score":0.14882594682293068,"rank":146,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17023731453127275,"rank":147,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16909092639948065,"rank":147,"remainingConfigurations":398},{"removed":"frontiercode","score":0.17645999150134975,"rank":147,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1702877405061578,"rank":147,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16888595822300637,"rank":147,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16994869395018322,"rank":147,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.16962755391246623,"rank":147,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1704300739355451,"rank":147,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16917105303066535,"rank":147,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17176320228412267,"rank":148,"remainingConfigurations":398},{"removed":"livebench-data","score":0.17043943321650282,"rank":146,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16808738326224512,"rank":147,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1693293067296271,"rank":146,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1721756772367348,"rank":147,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17398373350084986,"rank":146,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1633073457128158,"rank":146,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17159914086507225,"rank":147,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17549405854256753,"rank":146,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16954183822391297,"rank":147,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16974220934106735,"rank":147,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16964318424469157,"rank":147,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.17000190512170146,"rank":147,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1692903091630791,"rank":147,"remainingConfigurations":398}]},"deepseek-v3.2--effort-reasoning":{"score":0.1701740177531089,"rank":148,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19639986618138894,"rank":145,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14848847860186978,"rank":147,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16898384984586176,"rank":147,"remainingConfigurations":398},{"removed":"Scale","score":0.18372170715812364,"rank":148,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.17046650232514168,"rank":148,"remainingConfigurations":398},{"removed":"Cognition","score":0.17637306606379546,"rank":148,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17237294112278476,"rank":146,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1736166294839296,"rank":147,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.17102963030518822,"rank":139,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1654362240943289,"rank":148,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.17018102437021532,"rank":148,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.17003533878040944,"rank":148,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1699161938176655,"rank":148,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1701740177531089,"rank":148,"remainingConfigurations":398},{"removed":"All provider reports","score":0.16976263951426543,"rank":148,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17049563779533694,"rank":149,"remainingConfigurations":398},{"removed":"briefcase","score":0.16970759275433248,"rank":147,"remainingConfigurations":398},{"removed":"aime","score":0.1688528605716394,"rank":148,"remainingConfigurations":398},{"removed":"apex-agents","score":0.172890586389711,"rank":145,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16617272926700613,"rank":147,"remainingConfigurations":398},{"removed":"automationbench","score":0.16962990939605924,"rank":147,"remainingConfigurations":398},{"removed":"critpt","score":0.1677628028636142,"rank":150,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1698176608152793,"rank":147,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17142758890708543,"rank":145,"remainingConfigurations":398},{"removed":"gdpval","score":0.1813525805007866,"rank":134,"remainingConfigurations":398},{"removed":"gmmlu","score":0.171490165717509,"rank":148,"remainingConfigurations":398},{"removed":"gpqa","score":0.1685001216150447,"rank":149,"remainingConfigurations":398},{"removed":"harvey","score":0.16812412105225802,"rank":147,"remainingConfigurations":398},{"removed":"hle","score":0.17572657554822615,"rank":152,"remainingConfigurations":398},{"removed":"ifbench","score":0.1724731456060469,"rank":141,"remainingConfigurations":398},{"removed":"itbench","score":0.16977411764422815,"rank":148,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1678988275492168,"rank":148,"remainingConfigurations":398},{"removed":"math500","score":0.17052159600929262,"rank":147,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17267112282857996,"rank":149,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17870109648636975,"rank":148,"remainingConfigurations":398},{"removed":"omniscience","score":0.16246268441386236,"rank":153,"remainingConfigurations":398},{"removed":"scicode","score":0.1720226407390427,"rank":148,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16757366094606166,"rank":148,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1722534852896658,"rank":146,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19547174291519184,"rank":143,"remainingConfigurations":398},{"removed":"deepswe","score":0.14858944253640996,"rank":147,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.17021167091109082,"rank":148,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16908346462159587,"rank":148,"remainingConfigurations":398},{"removed":"frontiercode","score":0.17637306606379546,"rank":148,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.17022931543582628,"rank":148,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1688510414601859,"rank":148,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16992126023431633,"rank":148,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1695938352923759,"rank":148,"remainingConfigurations":398},{"removed":"livebench-math","score":0.17040412813743758,"rank":148,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16916725557756127,"rank":148,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1717472141122396,"rank":149,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1703943114041595,"rank":147,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16806359048441058,"rank":148,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1693118770898903,"rank":147,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17213602204054881,"rank":148,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1736166294839296,"rank":147,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1637711351617139,"rank":145,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17159057432554606,"rank":148,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1754671516817756,"rank":147,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16951997978593103,"rank":148,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16971464763134003,"rank":148,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16961556905762698,"rank":148,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16998117528079326,"rank":148,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1692740177298664,"rank":148,"remainingConfigurations":398}]},"mimo-v2-flash--effort-reasoning":{"score":0.16915166727461203,"rank":149,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1972155086166484,"rank":143,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14788035123309892,"rank":148,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16791318483557793,"rank":149,"remainingConfigurations":398},{"removed":"Scale","score":0.18299813953663388,"rank":150,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16952401238606862,"rank":149,"remainingConfigurations":398},{"removed":"Cognition","score":0.1757621425218325,"rank":149,"remainingConfigurations":398},{"removed":"LiveBench","score":0.171777102687064,"rank":148,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1723517720148345,"rank":148,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.16970861148462238,"rank":143,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1649363606270904,"rank":149,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1691596915803565,"rank":149,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16900952772522562,"rank":149,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16889969705722785,"rank":149,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.16915166727461203,"rank":149,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1687441732992249,"rank":149,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1695264469822122,"rank":151,"remainingConfigurations":398},{"removed":"briefcase","score":0.168447964167149,"rank":149,"remainingConfigurations":398},{"removed":"aime","score":0.16553769953201503,"rank":150,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1704449841166806,"rank":149,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16820130422474341,"rank":146,"remainingConfigurations":398},{"removed":"automationbench","score":0.16857201043953599,"rank":149,"remainingConfigurations":398},{"removed":"critpt","score":0.16321633978161115,"rank":151,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16911631961925813,"rank":148,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1704102599836469,"rank":147,"remainingConfigurations":398},{"removed":"gdpval","score":0.1699489982828771,"rank":149,"remainingConfigurations":398},{"removed":"gmmlu","score":0.17705117599694606,"rank":140,"remainingConfigurations":398},{"removed":"gpqa","score":0.1647745546804422,"rank":151,"remainingConfigurations":398},{"removed":"harvey","score":0.1674084642091825,"rank":148,"remainingConfigurations":398},{"removed":"hle","score":0.1761788076110716,"rank":151,"remainingConfigurations":398},{"removed":"ifbench","score":0.17052181920096207,"rank":144,"remainingConfigurations":398},{"removed":"itbench","score":0.16881632456172954,"rank":149,"remainingConfigurations":398},{"removed":"livecodebench","score":0.16549273729822098,"rank":149,"remainingConfigurations":398},{"removed":"math500","score":0.16923450809590398,"rank":149,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1745425054547288,"rank":147,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17785266425705817,"rank":149,"remainingConfigurations":398},{"removed":"omniscience","score":0.16869782355078863,"rank":149,"remainingConfigurations":398},{"removed":"scicode","score":0.17123011731554047,"rank":151,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16177438286101423,"rank":153,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.17706249606841343,"rank":140,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1962405199344087,"rank":142,"remainingConfigurations":398},{"removed":"deepswe","score":0.14797711700356303,"rank":148,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1691904471248097,"rank":149,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16803902760325684,"rank":149,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1757621425218325,"rank":149,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16920864035117633,"rank":149,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1678316483115758,"rank":149,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16890049797129889,"rank":149,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.16858726171709223,"rank":149,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1693832824278871,"rank":149,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16812625142544724,"rank":149,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17070928106796668,"rank":150,"remainingConfigurations":398},{"removed":"livebench-data","score":0.16938763102052093,"rank":148,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16704901694504423,"rank":149,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16828678191239219,"rank":148,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.17112573884105417,"rank":149,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1723517720148345,"rank":148,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16229034576257612,"rank":148,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17056499791347576,"rank":150,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17445997948000377,"rank":149,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16850033263375627,"rank":149,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16869559630612316,"rank":149,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16859759240166192,"rank":149,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16895733289324463,"rank":149,"remainingConfigurations":398},{"removed":"vibe-code","score":0.168249285122427,"rank":149,"remainingConfigurations":398}]},"claude-sonnet-5--effort-non-reasoning":{"score":0.1690355963418526,"rank":150,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19492352834286966,"rank":146,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14687399433149823,"rank":149,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16792074563889822,"rank":148,"remainingConfigurations":398},{"removed":"Scale","score":0.18190336919447433,"rank":151,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16925276209277898,"rank":150,"remainingConfigurations":398},{"removed":"Cognition","score":0.1745151810261245,"rank":151,"remainingConfigurations":398},{"removed":"LiveBench","score":0.17179787000667468,"rank":147,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1720967184712255,"rank":149,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.16982592677160432,"rank":142,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16461726087558157,"rank":150,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.16904120856156457,"rank":150,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16887985577298667,"rank":150,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1687623919780772,"rank":150,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1690355963418526,"rank":150,"remainingConfigurations":398},{"removed":"All provider reports","score":0.16859083619975024,"rank":150,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.16964829211120355,"rank":150,"remainingConfigurations":398},{"removed":"briefcase","score":0.16782599325737582,"rank":150,"remainingConfigurations":398},{"removed":"aime","score":0.16996682630233514,"rank":147,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1703994378452723,"rank":150,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16843853092865135,"rank":145,"remainingConfigurations":398},{"removed":"automationbench","score":0.16838375038725037,"rank":150,"remainingConfigurations":398},{"removed":"critpt","score":0.17046662860035502,"rank":148,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16893137208796838,"rank":149,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.17032726592970157,"rank":148,"remainingConfigurations":398},{"removed":"gdpval","score":0.1623436167349879,"rank":151,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1695297575633857,"rank":150,"remainingConfigurations":398},{"removed":"gpqa","score":0.1866316378199776,"rank":124,"remainingConfigurations":398},{"removed":"harvey","score":0.16729463684650736,"rank":149,"remainingConfigurations":398},{"removed":"hle","score":0.17673760849560813,"rank":149,"remainingConfigurations":398},{"removed":"ifbench","score":0.16533467985872322,"rank":149,"remainingConfigurations":398},{"removed":"itbench","score":0.16880505995955553,"rank":150,"remainingConfigurations":398},{"removed":"livecodebench","score":0.16876379257731047,"rank":147,"remainingConfigurations":398},{"removed":"math500","score":0.16904498463856607,"rank":150,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.17237919837611734,"rank":150,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.18285835594533875,"rank":144,"remainingConfigurations":398},{"removed":"omniscience","score":0.16349688289221756,"rank":152,"remainingConfigurations":398},{"removed":"scicode","score":0.1715603587758637,"rank":150,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1679227420804813,"rank":147,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15764067419849118,"rank":157,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19434385151565026,"rank":144,"remainingConfigurations":398},{"removed":"deepswe","score":0.14696887014719903,"rank":149,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.16907558631560524,"rank":150,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16794805543337385,"rank":150,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1745151810261245,"rank":151,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16912038451670774,"rank":150,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1677011298744477,"rank":150,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16879267438191584,"rank":150,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1684455107484014,"rank":150,"remainingConfigurations":398},{"removed":"livebench-math","score":0.16926862308027338,"rank":150,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1680211706748547,"rank":150,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17059551258927408,"rank":151,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1692836174739105,"rank":149,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16692918411466304,"rank":150,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16817128650486826,"rank":149,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1709879521553571,"rank":150,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1720967184712255,"rank":149,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16267621316868563,"rank":147,"remainingConfigurations":398},{"removed":"frontiermath","score":0.17020654263091964,"rank":151,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17427353059719253,"rank":150,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16837638685117676,"rank":150,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16858848658668912,"rank":150,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16848031469084415,"rank":150,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1688507997824076,"rank":150,"remainingConfigurations":398},{"removed":"vibe-code","score":0.16813003697026954,"rank":150,"remainingConfigurations":398}]},"qwen3.8-27b--effort-low":{"score":0.16690568121750918,"rank":151,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.19234082383280826,"rank":148,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14631349425954582,"rank":150,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1657244939889916,"rank":150,"remainingConfigurations":398},{"removed":"Scale","score":0.18034614413994488,"rank":152,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16718972351689876,"rank":151,"remainingConfigurations":398},{"removed":"Cognition","score":0.1729140032882764,"rank":152,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1701348032484201,"rank":149,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.17101626944525586,"rank":150,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1685190151307964,"rank":144,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1629717645899984,"rank":151,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.16691096774870226,"rank":151,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1667521414048614,"rank":151,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16663381377745093,"rank":151,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.16690568121750918,"rank":151,"remainingConfigurations":398},{"removed":"All provider reports","score":0.16646424263698487,"rank":151,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.16786504950946426,"rank":152,"remainingConfigurations":398},{"removed":"briefcase","score":0.1507867271719229,"rank":163,"remainingConfigurations":398},{"removed":"aime","score":0.1656318776812656,"rank":149,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16880286078365603,"rank":151,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15683665216552953,"rank":154,"remainingConfigurations":398},{"removed":"automationbench","score":0.15905818446823597,"rank":156,"remainingConfigurations":398},{"removed":"critpt","score":0.20427361735443716,"rank":123,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16756624263540776,"rank":151,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16641079109002632,"rank":151,"remainingConfigurations":398},{"removed":"gdpval","score":0.15687112257231015,"rank":156,"remainingConfigurations":398},{"removed":"gmmlu","score":0.16695650602531384,"rank":151,"remainingConfigurations":398},{"removed":"gpqa","score":0.16137096136631823,"rank":153,"remainingConfigurations":398},{"removed":"harvey","score":0.16591373619105468,"rank":151,"remainingConfigurations":398},{"removed":"hle","score":0.1803556475778166,"rank":147,"remainingConfigurations":398},{"removed":"ifbench","score":0.1616228656494558,"rank":153,"remainingConfigurations":398},{"removed":"itbench","score":0.16707087640502707,"rank":152,"remainingConfigurations":398},{"removed":"livecodebench","score":0.16475239862654054,"rank":151,"remainingConfigurations":398},{"removed":"math500","score":0.16617240821680213,"rank":151,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.16847991243609375,"rank":151,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17295427736270175,"rank":152,"remainingConfigurations":398},{"removed":"omniscience","score":0.19188106541243233,"rank":126,"remainingConfigurations":398},{"removed":"scicode","score":0.17844761049750366,"rank":141,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1566880418013353,"rank":156,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1602510363481303,"rank":155,"remainingConfigurations":398},{"removed":"arc-agi","score":0.19142081189356583,"rank":145,"remainingConfigurations":398},{"removed":"deepswe","score":0.14641098151845433,"rank":150,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.16694737424117956,"rank":151,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1658710767636495,"rank":151,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1729140032882764,"rank":152,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16702960747462745,"rank":151,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16558037322568042,"rank":151,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16667129332429165,"rank":151,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1663692186259865,"rank":151,"remainingConfigurations":398},{"removed":"livebench-math","score":0.16713219779220567,"rank":151,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16588982651286768,"rank":151,"remainingConfigurations":398},{"removed":"livebench-language","score":0.16847243946289822,"rank":152,"remainingConfigurations":398},{"removed":"livebench-data","score":0.167169616992348,"rank":151,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1647996244996415,"rank":151,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1660382701147221,"rank":151,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.16884783191325592,"rank":151,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.17101626944525586,"rank":150,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.16057832206511716,"rank":150,"remainingConfigurations":398},{"removed":"frontiermath","score":0.16804179758871204,"rank":152,"remainingConfigurations":398},{"removed":"simpleqa","score":0.17207124688291128,"rank":151,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1662522975325374,"rank":151,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16646367451130106,"rank":151,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16634934140585492,"rank":151,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1667284322576815,"rank":151,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1660009387371241,"rank":151,"remainingConfigurations":398}]},"gpt-5.4-nano--effort-xhigh":{"score":0.16482232269288688,"rank":152,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1599746435125162,"rank":103,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.2125837002541251,"rank":133,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14355053638305126,"rank":151,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16460595733226888,"rank":151,"remainingConfigurations":398},{"removed":"Scale","score":0.17745377221190606,"rank":153,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16556561344902285,"rank":152,"remainingConfigurations":398},{"removed":"Cognition","score":0.1755454520491795,"rank":150,"remainingConfigurations":398},{"removed":"LiveBench","score":0.14504164515097645,"rank":165,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.16516991880032317,"rank":153,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1667065893343663,"rank":145,"remainingConfigurations":381},{"removed":"Vals AI","score":0.16106420424040283,"rank":152,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.16483232558851865,"rank":152,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16474518740500185,"rank":152,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16442281520776061,"rank":152,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.16482232269288688,"rank":152,"remainingConfigurations":398},{"removed":"All provider reports","score":0.16433859381088226,"rank":152,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.16497890685355446,"rank":153,"remainingConfigurations":398},{"removed":"briefcase","score":0.165749056216533,"rank":151,"remainingConfigurations":398},{"removed":"aime","score":0.16437604703066286,"rank":151,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16298409391988833,"rank":154,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16372746439605024,"rank":150,"remainingConfigurations":398},{"removed":"automationbench","score":0.16572561176078385,"rank":151,"remainingConfigurations":398},{"removed":"critpt","score":0.1628697705702431,"rank":153,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16532225862016844,"rank":152,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16597586435323886,"rank":152,"remainingConfigurations":398},{"removed":"gdpval","score":0.1648728017338458,"rank":150,"remainingConfigurations":398},{"removed":"gmmlu","score":0.16493160933731302,"rank":152,"remainingConfigurations":398},{"removed":"gpqa","score":0.16424821126749636,"rank":152,"remainingConfigurations":398},{"removed":"harvey","score":0.16637475559241718,"rank":150,"remainingConfigurations":398},{"removed":"hle","score":0.16914525550563456,"rank":153,"remainingConfigurations":398},{"removed":"ifbench","score":0.15997561955600206,"rank":154,"remainingConfigurations":398},{"removed":"itbench","score":0.1675215177240185,"rank":151,"remainingConfigurations":398},{"removed":"livecodebench","score":0.16476080599687942,"rank":150,"remainingConfigurations":398},{"removed":"math500","score":0.16497955909303097,"rank":152,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1683438722008925,"rank":152,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17589588799718067,"rank":150,"remainingConfigurations":398},{"removed":"omniscience","score":0.16436239710368428,"rank":151,"remainingConfigurations":398},{"removed":"scicode","score":0.16455567719274553,"rank":153,"remainingConfigurations":398},{"removed":"tau-bench","score":0.16330032123835206,"rank":151,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16522278577577995,"rank":150,"remainingConfigurations":398},{"removed":"arc-agi","score":0.2107146636348225,"rank":132,"remainingConfigurations":398},{"removed":"deepswe","score":0.143627621230527,"rank":151,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1648725873677704,"rank":152,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16222781577706058,"rank":152,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1755454520491795,"rank":150,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16517564696319623,"rank":152,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16357962624366587,"rank":152,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16462373126313048,"rank":152,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1642617835173261,"rank":152,"remainingConfigurations":398},{"removed":"livebench-math","score":0.16205338470908637,"rank":153,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.17015542179110932,"rank":146,"remainingConfigurations":398},{"removed":"livebench-language","score":0.17236433606156035,"rank":147,"remainingConfigurations":398},{"removed":"livebench-data","score":0.16052493930555572,"rank":155,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16161281834477667,"rank":152,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16415717525971926,"rank":152,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.16299491096891722,"rank":155,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.16516991880032317,"rank":153,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.15913996093577978,"rank":152,"remainingConfigurations":398},{"removed":"frontiermath","score":0.16606645465376502,"rank":153,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1691496231669746,"rank":152,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16388970156130647,"rank":152,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16457994565030307,"rank":152,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16446565683682285,"rank":152,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16460591612461414,"rank":152,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1638031435757775,"rank":152,"remainingConfigurations":398}]},"nemotron-3-ultra--effort-reasoning":{"score":0.16243145161599118,"rank":153,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.18713844276207123,"rank":152,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1409268066823566,"rank":155,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1613410707872399,"rank":152,"remainingConfigurations":398},{"removed":"Scale","score":0.17555107902572575,"rank":154,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16249240529709,"rank":153,"remainingConfigurations":398},{"removed":"Cognition","score":0.16757261185146818,"rank":155,"remainingConfigurations":398},{"removed":"LiveBench","score":0.16518908837587035,"rank":150,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.16616437788559105,"rank":152,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.16436832580195682,"rank":147,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1580248702261254,"rank":154,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1624399170372745,"rank":153,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16227116335000996,"rank":153,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16216266296903256,"rank":153,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.16243145161599118,"rank":153,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1619898839006609,"rank":153,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.17103233864306092,"rank":147,"remainingConfigurations":398},{"removed":"briefcase","score":0.15855426621284707,"rank":155,"remainingConfigurations":398},{"removed":"aime","score":0.16241983294307538,"rank":152,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16396990890064944,"rank":153,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15474574182263498,"rank":157,"remainingConfigurations":398},{"removed":"automationbench","score":0.17051665260214907,"rank":146,"remainingConfigurations":398},{"removed":"critpt","score":0.16023097316034182,"rank":156,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16795275863300704,"rank":150,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16827159006258674,"rank":149,"remainingConfigurations":398},{"removed":"gdpval","score":0.1588760802463374,"rank":155,"remainingConfigurations":398},{"removed":"gmmlu","score":0.16286818265696845,"rank":153,"remainingConfigurations":398},{"removed":"gpqa","score":0.1555401027149028,"rank":157,"remainingConfigurations":398},{"removed":"harvey","score":0.1582939651851985,"rank":155,"remainingConfigurations":398},{"removed":"hle","score":0.16480113178251068,"rank":155,"remainingConfigurations":398},{"removed":"ifbench","score":0.14904966693938584,"rank":163,"remainingConfigurations":398},{"removed":"itbench","score":0.1619839428718298,"rank":154,"remainingConfigurations":398},{"removed":"livecodebench","score":0.16183689449731678,"rank":152,"remainingConfigurations":398},{"removed":"math500","score":0.16278481745478932,"rank":153,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.16576476400056897,"rank":153,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16988832804049384,"rank":154,"remainingConfigurations":398},{"removed":"omniscience","score":0.16881358883881578,"rank":148,"remainingConfigurations":398},{"removed":"scicode","score":0.17063213970621274,"rank":152,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1621481169138237,"rank":152,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16114896196428552,"rank":153,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1862633376959069,"rank":152,"remainingConfigurations":398},{"removed":"deepswe","score":0.14102982415540635,"rank":155,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.16247144315166037,"rank":153,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16144496087154278,"rank":153,"remainingConfigurations":398},{"removed":"frontiercode","score":0.16757261185146818,"rank":155,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16253993650740853,"rank":153,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16113548856513812,"rank":153,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16220131005382896,"rank":153,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1618824962812081,"rank":153,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1626478312152168,"rank":152,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1614608829826207,"rank":153,"remainingConfigurations":398},{"removed":"livebench-language","score":0.16398197282009855,"rank":153,"remainingConfigurations":398},{"removed":"livebench-data","score":0.16267847646516143,"rank":152,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.16035764475490263,"rank":153,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16159061527813093,"rank":153,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.16431362982929157,"rank":152,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.16616437788559105,"rank":152,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1568315826422008,"rank":153,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1635606338870398,"rank":154,"remainingConfigurations":398},{"removed":"simpleqa","score":0.16748799670926398,"rank":153,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1617976697075502,"rank":153,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16199332429784905,"rank":153,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16187845158876799,"rank":153,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16226270592239603,"rank":153,"remainingConfigurations":398},{"removed":"vibe-code","score":0.16154293095722858,"rank":153,"remainingConfigurations":398}]},"gemini-3.1-flash-lite--effort-high":{"score":0.1616340918410409,"rank":154,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15613672902737347,"rank":104,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.18830252478723788,"rank":151,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13895713181622524,"rank":156,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1612499224468891,"rank":153,"remainingConfigurations":398},{"removed":"Scale","score":0.17346499402386203,"rank":156,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16174296104409772,"rank":155,"remainingConfigurations":398},{"removed":"Cognition","score":0.1694961194268808,"rank":153,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1619383896702968,"rank":152,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.16272351900832752,"rank":156,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1564128453467466,"rank":156,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.16162781882578292,"rank":154,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16141437505308143,"rank":154,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1615063484964558,"rank":154,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1616340918410409,"rank":154,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1612631525132223,"rank":154,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1619311375149281,"rank":154,"remainingConfigurations":398},{"removed":"briefcase","score":0.16147126879510046,"rank":152,"remainingConfigurations":398},{"removed":"aime","score":0.15162804352713186,"rank":163,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16260227338774885,"rank":156,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16228496694834035,"rank":152,"remainingConfigurations":398},{"removed":"automationbench","score":0.16156086693533783,"rank":154,"remainingConfigurations":398},{"removed":"critpt","score":0.16104298726330482,"rank":154,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1617572194140795,"rank":154,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16241135361818235,"rank":155,"remainingConfigurations":398},{"removed":"gdpval","score":0.1608886158459175,"rank":153,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1622558494921664,"rank":154,"remainingConfigurations":398},{"removed":"gpqa","score":0.17700675963603,"rank":135,"remainingConfigurations":398},{"removed":"harvey","score":0.16004165017771663,"rank":153,"remainingConfigurations":398},{"removed":"hle","score":0.16629110676232076,"rank":154,"remainingConfigurations":398},{"removed":"ifbench","score":0.16203472956850648,"rank":151,"remainingConfigurations":398},{"removed":"itbench","score":0.1613871731859481,"rank":155,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1617601088907091,"rank":153,"remainingConfigurations":398},{"removed":"math500","score":0.16186286217897236,"rank":154,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.16558158247844537,"rank":154,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16973534417068603,"rank":155,"remainingConfigurations":398},{"removed":"omniscience","score":0.16138512504030145,"rank":154,"remainingConfigurations":398},{"removed":"scicode","score":0.16290254271875326,"rank":155,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15723992344508983,"rank":155,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16144221888607987,"rank":151,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18856157169003604,"rank":149,"remainingConfigurations":398},{"removed":"deepswe","score":0.13906883281890614,"rank":156,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1616663172001473,"rank":154,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.16073754545280658,"rank":154,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1694961194268808,"rank":153,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.16190972373023527,"rank":154,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.16018013672182185,"rank":155,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16143001098256302,"rank":154,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.16112113712668044,"rank":154,"remainingConfigurations":398},{"removed":"livebench-math","score":0.16201077376244188,"rank":154,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16017604509985692,"rank":155,"remainingConfigurations":398},{"removed":"livebench-language","score":0.16310404739724435,"rank":154,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1620263497963867,"rank":153,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15975737453885178,"rank":154,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16074164232388802,"rank":154,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1636251088299612,"rank":153,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.16272351900832752,"rank":156,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1232601284585496,"rank":177,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1779896666944801,"rank":140,"remainingConfigurations":398},{"removed":"simpleqa","score":0.16490952470395007,"rank":155,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16100054348832274,"rank":154,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16126658098013388,"rank":154,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1609653366327862,"rank":155,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16146959535299457,"rank":154,"remainingConfigurations":398},{"removed":"vibe-code","score":0.16088551988320995,"rank":154,"remainingConfigurations":398}]},"deepseek-v3.2-speciale--effort-reasoning":{"score":0.16153169474283594,"rank":155,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1888079683000319,"rank":150,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14102854766773032,"rank":154,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.16028847467138016,"rank":154,"remainingConfigurations":398},{"removed":"Scale","score":0.17489133454399605,"rank":155,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.16186289862961958,"rank":154,"remainingConfigurations":398},{"removed":"Cognition","score":0.1680972622755341,"rank":154,"remainingConfigurations":398},{"removed":"LiveBench","score":0.16413772302158236,"rank":151,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.16496378070890605,"rank":154,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.16143570030540513,"rank":148,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1574630118893804,"rank":155,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.16153955997310968,"rank":155,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.16139557234524235,"rank":155,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.16128766178927043,"rank":155,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.16153169474283594,"rank":155,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1611386508950762,"rank":155,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.16187167080751333,"rank":155,"remainingConfigurations":398},{"removed":"briefcase","score":0.16109687627594313,"rank":153,"remainingConfigurations":398},{"removed":"aime","score":0.15661549764310345,"rank":158,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16287149106625592,"rank":155,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.16132947330201702,"rank":153,"remainingConfigurations":398},{"removed":"automationbench","score":0.1612240494901037,"rank":155,"remainingConfigurations":398},{"removed":"critpt","score":0.15210593327582153,"rank":161,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16165212238652207,"rank":155,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16298662756114699,"rank":154,"remainingConfigurations":398},{"removed":"gdpval","score":0.16228703468083125,"rank":152,"remainingConfigurations":398},{"removed":"gmmlu","score":0.158822261836338,"rank":156,"remainingConfigurations":398},{"removed":"gpqa","score":0.1531584495042639,"rank":158,"remainingConfigurations":398},{"removed":"harvey","score":0.1599012661951111,"rank":154,"remainingConfigurations":398},{"removed":"hle","score":0.16291606704228112,"rank":158,"remainingConfigurations":398},{"removed":"ifbench","score":0.16195066865859112,"rank":152,"remainingConfigurations":398},{"removed":"itbench","score":0.16126966904409715,"rank":156,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15515719497446784,"rank":157,"remainingConfigurations":398},{"removed":"math500","score":0.16148671229634323,"rank":155,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.16174238567113586,"rank":156,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16961163055448258,"rank":156,"remainingConfigurations":398},{"removed":"omniscience","score":0.1476041110057641,"rank":162,"remainingConfigurations":398},{"removed":"scicode","score":0.16376885444629488,"rank":154,"remainingConfigurations":398},{"removed":"tau-bench","score":0.21591767006718512,"rank":116,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16117565197642372,"rank":152,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18779185900892115,"rank":150,"remainingConfigurations":398},{"removed":"deepswe","score":0.14112218265762896,"rank":154,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1615694306757504,"rank":155,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1604647358826791,"rank":155,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1680972622755341,"rank":154,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1615764771493298,"rank":155,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1602490573569498,"rank":154,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.16129069035652321,"rank":155,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.16098661290539604,"rank":155,"remainingConfigurations":398},{"removed":"livebench-math","score":0.16175655652130033,"rank":155,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.16053588656421094,"rank":154,"remainingConfigurations":398},{"removed":"livebench-language","score":0.16304404542668058,"rank":155,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1617619996802749,"rank":154,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15949028688783073,"rank":155,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.16069147506624024,"rank":155,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.16345032460616296,"rank":154,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.16496378070890605,"rank":154,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.154868700349399,"rank":155,"remainingConfigurations":398},{"removed":"frontiermath","score":0.16297948236811163,"rank":155,"remainingConfigurations":398},{"removed":"simpleqa","score":0.16668022088199455,"rank":154,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.16089860939091796,"rank":155,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.16108822745881315,"rank":155,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.16099406687654652,"rank":154,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.16134176420600252,"rank":155,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1606560407434527,"rank":155,"remainingConfigurations":398}]},"minimax-m2.7--effort-reasoning":{"score":0.15852162601774192,"rank":156,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.18271550796348945,"rank":153,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13741915055451767,"rank":157,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15747538921985937,"rank":155,"remainingConfigurations":398},{"removed":"Scale","score":0.17140889598785777,"rank":157,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15856974463944745,"rank":156,"remainingConfigurations":398},{"removed":"Cognition","score":0.1636289620731842,"rank":158,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1609792474282213,"rank":153,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1621021463888441,"rank":157,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1602235574261194,"rank":149,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1538318139049126,"rank":157,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15852653707222356,"rank":156,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.15837449036090692,"rank":156,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15826752377866307,"rank":156,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15852162601774192,"rank":156,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15810435560515956,"rank":156,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.16006004362032092,"rank":156,"remainingConfigurations":398},{"removed":"briefcase","score":0.15935316940214142,"rank":154,"remainingConfigurations":398},{"removed":"aime","score":0.15861340533187707,"rank":155,"remainingConfigurations":398},{"removed":"apex-agents","score":0.16645727890516113,"rank":152,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15614615462341044,"rank":155,"remainingConfigurations":398},{"removed":"automationbench","score":0.162993179700631,"rank":153,"remainingConfigurations":398},{"removed":"critpt","score":0.16292431802065963,"rank":152,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.15798298957707094,"rank":157,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16195568479849318,"rank":156,"remainingConfigurations":398},{"removed":"gdpval","score":0.15578254070759293,"rank":157,"remainingConfigurations":398},{"removed":"gmmlu","score":0.15891034254975459,"rank":155,"remainingConfigurations":398},{"removed":"gpqa","score":0.15074018639129552,"rank":162,"remainingConfigurations":398},{"removed":"harvey","score":0.15648654978423218,"rank":157,"remainingConfigurations":398},{"removed":"hle","score":0.15920696184017566,"rank":161,"remainingConfigurations":398},{"removed":"ifbench","score":0.1477179209303532,"rank":165,"remainingConfigurations":398},{"removed":"itbench","score":0.1644328309128503,"rank":153,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15808097925952114,"rank":154,"remainingConfigurations":398},{"removed":"math500","score":0.15890789415395778,"rank":156,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.161924109881364,"rank":155,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16578434920074203,"rank":158,"remainingConfigurations":398},{"removed":"omniscience","score":0.1583406807131251,"rank":156,"remainingConfigurations":398},{"removed":"scicode","score":0.1531139665322345,"rank":163,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1605987238922539,"rank":154,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.16036730148808334,"rank":154,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18183707008764802,"rank":153,"remainingConfigurations":398},{"removed":"deepswe","score":0.13751962019352168,"rank":157,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1585598557604714,"rank":156,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.15755999441086635,"rank":156,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1636289620731842,"rank":158,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1586028739108953,"rank":156,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.157254191865009,"rank":156,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15829750918986948,"rank":156,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.157949608118756,"rank":156,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15873576067898237,"rank":156,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1575761668259519,"rank":156,"remainingConfigurations":398},{"removed":"livebench-language","score":0.16004448255023965,"rank":156,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15874426929898727,"rank":156,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15649033153576347,"rank":156,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15769853209857157,"rank":156,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.16037321569467855,"rank":156,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1621021463888441,"rank":157,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.15298772596065122,"rank":156,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15962685272164523,"rank":158,"remainingConfigurations":398},{"removed":"simpleqa","score":0.16350240818589165,"rank":156,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1578993787187212,"rank":156,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.15808425916098914,"rank":156,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.15798247481375918,"rank":156,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1583460686674137,"rank":156,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15766063622108595,"rank":156,"remainingConfigurations":398}]},"step-3.7-flash--effort-reasoning":{"score":0.15783716870971165,"rank":157,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1824802290483054,"rank":154,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1369206328574654,"rank":158,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15678134250388628,"rank":156,"remainingConfigurations":398},{"removed":"Scale","score":0.17064220029863542,"rank":158,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15796123559436273,"rank":157,"remainingConfigurations":398},{"removed":"Cognition","score":0.1631971153572541,"rank":159,"remainingConfigurations":398},{"removed":"LiveBench","score":0.16015477327142025,"rank":154,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.16144300390157004,"rank":158,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15886537344876903,"rank":151,"remainingConfigurations":381},{"removed":"Vals AI","score":0.15321814610413884,"rank":158,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15784700460833667,"rank":157,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.15770307765200212,"rank":157,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15757348028028506,"rank":157,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15783716870971165,"rank":157,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15742799202211014,"rank":157,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1579558128016378,"rank":157,"remainingConfigurations":398},{"removed":"briefcase","score":0.15758499411459734,"rank":156,"remainingConfigurations":398},{"removed":"aime","score":0.15806318312130094,"rank":156,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1579801532312353,"rank":157,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15293713676610868,"rank":160,"remainingConfigurations":398},{"removed":"automationbench","score":0.1572652897474786,"rank":157,"remainingConfigurations":398},{"removed":"critpt","score":0.1562895395248352,"rank":157,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.16181426321547873,"rank":153,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1589993028911351,"rank":158,"remainingConfigurations":398},{"removed":"gdpval","score":0.15935802434404553,"rank":154,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1583586859344667,"rank":157,"remainingConfigurations":398},{"removed":"gpqa","score":0.15853099917430014,"rank":155,"remainingConfigurations":398},{"removed":"harvey","score":0.15745316610413826,"rank":156,"remainingConfigurations":398},{"removed":"hle","score":0.16307807213670922,"rank":157,"remainingConfigurations":398},{"removed":"ifbench","score":0.15361026344665318,"rank":159,"remainingConfigurations":398},{"removed":"itbench","score":0.16086808696099028,"rank":157,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15742091736738556,"rank":156,"remainingConfigurations":398},{"removed":"math500","score":0.1582246300753711,"rank":157,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.16118293186544932,"rank":157,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16247899577617422,"rank":159,"remainingConfigurations":398},{"removed":"omniscience","score":0.15838781348143963,"rank":155,"remainingConfigurations":398},{"removed":"scicode","score":0.1605803403345193,"rank":156,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15236087594536127,"rank":160,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15930640857056422,"rank":156,"remainingConfigurations":398},{"removed":"arc-agi","score":0.18158533070955932,"rank":154,"remainingConfigurations":398},{"removed":"deepswe","score":0.13702095063499012,"rank":158,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15787281432681408,"rank":157,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1568563636737483,"rank":157,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1631971153572541,"rank":159,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1579089528303897,"rank":157,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15658183536075232,"rank":157,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15760502480881317,"rank":157,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15727778754605873,"rank":157,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15804801052596043,"rank":158,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.15689826911956828,"rank":157,"remainingConfigurations":398},{"removed":"livebench-language","score":0.159355991926285,"rank":157,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15804527967909207,"rank":157,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15581990415907251,"rank":157,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1570189760418497,"rank":158,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1596844486486581,"rank":157,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.16144300390157004,"rank":158,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.15213507178608535,"rank":157,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15900387948609182,"rank":159,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1628121350936241,"rank":157,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15721637455589613,"rank":157,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1573992744012557,"rank":157,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.15730186711936764,"rank":157,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1576587062830961,"rank":157,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15698116916457802,"rank":157,"remainingConfigurations":398}]},"gemini-3.5-flash-lite--effort-high":{"score":0.15470206669808692,"rank":158,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.15236106662734247,"rank":106,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1618505225319679,"rank":164,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13225601996684086,"rank":163,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15504949800313023,"rank":157,"remainingConfigurations":398},{"removed":"Scale","score":0.16568297984411615,"rank":162,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1550795376659793,"rank":158,"remainingConfigurations":398},{"removed":"Cognition","score":0.1648414783638131,"rank":156,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1523634232690549,"rank":161,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.153013165911788,"rank":164,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15991078774036094,"rank":150,"remainingConfigurations":381},{"removed":"Vals AI","score":0.15836789840627388,"rank":153,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15469416505423755,"rank":158,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.15465395248157937,"rank":158,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15447658899129282,"rank":158,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15470206669808692,"rank":158,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15440732849972438,"rank":158,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15485787405899784,"rank":158,"remainingConfigurations":398},{"removed":"briefcase","score":0.15463416275781014,"rank":157,"remainingConfigurations":398},{"removed":"aime","score":0.15789946770857222,"rank":157,"remainingConfigurations":398},{"removed":"apex-agents","score":0.155105483821293,"rank":159,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1546543492508022,"rank":158,"remainingConfigurations":398},{"removed":"automationbench","score":0.15455129576769122,"rank":158,"remainingConfigurations":398},{"removed":"critpt","score":0.15472671288777298,"rank":158,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.15472568452943886,"rank":158,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.15522059731504456,"rank":160,"remainingConfigurations":398},{"removed":"gdpval","score":0.15465125700542093,"rank":158,"remainingConfigurations":398},{"removed":"gmmlu","score":0.154814914360574,"rank":158,"remainingConfigurations":398},{"removed":"gpqa","score":0.15299372655024582,"rank":159,"remainingConfigurations":398},{"removed":"harvey","score":0.1537811630116768,"rank":158,"remainingConfigurations":398},{"removed":"hle","score":0.1592326428209894,"rank":160,"remainingConfigurations":398},{"removed":"ifbench","score":0.15389757262807036,"rank":158,"remainingConfigurations":398},{"removed":"itbench","score":0.15447700512515614,"rank":158,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15513398881121754,"rank":158,"remainingConfigurations":398},{"removed":"math500","score":0.15478806630118305,"rank":158,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15864842351447841,"rank":158,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16237999668538894,"rank":160,"remainingConfigurations":398},{"removed":"omniscience","score":0.1539445078875932,"rank":158,"remainingConfigurations":398},{"removed":"scicode","score":0.15525604712423957,"rank":159,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1537494023958159,"rank":159,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15654902287386122,"rank":158,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1605139043261573,"rank":166,"remainingConfigurations":398},{"removed":"deepswe","score":0.1323412728334413,"rank":163,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15475747288066352,"rank":158,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1533961415873564,"rank":158,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1648414783638131,"rank":156,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.15496372070413827,"rank":158,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15352770942361918,"rank":158,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1545520519207642,"rank":158,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15395588875060587,"rank":158,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15839961099694128,"rank":157,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1513419086979194,"rank":163,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1577355238869861,"rank":158,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15559052338264387,"rank":158,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1513447654247466,"rank":163,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15723039642537986,"rank":157,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1512700129290839,"rank":164,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.153013165911788,"rank":164,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1429100068305487,"rank":164,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15976165497827102,"rank":157,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15785794934810224,"rank":161,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15152366019399097,"rank":163,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1567761383356491,"rank":158,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1546775672145481,"rank":158,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.15467096416214798,"rank":158,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15187068275762775,"rank":163,"remainingConfigurations":398}]},"mimo-v2.5--effort-reasoning":{"score":0.15399315786291665,"rank":159,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1787581864110712,"rank":157,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13351328489638317,"rank":160,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15288971065143525,"rank":159,"remainingConfigurations":398},{"removed":"Scale","score":0.16681272409123116,"rank":159,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15408822170978406,"rank":159,"remainingConfigurations":398},{"removed":"Cognition","score":0.15932150634283468,"rank":163,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1566501871067705,"rank":155,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.15739389531780956,"rank":159,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15528699118587666,"rank":152,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14970906821855243,"rank":159,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15399924576687943,"rank":159,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1538556899525069,"rank":159,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15373766763867533,"rank":160,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15399315786291665,"rank":159,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1535860120636402,"rank":160,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15429358931305273,"rank":159,"remainingConfigurations":398},{"removed":"briefcase","score":0.1530003985600343,"rank":161,"remainingConfigurations":398},{"removed":"aime","score":0.15423670856879104,"rank":161,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1554512816455728,"rank":158,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.14984966823874046,"rank":164,"remainingConfigurations":398},{"removed":"automationbench","score":0.15015478541986907,"rank":164,"remainingConfigurations":398},{"removed":"critpt","score":0.14964060479390798,"rank":164,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.153841804320661,"rank":160,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.16062194467835514,"rank":157,"remainingConfigurations":398},{"removed":"gdpval","score":0.15118686506957538,"rank":163,"remainingConfigurations":398},{"removed":"gmmlu","score":0.15470991379461663,"rank":159,"remainingConfigurations":398},{"removed":"gpqa","score":0.14816289648552353,"rank":164,"remainingConfigurations":398},{"removed":"harvey","score":0.15226273831128548,"rank":160,"remainingConfigurations":398},{"removed":"hle","score":0.15711569547020973,"rank":163,"remainingConfigurations":398},{"removed":"ifbench","score":0.15011652016297716,"rank":162,"remainingConfigurations":398},{"removed":"itbench","score":0.15367614480026118,"rank":160,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15353620866182557,"rank":161,"remainingConfigurations":398},{"removed":"math500","score":0.1543402119647956,"rank":159,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1572773562386027,"rank":160,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.15754265553993355,"rank":164,"remainingConfigurations":398},{"removed":"omniscience","score":0.17254626595697978,"rank":143,"remainingConfigurations":398},{"removed":"scicode","score":0.15670459339811252,"rank":157,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15497069452280401,"rank":157,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1539075648399287,"rank":161,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1779025257519025,"rank":158,"remainingConfigurations":398},{"removed":"deepswe","score":0.1336055049284102,"rank":160,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15403231622370228,"rank":159,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1530311275467275,"rank":160,"remainingConfigurations":398},{"removed":"frontiercode","score":0.15932150634283468,"rank":163,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.15407770235141438,"rank":160,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15274466002298573,"rank":160,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15377599654823831,"rank":159,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15342161845850705,"rank":160,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15420832754165217,"rank":160,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.15304000221125436,"rank":158,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1554779654258096,"rank":159,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1542348570376493,"rank":160,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15199843154905732,"rank":159,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15317487460148901,"rank":159,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15583052827164004,"rank":159,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.15739389531780956,"rank":159,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.14813923405701074,"rank":158,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15517443250449123,"rank":160,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15889368808223583,"rank":158,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15337265537188124,"rank":158,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.15357104039113156,"rank":160,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.15346726558041676,"rank":159,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.15382298305052391,"rank":159,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1531374984132097,"rank":159,"remainingConfigurations":398}]},"qwen3.7-plus--effort-non-reasoning":{"score":0.1539474635030306,"rank":160,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.14915935168083236,"rank":107,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.17761184171680244,"rank":159,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13108257934929382,"rank":164,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1535745870525921,"rank":158,"remainingConfigurations":398},{"removed":"Scale","score":0.1651476655906869,"rank":163,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15399267853151663,"rank":160,"remainingConfigurations":398},{"removed":"Cognition","score":0.16098163167131418,"rank":160,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1557453228276622,"rank":158,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.15521641059264302,"rank":163,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14894842132698563,"rank":162,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15394871151170272,"rank":160,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.15374107014400692,"rank":160,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15383176900810483,"rank":159,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1539474635030306,"rank":160,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15361000040664094,"rank":159,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15422707306070502,"rank":160,"remainingConfigurations":398},{"removed":"briefcase","score":0.15375565517132656,"rank":159,"remainingConfigurations":398},{"removed":"aime","score":0.14734647066442377,"rank":166,"remainingConfigurations":398},{"removed":"apex-agents","score":0.15485371721002036,"rank":161,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15443046680818207,"rank":159,"remainingConfigurations":398},{"removed":"automationbench","score":0.1538162462253031,"rank":159,"remainingConfigurations":398},{"removed":"critpt","score":0.15326355472133404,"rank":160,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1540671159104607,"rank":159,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.15464658160235709,"rank":161,"remainingConfigurations":398},{"removed":"gdpval","score":0.15316548301876762,"rank":162,"remainingConfigurations":398},{"removed":"gmmlu","score":0.154441220045844,"rank":161,"remainingConfigurations":398},{"removed":"gpqa","score":0.15984605998702742,"rank":154,"remainingConfigurations":398},{"removed":"harvey","score":0.15241846653282595,"rank":159,"remainingConfigurations":398},{"removed":"hle","score":0.15822546672236712,"rank":162,"remainingConfigurations":398},{"removed":"ifbench","score":0.15467745836987096,"rank":156,"remainingConfigurations":398},{"removed":"itbench","score":0.15370690188743857,"rank":159,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15412730497305768,"rank":159,"remainingConfigurations":398},{"removed":"math500","score":0.15416682418683342,"rank":160,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15766464436878536,"rank":159,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16180443994558683,"rank":161,"remainingConfigurations":398},{"removed":"omniscience","score":0.15383395322649684,"rank":159,"remainingConfigurations":398},{"removed":"scicode","score":0.1551541082311233,"rank":160,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15001135586630623,"rank":162,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15364408031246599,"rank":162,"remainingConfigurations":398},{"removed":"arc-agi","score":0.17781855289171453,"rank":159,"remainingConfigurations":398},{"removed":"deepswe","score":0.13118652938835793,"rank":164,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15397715699774617,"rank":160,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1531403648334102,"rank":159,"remainingConfigurations":398},{"removed":"frontiercode","score":0.16098163167131418,"rank":160,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1542313308511183,"rank":159,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15248776889264926,"rank":161,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15376054728410612,"rank":160,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.153485906518284,"rank":159,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15429802528454092,"rank":159,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.15258437034695096,"rank":160,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1553530412363687,"rank":160,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15436241111071128,"rank":159,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15210768987873993,"rank":158,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15310212216911634,"rank":160,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15583094758369082,"rank":158,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.15521641059264302,"rank":163,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1558688377919829,"rank":154,"remainingConfigurations":398},{"removed":"frontiermath","score":0.14042535104977866,"rank":168,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15730276850719502,"rank":163,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1533272215831026,"rank":159,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1535980764754501,"rank":159,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.15328670822817667,"rank":160,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.15378804476442914,"rank":160,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15323370314968107,"rank":158,"remainingConfigurations":398}]},"claude-sonnet-4-5-20250929--effort-reasoning":{"score":0.15360860855816758,"rank":161,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1781425514675391,"rank":158,"remainingConfigurations":398},{"removed":"Datacurve","score":0.133203145695912,"rank":162,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15242623947000955,"rank":161,"remainingConfigurations":398},{"removed":"Scale","score":0.16642653977333663,"rank":161,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15370394893992698,"rank":162,"remainingConfigurations":398},{"removed":"Cognition","score":0.15893869347489398,"rank":164,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1560886514430486,"rank":156,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1567964263045408,"rank":160,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15411200938596845,"rank":153,"remainingConfigurations":381},{"removed":"Vals AI","score":0.149206037564247,"rank":161,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15361449897624363,"rank":161,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1534694961129733,"rank":161,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15336062342268067,"rank":161,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15360860855816758,"rank":161,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15320714500921537,"rank":161,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15397029231318657,"rank":161,"remainingConfigurations":398},{"removed":"briefcase","score":0.15399478786626078,"rank":158,"remainingConfigurations":398},{"removed":"aime","score":0.15395559471786432,"rank":162,"remainingConfigurations":398},{"removed":"apex-agents","score":0.154993591170638,"rank":160,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15000772273309967,"rank":163,"remainingConfigurations":398},{"removed":"automationbench","score":0.15118999190896643,"rank":162,"remainingConfigurations":398},{"removed":"critpt","score":0.15370936928377746,"rank":159,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.15362934302659018,"rank":161,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.15792618051539323,"rank":159,"remainingConfigurations":398},{"removed":"gdpval","score":0.1538662738910401,"rank":160,"remainingConfigurations":398},{"removed":"gmmlu","score":0.15022351726988792,"rank":162,"remainingConfigurations":398},{"removed":"gpqa","score":0.15079363069897386,"rank":161,"remainingConfigurations":398},{"removed":"harvey","score":0.15210207841348874,"rank":161,"remainingConfigurations":398},{"removed":"hle","score":0.1610664140432875,"rank":159,"remainingConfigurations":398},{"removed":"ifbench","score":0.1544021607811712,"rank":157,"remainingConfigurations":398},{"removed":"itbench","score":0.15336790325767483,"rank":161,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15793655631913678,"rank":155,"remainingConfigurations":398},{"removed":"math500","score":0.15386649451307272,"rank":161,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1546785198968477,"rank":163,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16584827416812314,"rank":157,"remainingConfigurations":398},{"removed":"omniscience","score":0.1481685482717258,"rank":161,"remainingConfigurations":398},{"removed":"scicode","score":0.15319402478600927,"rank":162,"remainingConfigurations":398},{"removed":"tau-bench","score":0.14939989580923338,"rank":163,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15608622792630764,"rank":159,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1773460956757368,"rank":160,"remainingConfigurations":398},{"removed":"deepswe","score":0.13329522353641304,"rank":162,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15364756523462966,"rank":161,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1526308879795972,"rank":162,"remainingConfigurations":398},{"removed":"frontiercode","score":0.15893869347489398,"rank":164,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1536857822297241,"rank":161,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15237078470006807,"rank":162,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15338958022973995,"rank":161,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15304368044313257,"rank":162,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1538243781620294,"rank":161,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1526566927226198,"rank":159,"remainingConfigurations":398},{"removed":"livebench-language","score":0.15508794670388396,"rank":161,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1538442651890502,"rank":161,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15161983280766825,"rank":161,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15279392245869916,"rank":161,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15544551863243417,"rank":160,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1567964263045408,"rank":160,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.147655076227905,"rank":159,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1548212967868002,"rank":162,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15851987207750548,"rank":159,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15298963872289467,"rank":160,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.15318658005983876,"rank":161,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1530849808159234,"rank":161,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.15343740576724416,"rank":161,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1527546513238769,"rank":160,"remainingConfigurations":398}]},"glm-5v-turbo--effort-reasoning":{"score":0.1534808922672242,"rank":162,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.17889118570342585,"rank":156,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1334480259452611,"rank":161,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15235106311421828,"rank":162,"remainingConfigurations":398},{"removed":"Scale","score":0.1664787750676597,"rank":160,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15371564569575882,"rank":161,"remainingConfigurations":398},{"removed":"Cognition","score":0.15937707578271454,"rank":162,"remainingConfigurations":398},{"removed":"LiveBench","score":0.15602333751458367,"rank":157,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1566126167959068,"rank":161,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15361043835424723,"rank":154,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14945156206164098,"rank":160,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1534889270495319,"rank":162,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1533505953895398,"rank":162,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15324022535171594,"rank":162,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1534808922672242,"rank":162,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15309772998734764,"rank":162,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15378169714289777,"rank":162,"remainingConfigurations":398},{"removed":"briefcase","score":0.15266353389789328,"rank":162,"remainingConfigurations":398},{"removed":"aime","score":0.15445604111113753,"rank":160,"remainingConfigurations":398},{"removed":"apex-agents","score":0.15465370728833297,"rank":162,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1519927701359382,"rank":161,"remainingConfigurations":398},{"removed":"automationbench","score":0.15280703093963863,"rank":161,"remainingConfigurations":398},{"removed":"critpt","score":0.16050686172372006,"rank":155,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1532781478932284,"rank":163,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.15452579017088366,"rank":163,"remainingConfigurations":398},{"removed":"gdpval","score":0.15375662385728464,"rank":161,"remainingConfigurations":398},{"removed":"gmmlu","score":0.15460352219161058,"rank":160,"remainingConfigurations":398},{"removed":"gpqa","score":0.1570347562165161,"rank":156,"remainingConfigurations":398},{"removed":"harvey","score":0.1517363436833519,"rank":163,"remainingConfigurations":398},{"removed":"hle","score":0.16392853941867036,"rank":156,"remainingConfigurations":398},{"removed":"ifbench","score":0.1562068210022368,"rank":155,"remainingConfigurations":398},{"removed":"itbench","score":0.15316870639546645,"rank":163,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15340373138798194,"rank":162,"remainingConfigurations":398},{"removed":"math500","score":0.1538014006510349,"rank":162,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15685077039493087,"rank":162,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16032634711468027,"rank":163,"remainingConfigurations":398},{"removed":"omniscience","score":0.14526123736741123,"rank":165,"remainingConfigurations":398},{"removed":"scicode","score":0.15527785119936724,"rank":158,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13881531758550972,"rank":169,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15457908884754779,"rank":160,"remainingConfigurations":398},{"removed":"arc-agi","score":0.17809913017388299,"rank":157,"remainingConfigurations":398},{"removed":"deepswe","score":0.13353657627590962,"rank":161,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15351700522972275,"rank":162,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1524805209037601,"rank":163,"remainingConfigurations":398},{"removed":"frontiercode","score":0.15937707578271454,"rank":162,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.15354677862558827,"rank":162,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1522580127559868,"rank":163,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.153254145878956,"rank":162,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15295589447813165,"rank":163,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15369757241047918,"rank":162,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1525159336198904,"rank":162,"remainingConfigurations":398},{"removed":"livebench-language","score":0.15494303105522308,"rank":162,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15370973504846652,"rank":162,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1515090748826107,"rank":162,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15266691693203258,"rank":163,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15533551345543192,"rank":161,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1566126167959068,"rank":161,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.14718766773587108,"rank":161,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15483990627082536,"rank":161,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1584276884196609,"rank":160,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1528686697650253,"rank":161,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1530530798820721,"rank":162,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1529610895458783,"rank":162,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1532949011258721,"rank":162,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15263645909466889,"rank":161,"remainingConfigurations":398}]},"claude-opus-4-6--effort-non-reasoning":{"score":0.15339627214044602,"rank":163,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.12945649583036156,"rank":112,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15718527330061804,"rank":169,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1340374087748135,"rank":159,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15282592707470308,"rank":160,"remainingConfigurations":398},{"removed":"Scale","score":0.18498032265547248,"rank":146,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15220878327918222,"rank":163,"remainingConfigurations":398},{"removed":"Cognition","score":0.16042942373156122,"rank":161,"remainingConfigurations":398},{"removed":"LiveBench","score":0.15367155771582927,"rank":159,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.15546221982354558,"rank":162,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15037745371063668,"rank":158,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14799502963302424,"rank":163,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15340408490620946,"rank":163,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1532201648659606,"rank":163,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15320954893173522,"rank":163,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15339627214044602,"rank":163,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15302441568816075,"rank":163,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1536730157076721,"rank":163,"remainingConfigurations":398},{"removed":"briefcase","score":0.15329780659097278,"rank":160,"remainingConfigurations":398},{"removed":"aime","score":0.15446076783402704,"rank":159,"remainingConfigurations":398},{"removed":"apex-agents","score":0.15412265316973137,"rank":163,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.15539555710061492,"rank":156,"remainingConfigurations":398},{"removed":"automationbench","score":0.15354757761227225,"rank":160,"remainingConfigurations":398},{"removed":"critpt","score":0.15144838868674013,"rank":162,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.15343289515894423,"rank":162,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1546353712046575,"rank":162,"remainingConfigurations":398},{"removed":"gdpval","score":0.15438066227278088,"rank":159,"remainingConfigurations":398},{"removed":"gmmlu","score":0.14721925171241448,"rank":166,"remainingConfigurations":398},{"removed":"gpqa","score":0.15205380702982182,"rank":160,"remainingConfigurations":398},{"removed":"harvey","score":0.15202580097534088,"rank":162,"remainingConfigurations":398},{"removed":"hle","score":0.18154390032121648,"rank":144,"remainingConfigurations":398},{"removed":"ifbench","score":0.16503916584211972,"rank":150,"remainingConfigurations":398},{"removed":"itbench","score":0.1532238923612675,"rank":162,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15357170288687247,"rank":160,"remainingConfigurations":398},{"removed":"math500","score":0.15339092329594364,"rank":163,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15690247273604427,"rank":161,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.16131455281178597,"rank":162,"remainingConfigurations":398},{"removed":"omniscience","score":0.1415578865480576,"rank":167,"remainingConfigurations":398},{"removed":"scicode","score":0.15480332574824598,"rank":161,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15451937990606565,"rank":158,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.147707459294831,"rank":165,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1563717108695749,"rank":170,"remainingConfigurations":398},{"removed":"deepswe","score":0.13411636565321816,"rank":159,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15342615682686087,"rank":163,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.15265423068819617,"rank":161,"remainingConfigurations":398},{"removed":"frontiercode","score":0.16042942373156122,"rank":161,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.14563915518409357,"rank":166,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.15283233505844293,"rank":159,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15204224565748192,"rank":163,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15325518959556325,"rank":161,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1535759444394069,"rank":163,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.15255167331406164,"rank":161,"remainingConfigurations":398},{"removed":"livebench-language","score":0.15466019393059438,"rank":163,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15359793291926316,"rank":163,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.15166514474908954,"rank":160,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15269716690730473,"rank":162,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1550334059606384,"rank":162,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.15546221982354558,"rank":162,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1474875362605074,"rank":160,"remainingConfigurations":398},{"removed":"frontiermath","score":0.15429374583137948,"rank":163,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1576988098067522,"rank":162,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15286141213845958,"rank":162,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1530207009586931,"rank":163,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1529456787923092,"rank":163,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1532220393074028,"rank":163,"remainingConfigurations":398},{"removed":"vibe-code","score":0.152633051464685,"rank":162,"remainingConfigurations":398}]},"qwen3.5-397b-a17b--effort-non-reasoning":{"score":0.15088247869700758,"rank":164,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.19739282682512457,"rank":93,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.17430315970875976,"rank":161,"remainingConfigurations":398},{"removed":"Datacurve","score":0.13024717934997512,"rank":165,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15009597570703134,"rank":163,"remainingConfigurations":398},{"removed":"Scale","score":0.16254872966397862,"rank":164,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.15124829597932096,"rank":164,"remainingConfigurations":398},{"removed":"Cognition","score":0.1578140828889346,"rank":165,"remainingConfigurations":398},{"removed":"LiveBench","score":0.15328770442460146,"rank":160,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1526027157245075,"rank":165,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11665074351371735,"rank":174,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14648672131198895,"rank":165,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.15088650017701666,"rank":164,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.15068195328689687,"rank":164,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.15071325242834607,"rank":164,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.15088247869700758,"rank":164,"remainingConfigurations":398},{"removed":"All provider reports","score":0.15049897507503168,"rank":164,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.15109098769338558,"rank":164,"remainingConfigurations":398},{"removed":"briefcase","score":0.15022086778235996,"rank":164,"remainingConfigurations":398},{"removed":"aime","score":0.1475598697448815,"rank":165,"remainingConfigurations":398},{"removed":"apex-agents","score":0.15184891622398045,"rank":164,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1509628326797224,"rank":162,"remainingConfigurations":398},{"removed":"automationbench","score":0.15031626051759053,"rank":163,"remainingConfigurations":398},{"removed":"critpt","score":0.1499111425018945,"rank":163,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.15079447205045501,"rank":164,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.15160879543345848,"rank":164,"remainingConfigurations":398},{"removed":"gdpval","score":0.15037877551394618,"rank":164,"remainingConfigurations":398},{"removed":"gmmlu","score":0.14922951761643877,"rank":163,"remainingConfigurations":398},{"removed":"gpqa","score":0.13577783024394996,"rank":171,"remainingConfigurations":398},{"removed":"harvey","score":0.14920287859776904,"rank":164,"remainingConfigurations":398},{"removed":"hle","score":0.15407264904564058,"rank":165,"remainingConfigurations":398},{"removed":"ifbench","score":0.15356184313152374,"rank":160,"remainingConfigurations":398},{"removed":"itbench","score":0.15056355523817275,"rank":164,"remainingConfigurations":398},{"removed":"livecodebench","score":0.15036013361022132,"rank":163,"remainingConfigurations":398},{"removed":"math500","score":0.15100751265517084,"rank":164,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15381189065248166,"rank":164,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.17495157523218194,"rank":151,"remainingConfigurations":398},{"removed":"omniscience","score":0.1486644423339281,"rank":160,"remainingConfigurations":398},{"removed":"scicode","score":0.15216863986323892,"rank":165,"remainingConfigurations":398},{"removed":"tau-bench","score":0.147487577157818,"rank":165,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1474418169293673,"rank":166,"remainingConfigurations":398},{"removed":"arc-agi","score":0.17349747017941838,"rank":162,"remainingConfigurations":398},{"removed":"deepswe","score":0.13034350934602454,"rank":165,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.15091477304445214,"rank":164,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.14997563616127355,"rank":164,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1578140828889346,"rank":165,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1510087956295307,"rank":163,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1495761180702848,"rank":164,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.15067302852826456,"rank":164,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.15039951953616218,"rank":164,"remainingConfigurations":398},{"removed":"livebench-math","score":0.15115764841063428,"rank":164,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.149743792655863,"rank":164,"remainingConfigurations":398},{"removed":"livebench-language","score":0.15228848929461666,"rank":164,"remainingConfigurations":398},{"removed":"livebench-data","score":0.15122755403855723,"rank":164,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.14899296456504932,"rank":164,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.15006684289049668,"rank":164,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15271014846147282,"rank":163,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1526027157245075,"rank":165,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1433309792531885,"rank":162,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1623243484544411,"rank":156,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15442692396836197,"rank":164,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.15027708690647143,"rank":164,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.15050767180448255,"rank":164,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.15027916805097663,"rank":164,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1507212083209454,"rank":164,"remainingConfigurations":398},{"removed":"vibe-code","score":0.15013136999304674,"rank":164,"remainingConfigurations":398}]},"gpt-5.4-mini--effort-high":{"score":0.14886637339083877,"rank":165,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.13753215131870722,"rank":111,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12056852945504465,"rank":191,"remainingConfigurations":398},{"removed":"Datacurve","score":0.12208583978965132,"rank":167,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.15006204751197508,"rank":164,"remainingConfigurations":398},{"removed":"Scale","score":0.16119056877180435,"rank":165,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.14784526523046898,"rank":165,"remainingConfigurations":398},{"removed":"Cognition","score":0.19864757879036166,"rank":128,"remainingConfigurations":398},{"removed":"LiveBench","score":0.15230871654238892,"rank":162,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.14548937003912918,"rank":167,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.14646267709918953,"rank":160,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14717856330370216,"rank":164,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.14888370591795425,"rank":165,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.14898986386989085,"rank":165,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.14871218675041578,"rank":165,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.14886637339083877,"rank":165,"remainingConfigurations":398},{"removed":"All provider reports","score":0.14883202494461514,"rank":165,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.14908611753430834,"rank":165,"remainingConfigurations":398},{"removed":"briefcase","score":0.14861045340183368,"rank":166,"remainingConfigurations":398},{"removed":"aime","score":0.1485934242403871,"rank":164,"remainingConfigurations":398},{"removed":"apex-agents","score":0.14952242798811496,"rank":165,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.14873340425254264,"rank":166,"remainingConfigurations":398},{"removed":"automationbench","score":0.14845373398380182,"rank":165,"remainingConfigurations":398},{"removed":"critpt","score":0.14917547825342317,"rank":165,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.14891241387213447,"rank":165,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.14859789677350058,"rank":166,"remainingConfigurations":398},{"removed":"gdpval","score":0.1489231810744719,"rank":165,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1488814869801113,"rank":164,"remainingConfigurations":398},{"removed":"gpqa","score":0.14852986565030393,"rank":163,"remainingConfigurations":398},{"removed":"harvey","score":0.14772276131219578,"rank":165,"remainingConfigurations":398},{"removed":"hle","score":0.15465617336291365,"rank":164,"remainingConfigurations":398},{"removed":"ifbench","score":0.14814125469563924,"rank":164,"remainingConfigurations":398},{"removed":"itbench","score":0.1486795392554711,"rank":165,"remainingConfigurations":398},{"removed":"livecodebench","score":0.14999049082597482,"rank":164,"remainingConfigurations":398},{"removed":"math500","score":0.14893384597987933,"rank":165,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15312871402679198,"rank":165,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.15653130076755983,"rank":165,"remainingConfigurations":398},{"removed":"omniscience","score":0.14707167301982232,"rank":163,"remainingConfigurations":398},{"removed":"scicode","score":0.1494930493754514,"rank":166,"remainingConfigurations":398},{"removed":"tau-bench","score":0.14926627699461384,"rank":164,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.15276965252313193,"rank":163,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12115767852766109,"rank":192,"remainingConfigurations":398},{"removed":"deepswe","score":0.12208779304116658,"rank":168,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.14889633464423035,"rank":165,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1472373087423323,"rank":165,"remainingConfigurations":398},{"removed":"frontiercode","score":0.19864757879036166,"rank":128,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.149142762650626,"rank":164,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1475823857405585,"rank":165,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.14871609611170697,"rank":165,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.14842113162153486,"rank":165,"remainingConfigurations":398},{"removed":"livebench-math","score":0.14911402632451784,"rank":165,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1477748209750053,"rank":165,"remainingConfigurations":398},{"removed":"livebench-language","score":0.15020459873299233,"rank":165,"remainingConfigurations":398},{"removed":"livebench-data","score":0.14902762222505908,"rank":165,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.14697608703560913,"rank":165,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.14806791130004296,"rank":165,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.15092287455183293,"rank":165,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.14548937003912918,"rank":167,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.14150050673837095,"rank":165,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1500338537063523,"rank":164,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15324293642280334,"rank":165,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.14800920184790298,"rank":165,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.14888903304654152,"rank":165,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.14896717476736077,"rank":165,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.14922648183287732,"rank":165,"remainingConfigurations":398},{"removed":"vibe-code","score":0.14858278812087375,"rank":165,"remainingConfigurations":398}]},"deepseek-v4-pro-0424--effort-high":{"score":0.14687571597873708,"rank":166,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08418949181391787,"rank":127,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.16022812266042463,"rank":165,"remainingConfigurations":398},{"removed":"Datacurve","score":0.14190224561409098,"rank":152,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.14651120635946807,"rank":165,"remainingConfigurations":398},{"removed":"Scale","score":0.15908908656860613,"rank":166,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.14516340526411553,"rank":166,"remainingConfigurations":398},{"removed":"Cognition","score":0.15184996128182213,"rank":166,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1489581487942074,"rank":163,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.28641711491349403,"rank":90,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.15301692664335156,"rank":155,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14162125925339344,"rank":166,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.14689154045231562,"rank":166,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.147680008679648,"rank":166,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.14677216587400801,"rank":166,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.14687571597873708,"rank":166,"remainingConfigurations":398},{"removed":"All provider reports","score":0.14756886580043246,"rank":166,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.14728256362197215,"rank":166,"remainingConfigurations":398},{"removed":"briefcase","score":0.1473177156890023,"rank":167,"remainingConfigurations":398},{"removed":"aime","score":0.14654225126409914,"rank":167,"remainingConfigurations":398},{"removed":"apex-agents","score":0.14806157610309326,"rank":166,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.14977182626353278,"rank":165,"remainingConfigurations":398},{"removed":"automationbench","score":0.14742626338439185,"rank":166,"remainingConfigurations":398},{"removed":"critpt","score":0.1446128573909532,"rank":167,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.14719867435803197,"rank":166,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.14841313715223772,"rank":167,"remainingConfigurations":398},{"removed":"gdpval","score":0.14305774928351697,"rank":167,"remainingConfigurations":398},{"removed":"gmmlu","score":0.14801258088267052,"rank":165,"remainingConfigurations":398},{"removed":"gpqa","score":0.14358478202053204,"rank":166,"remainingConfigurations":398},{"removed":"harvey","score":0.1456531133337763,"rank":166,"remainingConfigurations":398},{"removed":"hle","score":0.15103292997608572,"rank":166,"remainingConfigurations":398},{"removed":"ifbench","score":0.14649795919311953,"rank":166,"remainingConfigurations":398},{"removed":"itbench","score":0.14689419075586363,"rank":167,"remainingConfigurations":398},{"removed":"livecodebench","score":0.14746698743118505,"rank":165,"remainingConfigurations":398},{"removed":"math500","score":0.14719171540015982,"rank":166,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.15066878808874976,"rank":166,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.15562332379146313,"rank":166,"remainingConfigurations":398},{"removed":"omniscience","score":0.1441193297775475,"rank":166,"remainingConfigurations":398},{"removed":"scicode","score":0.14903256567527004,"rank":167,"remainingConfigurations":398},{"removed":"tau-bench","score":0.14358030175170855,"rank":166,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.14466189175200747,"rank":167,"remainingConfigurations":398},{"removed":"arc-agi","score":0.16078001906501369,"rank":165,"remainingConfigurations":398},{"removed":"deepswe","score":0.1418684610475207,"rank":152,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1468801271141392,"rank":166,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.14601284252866564,"rank":166,"remainingConfigurations":398},{"removed":"frontiercode","score":0.15184996128182213,"rank":166,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.14804828005864,"rank":165,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.14400470221097622,"rank":166,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.14698483862139752,"rank":166,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.14660974240654642,"rank":166,"remainingConfigurations":398},{"removed":"livebench-math","score":0.14708657198831104,"rank":166,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1457057611484828,"rank":166,"remainingConfigurations":398},{"removed":"livebench-language","score":0.14797751151411276,"rank":166,"remainingConfigurations":398},{"removed":"livebench-data","score":0.14729455103685316,"rank":166,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.14511279119404696,"rank":166,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1458642876638129,"rank":166,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.14912679658260342,"rank":166,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.28641711491349403,"rank":90,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1432914976684516,"rank":163,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1472818021544591,"rank":165,"remainingConfigurations":398},{"removed":"simpleqa","score":0.15131365330583235,"rank":166,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.14648556184802905,"rank":166,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.14645550057581783,"rank":166,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.14632439968820773,"rank":166,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1466672702529637,"rank":166,"remainingConfigurations":398},{"removed":"vibe-code","score":0.14612806183021454,"rank":166,"remainingConfigurations":398}]},"qwen3.5-122b-a10b--effort-reasoning":{"score":0.14423866718655834,"rank":167,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1674758198292596,"rank":162,"remainingConfigurations":398},{"removed":"Datacurve","score":0.12484247482140921,"rank":166,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1432390185052889,"rank":166,"remainingConfigurations":398},{"removed":"Scale","score":0.15663624023173583,"rank":167,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1442979576111413,"rank":167,"remainingConfigurations":398},{"removed":"Cognition","score":0.14929346570713778,"rank":167,"remainingConfigurations":398},{"removed":"LiveBench","score":0.14659299288896618,"rank":164,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.14752074174006405,"rank":166,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.14580273057284884,"rank":161,"remainingConfigurations":381},{"removed":"Vals AI","score":0.14018332618647641,"rank":167,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.14424424500180436,"rank":167,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.14410895433867063,"rank":167,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1440002527084917,"rank":167,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.14423866718655834,"rank":167,"remainingConfigurations":398},{"removed":"All provider reports","score":0.14385663716466723,"rank":167,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1442456501325152,"rank":167,"remainingConfigurations":398},{"removed":"briefcase","score":0.14882311492198932,"rank":165,"remainingConfigurations":398},{"removed":"aime","score":0.14497658590472515,"rank":168,"remainingConfigurations":398},{"removed":"apex-agents","score":0.14539865918755937,"rank":167,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.13782202766621937,"rank":169,"remainingConfigurations":398},{"removed":"automationbench","score":0.1454448878094627,"rank":167,"remainingConfigurations":398},{"removed":"critpt","score":0.14761226406674102,"rank":166,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.14389566592056854,"rank":167,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1513726139911211,"rank":165,"remainingConfigurations":398},{"removed":"gdpval","score":0.14485662970869936,"rank":166,"remainingConfigurations":398},{"removed":"gmmlu","score":0.14088006338466028,"rank":167,"remainingConfigurations":398},{"removed":"gpqa","score":0.13853936632254737,"rank":168,"remainingConfigurations":398},{"removed":"harvey","score":0.14231378754945515,"rank":167,"remainingConfigurations":398},{"removed":"hle","score":0.1477798210943075,"rank":169,"remainingConfigurations":398},{"removed":"ifbench","score":0.1345763062575862,"rank":170,"remainingConfigurations":398},{"removed":"itbench","score":0.14375137853643682,"rank":168,"remainingConfigurations":398},{"removed":"livecodebench","score":0.14431815192225775,"rank":166,"remainingConfigurations":398},{"removed":"math500","score":0.14460056632955923,"rank":167,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1478262955102328,"rank":167,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1482559677271566,"rank":168,"remainingConfigurations":398},{"removed":"omniscience","score":0.14604466654258788,"rank":164,"remainingConfigurations":398},{"removed":"scicode","score":0.15267011383462706,"rank":164,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13937638290796425,"rank":167,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.14920725638792526,"rank":164,"remainingConfigurations":398},{"removed":"arc-agi","score":0.16667581729768874,"rank":163,"remainingConfigurations":398},{"removed":"deepswe","score":0.12492926994874183,"rank":166,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.14427590881359792,"rank":167,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.14333036344203412,"rank":167,"remainingConfigurations":398},{"removed":"frontiercode","score":0.14929346570713778,"rank":167,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1443342719258827,"rank":167,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.14307206472360914,"rank":167,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.14403310460707197,"rank":167,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.14370543485635073,"rank":167,"remainingConfigurations":398},{"removed":"livebench-math","score":0.14444412551479738,"rank":167,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.14332043132370018,"rank":167,"remainingConfigurations":398},{"removed":"livebench-language","score":0.14565734300037225,"rank":167,"remainingConfigurations":398},{"removed":"livebench-data","score":0.14447078976938685,"rank":167,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.14233335681973025,"rank":167,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1434550844999971,"rank":167,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.14600470153245684,"rank":167,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.14752074174006405,"rank":166,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.13869810971399057,"rank":167,"remainingConfigurations":398},{"removed":"frontiermath","score":0.14536396900799659,"rank":166,"remainingConfigurations":398},{"removed":"simpleqa","score":0.14893317636544423,"rank":167,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.14364658260827382,"rank":167,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.14383391104564655,"rank":167,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1437364390160484,"rank":167,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.14407197551177073,"rank":167,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1434218161516879,"rank":167,"remainingConfigurations":398}]},"gemini-3-flash-preview--effort-non-reasoning":{"score":0.14034269218660642,"rank":168,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.16601124312339416,"rank":163,"remainingConfigurations":398},{"removed":"Datacurve","score":0.12204812173575726,"rank":168,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.13909071014703953,"rank":167,"remainingConfigurations":398},{"removed":"Scale","score":0.15287381577894185,"rank":168,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.14054086793568335,"rank":168,"remainingConfigurations":398},{"removed":"Cognition","score":0.14627655970540093,"rank":169,"remainingConfigurations":398},{"removed":"LiveBench","score":0.14291125868434718,"rank":166,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.14373786580633444,"rank":168,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1403124538553058,"rank":162,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1369028113949212,"rank":168,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1403496721834865,"rank":168,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.14021985127236988,"rank":168,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.14012610981536547,"rank":168,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.14034269218660642,"rank":168,"remainingConfigurations":398},{"removed":"All provider reports","score":0.13999129556430767,"rank":168,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.14072396703365023,"rank":169,"remainingConfigurations":398},{"removed":"briefcase","score":0.1401557788063748,"rank":168,"remainingConfigurations":398},{"removed":"aime","score":0.1601083175560574,"rank":153,"remainingConfigurations":398},{"removed":"apex-agents","score":0.14169528044844634,"rank":168,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.142391638630341,"rank":167,"remainingConfigurations":398},{"removed":"automationbench","score":0.14027574717815106,"rank":168,"remainingConfigurations":398},{"removed":"critpt","score":0.13729640042194896,"rank":169,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.14044448577513793,"rank":168,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1418666816412768,"rank":168,"remainingConfigurations":398},{"removed":"gdpval","score":0.14116342756968112,"rank":168,"remainingConfigurations":398},{"removed":"gmmlu","score":0.13045459108971155,"rank":173,"remainingConfigurations":398},{"removed":"gpqa","score":0.13950398299743735,"rank":167,"remainingConfigurations":398},{"removed":"harvey","score":0.1389367871057022,"rank":168,"remainingConfigurations":398},{"removed":"hle","score":0.1493857536474679,"rank":168,"remainingConfigurations":398},{"removed":"ifbench","score":0.14326103253374742,"rank":167,"remainingConfigurations":398},{"removed":"itbench","score":0.14015665924894316,"rank":169,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1379748612314298,"rank":167,"remainingConfigurations":398},{"removed":"math500","score":0.14030857831808918,"rank":168,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13761195388301758,"rank":171,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.13802601567236886,"rank":172,"remainingConfigurations":398},{"removed":"omniscience","score":0.12454463790339022,"rank":173,"remainingConfigurations":398},{"removed":"scicode","score":0.14259376584575803,"rank":168,"remainingConfigurations":398},{"removed":"tau-bench","score":0.15147735196284037,"rank":161,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.14143036364245395,"rank":168,"remainingConfigurations":398},{"removed":"arc-agi","score":0.16503862354089105,"rank":164,"remainingConfigurations":398},{"removed":"deepswe","score":0.12213054557016623,"rank":167,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1403765381746512,"rank":168,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.13941171031515107,"rank":168,"remainingConfigurations":398},{"removed":"frontiercode","score":0.14627655970540093,"rank":169,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.14040311615113607,"rank":168,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13919741461487245,"rank":168,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.14013531378164648,"rank":168,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.13986400018080158,"rank":168,"remainingConfigurations":398},{"removed":"livebench-math","score":0.14054613476949943,"rank":168,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1394302851810205,"rank":168,"remainingConfigurations":398},{"removed":"livebench-language","score":0.14171624236420488,"rank":168,"remainingConfigurations":398},{"removed":"livebench-data","score":0.14055767361812868,"rank":168,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.13849025574225646,"rank":168,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.13957696772857903,"rank":168,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.142095786172649,"rank":168,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.14373786580633444,"rank":168,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.13435033179234912,"rank":168,"remainingConfigurations":398},{"removed":"frontiermath","score":0.14158145856299706,"rank":167,"remainingConfigurations":398},{"removed":"simpleqa","score":0.14502705198427307,"rank":168,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.13976747708451256,"rank":168,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.13993855996879398,"rank":168,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.13985492395339674,"rank":168,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.14016333960439567,"rank":168,"remainingConfigurations":398},{"removed":"vibe-code","score":0.13954841001909482,"rank":168,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-non-reasoning":{"score":0.13495191746472016,"rank":169,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15686110467334582,"rank":170,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11673501103187915,"rank":170,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1338288704709282,"rank":168,"remainingConfigurations":398},{"removed":"Scale","score":0.14640117217610052,"rank":171,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.13499544730062,"rank":169,"remainingConfigurations":398},{"removed":"Cognition","score":0.13955627394931622,"rank":174,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1375367023579668,"rank":167,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.13772641605456878,"rank":171,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13494061649953773,"rank":165,"remainingConfigurations":381},{"removed":"Vals AI","score":0.13141848593321498,"rank":169,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1349572986916852,"rank":169,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1348276079641671,"rank":169,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.13473092918091914,"rank":169,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.13495191746472016,"rank":169,"remainingConfigurations":398},{"removed":"All provider reports","score":0.13459349932929224,"rank":169,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1355663580267583,"rank":170,"remainingConfigurations":398},{"removed":"briefcase","score":0.12723184781792235,"rank":175,"remainingConfigurations":398},{"removed":"aime","score":0.1355729260262043,"rank":172,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13644152525192996,"rank":169,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.14203348367130778,"rank":168,"remainingConfigurations":398},{"removed":"automationbench","score":0.13500749345988708,"rank":169,"remainingConfigurations":398},{"removed":"critpt","score":0.12742477251287856,"rank":176,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.13527038710422132,"rank":170,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.13666736462618365,"rank":169,"remainingConfigurations":398},{"removed":"gdpval","score":0.1257566085104515,"rank":176,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1353557315125225,"rank":170,"remainingConfigurations":398},{"removed":"gpqa","score":0.14767677443893212,"rank":165,"remainingConfigurations":398},{"removed":"harvey","score":0.13378327307534219,"rank":170,"remainingConfigurations":398},{"removed":"hle","score":0.15041052223796356,"rank":167,"remainingConfigurations":398},{"removed":"ifbench","score":0.1316696852854493,"rank":171,"remainingConfigurations":398},{"removed":"itbench","score":0.13493990322970692,"rank":170,"remainingConfigurations":398},{"removed":"livecodebench","score":0.13443304120333907,"rank":170,"remainingConfigurations":398},{"removed":"math500","score":0.1349624289349236,"rank":171,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13774801520795935,"rank":169,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.15240404894757018,"rank":167,"remainingConfigurations":398},{"removed":"omniscience","score":0.12150520167210434,"rank":176,"remainingConfigurations":398},{"removed":"scicode","score":0.13767804736693356,"rank":169,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13121550787692443,"rank":173,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1326068550070511,"rank":173,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15619163860387575,"rank":171,"remainingConfigurations":398},{"removed":"deepswe","score":0.11681520285955682,"rank":170,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.13498604717914375,"rank":169,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.13403103526036078,"rank":169,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13955627394931622,"rank":174,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.13505028398330984,"rank":169,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13383882774791536,"rank":169,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.13475724748107862,"rank":169,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.13449662367426768,"rank":169,"remainingConfigurations":398},{"removed":"livebench-math","score":0.13514918033440623,"rank":169,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1340630623694248,"rank":169,"remainingConfigurations":398},{"removed":"livebench-language","score":0.13629499411996737,"rank":169,"remainingConfigurations":398},{"removed":"livebench-data","score":0.13517638331297474,"rank":169,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.13314308676556938,"rank":169,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.13420298673816647,"rank":169,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1366507228611924,"rank":169,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.13772641605456878,"rank":171,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12918484242849873,"rank":171,"remainingConfigurations":398},{"removed":"frontiermath","score":0.13611392087442636,"rank":169,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1394532292477401,"rank":169,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.13438964166854087,"rank":169,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.13456515967355945,"rank":169,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1344753134385836,"rank":169,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.13478491018087366,"rank":169,"remainingConfigurations":398},{"removed":"vibe-code","score":0.13417726162568802,"rank":169,"remainingConfigurations":398}]},"gpt-5.5--effort-non-reasoning":{"score":0.1348282854004683,"rank":170,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15815966186637917,"rank":166,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11689082312394376,"rank":169,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.133799329643455,"rank":169,"remainingConfigurations":398},{"removed":"Scale","score":0.14647193732809363,"rank":170,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.13493105486408075,"rank":170,"remainingConfigurations":398},{"removed":"Cognition","score":0.13999252652329672,"rank":171,"remainingConfigurations":398},{"removed":"LiveBench","score":0.13740971077883166,"rank":168,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1377363770708738,"rank":170,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13529432516019826,"rank":164,"remainingConfigurations":381},{"removed":"Vals AI","score":0.13114814360640195,"rank":170,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.13483382297090468,"rank":170,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.13468180717480013,"rank":170,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.13461487190001606,"rank":170,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1348282854004683,"rank":170,"remainingConfigurations":398},{"removed":"All provider reports","score":0.13445568523132045,"rank":170,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.14280141136260777,"rank":168,"remainingConfigurations":398},{"removed":"briefcase","score":0.13407041276777024,"rank":171,"remainingConfigurations":398},{"removed":"aime","score":0.1357177529840923,"rank":171,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13605261456329765,"rank":170,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1309679235652854,"rank":171,"remainingConfigurations":398},{"removed":"automationbench","score":0.1343902188867881,"rank":170,"remainingConfigurations":398},{"removed":"critpt","score":0.13126796084533304,"rank":173,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1346709159512815,"rank":171,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1360949995256008,"rank":170,"remainingConfigurations":398},{"removed":"gdpval","score":0.1330294072722648,"rank":173,"remainingConfigurations":398},{"removed":"gmmlu","score":0.13553241824713777,"rank":169,"remainingConfigurations":398},{"removed":"gpqa","score":0.13836847426867033,"rank":169,"remainingConfigurations":398},{"removed":"harvey","score":0.1331370619643796,"rank":171,"remainingConfigurations":398},{"removed":"hle","score":0.1444124540367255,"rank":170,"remainingConfigurations":398},{"removed":"ifbench","score":0.1430352741922967,"rank":168,"remainingConfigurations":398},{"removed":"itbench","score":0.13437572499814276,"rank":171,"remainingConfigurations":398},{"removed":"livecodebench","score":0.13479695125088983,"rank":168,"remainingConfigurations":398},{"removed":"math500","score":0.13518528786035985,"rank":170,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13803085626180284,"rank":168,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.14105990509661745,"rank":170,"remainingConfigurations":398},{"removed":"omniscience","score":0.12124848408719564,"rank":178,"remainingConfigurations":398},{"removed":"scicode","score":0.1367651996999472,"rank":170,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13889670092838405,"rank":168,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.12460745736496552,"rank":176,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15723933983198118,"rank":167,"remainingConfigurations":398},{"removed":"deepswe","score":0.11697298236001012,"rank":169,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.13486167877798694,"rank":170,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.133953851090146,"rank":170,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13999252652329672,"rank":171,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1349099968303417,"rank":170,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13371805467994716,"rank":170,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.13463390359537616,"rank":170,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.13435485432786723,"rank":170,"remainingConfigurations":398},{"removed":"livebench-math","score":0.135024045135894,"rank":170,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.13394244194756358,"rank":170,"remainingConfigurations":398},{"removed":"livebench-language","score":0.13616555179466397,"rank":170,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1350477270295606,"rank":170,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.13302354898129123,"rank":170,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.13408479720425417,"rank":170,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.13652659923717514,"rank":170,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1377363770708738,"rank":170,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12924462940004885,"rank":170,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1358699037877632,"rank":170,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13934835514889657,"rank":170,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.13427547893735214,"rank":170,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1344356799342318,"rank":170,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1343490736945919,"rank":170,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.13465416571537603,"rank":170,"remainingConfigurations":398},{"removed":"vibe-code","score":0.13405852851809666,"rank":170,"remainingConfigurations":398}]},"qwen3.5-35b-a3b--effort-reasoning":{"score":0.1344816193619045,"rank":171,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1578847103152401,"rank":167,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11652724728931253,"rank":171,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.13350102147515736,"rank":170,"remainingConfigurations":398},{"removed":"Scale","score":0.1465748666061326,"rank":169,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.13459507981713487,"rank":171,"remainingConfigurations":398},{"removed":"Cognition","score":0.1399524605956998,"rank":172,"remainingConfigurations":398},{"removed":"LiveBench","score":0.13664465487654026,"rank":169,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.13741801264996528,"rank":172,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13591821691000874,"rank":163,"remainingConfigurations":381},{"removed":"Vals AI","score":0.13064844642109655,"rank":171,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.13448842251277088,"rank":171,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1343679910383699,"rank":171,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.13426768746478468,"rank":171,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1344816193619045,"rank":171,"remainingConfigurations":398},{"removed":"All provider reports","score":0.13414206054744332,"rank":171,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.13436682490608434,"rank":172,"remainingConfigurations":398},{"removed":"briefcase","score":0.13363944284540452,"rank":173,"remainingConfigurations":398},{"removed":"aime","score":0.1355350017309813,"rank":173,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13532228408875668,"rank":171,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12918876596073034,"rank":173,"remainingConfigurations":398},{"removed":"automationbench","score":0.13363198208444096,"rank":172,"remainingConfigurations":398},{"removed":"critpt","score":0.13563734165017022,"rank":170,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.13408322765928865,"rank":173,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.13517105532447646,"rank":172,"remainingConfigurations":398},{"removed":"gdpval","score":0.13448366667530193,"rank":172,"remainingConfigurations":398},{"removed":"gmmlu","score":0.13464502827524313,"rank":171,"remainingConfigurations":398},{"removed":"gpqa","score":0.12865745647380025,"rank":173,"remainingConfigurations":398},{"removed":"harvey","score":0.1325967909786175,"rank":173,"remainingConfigurations":398},{"removed":"hle","score":0.13831531128011015,"rank":172,"remainingConfigurations":398},{"removed":"ifbench","score":0.1248316292653155,"rank":175,"remainingConfigurations":398},{"removed":"itbench","score":0.14844447249501683,"rank":166,"remainingConfigurations":398},{"removed":"livecodebench","score":0.13458891560297162,"rank":169,"remainingConfigurations":398},{"removed":"math500","score":0.13487196807814406,"rank":172,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13766851741370909,"rank":170,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1396319818882778,"rank":171,"remainingConfigurations":398},{"removed":"omniscience","score":0.14128058388238873,"rank":168,"remainingConfigurations":398},{"removed":"scicode","score":0.13569037197400127,"rank":172,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12999896844818845,"rank":174,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.13880848697768566,"rank":169,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15700618139557534,"rank":168,"remainingConfigurations":398},{"removed":"deepswe","score":0.11660850328684409,"rank":171,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1345136549217037,"rank":171,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.133597554005926,"rank":171,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1399524605956998,"rank":172,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.13455611366874456,"rank":171,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13339431305634922,"rank":171,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.13428204004258873,"rank":171,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1340175098987785,"rank":171,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1346755377229916,"rank":171,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.13360803727735462,"rank":171,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1358210625073268,"rank":171,"remainingConfigurations":398},{"removed":"livebench-data","score":0.13467827231593352,"rank":171,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.13268716088194385,"rank":171,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.13374239232436255,"rank":171,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.13617461314951498,"rank":171,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.13741801264996528,"rank":172,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1293926630827513,"rank":169,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1356148345142654,"rank":171,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13899051630039091,"rank":171,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.13392746894795737,"rank":171,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.1340854582507203,"rank":171,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.13400998308473844,"rank":171,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1343046149409699,"rank":171,"remainingConfigurations":398},{"removed":"vibe-code","score":0.13372000607638143,"rank":171,"remainingConfigurations":398}]},"minimax-m2.1--effort-reasoning":{"score":0.1341475340749492,"rank":172,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15763057131362357,"rank":168,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1164452633704605,"rank":172,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.13295924546576604,"rank":171,"remainingConfigurations":398},{"removed":"Scale","score":0.14616452944878622,"rank":172,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.13431786426066433,"rank":172,"remainingConfigurations":398},{"removed":"Cognition","score":0.13994501616052352,"rank":173,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1365050226304812,"rank":170,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1369060664308517,"rank":173,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13429554341529373,"rank":167,"remainingConfigurations":381},{"removed":"Vals AI","score":0.13064552322520115,"rank":172,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1341544207332086,"rank":172,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.13403152816873043,"rank":172,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.13393878046013358,"rank":172,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.1341475340749492,"rank":172,"remainingConfigurations":398},{"removed":"All provider reports","score":0.13381131597699994,"rank":172,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.134388236626807,"rank":171,"remainingConfigurations":398},{"removed":"briefcase","score":0.13365403173861293,"rank":172,"remainingConfigurations":398},{"removed":"aime","score":0.13755521226006615,"rank":170,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13528141566650126,"rank":172,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1333115775935489,"rank":170,"remainingConfigurations":398},{"removed":"automationbench","score":0.13379701067272046,"rank":171,"remainingConfigurations":398},{"removed":"critpt","score":0.140029171937392,"rank":168,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1341101095053904,"rank":172,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.13530127978278597,"rank":171,"remainingConfigurations":398},{"removed":"gdpval","score":0.13474641406386204,"rank":170,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1390736717210751,"rank":168,"remainingConfigurations":398},{"removed":"gpqa","score":0.13063115604656617,"rank":172,"remainingConfigurations":398},{"removed":"harvey","score":0.13266257569080106,"rank":172,"remainingConfigurations":398},{"removed":"hle","score":0.13702286322387972,"rank":173,"remainingConfigurations":398},{"removed":"ifbench","score":0.12837885924632664,"rank":173,"remainingConfigurations":398},{"removed":"itbench","score":0.1338875889214485,"rank":172,"remainingConfigurations":398},{"removed":"livecodebench","score":0.13084019177311426,"rank":173,"remainingConfigurations":398},{"removed":"math500","score":0.13428730148029927,"rank":173,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13138923207407519,"rank":173,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.14147965428361775,"rank":169,"remainingConfigurations":398},{"removed":"omniscience","score":0.13485275667909044,"rank":170,"remainingConfigurations":398},{"removed":"scicode","score":0.13598244467622808,"rank":171,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13174388057842826,"rank":172,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1361099556586012,"rank":170,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15664180462918623,"rank":169,"remainingConfigurations":398},{"removed":"deepswe","score":0.11652499318466703,"rank":172,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1341804644219967,"rank":172,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1332479148741426,"rank":172,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13994501616052352,"rank":173,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.13421736976756704,"rank":172,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13304864765428367,"rank":172,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.13394709526166187,"rank":172,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.13368544428401843,"rank":172,"remainingConfigurations":398},{"removed":"livebench-math","score":0.13434504888872403,"rank":172,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.13326140966190747,"rank":172,"remainingConfigurations":398},{"removed":"livebench-language","score":0.13547760572959242,"rank":172,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1343568299033442,"rank":172,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1323534340276857,"rank":172,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.13340499393446692,"rank":172,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.13584925108503967,"rank":172,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1369060664308517,"rank":173,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12827612712507158,"rank":173,"remainingConfigurations":398},{"removed":"frontiermath","score":0.13538448552746915,"rank":172,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13867933112410383,"rank":172,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.13359014437226682,"rank":172,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.13375574816877275,"rank":172,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.13367562852812143,"rank":172,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.13397344187190038,"rank":172,"remainingConfigurations":398},{"removed":"vibe-code","score":0.13337904906780154,"rank":172,"remainingConfigurations":398}]},"gemma-4-31b-it--effort-reasoning":{"score":0.13190272509340084,"rank":173,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15306231954098695,"rank":171,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11367151705825856,"rank":174,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.13101511241671418,"rank":172,"remainingConfigurations":398},{"removed":"Scale","score":0.14358092381272655,"rank":173,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.13189984014664535,"rank":173,"remainingConfigurations":398},{"removed":"Cognition","score":0.1364419859815498,"rank":175,"remainingConfigurations":398},{"removed":"LiveBench","score":0.13410871392977938,"rank":171,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1349209673284354,"rank":174,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1338337929661367,"rank":168,"remainingConfigurations":381},{"removed":"Vals AI","score":0.12828093150135364,"rank":173,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.13191056592709308,"rank":173,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.13178546578832,"rank":173,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.13167560768802367,"rank":173,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.13190272509340084,"rank":173,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1315474658658293,"rank":173,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.13216408830583834,"rank":173,"remainingConfigurations":398},{"removed":"briefcase","score":0.13822604237219327,"rank":169,"remainingConfigurations":398},{"removed":"aime","score":0.13215575503078122,"rank":174,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13325196255142457,"rank":173,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12982664481093842,"rank":172,"remainingConfigurations":398},{"removed":"automationbench","score":0.13321705762035618,"rank":174,"remainingConfigurations":398},{"removed":"critpt","score":0.13050751486076045,"rank":174,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.13593690524979693,"rank":169,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.13253199194668366,"rank":173,"remainingConfigurations":398},{"removed":"gdpval","score":0.13469257455986774,"rank":171,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1325266296859577,"rank":172,"remainingConfigurations":398},{"removed":"gpqa","score":0.12603041139234095,"rank":175,"remainingConfigurations":398},{"removed":"harvey","score":0.13619101686500634,"rank":169,"remainingConfigurations":398},{"removed":"hle","score":0.13485004055377875,"rank":174,"remainingConfigurations":398},{"removed":"ifbench","score":0.12262548415482939,"rank":176,"remainingConfigurations":398},{"removed":"itbench","score":0.12276139037748658,"rank":178,"remainingConfigurations":398},{"removed":"livecodebench","score":0.13177585982235196,"rank":171,"remainingConfigurations":398},{"removed":"math500","score":0.13227913403893773,"rank":174,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13508909698004035,"rank":172,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.13705340334113503,"rank":173,"remainingConfigurations":398},{"removed":"omniscience","score":0.13762270912989918,"rank":169,"remainingConfigurations":398},{"removed":"scicode","score":0.12991018887751893,"rank":175,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13220249880277662,"rank":171,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.133976501586809,"rank":172,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15232356320845025,"rank":172,"remainingConfigurations":398},{"removed":"deepswe","score":0.1137563308597289,"rank":174,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.13193605047386084,"rank":173,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.13108075165782074,"rank":173,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1364419859815498,"rank":175,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.13200138897848804,"rank":173,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.13081932637485089,"rank":173,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.13171357936750364,"rank":173,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1314165062228683,"rank":173,"remainingConfigurations":398},{"removed":"livebench-math","score":0.13208847052011116,"rank":173,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1310564072088468,"rank":173,"remainingConfigurations":398},{"removed":"livebench-language","score":0.13324669384334617,"rank":173,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1321063465477201,"rank":173,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.13011626802032747,"rank":173,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1311726179684979,"rank":173,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.13354945472679328,"rank":173,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1349209673284354,"rank":174,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12711013552719547,"rank":174,"remainingConfigurations":398},{"removed":"frontiermath","score":0.13288366050222136,"rank":173,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13629302214397376,"rank":173,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1313529512727794,"rank":173,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.13151855306589372,"rank":173,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1314302722037151,"rank":173,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1317447734403299,"rank":173,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1311426553619852,"rank":173,"remainingConfigurations":398}]},"gemini-2.5-pro--effort-reasoning":{"score":0.12948239171788967,"rank":174,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15118240575082645,"rank":173,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11185178163321731,"rank":176,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12831961613450849,"rank":173,"remainingConfigurations":398},{"removed":"Scale","score":0.1410921618059688,"rank":174,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12951135338895556,"rank":174,"remainingConfigurations":398},{"removed":"Cognition","score":0.13450402606233336,"rank":177,"remainingConfigurations":398},{"removed":"LiveBench","score":0.13176997698212062,"rank":172,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.13243175436381663,"rank":175,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13052452895369185,"rank":169,"remainingConfigurations":381},{"removed":"Vals AI","score":0.12589276220003415,"rank":174,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.12948822343644714,"rank":174,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.129365447537701,"rank":174,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.12926851887287358,"rank":174,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12948239171788967,"rank":174,"remainingConfigurations":398},{"removed":"All provider reports","score":0.12913947367648662,"rank":174,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.12977435131393578,"rank":174,"remainingConfigurations":398},{"removed":"briefcase","score":0.13488236259037015,"rank":170,"remainingConfigurations":398},{"removed":"aime","score":0.12889956857295298,"rank":176,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13070410644811278,"rank":174,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12779935665381958,"rank":175,"remainingConfigurations":398},{"removed":"automationbench","score":0.13357569523057247,"rank":173,"remainingConfigurations":398},{"removed":"critpt","score":0.12631485226698277,"rank":178,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1294805001643284,"rank":174,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1273380179887093,"rank":175,"remainingConfigurations":398},{"removed":"gdpval","score":0.13567163491523235,"rank":169,"remainingConfigurations":398},{"removed":"gmmlu","score":0.12477609163451292,"rank":175,"remainingConfigurations":398},{"removed":"gpqa","score":0.12507310893202198,"rank":178,"remainingConfigurations":398},{"removed":"harvey","score":0.1281284248356024,"rank":174,"remainingConfigurations":398},{"removed":"hle","score":0.13332449252540637,"rank":175,"remainingConfigurations":398},{"removed":"ifbench","score":0.1314804225702583,"rank":172,"remainingConfigurations":398},{"removed":"itbench","score":0.12923807892778127,"rank":173,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1277327577942811,"rank":175,"remainingConfigurations":398},{"removed":"math500","score":0.13537848907687963,"rank":169,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13005244667714155,"rank":175,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1337920461991486,"rank":176,"remainingConfigurations":398},{"removed":"omniscience","score":0.12083131850984896,"rank":179,"remainingConfigurations":398},{"removed":"scicode","score":0.12763545928120443,"rank":177,"remainingConfigurations":398},{"removed":"tau-bench","score":0.13225305028074988,"rank":170,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1341629786472283,"rank":171,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15035718982591476,"rank":174,"remainingConfigurations":398},{"removed":"deepswe","score":0.11193124574410185,"rank":176,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1295162116649981,"rank":174,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.12863702338484156,"rank":174,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13450402606233336,"rank":177,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.12955532773302722,"rank":174,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12840366861308486,"rank":174,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1292966321589133,"rank":174,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12900643041135745,"rank":174,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1296730646581396,"rank":174,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12863185140737,"rank":174,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1307923193851005,"rank":174,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1296910404484026,"rank":174,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.12772282572594862,"rank":174,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.12875842274385926,"rank":174,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1311245849150306,"rank":174,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.13243175436381663,"rank":175,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12415622867728433,"rank":175,"remainingConfigurations":398},{"removed":"frontiermath","score":0.13053687337648592,"rank":174,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13385378463728517,"rank":174,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.12893400231391589,"rank":174,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12910454380086184,"rank":174,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12902062771688158,"rank":174,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.12932187445936424,"rank":174,"remainingConfigurations":398},{"removed":"vibe-code","score":0.12872845211711995,"rank":174,"remainingConfigurations":398}]},"claude-opus-4-5-20251101--effort-non-reasoning":{"score":0.12921296797653162,"rank":175,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.15286995942862197,"rank":172,"remainingConfigurations":398},{"removed":"Datacurve","score":0.11193028138240702,"rank":175,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12808540790754322,"rank":174,"remainingConfigurations":398},{"removed":"Scale","score":0.14069834618938346,"rank":175,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12934884422809959,"rank":175,"remainingConfigurations":398},{"removed":"Cognition","score":0.13470898470091322,"rank":176,"remainingConfigurations":398},{"removed":"LiveBench","score":0.1315942052487552,"rank":173,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1323136280602916,"rank":176,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.12911650879696532,"rank":170,"remainingConfigurations":381},{"removed":"Vals AI","score":0.12587402602277065,"rank":175,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.12921969197301253,"rank":175,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1290991445185181,"rank":175,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1290092217538644,"rank":175,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12921296797653162,"rank":175,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1288842111572753,"rank":175,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.129512025028409,"rank":175,"remainingConfigurations":398},{"removed":"briefcase","score":0.12879334211523222,"rank":174,"remainingConfigurations":398},{"removed":"aime","score":0.14334643261228247,"rank":169,"remainingConfigurations":398},{"removed":"apex-agents","score":0.13031871590075525,"rank":175,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12548267342369415,"rank":176,"remainingConfigurations":398},{"removed":"automationbench","score":0.12889533701576492,"rank":175,"remainingConfigurations":398},{"removed":"critpt","score":0.13422012274334794,"rank":171,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.12924625009362417,"rank":175,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1303925067355017,"rank":174,"remainingConfigurations":398},{"removed":"gdpval","score":0.12966385924064894,"rank":174,"remainingConfigurations":398},{"removed":"gmmlu","score":0.12126632314474073,"rank":179,"remainingConfigurations":398},{"removed":"gpqa","score":0.12808103896370326,"rank":174,"remainingConfigurations":398},{"removed":"harvey","score":0.12779823009461858,"rank":175,"remainingConfigurations":398},{"removed":"hle","score":0.13915234081797823,"rank":171,"remainingConfigurations":398},{"removed":"ifbench","score":0.1404235401234216,"rank":169,"remainingConfigurations":398},{"removed":"itbench","score":0.12900309373527621,"rank":174,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1309362476030067,"rank":172,"remainingConfigurations":398},{"removed":"math500","score":0.12939622525947,"rank":175,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.12605721502256956,"rank":178,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.13532494346068324,"rank":174,"remainingConfigurations":398},{"removed":"omniscience","score":0.1152751619562307,"rank":182,"remainingConfigurations":398},{"removed":"scicode","score":0.13103344456859017,"rank":174,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12619427967372157,"rank":176,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.12386339733175704,"rank":177,"remainingConfigurations":398},{"removed":"arc-agi","score":0.15205929984605523,"rank":173,"remainingConfigurations":398},{"removed":"deepswe","score":0.11200664268179679,"rank":175,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.12924474130391805,"rank":175,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.12834551409465636,"rank":175,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13470898470091322,"rank":176,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1292787234504483,"rank":175,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12814797926265173,"rank":175,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1290208996569486,"rank":175,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12876808069580367,"rank":175,"remainingConfigurations":398},{"removed":"livebench-math","score":0.12940493888726942,"rank":175,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12834813024893443,"rank":175,"remainingConfigurations":398},{"removed":"livebench-language","score":0.130506434113831,"rank":175,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1294180460572886,"rank":175,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.12746856913741011,"rank":175,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1284899447342429,"rank":175,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.13087158916141287,"rank":175,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1323136280602916,"rank":176,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.12358058040226472,"rank":176,"remainingConfigurations":398},{"removed":"frontiermath","score":0.13039914935758704,"rank":175,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13362068695541154,"rank":175,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.12867066275205694,"rank":175,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12883165539619956,"rank":175,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12875444248048315,"rank":175,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.12904101424143843,"rank":175,"remainingConfigurations":398},{"removed":"vibe-code","score":0.12846587781849153,"rank":175,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-medium":{"score":0.12765487127159783,"rank":176,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.09171513808312685,"rank":120,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1387826822106548,"rank":176,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1153638156195666,"rank":173,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1275528855854873,"rank":175,"remainingConfigurations":398},{"removed":"Scale","score":0.13842188602045016,"rank":176,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12682677461773498,"rank":176,"remainingConfigurations":398},{"removed":"Cognition","score":0.12459611766084851,"rank":181,"remainingConfigurations":398},{"removed":"LiveBench","score":0.13087169099948875,"rank":174,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.14308554535696996,"rank":169,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1466387704171477,"rank":159,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1232160995144471,"rank":176,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.12767706722138644,"rank":176,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1277349301075694,"rank":176,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.12760349021316836,"rank":176,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12765487127159783,"rank":176,"remainingConfigurations":398},{"removed":"All provider reports","score":0.12768701738172494,"rank":176,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.12804694879934572,"rank":176,"remainingConfigurations":398},{"removed":"briefcase","score":0.1269537687671223,"rank":176,"remainingConfigurations":398},{"removed":"aime","score":0.12670493529372795,"rank":178,"remainingConfigurations":398},{"removed":"apex-agents","score":0.12860800316460627,"rank":176,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12804352070425093,"rank":174,"remainingConfigurations":398},{"removed":"automationbench","score":0.12681755544501455,"rank":176,"remainingConfigurations":398},{"removed":"critpt","score":0.1271965354330208,"rank":177,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.12796814401837237,"rank":176,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.12648500677928956,"rank":176,"remainingConfigurations":398},{"removed":"gdpval","score":0.12659443734601225,"rank":175,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1280320387803491,"rank":174,"remainingConfigurations":398},{"removed":"gpqa","score":0.12558903291158818,"rank":177,"remainingConfigurations":398},{"removed":"harvey","score":0.12664780149305854,"rank":176,"remainingConfigurations":398},{"removed":"hle","score":0.1327853412487918,"rank":176,"remainingConfigurations":398},{"removed":"ifbench","score":0.1273127499889735,"rank":174,"remainingConfigurations":398},{"removed":"itbench","score":0.12764217063645647,"rank":175,"remainingConfigurations":398},{"removed":"livecodebench","score":0.12788405938833036,"rank":174,"remainingConfigurations":398},{"removed":"math500","score":0.12784145858293827,"rank":176,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.13092582121359567,"rank":174,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1340796081045769,"rank":175,"remainingConfigurations":398},{"removed":"omniscience","score":0.12604184936283383,"rank":172,"remainingConfigurations":398},{"removed":"scicode","score":0.12837706146858627,"rank":176,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12768156235959383,"rank":175,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.12780391779404382,"rank":174,"remainingConfigurations":398},{"removed":"arc-agi","score":0.14296172867995546,"rank":176,"remainingConfigurations":398},{"removed":"deepswe","score":0.11536929034223282,"rank":173,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.1276812814030627,"rank":176,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.12701153415906052,"rank":176,"remainingConfigurations":398},{"removed":"frontiercode","score":0.12459611766084851,"rank":181,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1279764402861136,"rank":176,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12627235716994345,"rank":176,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.12760706592583201,"rank":176,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12721760842987573,"rank":176,"remainingConfigurations":398},{"removed":"livebench-math","score":0.12788270699010132,"rank":176,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12671355121326255,"rank":176,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1288262513283971,"rank":176,"remainingConfigurations":398},{"removed":"livebench-data","score":0.12783802158045982,"rank":176,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.12596260611964205,"rank":176,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.12691204959595195,"rank":176,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1294795160076804,"rank":176,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.14308554535696996,"rank":169,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.13986609182754314,"rank":166,"remainingConfigurations":398},{"removed":"frontiermath","score":0.12731952990920042,"rank":176,"remainingConfigurations":398},{"removed":"simpleqa","score":0.13160636234896853,"rank":176,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.12720162305198854,"rank":176,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12724772146543692,"rank":176,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12721522820743453,"rank":176,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.127454697009838,"rank":176,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1269395384775626,"rank":176,"remainingConfigurations":398}]},"qwen3.6-35b-a3b--effort-reasoning":{"score":0.12395568088189,"rank":177,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1445608601721744,"rank":174,"remainingConfigurations":398},{"removed":"Datacurve","score":0.10676151056031581,"rank":177,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12303808915297522,"rank":177,"remainingConfigurations":398},{"removed":"Scale","score":0.1352738610288806,"rank":177,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12395798889956293,"rank":177,"remainingConfigurations":398},{"removed":"Cognition","score":0.12843412115250072,"rank":179,"remainingConfigurations":398},{"removed":"LiveBench","score":0.12626630160235333,"rank":175,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.12670126376191615,"rank":177,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.12556606555614777,"rank":171,"remainingConfigurations":381},{"removed":"Vals AI","score":0.12049979104784515,"rank":177,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.12396097801464183,"rank":177,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.12384381266233646,"rank":177,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.12374752434994622,"rank":177,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12395568088189,"rank":177,"remainingConfigurations":398},{"removed":"All provider reports","score":0.12362341453665687,"rank":177,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.12417882760628672,"rank":177,"remainingConfigurations":398},{"removed":"briefcase","score":0.12253702817583505,"rank":179,"remainingConfigurations":398},{"removed":"aime","score":0.12437065638738452,"rank":179,"remainingConfigurations":398},{"removed":"apex-agents","score":0.12510402300147147,"rank":177,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.11982130716561118,"rank":179,"remainingConfigurations":398},{"removed":"automationbench","score":0.12452550417843651,"rank":177,"remainingConfigurations":398},{"removed":"critpt","score":0.12808614644601887,"rank":175,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1238146176682337,"rank":177,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.12308763062288336,"rank":178,"remainingConfigurations":398},{"removed":"gdpval","score":0.12274368212533866,"rank":179,"remainingConfigurations":398},{"removed":"gmmlu","score":0.12463166296632831,"rank":176,"remainingConfigurations":398},{"removed":"gpqa","score":0.11933927956520439,"rank":180,"remainingConfigurations":398},{"removed":"harvey","score":0.12235018589467354,"rank":177,"remainingConfigurations":398},{"removed":"hle","score":0.12667404304783322,"rank":178,"remainingConfigurations":398},{"removed":"ifbench","score":0.11976197321220057,"rank":180,"remainingConfigurations":398},{"removed":"itbench","score":0.12366225640553159,"rank":176,"remainingConfigurations":398},{"removed":"livecodebench","score":0.12382250354405899,"rank":176,"remainingConfigurations":398},{"removed":"math500","score":0.12427727547409377,"rank":177,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1270012104590776,"rank":176,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1258200715648839,"rank":179,"remainingConfigurations":398},{"removed":"omniscience","score":0.13111435031820148,"rank":171,"remainingConfigurations":398},{"removed":"scicode","score":0.13350426052380848,"rank":173,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1198215358389123,"rank":180,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.12583526604127443,"rank":175,"remainingConfigurations":398},{"removed":"arc-agi","score":0.14386484474108727,"rank":175,"remainingConfigurations":398},{"removed":"deepswe","score":0.10683722992479246,"rank":177,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.12398871946755423,"rank":177,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.12317025707083488,"rank":177,"remainingConfigurations":398},{"removed":"frontiercode","score":0.12843412115250072,"rank":179,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1240494660772614,"rank":177,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12291695108483504,"rank":177,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.12378015327561931,"rank":177,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12349436979907985,"rank":177,"remainingConfigurations":398},{"removed":"livebench-math","score":0.12413917419299643,"rank":177,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12312551130552984,"rank":177,"remainingConfigurations":398},{"removed":"livebench-language","score":0.12522705380672153,"rank":177,"remainingConfigurations":398},{"removed":"livebench-data","score":0.12416759546265939,"rank":177,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.12224956644397501,"rank":177,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.12325058260895988,"rank":177,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.12554950518111355,"rank":177,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.12670126376191615,"rank":177,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.11916042912113532,"rank":178,"remainingConfigurations":398},{"removed":"frontiermath","score":0.12492391804523793,"rank":178,"remainingConfigurations":398},{"removed":"simpleqa","score":0.12816931107852306,"rank":178,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.12342535473949812,"rank":177,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12359113530173821,"rank":177,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12350631848782513,"rank":177,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.12380071429463883,"rank":177,"remainingConfigurations":398},{"removed":"vibe-code","score":0.12322536426010629,"rank":177,"remainingConfigurations":398}]},"gemini-3.6-flash--effort-minimal":{"score":0.12326136435379197,"rank":178,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.1150530134102599,"rank":113,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.3037839934546713,"rank":93,"remainingConfigurations":398},{"removed":"Datacurve","score":0.10657748582264505,"rank":178,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12345283222557497,"rank":176,"remainingConfigurations":398},{"removed":"Scale","score":0.13383681899021138,"rank":178,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12279157705972088,"rank":178,"remainingConfigurations":398},{"removed":"Cognition","score":0.13311053673706022,"rank":178,"remainingConfigurations":398},{"removed":"LiveBench","score":0.12399096905803254,"rank":176,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.12081320822298575,"rank":179,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.062082671658886195,"rank":231,"remainingConfigurations":381},{"removed":"Vals AI","score":0.11929565533352883,"rank":178,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1232621362477523,"rank":178,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.12305816310309825,"rank":178,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.12315023863977616,"rank":178,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12326136435379197,"rank":178,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1229330252229272,"rank":178,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.1234640404262915,"rank":178,"remainingConfigurations":398},{"removed":"briefcase","score":0.12312929775772415,"rank":178,"remainingConfigurations":398},{"removed":"aime","score":0.13161268541564958,"rank":175,"remainingConfigurations":398},{"removed":"apex-agents","score":0.12392473577886219,"rank":178,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12319621503520554,"rank":177,"remainingConfigurations":398},{"removed":"automationbench","score":0.12310404039489993,"rank":178,"remainingConfigurations":398},{"removed":"critpt","score":0.12332766517390674,"rank":179,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.12329154324764857,"rank":178,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.12373006417245157,"rank":177,"remainingConfigurations":398},{"removed":"gdpval","score":0.12328142548395275,"rank":177,"remainingConfigurations":398},{"removed":"gmmlu","score":0.12341564925642907,"rank":177,"remainingConfigurations":398},{"removed":"gpqa","score":0.12585729021952283,"rank":176,"remainingConfigurations":398},{"removed":"harvey","score":0.12200855179604769,"rank":178,"remainingConfigurations":398},{"removed":"hle","score":0.12786143814744574,"rank":177,"remainingConfigurations":398},{"removed":"ifbench","score":0.12226727316211539,"rank":177,"remainingConfigurations":398},{"removed":"itbench","score":0.12309452421974805,"rank":177,"remainingConfigurations":398},{"removed":"livecodebench","score":0.12347992488320214,"rank":177,"remainingConfigurations":398},{"removed":"math500","score":0.12338677080269445,"rank":178,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.12649887785268282,"rank":177,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1302000677203076,"rank":177,"remainingConfigurations":398},{"removed":"omniscience","score":0.12162213803105791,"rank":175,"remainingConfigurations":398},{"removed":"scicode","score":0.12414495590792886,"rank":178,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12223503114585665,"rank":178,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1226788142218458,"rank":179,"remainingConfigurations":398},{"removed":"arc-agi","score":0.3038891985767281,"rank":91,"remainingConfigurations":398},{"removed":"deepswe","score":0.10664137633936961,"rank":178,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.12328703972447912,"rank":178,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.12086907542287696,"rank":178,"remainingConfigurations":398},{"removed":"frontiercode","score":0.13311053673706022,"rank":178,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.12348113329175674,"rank":178,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12219877856135263,"rank":178,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.12308823323684744,"rank":178,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12280674368502886,"rank":178,"remainingConfigurations":398},{"removed":"livebench-math","score":0.12345429141525371,"rank":178,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12226426952050133,"rank":178,"remainingConfigurations":398},{"removed":"livebench-language","score":0.12445753080994824,"rank":178,"remainingConfigurations":398},{"removed":"livebench-data","score":0.12341941276086173,"rank":178,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1216146715156536,"rank":178,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.12257292754062794,"rank":178,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.12505878695540124,"rank":178,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.12081320822298575,"rank":179,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0978780754812601,"rank":190,"remainingConfigurations":398},{"removed":"frontiermath","score":0.12671212425366626,"rank":177,"remainingConfigurations":398},{"removed":"simpleqa","score":0.12859048745804844,"rank":177,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1227604735654571,"rank":178,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12287691342644556,"rank":178,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12286893372289576,"rank":178,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.12302892449088033,"rank":178,"remainingConfigurations":398},{"removed":"vibe-code","score":0.12253188336241826,"rank":178,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-low":{"score":0.12123320299992195,"rank":179,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10212567213258417,"rank":119,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.13495049318049054,"rank":180,"remainingConfigurations":398},{"removed":"Datacurve","score":0.10563591729123734,"rank":179,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.12113792869054525,"rank":178,"remainingConfigurations":398},{"removed":"Scale","score":0.13161208056060264,"rank":179,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.12098141701809927,"rank":179,"remainingConfigurations":398},{"removed":"Cognition","score":0.14516009382215342,"rank":170,"remainingConfigurations":398},{"removed":"LiveBench","score":0.12362016619520777,"rank":177,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.12064755718539288,"rank":180,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11436726908610283,"rank":175,"remainingConfigurations":381},{"removed":"Vals AI","score":0.11699234553595222,"rank":179,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.12125525669888271,"rank":179,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.12121553878632875,"rank":179,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.1211650452057962,"rank":179,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.12123320299992195,"rank":179,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1211521959389041,"rank":179,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.12154321300723026,"rank":179,"remainingConfigurations":398},{"removed":"briefcase","score":0.12114892508884723,"rank":180,"remainingConfigurations":398},{"removed":"aime","score":0.12774682549139485,"rank":177,"remainingConfigurations":398},{"removed":"apex-agents","score":0.12207966961313821,"rank":179,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.12167849207343696,"rank":178,"remainingConfigurations":398},{"removed":"automationbench","score":0.12085147848066032,"rank":179,"remainingConfigurations":398},{"removed":"critpt","score":0.12070414039211678,"rank":180,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1214220732942431,"rank":179,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1193436809346919,"rank":180,"remainingConfigurations":398},{"removed":"gdpval","score":0.12067641923639949,"rank":180,"remainingConfigurations":398},{"removed":"gmmlu","score":0.12164876955750183,"rank":178,"remainingConfigurations":398},{"removed":"gpqa","score":0.120546612000539,"rank":179,"remainingConfigurations":398},{"removed":"harvey","score":0.1202139138159465,"rank":180,"remainingConfigurations":398},{"removed":"hle","score":0.12617603942361585,"rank":179,"remainingConfigurations":398},{"removed":"ifbench","score":0.12079641966623585,"rank":179,"remainingConfigurations":398},{"removed":"itbench","score":0.12113911200664167,"rank":179,"remainingConfigurations":398},{"removed":"livecodebench","score":0.12158044024503456,"rank":178,"remainingConfigurations":398},{"removed":"math500","score":0.12144439918200949,"rank":179,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.12454614101649897,"rank":179,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.12746019047663718,"rank":178,"remainingConfigurations":398},{"removed":"omniscience","score":0.1189452573173513,"rank":181,"remainingConfigurations":398},{"removed":"scicode","score":0.12142826214770314,"rank":179,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12116259639281103,"rank":179,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1227652539174827,"rank":178,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1410921346771912,"rank":177,"remainingConfigurations":398},{"removed":"deepswe","score":0.10566262025057176,"rank":179,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.12126123510197513,"rank":179,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11710525863277747,"rank":181,"remainingConfigurations":398},{"removed":"frontiercode","score":0.14516009382215342,"rank":170,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.12144216773395855,"rank":179,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.12005067925441505,"rank":179,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.12112944374472011,"rank":179,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.12081488675045704,"rank":179,"remainingConfigurations":398},{"removed":"livebench-math","score":0.12147080669373789,"rank":179,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.12031979797826432,"rank":179,"remainingConfigurations":398},{"removed":"livebench-language","score":0.12239679060320591,"rank":179,"remainingConfigurations":398},{"removed":"livebench-data","score":0.12138610683267963,"rank":179,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.11959112708197284,"rank":179,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.1205425318426237,"rank":179,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.12294859905927447,"rank":179,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.12064755718539288,"rank":180,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1134401695019917,"rank":179,"remainingConfigurations":398},{"removed":"frontiermath","score":0.11759126961811316,"rank":181,"remainingConfigurations":398},{"removed":"simpleqa","score":0.12502477781473462,"rank":179,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.12071015995534295,"rank":179,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.12086204393767773,"rank":179,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.12080079031463979,"rank":179,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.12100895250779863,"rank":179,"remainingConfigurations":398},{"removed":"vibe-code","score":0.12052863696480993,"rank":179,"remainingConfigurations":398}]},"qwen3.5-122b-a10b--effort-non-reasoning":{"score":0.11888462506694335,"rank":180,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.11394344710801131,"rank":115,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.13932467493367454,"rank":175,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1024993435115207,"rank":181,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.11813849289580695,"rank":180,"remainingConfigurations":398},{"removed":"Scale","score":0.12959426610020355,"rank":180,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11876869002501957,"rank":180,"remainingConfigurations":398},{"removed":"Cognition","score":0.12376288778805948,"rank":182,"remainingConfigurations":398},{"removed":"LiveBench","score":0.12108211834694795,"rank":179,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.12202113809516639,"rank":178,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1116162943874489,"rank":176,"remainingConfigurations":381},{"removed":"Vals AI","score":0.11559346047959962,"rank":180,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11889911393211854,"rank":180,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.11878261579576958,"rank":180,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11872213242163283,"rank":180,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11888462506694335,"rank":180,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11861829287672589,"rank":180,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11908341439097081,"rank":181,"remainingConfigurations":398},{"removed":"briefcase","score":0.11845768528130818,"rank":181,"remainingConfigurations":398},{"removed":"aime","score":0.12024022350406217,"rank":180,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11983063164814702,"rank":180,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1195761149004269,"rank":180,"remainingConfigurations":398},{"removed":"automationbench","score":0.11856514620380415,"rank":180,"remainingConfigurations":398},{"removed":"critpt","score":0.11735180371463207,"rank":181,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1188012439152301,"rank":181,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11960444832849426,"rank":179,"remainingConfigurations":398},{"removed":"gdpval","score":0.11922998580893313,"rank":181,"remainingConfigurations":398},{"removed":"gmmlu","score":0.11787429860133146,"rank":181,"remainingConfigurations":398},{"removed":"gpqa","score":0.11439599201814825,"rank":181,"remainingConfigurations":398},{"removed":"harvey","score":0.1175676543444233,"rank":181,"remainingConfigurations":398},{"removed":"hle","score":0.12274135467241061,"rank":180,"remainingConfigurations":398},{"removed":"ifbench","score":0.12090307354162631,"rank":178,"remainingConfigurations":398},{"removed":"itbench","score":0.11866472536217847,"rank":180,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1186127838306914,"rank":179,"remainingConfigurations":398},{"removed":"math500","score":0.11917526294781501,"rank":180,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.12173330991201604,"rank":180,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.12478337749231246,"rank":180,"remainingConfigurations":398},{"removed":"omniscience","score":0.1214617813491173,"rank":177,"remainingConfigurations":398},{"removed":"scicode","score":0.12027622034723967,"rank":180,"remainingConfigurations":398},{"removed":"tau-bench","score":0.11639010415619787,"rank":182,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11731257950170738,"rank":181,"remainingConfigurations":398},{"removed":"arc-agi","score":0.13812425886871127,"rank":178,"remainingConfigurations":398},{"removed":"deepswe","score":0.1025661237667428,"rank":181,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11891184300252051,"rank":180,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11837228118647745,"rank":180,"remainingConfigurations":398},{"removed":"frontiercode","score":0.12376288778805948,"rank":182,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11914838565347279,"rank":180,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.11762913708443871,"rank":180,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.11875302626529016,"rank":180,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11852599555321126,"rank":180,"remainingConfigurations":398},{"removed":"livebench-math","score":0.11908255438627628,"rank":180,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.11800535917804544,"rank":180,"remainingConfigurations":398},{"removed":"livebench-language","score":0.1200686615261526,"rank":180,"remainingConfigurations":398},{"removed":"livebench-data","score":0.11912992569708176,"rank":180,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.11727731065265005,"rank":180,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11819987874130733,"rank":180,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.12044851316559242,"rank":180,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.12202113809516639,"rank":178,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10612198031922875,"rank":184,"remainingConfigurations":398},{"removed":"frontiermath","score":0.12184779715605763,"rank":179,"remainingConfigurations":398},{"removed":"simpleqa","score":0.12257789194466917,"rank":180,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.1183688341436233,"rank":180,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11854411578558703,"rank":180,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11842890978005387,"rank":180,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.11871570497753614,"rank":180,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11820557434495686,"rank":180,"remainingConfigurations":398}]},"gemini-3.1-flash-lite--effort-reasoning":{"score":0.11723964313197026,"rank":181,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1366227548779351,"rank":177,"remainingConfigurations":398},{"removed":"Datacurve","score":0.1007597726836643,"rank":182,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.11644028848501688,"rank":182,"remainingConfigurations":398},{"removed":"Scale","score":0.1280295782841139,"rank":181,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11721837887749424,"rank":181,"remainingConfigurations":398},{"removed":"Cognition","score":0.12147066529686977,"rank":183,"remainingConfigurations":398},{"removed":"LiveBench","score":0.11925889653135602,"rank":180,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.12010048996006824,"rank":181,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11923979933934248,"rank":172,"remainingConfigurations":381},{"removed":"Vals AI","score":0.11384572043767498,"rank":181,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11724632303139589,"rank":181,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.1171291984125674,"rank":181,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11703913662503192,"rank":181,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11723964313197026,"rank":181,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11691841610066962,"rank":181,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11947013928125098,"rank":180,"remainingConfigurations":398},{"removed":"briefcase","score":0.12340508226201613,"rank":177,"remainingConfigurations":398},{"removed":"aime","score":0.11721954558710264,"rank":181,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11955163500522747,"rank":181,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.11349379798454806,"rank":183,"remainingConfigurations":398},{"removed":"automationbench","score":0.11604839781932795,"rank":182,"remainingConfigurations":398},{"removed":"critpt","score":0.11575203311805161,"rank":183,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.12057873222794054,"rank":180,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11654028647634236,"rank":182,"remainingConfigurations":398},{"removed":"gdpval","score":0.1228747372944869,"rank":178,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1174642505306727,"rank":182,"remainingConfigurations":398},{"removed":"gpqa","score":0.11396397669894252,"rank":182,"remainingConfigurations":398},{"removed":"harvey","score":0.12066764096733923,"rank":179,"remainingConfigurations":398},{"removed":"hle","score":0.12130927867979495,"rank":181,"remainingConfigurations":398},{"removed":"ifbench","score":0.10650823978068036,"rank":190,"remainingConfigurations":398},{"removed":"itbench","score":0.11692347408121728,"rank":181,"remainingConfigurations":398},{"removed":"livecodebench","score":0.11693473598551353,"rank":182,"remainingConfigurations":398},{"removed":"math500","score":0.11753105493143001,"rank":181,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11998853370650255,"rank":181,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11843030764467488,"rank":182,"remainingConfigurations":398},{"removed":"omniscience","score":0.11094737203552803,"rank":185,"remainingConfigurations":398},{"removed":"scicode","score":0.11790921808328735,"rank":181,"remainingConfigurations":398},{"removed":"tau-bench","score":0.12257511808734839,"rank":177,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11785802409006145,"rank":180,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1358707669609607,"rank":180,"remainingConfigurations":398},{"removed":"deepswe","score":0.10083697408215787,"rank":182,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11726969269088588,"rank":181,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11650291950314075,"rank":182,"remainingConfigurations":398},{"removed":"frontiercode","score":0.12147066529686977,"rank":183,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11732623022887885,"rank":181,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.11624873976907966,"rank":181,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.11707123914535833,"rank":181,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11680334719573156,"rank":181,"remainingConfigurations":398},{"removed":"livebench-math","score":0.11740999782952866,"rank":181,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.11646526742519046,"rank":181,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11846859443287783,"rank":181,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1174247151437614,"rank":181,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1156040211918105,"rank":181,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11657193154124229,"rank":181,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11875228492091171,"rank":181,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.12010048996006824,"rank":181,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.11284234255722929,"rank":180,"remainingConfigurations":398},{"removed":"frontiermath","score":0.11810384848162082,"rank":180,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1212646765707426,"rank":181,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.11673717502656193,"rank":181,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11688559662274646,"rank":181,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11680572500917573,"rank":181,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.11709021088983655,"rank":181,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11654481576511351,"rank":181,"remainingConfigurations":398}]},"claude-opus-4-6--effort-low":{"score":0.11634139662190564,"rank":182,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.11459981302067478,"rank":114,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04759563867633613,"rank":286,"remainingConfigurations":398},{"removed":"Datacurve","score":0.10419163889125484,"rank":180,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.11709019169221814,"rank":181,"remainingConfigurations":398},{"removed":"Scale","score":0.12703209087230183,"rank":182,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11543387204619004,"rank":182,"remainingConfigurations":398},{"removed":"Cognition","score":0.14697881465352788,"rank":168,"remainingConfigurations":398},{"removed":"LiveBench","score":0.11783945691134763,"rank":181,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.11491749230405757,"rank":182,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.23816848354188283,"rank":106,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1120061886584539,"rank":182,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11634936609783748,"rank":182,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.11614183368805153,"rank":182,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11624365920702794,"rank":182,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11634139662190564,"rank":182,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11603861352135303,"rank":182,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11644572105094003,"rank":182,"remainingConfigurations":398},{"removed":"briefcase","score":0.11611334041966687,"rank":182,"remainingConfigurations":398},{"removed":"aime","score":0.10670972773151262,"rank":187,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11688316458163354,"rank":182,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.11626151817659343,"rank":182,"remainingConfigurations":398},{"removed":"automationbench","score":0.11620819888618616,"rank":181,"remainingConfigurations":398},{"removed":"critpt","score":0.11675240290528026,"rank":182,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.11630821103027456,"rank":182,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11675026833795032,"rank":181,"remainingConfigurations":398},{"removed":"gdpval","score":0.11642396112052548,"rank":182,"remainingConfigurations":398},{"removed":"gmmlu","score":0.1163556765930724,"rank":183,"remainingConfigurations":398},{"removed":"gpqa","score":0.10750073545975238,"rank":186,"remainingConfigurations":398},{"removed":"harvey","score":0.11521874585275484,"rank":182,"remainingConfigurations":398},{"removed":"hle","score":0.12127760517193852,"rank":182,"remainingConfigurations":398},{"removed":"ifbench","score":0.11533210695514494,"rank":181,"remainingConfigurations":398},{"removed":"itbench","score":0.11613268012077994,"rank":182,"remainingConfigurations":398},{"removed":"livecodebench","score":0.1169939086037678,"rank":181,"remainingConfigurations":398},{"removed":"math500","score":0.1163982441941795,"rank":182,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11911145991919343,"rank":182,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.12299361491323674,"rank":181,"remainingConfigurations":398},{"removed":"omniscience","score":0.11497132405912121,"rank":183,"remainingConfigurations":398},{"removed":"scicode","score":0.11696409143983755,"rank":182,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1160739118494815,"rank":183,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11574887706776084,"rank":182,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04750978608116637,"rank":286,"remainingConfigurations":398},{"removed":"deepswe","score":0.10426675580524507,"rank":180,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11636581821483799,"rank":182,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11932980669614818,"rank":179,"remainingConfigurations":398},{"removed":"frontiercode","score":0.14697881465352788,"rank":168,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11676999962836139,"rank":182,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1151593477034667,"rank":182,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.11623870064328183,"rank":182,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11577965572248677,"rank":182,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1164673670382315,"rank":182,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.11505319528253116,"rank":182,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11759904624005495,"rank":182,"remainingConfigurations":398},{"removed":"livebench-data","score":0.11661423918359604,"rank":182,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.11485913730645099,"rank":182,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11553090921580482,"rank":182,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11828456366357958,"rank":182,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.11491749230405757,"rank":182,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.2240730437208384,"rank":111,"remainingConfigurations":398},{"removed":"frontiermath","score":0.11707864822527947,"rank":183,"remainingConfigurations":398},{"removed":"simpleqa","score":0.11936674568664447,"rank":182,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.11593746868036536,"rank":182,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11592823812932133,"rank":182,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11592970885449298,"rank":182,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.11604636466487285,"rank":182,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11566485540459111,"rank":182,"remainingConfigurations":398}]},"gpt-5.4-mini--effort-medium":{"score":0.11156437708414735,"rank":183,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08935335534225664,"rank":121,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.13629917751751075,"rank":179,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09389790408818129,"rank":185,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.11150197415379748,"rank":183,"remainingConfigurations":398},{"removed":"Scale","score":0.12236489183819536,"rank":183,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11131626711019832,"rank":184,"remainingConfigurations":398},{"removed":"Cognition","score":0.1262904040548035,"rank":180,"remainingConfigurations":398},{"removed":"LiveBench","score":0.11369602900643001,"rank":182,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.11153531478205851,"rank":186,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10958088813975449,"rank":180,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10765336070562458,"rank":185,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11157497228305176,"rank":183,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.11154586447534305,"rank":183,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11144442202983508,"rank":183,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11156437708414735,"rank":183,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11141969547490356,"rank":183,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11179700170594199,"rank":183,"remainingConfigurations":398},{"removed":"briefcase","score":0.11134722803741227,"rank":183,"remainingConfigurations":398},{"removed":"aime","score":0.11192189676243326,"rank":184,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11231883427010192,"rank":184,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.11141003546536771,"rank":184,"remainingConfigurations":398},{"removed":"automationbench","score":0.11131800900162096,"rank":183,"remainingConfigurations":398},{"removed":"critpt","score":0.10946849892806598,"rank":186,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.11162682361609061,"rank":183,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11190061206893515,"rank":184,"remainingConfigurations":398},{"removed":"gdpval","score":0.11190630188799494,"rank":183,"remainingConfigurations":398},{"removed":"gmmlu","score":0.11199431748487106,"rank":185,"remainingConfigurations":398},{"removed":"gpqa","score":0.11087438635724071,"rank":184,"remainingConfigurations":398},{"removed":"harvey","score":0.1104978266109302,"rank":183,"remainingConfigurations":398},{"removed":"hle","score":0.11670227551079103,"rank":184,"remainingConfigurations":398},{"removed":"ifbench","score":0.10978867377029417,"rank":186,"remainingConfigurations":398},{"removed":"itbench","score":0.11141274669510089,"rank":183,"remainingConfigurations":398},{"removed":"livecodebench","score":0.11194642465458875,"rank":183,"remainingConfigurations":398},{"removed":"math500","score":0.1118160613258759,"rank":183,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11466987063798902,"rank":184,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11760396787936749,"rank":184,"remainingConfigurations":398},{"removed":"omniscience","score":0.10580785327834724,"rank":191,"remainingConfigurations":398},{"removed":"scicode","score":0.11262633055471737,"rank":184,"remainingConfigurations":398},{"removed":"tau-bench","score":0.11712868887526025,"rank":181,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11077933050489297,"rank":185,"remainingConfigurations":398},{"removed":"arc-agi","score":0.13718789088108038,"rank":179,"remainingConfigurations":398},{"removed":"deepswe","score":0.09391922083405328,"rank":185,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11158858841303886,"rank":183,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11014486358778691,"rank":184,"remainingConfigurations":398},{"removed":"frontiercode","score":0.1262904040548035,"rank":180,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11177421879704073,"rank":183,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.11065626093684584,"rank":183,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.1114245182124517,"rank":183,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11121368332572368,"rank":183,"remainingConfigurations":398},{"removed":"livebench-math","score":0.11174051355835635,"rank":183,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.11072771039371392,"rank":183,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11267842741224121,"rank":183,"remainingConfigurations":398},{"removed":"livebench-data","score":0.11170050643352582,"rank":183,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1100228612805662,"rank":183,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11091354129603093,"rank":183,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11319072535000833,"rank":183,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.11153531478205851,"rank":186,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10572840897879626,"rank":185,"remainingConfigurations":398},{"removed":"frontiermath","score":0.1127114830995697,"rank":184,"remainingConfigurations":398},{"removed":"simpleqa","score":0.11533100787796968,"rank":183,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.11109537518312484,"rank":183,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11114779284248388,"rank":183,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11120816334842037,"rank":183,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.11130291733294694,"rank":183,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11084672706616407,"rank":183,"remainingConfigurations":398}]},"glm-5.1--effort-non-reasoning":{"score":0.11142890334002291,"rank":184,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08721406208741726,"rank":123,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1323120254274783,"rank":181,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09558649814873188,"rank":184,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.11069020712212933,"rank":184,"remainingConfigurations":398},{"removed":"Scale","score":0.12167944244636135,"rank":184,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11142710405153139,"rank":183,"remainingConfigurations":398},{"removed":"Cognition","score":0.11634002004181145,"rank":184,"remainingConfigurations":398},{"removed":"LiveBench","score":0.11344106940234612,"rank":183,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.11402277344284782,"rank":184,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11800094087108526,"rank":173,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10810488020940288,"rank":183,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11143365270102434,"rank":184,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.11132349585707142,"rank":184,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11128167378293331,"rank":184,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11142890334002291,"rank":184,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11116562317696288,"rank":184,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11170630731751618,"rank":184,"remainingConfigurations":398},{"removed":"briefcase","score":0.11116934164483505,"rank":184,"remainingConfigurations":398},{"removed":"aime","score":0.11155668286054617,"rank":185,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1124133622664009,"rank":183,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.11661686409462292,"rank":181,"remainingConfigurations":398},{"removed":"automationbench","score":0.1112605843013897,"rank":184,"remainingConfigurations":398},{"removed":"critpt","score":0.13131642053427023,"rank":172,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.11150235268006085,"rank":184,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11238497735203606,"rank":183,"remainingConfigurations":398},{"removed":"gdpval","score":0.11139582307549568,"rank":184,"remainingConfigurations":398},{"removed":"gmmlu","score":0.11224257547023386,"rank":184,"remainingConfigurations":398},{"removed":"gpqa","score":0.1058919997553006,"rank":188,"remainingConfigurations":398},{"removed":"harvey","score":0.11022346202090634,"rank":184,"remainingConfigurations":398},{"removed":"hle","score":0.10885539732404208,"rank":191,"remainingConfigurations":398},{"removed":"ifbench","score":0.11408657237870169,"rank":182,"remainingConfigurations":398},{"removed":"itbench","score":0.11126838800822748,"rank":184,"remainingConfigurations":398},{"removed":"livecodebench","score":0.11123572963809726,"rank":184,"remainingConfigurations":398},{"removed":"math500","score":0.11158888078597441,"rank":184,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11408225047958438,"rank":185,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11809477290095753,"rank":183,"remainingConfigurations":398},{"removed":"omniscience","score":0.10683564993500909,"rank":187,"remainingConfigurations":398},{"removed":"scicode","score":0.11294370704391825,"rank":183,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10051150419252931,"rank":191,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1065248077279783,"rank":188,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1317576858164102,"rank":182,"remainingConfigurations":398},{"removed":"deepswe","score":0.09565708765727847,"rank":184,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11145541081343335,"rank":184,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.11071002798391509,"rank":183,"remainingConfigurations":398},{"removed":"frontiercode","score":0.11634002004181145,"rank":184,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11156091468219065,"rank":184,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.11041993732798093,"rank":184,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.11127422882469895,"rank":184,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11105695473353226,"rank":184,"remainingConfigurations":398},{"removed":"livebench-math","score":0.11162291473793913,"rank":184,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1105794528450443,"rank":184,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11257227507161782,"rank":184,"remainingConfigurations":398},{"removed":"livebench-data","score":0.11166401352563916,"rank":184,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10989270299625797,"rank":184,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11078172155905723,"rank":184,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11290856242221824,"rank":184,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.11402277344284782,"rank":184,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09782042705648016,"rank":191,"remainingConfigurations":398},{"removed":"frontiermath","score":0.11757741361715357,"rank":182,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1143570939040162,"rank":185,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.11093422958177618,"rank":184,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11110684774588404,"rank":184,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11099137377889236,"rank":184,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1112763971052085,"rank":184,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11078261597615034,"rank":184,"remainingConfigurations":398}]},"minimax-m2--effort-reasoning":{"score":0.11073308478718895,"rank":185,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.13062006294568107,"rank":183,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09562929830370036,"rank":183,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.10965980775391233,"rank":185,"remainingConfigurations":398},{"removed":"Scale","score":0.12136802508092041,"rank":185,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.11080465220467776,"rank":185,"remainingConfigurations":398},{"removed":"Cognition","score":0.11575635381784938,"rank":185,"remainingConfigurations":398},{"removed":"LiveBench","score":0.11284473460190303,"rank":184,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.11315817393745013,"rank":185,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11113715542645274,"rank":178,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10779198039806663,"rank":184,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.11073902540529447,"rank":185,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.11063499303239695,"rank":185,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.11055629804473434,"rank":185,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.11073308478718895,"rank":185,"remainingConfigurations":398},{"removed":"All provider reports","score":0.11044819736345794,"rank":185,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.11095988140276015,"rank":185,"remainingConfigurations":398},{"removed":"briefcase","score":0.11046207719551372,"rank":186,"remainingConfigurations":398},{"removed":"aime","score":0.11476206595869733,"rank":183,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11171925656802219,"rank":185,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10986795833528024,"rank":185,"remainingConfigurations":398},{"removed":"automationbench","score":0.11056765976299043,"rank":185,"remainingConfigurations":398},{"removed":"critpt","score":0.1086239782121124,"rank":187,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.11069858690264005,"rank":185,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.11185834276628105,"rank":185,"remainingConfigurations":398},{"removed":"gdpval","score":0.111269500747258,"rank":185,"remainingConfigurations":398},{"removed":"gmmlu","score":0.11999305643851516,"rank":180,"remainingConfigurations":398},{"removed":"gpqa","score":0.11121192566779654,"rank":183,"remainingConfigurations":398},{"removed":"harvey","score":0.10945919221631693,"rank":185,"remainingConfigurations":398},{"removed":"hle","score":0.11788180979088858,"rank":183,"remainingConfigurations":398},{"removed":"ifbench","score":0.10190198233895136,"rank":193,"remainingConfigurations":398},{"removed":"itbench","score":0.11049036735659441,"rank":185,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10522338920623925,"rank":188,"remainingConfigurations":398},{"removed":"math500","score":0.11086765997171151,"rank":185,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11557394510338863,"rank":183,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11703959938577402,"rank":185,"remainingConfigurations":398},{"removed":"omniscience","score":0.10634012484314359,"rank":189,"remainingConfigurations":398},{"removed":"scicode","score":0.11243877402329122,"rank":185,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10602349673793114,"rank":186,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11224056541072541,"rank":183,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12974447706928674,"rank":184,"remainingConfigurations":398},{"removed":"deepswe","score":0.09569647304704393,"rank":183,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.11076143202847806,"rank":185,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.10998137250403728,"rank":185,"remainingConfigurations":398},{"removed":"frontiercode","score":0.11575635381784938,"rank":185,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.11080315746029774,"rank":185,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10980391185925091,"rank":185,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.110567775930474,"rank":185,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.11034416710582805,"rank":185,"remainingConfigurations":398},{"removed":"livebench-math","score":0.11090398324094763,"rank":185,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10995808611075934,"rank":185,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11188511652407422,"rank":185,"remainingConfigurations":398},{"removed":"livebench-data","score":0.11091940734966589,"rank":185,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10918023407271922,"rank":185,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.11008737637274017,"rank":185,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11221728470720327,"rank":185,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.11315817393745013,"rank":185,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10564312382258985,"rank":186,"remainingConfigurations":398},{"removed":"frontiermath","score":0.11177889968083828,"rank":185,"remainingConfigurations":398},{"removed":"simpleqa","score":0.11466220855267083,"rank":184,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.11024993939543692,"rank":185,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.11039255018236564,"rank":185,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.11032499198898586,"rank":185,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.11057733758522663,"rank":185,"remainingConfigurations":398},{"removed":"vibe-code","score":0.11006863575953259,"rank":185,"remainingConfigurations":398}]},"gpt-5-mini--effort-high":{"score":0.10910072700545992,"rank":186,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0793903388358968,"rank":129,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.13166932972161952,"rank":182,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09291487839124778,"rank":186,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.10896225355863615,"rank":186,"remainingConfigurations":398},{"removed":"Scale","score":0.11955016110483947,"rank":186,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.10860739127803459,"rank":186,"remainingConfigurations":398},{"removed":"Cognition","score":0.11472363648028688,"rank":186,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10965231339998172,"rank":186,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.11409585638455116,"rank":183,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11145896398860271,"rank":177,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10507839654770747,"rank":186,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10910743977784788,"rank":186,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10897350469596251,"rank":186,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10896394962373879,"rank":186,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10910072700545992,"rank":186,"remainingConfigurations":398},{"removed":"All provider reports","score":0.1088285970948184,"rank":186,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10932065074212738,"rank":186,"remainingConfigurations":398},{"removed":"briefcase","score":0.1106630421645286,"rank":185,"remainingConfigurations":398},{"removed":"aime","score":0.10778344494071125,"rank":186,"remainingConfigurations":398},{"removed":"apex-agents","score":0.11002346893028692,"rank":186,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10735809794555,"rank":187,"remainingConfigurations":398},{"removed":"automationbench","score":0.10910275076199157,"rank":186,"remainingConfigurations":398},{"removed":"critpt","score":0.11299984559981453,"rank":185,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.10930771661228485,"rank":186,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10896675184970185,"rank":186,"remainingConfigurations":398},{"removed":"gdpval","score":0.10946977591042929,"rank":186,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10808571949729612,"rank":187,"remainingConfigurations":398},{"removed":"gpqa","score":0.10743271779192964,"rank":187,"remainingConfigurations":398},{"removed":"harvey","score":0.10820787670967004,"rank":186,"remainingConfigurations":398},{"removed":"hle","score":0.11313883092741091,"rank":186,"remainingConfigurations":398},{"removed":"ifbench","score":0.10482605676764933,"rank":191,"remainingConfigurations":398},{"removed":"itbench","score":0.10922556247030235,"rank":186,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10780237445750596,"rank":186,"remainingConfigurations":398},{"removed":"math500","score":0.10927453469694642,"rank":186,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11198979455203334,"rank":186,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11567225037408206,"rank":187,"remainingConfigurations":398},{"removed":"omniscience","score":0.10630908043952109,"rank":190,"remainingConfigurations":398},{"removed":"scicode","score":0.11184788963613583,"rank":186,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10872528665099573,"rank":185,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.11099551108036006,"rank":184,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1308930887006716,"rank":183,"remainingConfigurations":398},{"removed":"deepswe","score":0.09297086724456764,"rank":186,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10912714481113099,"rank":186,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1075167111657137,"rank":186,"remainingConfigurations":398},{"removed":"frontiercode","score":0.11472363648028688,"rank":186,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10920450158297623,"rank":186,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10814204553600175,"rank":186,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10894472173569707,"rank":186,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.10870263795458997,"rank":186,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10925204663535804,"rank":186,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10833355453649147,"rank":186,"remainingConfigurations":398},{"removed":"livebench-language","score":0.11014021822326973,"rank":186,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10925856716491815,"rank":186,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.1075850506752435,"rank":186,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10842983807005808,"rank":186,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.11072399691360912,"rank":186,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.11409585638455116,"rank":183,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10695872336959766,"rank":183,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10996277202289624,"rank":186,"remainingConfigurations":398},{"removed":"simpleqa","score":0.1127661437556736,"rank":186,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10861838049028473,"rank":186,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10874740690135774,"rank":186,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10874819597489281,"rank":186,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.10890414732644643,"rank":186,"remainingConfigurations":398},{"removed":"vibe-code","score":0.1084063804219159,"rank":186,"remainingConfigurations":398}]},"qwen3.6-27b--effort-non-reasoning":{"score":0.10775481130802657,"rank":187,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10563815526703434,"rank":116,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1268805963378535,"rank":184,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09226639767626633,"rank":187,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1071677483062178,"rank":187,"remainingConfigurations":398},{"removed":"Scale","score":0.1173425821141022,"rank":187,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1078591419293378,"rank":187,"remainingConfigurations":398},{"removed":"Cognition","score":0.11295772691827775,"rank":187,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10983917362856373,"rank":185,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10953099378592178,"rank":187,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.11028821033752458,"rank":179,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10465331460286344,"rank":187,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10775843693626504,"rank":187,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10762141894483913,"rank":187,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10762127137846855,"rank":187,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10775481130802657,"rank":187,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10747720885691259,"rank":187,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10798129891518797,"rank":187,"remainingConfigurations":398},{"removed":"briefcase","score":0.10744473396891786,"rank":187,"remainingConfigurations":398},{"removed":"aime","score":0.11539612828194407,"rank":182,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10862147007140903,"rank":187,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10648161416428943,"rank":188,"remainingConfigurations":398},{"removed":"automationbench","score":0.10754210346648023,"rank":187,"remainingConfigurations":398},{"removed":"critpt","score":0.10612295730512368,"rank":188,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.10778166486807468,"rank":187,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10853787550045625,"rank":187,"remainingConfigurations":398},{"removed":"gdpval","score":0.10536485474487234,"rank":189,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10837521957583272,"rank":186,"remainingConfigurations":398},{"removed":"gpqa","score":0.09409644437296827,"rank":201,"remainingConfigurations":398},{"removed":"harvey","score":0.10655916389130793,"rank":187,"remainingConfigurations":398},{"removed":"hle","score":0.11148630161768769,"rank":188,"remainingConfigurations":398},{"removed":"ifbench","score":0.11094403019598405,"rank":185,"remainingConfigurations":398},{"removed":"itbench","score":0.10754841643788184,"rank":187,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10773177860635332,"rank":187,"remainingConfigurations":398},{"removed":"math500","score":0.10799426465779383,"rank":187,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.11046699617297266,"rank":187,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11198433990263705,"rank":189,"remainingConfigurations":398},{"removed":"omniscience","score":0.11349851861978139,"rank":184,"remainingConfigurations":398},{"removed":"scicode","score":0.10902102499710235,"rank":187,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10374309680649407,"rank":189,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1079257201783002,"rank":186,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12616891166795338,"rank":185,"remainingConfigurations":398},{"removed":"deepswe","score":0.09233714496300095,"rank":187,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10778049121767426,"rank":187,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.10709154430025354,"rank":187,"remainingConfigurations":398},{"removed":"frontiercode","score":0.11295772691827775,"rank":187,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.1078907144937853,"rank":187,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10677323559015615,"rank":187,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10760759641806293,"rank":187,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.10738684672402136,"rank":187,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10796669334137027,"rank":187,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10686831728043782,"rank":187,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10886155816578469,"rank":187,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1080141855896245,"rank":187,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10627546232214186,"rank":187,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10711556571812053,"rank":187,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.10920008727633614,"rank":187,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10953099378592178,"rank":187,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.11069672437102966,"rank":182,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10178689503091327,"rank":192,"remainingConfigurations":398},{"removed":"simpleqa","score":0.11114446094752839,"rank":187,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10728025377789958,"rank":187,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10745458914216278,"rank":187,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.1072980514066777,"rank":187,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.10761944381552986,"rank":187,"remainingConfigurations":398},{"removed":"vibe-code","score":0.10715890613052596,"rank":187,"remainingConfigurations":398}]},"glm-4.6--effort-reasoning":{"score":0.10642502099679403,"rank":188,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1251525708150272,"rank":186,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09160356844692313,"rank":188,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.10544685582900908,"rank":188,"remainingConfigurations":398},{"removed":"Scale","score":0.11653438763772526,"rank":188,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.10642862903126436,"rank":188,"remainingConfigurations":398},{"removed":"Cognition","score":0.11084674852485739,"rank":188,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10847355901405144,"rank":187,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10866829625640205,"rank":188,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10679578747683562,"rank":181,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10350164778105882,"rank":188,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10643030593553238,"rank":188,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10632886839767886,"rank":188,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10625308931762234,"rank":188,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10642502099679403,"rank":188,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10614670596600569,"rank":188,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10669909014604632,"rank":188,"remainingConfigurations":398},{"removed":"briefcase","score":0.10608000223516156,"rank":188,"remainingConfigurations":398},{"removed":"aime","score":0.10462032166149675,"rank":188,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10741728719199978,"rank":188,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10835667889646856,"rank":186,"remainingConfigurations":398},{"removed":"automationbench","score":0.10622327966633806,"rank":188,"remainingConfigurations":398},{"removed":"critpt","score":0.10294868638190831,"rank":190,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1063987377303255,"rank":188,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.1074946450152026,"rank":188,"remainingConfigurations":398},{"removed":"gdpval","score":0.10641529788107278,"rank":187,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10453336461884022,"rank":189,"remainingConfigurations":398},{"removed":"gpqa","score":0.10584805939687092,"rank":189,"remainingConfigurations":398},{"removed":"harvey","score":0.10520797570780155,"rank":188,"remainingConfigurations":398},{"removed":"hle","score":0.1114108315819759,"rank":189,"remainingConfigurations":398},{"removed":"ifbench","score":0.11132142123436857,"rank":184,"remainingConfigurations":398},{"removed":"itbench","score":0.10623251189727541,"rank":188,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10951913672018328,"rank":185,"remainingConfigurations":398},{"removed":"math500","score":0.10666968929726217,"rank":188,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1090619489797739,"rank":188,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11252491815014955,"rank":188,"remainingConfigurations":398},{"removed":"omniscience","score":0.09970491407784725,"rank":194,"remainingConfigurations":398},{"removed":"scicode","score":0.10805955273077524,"rank":188,"remainingConfigurations":398},{"removed":"tau-bench","score":0.1040523003698725,"rank":188,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.10580059546245806,"rank":189,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12445011646564293,"rank":187,"remainingConfigurations":398},{"removed":"deepswe","score":0.09166837567220631,"rank":188,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10645282370662962,"rank":188,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.10570764771465917,"rank":188,"remainingConfigurations":398},{"removed":"frontiercode","score":0.11084674852485739,"rank":188,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10649277421449614,"rank":188,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10551374035049631,"rank":188,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10626853073483938,"rank":188,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.10604387031234717,"rank":188,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10659099194176042,"rank":188,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10567392551473465,"rank":188,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10754389498713579,"rank":188,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10660881956563921,"rank":188,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10491764504225011,"rank":188,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10579832766377001,"rank":188,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1078622107791286,"rank":188,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10866829625640205,"rank":188,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10153920216343727,"rank":187,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10738853954101703,"rank":187,"remainingConfigurations":398},{"removed":"simpleqa","score":0.11022011756862848,"rank":188,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10595550777154716,"rank":188,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10609599275052091,"rank":188,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10602844950511638,"rank":188,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.106275573014471,"rank":188,"remainingConfigurations":398},{"removed":"vibe-code","score":0.10577977683314026,"rank":188,"remainingConfigurations":398}]},"ernie-5.0-thinking-preview--effort-reasoning":{"score":0.10526911111156373,"rank":189,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12451829817190203,"rank":187,"remainingConfigurations":398},{"removed":"Datacurve","score":0.09071725832034484,"rank":189,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.10416837783572035,"rank":189,"remainingConfigurations":398},{"removed":"Scale","score":0.11543611355129603,"rank":189,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.10529496075567812,"rank":189,"remainingConfigurations":398},{"removed":"Cognition","score":0.10999109687198623,"rank":189,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10728935540875872,"rank":188,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10752425337370673,"rank":190,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.1054359660571011,"rank":182,"remainingConfigurations":381},{"removed":"Vals AI","score":0.10241128708856163,"rank":189,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10527492039998525,"rank":189,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10517442651713921,"rank":189,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10509863937210966,"rank":189,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10526911111156373,"rank":189,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10499440840163614,"rank":189,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10547807903279076,"rank":189,"remainingConfigurations":398},{"removed":"briefcase","score":0.10490959400735127,"rank":189,"remainingConfigurations":398},{"removed":"aime","score":0.10316327687222614,"rank":189,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1061664868705503,"rank":189,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10412486581619552,"rank":191,"remainingConfigurations":398},{"removed":"automationbench","score":0.10503246636839376,"rank":189,"remainingConfigurations":398},{"removed":"critpt","score":0.10012318053569304,"rank":191,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.10518231410208585,"rank":189,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10624774437296042,"rank":189,"remainingConfigurations":398},{"removed":"gdpval","score":0.10588236689179065,"rank":188,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10165652003625719,"rank":191,"remainingConfigurations":398},{"removed":"gpqa","score":0.10515336160429489,"rank":192,"remainingConfigurations":398},{"removed":"harvey","score":0.10401768809116242,"rank":189,"remainingConfigurations":398},{"removed":"hle","score":0.11187955046825887,"rank":187,"remainingConfigurations":398},{"removed":"ifbench","score":0.11405636465090467,"rank":183,"remainingConfigurations":398},{"removed":"itbench","score":0.10503709832688501,"rank":189,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10013063906333615,"rank":192,"remainingConfigurations":398},{"removed":"math500","score":0.10553834212076785,"rank":189,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1070040095867444,"rank":189,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11639140421082372,"rank":186,"remainingConfigurations":398},{"removed":"omniscience","score":0.10185047429547393,"rank":192,"remainingConfigurations":398},{"removed":"scicode","score":0.10680382553275176,"rank":189,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10274953583462787,"rank":190,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.10669573946719717,"rank":187,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12370226466361227,"rank":188,"remainingConfigurations":398},{"removed":"deepswe","score":0.09078111237922877,"rank":189,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10529615486141362,"rank":189,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1045533492784083,"rank":189,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10999109687198623,"rank":189,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10533028817827737,"rank":189,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10436653244275527,"rank":189,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10511235575282689,"rank":189,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1048988684119665,"rank":189,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10543307681035181,"rank":189,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.1045238449584569,"rank":189,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10637612483021504,"rank":189,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10544805666758837,"rank":189,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10377745107127011,"rank":189,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10464844936225375,"rank":189,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.10669723978110988,"rank":189,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10752425337370673,"rank":190,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.10037594825300122,"rank":188,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10627416050568883,"rank":188,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10904421576765133,"rank":189,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10480463733147398,"rank":189,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10494128438113932,"rank":189,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10487731947294704,"rank":189,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.10511734699408265,"rank":189,"remainingConfigurations":398},{"removed":"vibe-code","score":0.10463097625278962,"rank":189,"remainingConfigurations":398}]},"mistral-medium-3.5--effort-reasoning":{"score":0.10279468426519034,"rank":190,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12051203783539444,"rank":192,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08810111326223476,"rank":190,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.10190368310786711,"rank":190,"remainingConfigurations":398},{"removed":"Scale","score":0.11260105534510152,"rank":190,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.10276125943817084,"rank":190,"remainingConfigurations":398},{"removed":"Cognition","score":0.10671098551775661,"rank":190,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10500818664317911,"rank":189,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10532476597149608,"rank":191,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10477979348497035,"rank":183,"remainingConfigurations":381},{"removed":"Vals AI","score":0.1001203450640447,"rank":190,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10280078928643059,"rank":190,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10269533916314401,"rank":190,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10261732061419465,"rank":190,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10279468426519034,"rank":190,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10250886613720328,"rank":190,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10064622857947723,"rank":192,"remainingConfigurations":398},{"removed":"briefcase","score":0.10280521348995057,"rank":190,"remainingConfigurations":398},{"removed":"aime","score":0.10278637982135043,"rank":191,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10402075043232391,"rank":190,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10214447599403996,"rank":193,"remainingConfigurations":398},{"removed":"automationbench","score":0.10129066666248406,"rank":190,"remainingConfigurations":398},{"removed":"critpt","score":0.11399424774411297,"rank":184,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09922378164790474,"rank":194,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10613441035569328,"rank":190,"remainingConfigurations":398},{"removed":"gdpval","score":0.10219305795135997,"rank":190,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10318431966609694,"rank":190,"remainingConfigurations":398},{"removed":"gpqa","score":0.103304585476564,"rank":194,"remainingConfigurations":398},{"removed":"harvey","score":0.10160046079518124,"rank":190,"remainingConfigurations":398},{"removed":"hle","score":0.1075347408280926,"rank":192,"remainingConfigurations":398},{"removed":"ifbench","score":0.09604129047708469,"rank":197,"remainingConfigurations":398},{"removed":"itbench","score":0.10264833541251665,"rank":190,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10234223292881538,"rank":189,"remainingConfigurations":398},{"removed":"math500","score":0.10303185400403884,"rank":190,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.10527635831674526,"rank":190,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.11153812939614709,"rank":190,"remainingConfigurations":398},{"removed":"omniscience","score":0.10075879415155219,"rank":193,"remainingConfigurations":398},{"removed":"scicode","score":0.10543233914973771,"rank":190,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09620134548509679,"rank":194,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.10235399431118204,"rank":192,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11981892117181346,"rank":193,"remainingConfigurations":398},{"removed":"deepswe","score":0.08816817521371889,"rank":190,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10282229626256761,"rank":190,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.10213820094297403,"rank":190,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10671098551775661,"rank":190,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10287609707678513,"rank":190,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.1019057035048957,"rank":190,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10264813148021495,"rank":190,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.1024110027698244,"rank":190,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10294983834036925,"rank":190,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10208272673451042,"rank":190,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10390086965569019,"rank":190,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10297185554084094,"rank":190,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.10131789251972152,"rank":190,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10218756815957801,"rank":190,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1041731813768426,"rank":190,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10532476597149608,"rank":191,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09871573946477542,"rank":189,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10358371525519706,"rank":189,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10644132881413755,"rank":190,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10234020309166635,"rank":190,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10247530378950058,"rank":190,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10240379431838081,"rank":190,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.10265681164531587,"rank":190,"remainingConfigurations":398},{"removed":"vibe-code","score":0.10216563378310613,"rank":190,"remainingConfigurations":398}]},"gpt-5.4--effort-non-reasoning":{"score":0.10116567856734593,"rank":191,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11970211284520989,"rank":193,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08702569084185953,"rank":191,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.1002589403536991,"rank":191,"remainingConfigurations":398},{"removed":"Scale","score":0.11071212477026882,"rank":191,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.1011599169978822,"rank":191,"remainingConfigurations":398},{"removed":"Cognition","score":0.10540638917435863,"rank":191,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10321181495309957,"rank":190,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10325086493056874,"rank":192,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10099725638107099,"rank":184,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09840376243502647,"rank":191,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.1011712765806409,"rank":191,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10107443122897315,"rank":191,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10099976121796049,"rank":191,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10116567856734593,"rank":191,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10089915633093705,"rank":191,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10143625880688027,"rank":190,"remainingConfigurations":398},{"removed":"briefcase","score":0.10068044978458636,"rank":191,"remainingConfigurations":398},{"removed":"aime","score":0.10191062495163954,"rank":192,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10207191211334475,"rank":191,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10282294376029744,"rank":192,"remainingConfigurations":398},{"removed":"automationbench","score":0.10094052377402203,"rank":191,"remainingConfigurations":398},{"removed":"critpt","score":0.09936002225301115,"rank":192,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.10117008733001454,"rank":190,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10215780831018717,"rank":191,"remainingConfigurations":398},{"removed":"gdpval","score":0.10099620367067265,"rank":191,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10155107384833757,"rank":192,"remainingConfigurations":398},{"removed":"gpqa","score":0.10508885078183895,"rank":193,"remainingConfigurations":398},{"removed":"harvey","score":0.09994696146759162,"rank":191,"remainingConfigurations":398},{"removed":"hle","score":0.1095488427896162,"rank":190,"remainingConfigurations":398},{"removed":"ifbench","score":0.10424478706771788,"rank":192,"remainingConfigurations":398},{"removed":"itbench","score":0.10096467272579233,"rank":191,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10107998504586228,"rank":190,"remainingConfigurations":398},{"removed":"math500","score":0.10154503969295985,"rank":191,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.10371558760068735,"rank":191,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10311276401076601,"rank":194,"remainingConfigurations":398},{"removed":"omniscience","score":0.08624515040219209,"rank":211,"remainingConfigurations":398},{"removed":"scicode","score":0.10275404121529098,"rank":191,"remainingConfigurations":398},{"removed":"tau-bench","score":0.11119316333538239,"rank":184,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09310620222538345,"rank":199,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11906680178126276,"rank":194,"remainingConfigurations":398},{"removed":"deepswe","score":0.0870871017710181,"rank":191,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10119214570510966,"rank":191,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.10048903782819385,"rank":191,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10540638917435863,"rank":191,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10123297660322943,"rank":191,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.10029524049542125,"rank":191,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10101618210724583,"rank":191,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.10080641720863087,"rank":191,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10132406456521098,"rank":191,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10043981809143894,"rank":191,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10223974869142101,"rank":191,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10134475017297732,"rank":191,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09971981564822806,"rank":191,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10056238272303723,"rank":191,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.10255038659489513,"rank":191,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10325086493056874,"rank":192,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09627572634511623,"rank":192,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10216609576862823,"rank":191,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10481258791935162,"rank":191,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10071598807580086,"rank":191,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10084910159182219,"rank":191,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10078534417773126,"rank":191,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.10101904625899882,"rank":191,"remainingConfigurations":398},{"removed":"vibe-code","score":0.100547879692155,"rank":191,"remainingConfigurations":398}]},"deepseek-v4-pro-0424--effort-non-reasoning":{"score":0.10083732803951044,"rank":192,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1196565337357942,"rank":194,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08669891889791297,"rank":192,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09995921767072204,"rank":192,"remainingConfigurations":398},{"removed":"Scale","score":0.1105760384040204,"rank":192,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.10083392247642464,"rank":192,"remainingConfigurations":398},{"removed":"Cognition","score":0.10509045428616726,"rank":192,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10286976597063403,"rank":191,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10317506886836308,"rank":193,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10093020788646416,"rank":185,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0980871024768352,"rank":192,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.10084284019796597,"rank":192,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.10074572240099493,"rank":192,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.10067358978074298,"rank":192,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.10083732803951044,"rank":192,"remainingConfigurations":398},{"removed":"All provider reports","score":0.10057260422631027,"rank":192,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10108539745544752,"rank":191,"remainingConfigurations":398},{"removed":"briefcase","score":0.10029457929827416,"rank":192,"remainingConfigurations":398},{"removed":"aime","score":0.10159246998525258,"rank":193,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10177738676145198,"rank":192,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10579807663275705,"rank":190,"remainingConfigurations":398},{"removed":"automationbench","score":0.10050718925032265,"rank":192,"remainingConfigurations":398},{"removed":"critpt","score":0.09603686384990838,"rank":197,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.1008148527928941,"rank":191,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10171699524796855,"rank":192,"remainingConfigurations":398},{"removed":"gdpval","score":0.10074214110003549,"rank":192,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10155003394743062,"rank":193,"remainingConfigurations":398},{"removed":"gpqa","score":0.11007475359806,"rank":185,"remainingConfigurations":398},{"removed":"harvey","score":0.0996082221610764,"rank":192,"remainingConfigurations":398},{"removed":"hle","score":0.11655800064128367,"rank":185,"remainingConfigurations":398},{"removed":"ifbench","score":0.10806754482380253,"rank":188,"remainingConfigurations":398},{"removed":"itbench","score":0.10070975274458827,"rank":192,"remainingConfigurations":398},{"removed":"livecodebench","score":0.10069045589442692,"rank":191,"remainingConfigurations":398},{"removed":"math500","score":0.10116349956280224,"rank":192,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.10332954615249314,"rank":192,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10684942353792563,"rank":191,"remainingConfigurations":398},{"removed":"omniscience","score":0.08693249971413547,"rank":208,"remainingConfigurations":398},{"removed":"scicode","score":0.102304474257938,"rank":192,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09126302287632548,"rank":199,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.092353582995097,"rank":201,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11896605622654012,"rank":195,"remainingConfigurations":398},{"removed":"deepswe","score":0.08676051669244463,"rank":192,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10086363642945173,"rank":192,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.1001551476926032,"rank":192,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10509045428616726,"rank":192,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10090790132903615,"rank":192,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09997885219075513,"rank":192,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.10068747605971169,"rank":192,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.10047742861900122,"rank":192,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10099570133448314,"rank":192,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.10011346211192708,"rank":192,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10190888617755207,"rank":192,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1010152815721599,"rank":192,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09939465864095738,"rank":192,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.10023588997874762,"rank":192,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.1022186276385535,"rank":192,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10317506886836308,"rank":193,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09600778772662878,"rank":193,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10169070978736194,"rank":193,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10447757950825665,"rank":192,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.10038819309853216,"rank":192,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.10052123243366878,"rank":192,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.10045772988917334,"rank":192,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.1006912642224259,"rank":192,"remainingConfigurations":398},{"removed":"vibe-code","score":0.10022056321833954,"rank":192,"remainingConfigurations":398}]},"qwen3.5-omni-plus--effort-non-reasoning":{"score":0.09998619014084287,"rank":193,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11855026561844019,"rank":195,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08596442916552356,"rank":193,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.099140205819928,"rank":193,"remainingConfigurations":398},{"removed":"Scale","score":0.10971029473767076,"rank":193,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09997736629879199,"rank":193,"remainingConfigurations":398},{"removed":"Cognition","score":0.10434822953143345,"rank":193,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10202172234595941,"rank":192,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10239695605325368,"rank":194,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.10037931263394351,"rank":186,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09720738060768248,"rank":193,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09999185278844543,"rank":193,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09989692550913859,"rank":193,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09982191980569366,"rank":193,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09998619014084287,"rank":193,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09972349823954281,"rank":193,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10020391211693291,"rank":193,"remainingConfigurations":398},{"removed":"briefcase","score":0.09957390449511377,"rank":193,"remainingConfigurations":398},{"removed":"aime","score":0.10069393136195258,"rank":194,"remainingConfigurations":398},{"removed":"apex-agents","score":0.1008573143059139,"rank":193,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09877827436640224,"rank":195,"remainingConfigurations":398},{"removed":"automationbench","score":0.09969065058523331,"rank":193,"remainingConfigurations":398},{"removed":"critpt","score":0.09915291982134877,"rank":193,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09991220369604133,"rank":192,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10088086970545163,"rank":193,"remainingConfigurations":398},{"removed":"gdpval","score":0.1002842270889203,"rank":194,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10070275229925525,"rank":194,"remainingConfigurations":398},{"removed":"gpqa","score":0.09457839978708438,"rank":200,"remainingConfigurations":398},{"removed":"harvey","score":0.09877526978096697,"rank":193,"remainingConfigurations":398},{"removed":"hle","score":0.10350829725544385,"rank":194,"remainingConfigurations":398},{"removed":"ifbench","score":0.10137357854204398,"rank":194,"remainingConfigurations":398},{"removed":"itbench","score":0.09975182256777719,"rank":193,"remainingConfigurations":398},{"removed":"livecodebench","score":0.100060315145573,"rank":193,"remainingConfigurations":398},{"removed":"math500","score":0.10040444400107168,"rank":193,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.1026476889192997,"rank":193,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10248622951094767,"rank":196,"remainingConfigurations":398},{"removed":"omniscience","score":0.10733538810972337,"rank":186,"remainingConfigurations":398},{"removed":"scicode","score":0.10144398312743504,"rank":193,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0925477328144773,"rank":198,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.10298834755508968,"rank":191,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11786733753041971,"rank":196,"remainingConfigurations":398},{"removed":"deepswe","score":0.08602510239582674,"rank":193,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.10001214008345549,"rank":193,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09931366197982743,"rank":193,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10434822953143345,"rank":193,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.10005446303927625,"rank":193,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09913172632097667,"rank":193,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0998381126412816,"rank":193,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09962953210410767,"rank":193,"remainingConfigurations":398},{"removed":"livebench-math","score":0.10014350153450585,"rank":193,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0992683346872848,"rank":193,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10104979363448484,"rank":193,"remainingConfigurations":398},{"removed":"livebench-data","score":0.10016211221445864,"rank":193,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09855404116080047,"rank":193,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09938886900659409,"rank":193,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.10135789130868121,"rank":193,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10239695605325368,"rank":194,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0954146801213358,"rank":194,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10092715227618436,"rank":194,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10359516754973741,"rank":193,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09954026843144588,"rank":193,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09967209526187432,"rank":193,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09960939230142381,"rank":193,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09984048929915379,"rank":193,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09937432118498839,"rank":193,"remainingConfigurations":398}]},"deepseek-r1-0528--effort-reasoning":{"score":0.09984674330952174,"rank":194,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1183499502388577,"rank":196,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0859326383002153,"rank":194,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09882011125160413,"rank":194,"remainingConfigurations":398},{"removed":"Scale","score":0.10960439528205801,"rank":194,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09986098826613672,"rank":194,"remainingConfigurations":398},{"removed":"Cognition","score":0.10433828851383288,"rank":194,"remainingConfigurations":398},{"removed":"LiveBench","score":0.10183221081352177,"rank":193,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.1021623873512555,"rank":195,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09997769313088106,"rank":187,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09714327729630569,"rank":194,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0998521933519616,"rank":194,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09975706791188067,"rank":194,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0996854744922282,"rank":194,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09984674330952174,"rank":194,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09958653399575845,"rank":194,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.10008121760262567,"rank":194,"remainingConfigurations":398},{"removed":"briefcase","score":0.0995574907776869,"rank":194,"remainingConfigurations":398},{"removed":"aime","score":0.10285217126666918,"rank":190,"remainingConfigurations":398},{"removed":"apex-agents","score":0.10078040010925902,"rank":194,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.1010724306842794,"rank":194,"remainingConfigurations":398},{"removed":"automationbench","score":0.09965772980615036,"rank":194,"remainingConfigurations":398},{"removed":"critpt","score":0.09463183744829105,"rank":201,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09986429622442645,"rank":193,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.10082831486829706,"rank":194,"remainingConfigurations":398},{"removed":"gdpval","score":0.10033747023073936,"rank":193,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09740527405675677,"rank":195,"remainingConfigurations":398},{"removed":"gpqa","score":0.0964870202682539,"rank":196,"remainingConfigurations":398},{"removed":"harvey","score":0.09872135187770908,"rank":194,"remainingConfigurations":398},{"removed":"hle","score":0.10356626134772035,"rank":193,"remainingConfigurations":398},{"removed":"ifbench","score":0.10872129560603193,"rank":187,"remainingConfigurations":398},{"removed":"itbench","score":0.0996708857202741,"rank":194,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09704301093604083,"rank":195,"remainingConfigurations":398},{"removed":"math500","score":0.09825632883757347,"rank":194,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09880496726143286,"rank":195,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.1057227131149409,"rank":192,"remainingConfigurations":398},{"removed":"omniscience","score":0.08950941161892677,"rank":203,"remainingConfigurations":398},{"removed":"scicode","score":0.10137295172433425,"rank":194,"remainingConfigurations":398},{"removed":"tau-bench","score":0.10595689629853382,"rank":187,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.1043168014939802,"rank":190,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1176032664228197,"rank":197,"remainingConfigurations":398},{"removed":"deepswe","score":0.08599375216980631,"rank":194,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09987281279211514,"rank":194,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09916305501674129,"rank":194,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10433828851383288,"rank":194,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09990459508115207,"rank":194,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09898523529402214,"rank":194,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09969808984733199,"rank":194,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09949318157775398,"rank":194,"remainingConfigurations":398},{"removed":"livebench-math","score":0.1000042026562673,"rank":194,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09912932982936405,"rank":194,"remainingConfigurations":398},{"removed":"livebench-language","score":0.10090881103669523,"rank":194,"remainingConfigurations":398},{"removed":"livebench-data","score":0.1000203209388184,"rank":194,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09841572813284849,"rank":194,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09925058117668571,"rank":194,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.10121920487207951,"rank":194,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.1021623873512555,"rank":195,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09516374340985218,"rank":195,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10080357691832746,"rank":195,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10347619613759318,"rank":194,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09940116685136947,"rank":194,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0995322941195851,"rank":194,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09947096760684698,"rank":194,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0997010930706921,"rank":194,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09923462277953204,"rank":194,"remainingConfigurations":398}]},"doubao-seed-code--effort-reasoning":{"score":0.09655552591790321,"rank":195,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11423702245738847,"rank":197,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08301557594848115,"rank":195,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09561584335705799,"rank":196,"remainingConfigurations":398},{"removed":"Scale","score":0.10606772873889586,"rank":195,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09655337596824608,"rank":195,"remainingConfigurations":398},{"removed":"Cognition","score":0.10089792143397812,"rank":197,"remainingConfigurations":398},{"removed":"LiveBench","score":0.098497152526921,"rank":194,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09867989671365794,"rank":196,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09676064644423603,"rank":189,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09391364425887135,"rank":195,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0965609065745664,"rank":195,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09646795069573082,"rank":195,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09639706634902755,"rank":195,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09655552591790321,"rank":195,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09630052247068473,"rank":195,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09676368178980783,"rank":195,"remainingConfigurations":398},{"removed":"briefcase","score":0.09620450960589512,"rank":195,"remainingConfigurations":398},{"removed":"aime","score":0.09830748006942819,"rank":196,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09738322847350665,"rank":195,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09150806102640169,"rank":202,"remainingConfigurations":398},{"removed":"automationbench","score":0.09631764175807789,"rank":195,"remainingConfigurations":398},{"removed":"critpt","score":0.09713251141486266,"rank":194,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09650265293413988,"rank":195,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09745893491528572,"rank":195,"remainingConfigurations":398},{"removed":"gdpval","score":0.09698029677889809,"rank":195,"remainingConfigurations":398},{"removed":"gmmlu","score":0.10526327988135149,"rank":188,"remainingConfigurations":398},{"removed":"gpqa","score":0.09633422942871857,"rank":197,"remainingConfigurations":398},{"removed":"harvey","score":0.09541812960310066,"rank":195,"remainingConfigurations":398},{"removed":"hle","score":0.1009274782327999,"rank":197,"remainingConfigurations":398},{"removed":"ifbench","score":0.09608468213667375,"rank":196,"remainingConfigurations":398},{"removed":"itbench","score":0.09631871161605156,"rank":195,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09436329163709602,"rank":199,"remainingConfigurations":398},{"removed":"math500","score":0.09677928264605334,"rank":195,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0948252897604141,"rank":199,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10270650712736445,"rank":195,"remainingConfigurations":398},{"removed":"omniscience","score":0.09018311398354807,"rank":200,"remainingConfigurations":398},{"removed":"scicode","score":0.09797816441886566,"rank":195,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0976153902978043,"rank":192,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09628015489186208,"rank":194,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11350062573161407,"rank":198,"remainingConfigurations":398},{"removed":"deepswe","score":0.08307461241180307,"rank":195,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09658079383430752,"rank":195,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0958953998014258,"rank":195,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10089792143397812,"rank":197,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09661184294367052,"rank":195,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09571805466549627,"rank":195,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09641192510625073,"rank":195,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09621221062041246,"rank":195,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09670857133206008,"rank":195,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09585740612964098,"rank":195,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09758936678001263,"rank":195,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09672468683713316,"rank":195,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09516291638863368,"rank":195,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09597506485220154,"rank":195,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09789190540995979,"rank":195,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09867989671365794,"rank":196,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09195562472740441,"rank":196,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09748081040741814,"rank":196,"remainingConfigurations":398},{"removed":"simpleqa","score":0.10007986152887853,"rank":195,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09612162568056225,"rank":195,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09624930389825852,"rank":195,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09618992036630569,"rank":196,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09641270662619011,"rank":195,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09596009055220169,"rank":195,"remainingConfigurations":398}]},"mimo-v2.5-pro--effort-non-reasoning":{"score":0.09596264490944895,"rank":196,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11374258364747136,"rank":199,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08242930868939184,"rank":196,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09512571880830849,"rank":198,"remainingConfigurations":398},{"removed":"Scale","score":0.10506092773216563,"rank":197,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09593464708408495,"rank":196,"remainingConfigurations":398},{"removed":"Cognition","score":0.10005016912648125,"rank":198,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09790401837338036,"rank":195,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09804090161229416,"rank":197,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09548875803684083,"rank":191,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09330714440362424,"rank":196,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09596799468880889,"rank":196,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09587733377220826,"rank":196,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09580639523436636,"rank":196,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09596264490944895,"rank":196,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09571210227091019,"rank":196,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09622011783831604,"rank":196,"remainingConfigurations":398},{"removed":"briefcase","score":0.09548779376098,"rank":197,"remainingConfigurations":398},{"removed":"aime","score":0.09676318227769444,"rank":198,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09681802820207729,"rank":196,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.10637869645796867,"rank":189,"remainingConfigurations":398},{"removed":"automationbench","score":0.09569889161905439,"rank":197,"remainingConfigurations":398},{"removed":"critpt","score":0.08856579045515132,"rank":207,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0959417745717203,"rank":196,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09686135321286508,"rank":196,"remainingConfigurations":398},{"removed":"gdpval","score":0.0959396455788038,"rank":198,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09664672562014254,"rank":196,"remainingConfigurations":398},{"removed":"gpqa","score":0.09728638185652787,"rank":195,"remainingConfigurations":398},{"removed":"harvey","score":0.09480751220434545,"rank":197,"remainingConfigurations":398},{"removed":"hle","score":0.09807679009128206,"rank":201,"remainingConfigurations":398},{"removed":"ifbench","score":0.10726561757505981,"rank":189,"remainingConfigurations":398},{"removed":"itbench","score":0.09578028853010796,"rank":196,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09599193707561676,"rank":196,"remainingConfigurations":398},{"removed":"math500","score":0.09636454902442508,"rank":197,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09854911710831347,"rank":197,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10144483350979681,"rank":198,"remainingConfigurations":398},{"removed":"omniscience","score":0.08537820397602104,"rank":212,"remainingConfigurations":398},{"removed":"scicode","score":0.09745181446247934,"rank":196,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09510683911017159,"rank":196,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08810716049002014,"rank":210,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11310849444854366,"rank":200,"remainingConfigurations":398},{"removed":"deepswe","score":0.08248792553293492,"rank":196,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09598782321497622,"rank":196,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09531259966470636,"rank":196,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10005016912648125,"rank":198,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0960295330629068,"rank":196,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09513156194643324,"rank":196,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09582084275024487,"rank":196,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09561921855403215,"rank":196,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09611486187677944,"rank":196,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09526507339237077,"rank":196,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09699173442202141,"rank":196,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09613486839565817,"rank":196,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09457676384850537,"rank":196,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09538367582060474,"rank":196,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09729312377499329,"rank":197,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09804090161229416,"rank":197,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09106415690184282,"rank":198,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0967043692190943,"rank":198,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09946132247483563,"rank":196,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09553141047070741,"rank":196,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09565858207662527,"rank":196,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09559785751614824,"rank":197,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09582134350142035,"rank":196,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09537030191547567,"rank":196,"remainingConfigurations":398}]},"gpt-5-mini--effort-medium":{"score":0.09583023823062868,"rank":197,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06807597980270667,"rank":135,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12290644423618424,"rank":189,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08144504698993986,"rank":198,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09579552146732967,"rank":195,"remainingConfigurations":398},{"removed":"Scale","score":0.10543714922721904,"rank":196,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09537666570078097,"rank":198,"remainingConfigurations":398},{"removed":"Cognition","score":0.10120184838657441,"rank":195,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09656379493283039,"rank":198,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.10820702255054894,"rank":189,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09517670419252672,"rank":192,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0922629781904538,"rank":198,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09583464713257261,"rank":197,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09571137184230437,"rank":197,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09570347818393893,"rank":197,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09583023823062868,"rank":197,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09557557553752893,"rank":197,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09603057503373792,"rank":197,"remainingConfigurations":398},{"removed":"briefcase","score":0.09587168626095884,"rank":196,"remainingConfigurations":398},{"removed":"aime","score":0.0955807361809552,"rank":200,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0965546447820726,"rank":197,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09384948045568915,"rank":197,"remainingConfigurations":398},{"removed":"automationbench","score":0.09584552088929899,"rank":196,"remainingConfigurations":398},{"removed":"critpt","score":0.09540470838022612,"rank":198,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09590526339172782,"rank":197,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09650742268034168,"rank":197,"remainingConfigurations":398},{"removed":"gdpval","score":0.09633811433598234,"rank":197,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09541353053574246,"rank":199,"remainingConfigurations":398},{"removed":"gpqa","score":0.09538973079584144,"rank":198,"remainingConfigurations":398},{"removed":"harvey","score":0.09486651931066935,"rank":196,"remainingConfigurations":398},{"removed":"hle","score":0.10053708858928952,"rank":198,"remainingConfigurations":398},{"removed":"ifbench","score":0.09267307085687021,"rank":200,"remainingConfigurations":398},{"removed":"itbench","score":0.09577192281105414,"rank":197,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09794530404000266,"rank":194,"remainingConfigurations":398},{"removed":"math500","score":0.09639078329651331,"rank":196,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09875201048038194,"rank":196,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10212142972687736,"rank":197,"remainingConfigurations":398},{"removed":"omniscience","score":0.09238078197586379,"rank":199,"remainingConfigurations":398},{"removed":"scicode","score":0.09706150148639907,"rank":198,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09630371630405087,"rank":193,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09586972894327096,"rank":195,"remainingConfigurations":398},{"removed":"arc-agi","score":0.12220270913193175,"rank":190,"remainingConfigurations":398},{"removed":"deepswe","score":0.08149220159723942,"rank":198,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09585275560552613,"rank":197,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09433922772819996,"rank":198,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10120184838657441,"rank":195,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09592214755031293,"rank":197,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09499123151304541,"rank":197,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09568916543201512,"rank":197,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09548166667197872,"rank":197,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09596644358778054,"rank":197,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09512851420880224,"rank":197,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09677148934682767,"rank":197,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09596896491621565,"rank":197,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0944621093078206,"rank":197,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09523511322819199,"rank":197,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09729848422200833,"rank":196,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.10820702255054894,"rank":189,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.09147800506084809,"rank":197,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0968096124544376,"rank":197,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09915974453430615,"rank":198,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09539828305200848,"rank":197,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09550509064832596,"rank":197,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09551958841946735,"rank":198,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09564129114387504,"rank":197,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09520253126980173,"rank":197,"remainingConfigurations":398}]},"qwen3.5-27b--effort-non-reasoning":{"score":0.0957008859551281,"rank":198,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1137886995297205,"rank":198,"remainingConfigurations":398},{"removed":"Datacurve","score":0.08223303803563813,"rank":197,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09488943557504272,"rank":199,"remainingConfigurations":398},{"removed":"Scale","score":0.10504840181202406,"rank":198,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09567572932005136,"rank":197,"remainingConfigurations":398},{"removed":"Cognition","score":0.09984978997781209,"rank":199,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09766941536229345,"rank":196,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0979037997351947,"rank":198,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0960382945097326,"rank":190,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09304004758712502,"rank":197,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09570622857020072,"rank":198,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09561439270891904,"rank":198,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09554381515186348,"rank":198,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0957008859551281,"rank":198,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09544837519224177,"rank":198,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09591004950692739,"rank":198,"remainingConfigurations":398},{"removed":"briefcase","score":0.0951707211935986,"rank":198,"remainingConfigurations":398},{"removed":"aime","score":0.09661995198068608,"rank":199,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09653191220592523,"rank":198,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09352513553633184,"rank":199,"remainingConfigurations":398},{"removed":"automationbench","score":0.09530534851151833,"rank":198,"remainingConfigurations":398},{"removed":"critpt","score":0.09686591611601421,"rank":196,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0956468416203241,"rank":198,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09644066635642436,"rank":198,"remainingConfigurations":398},{"removed":"gdpval","score":0.09578527800111451,"rank":199,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09622202060170598,"rank":198,"remainingConfigurations":398},{"removed":"gpqa","score":0.08831476422017405,"rank":205,"remainingConfigurations":398},{"removed":"harvey","score":0.09451026800423394,"rank":198,"remainingConfigurations":398},{"removed":"hle","score":0.09968930791608711,"rank":199,"remainingConfigurations":398},{"removed":"ifbench","score":0.09899072073752539,"rank":195,"remainingConfigurations":398},{"removed":"itbench","score":0.0954427549142895,"rank":198,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09581377196670653,"rank":197,"remainingConfigurations":398},{"removed":"math500","score":0.09598413787104648,"rank":198,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09826220504994737,"rank":198,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09923213067914938,"rank":200,"remainingConfigurations":398},{"removed":"omniscience","score":0.1065466110868596,"rank":188,"remainingConfigurations":398},{"removed":"scicode","score":0.09699137781471222,"rank":199,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08933627696262252,"rank":202,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.092804842776061,"rank":200,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11311955809073959,"rank":199,"remainingConfigurations":398},{"removed":"deepswe","score":0.08229130494296424,"rank":197,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09572592031747856,"rank":198,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09505042410523377,"rank":197,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09984978997781209,"rank":199,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09576447223155844,"rank":198,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09487663966635185,"rank":198,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09555848941899264,"rank":198,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09535920582359324,"rank":198,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09585284857036004,"rank":198,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.095005873847946,"rank":198,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09672716594969231,"rank":198,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0958708724765353,"rank":198,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09431858529318803,"rank":198,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09512402939216448,"rank":198,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09702832722991585,"rank":198,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0979037997351947,"rank":198,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0910423148087851,"rank":199,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09655805662834423,"rank":199,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09918790001619053,"rank":197,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09527042745002508,"rank":198,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09539716907168637,"rank":198,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09533739194114693,"rank":199,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09555891048033859,"rank":198,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09511001142543436,"rank":198,"remainingConfigurations":398}]},"gpt-5.4-nano--effort-high":{"score":0.09478856680957921,"rank":199,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08757435053652333,"rank":122,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11332003036894907,"rank":200,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07917721252069766,"rank":200,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09545834891626422,"rank":197,"remainingConfigurations":398},{"removed":"Scale","score":0.10443555901243991,"rank":199,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09456668144810904,"rank":199,"remainingConfigurations":398},{"removed":"Cognition","score":0.10089968602191839,"rank":196,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0968917176934645,"rank":197,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09234931004720093,"rank":202,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09208144031352163,"rank":196,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08299181825879212,"rank":215,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09478659463637647,"rank":199,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09467558207390543,"rank":199,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09462612521680304,"rank":199,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09478856680957921,"rank":199,"remainingConfigurations":398},{"removed":"All provider reports","score":0.094501604425542,"rank":199,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09493909936670412,"rank":199,"remainingConfigurations":398},{"removed":"briefcase","score":0.09470232420019453,"rank":199,"remainingConfigurations":398},{"removed":"aime","score":0.09466278990687634,"rank":202,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09516306437359213,"rank":199,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09460775255855952,"rank":196,"remainingConfigurations":398},{"removed":"automationbench","score":0.09468498939473684,"rank":199,"remainingConfigurations":398},{"removed":"critpt","score":0.09540150690434829,"rank":199,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09482086763465457,"rank":199,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09512196024118995,"rank":199,"remainingConfigurations":398},{"removed":"gdpval","score":0.09495355166841514,"rank":202,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09476470492612787,"rank":200,"remainingConfigurations":398},{"removed":"gpqa","score":0.09481815733651992,"rank":199,"remainingConfigurations":398},{"removed":"harvey","score":0.09306434275502955,"rank":199,"remainingConfigurations":398},{"removed":"hle","score":0.09945791606533655,"rank":200,"remainingConfigurations":398},{"removed":"ifbench","score":0.09378227104551247,"rank":199,"remainingConfigurations":398},{"removed":"itbench","score":0.094589509277851,"rank":199,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09532534411980942,"rank":198,"remainingConfigurations":398},{"removed":"math500","score":0.09485039706448768,"rank":199,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09881127164925718,"rank":194,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.10033344494139051,"rank":199,"remainingConfigurations":398},{"removed":"omniscience","score":0.09339355580811648,"rank":196,"remainingConfigurations":398},{"removed":"scicode","score":0.09527988589386434,"rank":200,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09480210012481259,"rank":197,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.096873658976864,"rank":193,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11229857427601674,"rank":201,"remainingConfigurations":398},{"removed":"deepswe","score":0.07924295878526093,"rank":200,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09481680236273982,"rank":199,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09313423590512888,"rank":199,"remainingConfigurations":398},{"removed":"frontiercode","score":0.10089968602191839,"rank":196,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09494748668062854,"rank":199,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09401730886685711,"rank":199,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09467838840453886,"rank":199,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0943488525933681,"rank":199,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09503331366411334,"rank":199,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09407594756856912,"rank":199,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0957267057029501,"rank":199,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09493080864711684,"rank":199,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09337021711075805,"rank":199,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09434945577320371,"rank":199,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09604505831727474,"rank":199,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09234931004720093,"rank":202,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.088819184127387,"rank":200,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0958810352451031,"rank":200,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09757782684191635,"rank":199,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09443498025715084,"rank":199,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09177166303205818,"rank":201,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09738161434956527,"rank":195,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09248276364947766,"rank":200,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0931952463422326,"rank":199,"remainingConfigurations":398}]},"amazon-nova-2-pro-preview--effort-medium":{"score":0.09292110506024916,"rank":200,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.11083941819014549,"rank":201,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07981712957747582,"rank":199,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09205191821166099,"rank":200,"remainingConfigurations":398},{"removed":"Scale","score":0.10218836013038772,"rank":200,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09291410875096544,"rank":200,"remainingConfigurations":398},{"removed":"Cognition","score":0.0970448519859405,"rank":200,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09484939773304078,"rank":199,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09529951492195436,"rank":199,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09281721379016877,"rank":193,"remainingConfigurations":381},{"removed":"Vals AI","score":0.09039177147704124,"rank":199,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09292606335097574,"rank":200,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0928360587830016,"rank":200,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09277045210363431,"rank":200,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09292110506024916,"rank":200,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09267642552435258,"rank":200,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09317493970346892,"rank":200,"remainingConfigurations":398},{"removed":"briefcase","score":0.0925334573534643,"rank":200,"remainingConfigurations":398},{"removed":"aime","score":0.08979172453363322,"rank":208,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09383917154126041,"rank":200,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0912709316396519,"rank":203,"remainingConfigurations":398},{"removed":"automationbench","score":0.09264848689213251,"rank":200,"remainingConfigurations":398},{"removed":"critpt","score":0.10339419594478312,"rank":189,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09285372550310227,"rank":200,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09376652794774788,"rank":200,"remainingConfigurations":398},{"removed":"gdpval","score":0.09545522170051053,"rank":200,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09355727469946633,"rank":201,"remainingConfigurations":398},{"removed":"gpqa","score":0.0910869816266024,"rank":202,"remainingConfigurations":398},{"removed":"harvey","score":0.09181166362790806,"rank":200,"remainingConfigurations":398},{"removed":"hle","score":0.10171620275164217,"rank":196,"remainingConfigurations":398},{"removed":"ifbench","score":0.08182638445335287,"rank":214,"remainingConfigurations":398},{"removed":"itbench","score":0.0927543126164191,"rank":200,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09238929376004446,"rank":201,"remainingConfigurations":398},{"removed":"math500","score":0.09333320208423063,"rank":200,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09421169334573566,"rank":200,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.103819873585543,"rank":193,"remainingConfigurations":398},{"removed":"omniscience","score":0.08981561005877421,"rank":201,"remainingConfigurations":398},{"removed":"scicode","score":0.09429902178896499,"rank":201,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08654515356242044,"rank":208,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09412707636097445,"rank":197,"remainingConfigurations":398},{"removed":"arc-agi","score":0.11015661038143258,"rank":202,"remainingConfigurations":398},{"removed":"deepswe","score":0.07987423451540308,"rank":199,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09294563438552499,"rank":200,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0922973514353781,"rank":200,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0970448519859405,"rank":200,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09300404647031163,"rank":200,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09212096432335642,"rank":200,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09278601423934268,"rank":200,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09258789108721949,"rank":200,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09306874552884736,"rank":200,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0922436198155826,"rank":200,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09392511660007753,"rank":200,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09308824896937479,"rank":200,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09157023692420525,"rank":200,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09235744534174593,"rank":200,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0942159989409934,"rank":200,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09529951492195436,"rank":199,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08844760996706152,"rank":201,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09370020161007729,"rank":202,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09633214610514096,"rank":200,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09250068701617786,"rank":200,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09262456878327008,"rank":199,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09256537096738988,"rank":200,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09278303269906046,"rank":199,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0923430964262803,"rank":200,"remainingConfigurations":398}]},"qwen3.8-27b--effort-non-reasoning":{"score":0.09210270877812159,"rank":201,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10915594980442012,"rank":202,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07892245792649108,"rank":201,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09134583470907592,"rank":201,"remainingConfigurations":398},{"removed":"Scale","score":0.10110134157133642,"rank":201,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09204159139632438,"rank":201,"remainingConfigurations":398},{"removed":"Cognition","score":0.09574729690494353,"rank":201,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09408408584110622,"rank":200,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09416921986637283,"rank":200,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09251742885056254,"rank":195,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0895448175290382,"rank":200,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09210722066600047,"rank":201,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09201693044572119,"rank":201,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09194770182008986,"rank":201,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09210270877812159,"rank":201,"remainingConfigurations":398},{"removed":"All provider reports","score":0.09185255246325025,"rank":201,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09239652992514807,"rank":201,"remainingConfigurations":398},{"removed":"briefcase","score":0.09178273807192723,"rank":201,"remainingConfigurations":398},{"removed":"aime","score":0.09229714591581378,"rank":203,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09302924188625909,"rank":201,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08585921097868425,"rank":211,"remainingConfigurations":398},{"removed":"automationbench","score":0.09198835991907413,"rank":201,"remainingConfigurations":398},{"removed":"critpt","score":0.09334437677050007,"rank":202,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0922302718641359,"rank":201,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09312600300538794,"rank":201,"remainingConfigurations":398},{"removed":"gdpval","score":0.08294133499786054,"rank":217,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09244850905022445,"rank":203,"remainingConfigurations":398},{"removed":"gpqa","score":0.08563431768523837,"rank":214,"remainingConfigurations":398},{"removed":"harvey","score":0.09105801772992471,"rank":201,"remainingConfigurations":398},{"removed":"hle","score":0.09671701707667801,"rank":203,"remainingConfigurations":398},{"removed":"ifbench","score":0.08930119754557912,"rank":204,"remainingConfigurations":398},{"removed":"itbench","score":0.09195354076821254,"rank":201,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09178617740819221,"rank":202,"remainingConfigurations":398},{"removed":"math500","score":0.09210388214795717,"rank":202,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09416971415390914,"rank":201,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09489761681945791,"rank":203,"remainingConfigurations":398},{"removed":"omniscience","score":0.12165674823266466,"rank":174,"remainingConfigurations":398},{"removed":"scicode","score":0.09737893231448484,"rank":197,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0855941222292886,"rank":210,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09024983527577098,"rank":205,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10859045097379293,"rank":203,"remainingConfigurations":398},{"removed":"deepswe","score":0.07897887621919082,"rank":201,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09212760552526421,"rank":201,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09148672316456391,"rank":201,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09574729690494353,"rank":201,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09218142993916512,"rank":201,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09130008344340555,"rank":201,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0919697112300032,"rank":201,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09176419975687777,"rank":201,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09224964406101999,"rank":201,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.09142923083789034,"rank":201,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0931018618483206,"rank":201,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09227361638892732,"rank":201,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.09075885607052535,"rank":201,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09154140601686474,"rank":201,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09338651650331821,"rank":201,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09416921986637283,"rank":200,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08787933633231387,"rank":202,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09289056806803873,"rank":203,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09546808006037455,"rank":201,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09168381589677099,"rank":201,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09181047849122093,"rank":200,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09174869474525886,"rank":201,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09196826868304198,"rank":201,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09152816714212421,"rank":201,"remainingConfigurations":398}]},"k-exaone-2.0-750b-a37b--effort-reasoning":{"score":0.09180444828185817,"rank":202,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10828986126070173,"rank":203,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07857329666306444,"rank":202,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.09106524798018074,"rank":202,"remainingConfigurations":398},{"removed":"Scale","score":0.10086291008718073,"rank":202,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.09175063164776753,"rank":202,"remainingConfigurations":398},{"removed":"Cognition","score":0.09543899229172959,"rank":202,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09371223682855344,"rank":201,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09404071623848193,"rank":201,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09281514561405617,"rank":194,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08918014252781187,"rank":201,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.09180876234807654,"rank":202,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.09171969698243872,"rank":202,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.09165048266730667,"rank":202,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.09180444828185817,"rank":202,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0915561899157779,"rank":202,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09208987544608331,"rank":202,"remainingConfigurations":398},{"removed":"briefcase","score":0.0915501912447772,"rank":202,"remainingConfigurations":398},{"removed":"aime","score":0.09197413261891184,"rank":204,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09276887072132033,"rank":202,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09202577313844133,"rank":201,"remainingConfigurations":398},{"removed":"automationbench","score":0.0917010779566141,"rank":202,"remainingConfigurations":398},{"removed":"critpt","score":0.08638052203134315,"rank":210,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.09184268770676583,"rank":202,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09288165171947893,"rank":202,"remainingConfigurations":398},{"removed":"gdpval","score":0.08809086739137957,"rank":209,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09247691256457229,"rank":202,"remainingConfigurations":398},{"removed":"gpqa","score":0.08364856527392654,"rank":216,"remainingConfigurations":398},{"removed":"harvey","score":0.09072174918537423,"rank":202,"remainingConfigurations":398},{"removed":"hle","score":0.09011093639469019,"rank":213,"remainingConfigurations":398},{"removed":"ifbench","score":0.08927058427444362,"rank":205,"remainingConfigurations":398},{"removed":"itbench","score":0.09159545177191501,"rank":202,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09152993365075478,"rank":203,"remainingConfigurations":398},{"removed":"math500","score":0.09199031812391094,"rank":203,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09407059032695593,"rank":202,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09734041060146499,"rank":201,"remainingConfigurations":398},{"removed":"omniscience","score":0.11924867331887969,"rank":180,"remainingConfigurations":398},{"removed":"scicode","score":0.09095294420727097,"rank":202,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08956557870577343,"rank":200,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09136200625180319,"rank":203,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10778711931413915,"rank":204,"remainingConfigurations":398},{"removed":"deepswe","score":0.07862998067626552,"rank":202,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.09182962711214676,"rank":202,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.09119670877366252,"rank":202,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09543899229172959,"rank":202,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09188547144523025,"rank":202,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.09100382089231863,"rank":202,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.09167229751189669,"rank":202,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.09146400554674193,"rank":202,"remainingConfigurations":398},{"removed":"livebench-math","score":0.09195126141325138,"rank":202,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.091133367765665,"rank":202,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09280306238574797,"rank":202,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09197668741882942,"rank":202,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0904618868084664,"rank":202,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.09124406831234262,"rank":202,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09308307051247305,"rank":202,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09404071623848193,"rank":201,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08775461365383179,"rank":203,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09256463184012,"rank":204,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09515779891899119,"rank":202,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.09138602680638187,"rank":202,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.09151375985322951,"rank":202,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.09145040764076423,"rank":202,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.09167280551040431,"rank":202,"remainingConfigurations":398},{"removed":"vibe-code","score":0.09123065019500436,"rank":202,"remainingConfigurations":398}]},"gpt-5.5--effort-none":{"score":0.08990590596183258,"rank":203,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0828163494345986,"rank":128,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10679820280534759,"rank":204,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07669232031535489,"rank":205,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08960476964539717,"rank":203,"remainingConfigurations":398},{"removed":"Scale","score":0.09807441862106515,"rank":205,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08988749763376287,"rank":203,"remainingConfigurations":398},{"removed":"Cognition","score":0.09520005814006893,"rank":203,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09049722986600417,"rank":207,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09114287231587953,"rank":206,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08703403537784515,"rank":203,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08991112173455391,"rank":203,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08978978577771336,"rank":203,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08981611127898426,"rank":203,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08990590596183258,"rank":203,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08969353273653308,"rank":203,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.09010174653281688,"rank":203,"remainingConfigurations":398},{"removed":"briefcase","score":0.08982854571777137,"rank":205,"remainingConfigurations":398},{"removed":"aime","score":0.09801309022976419,"rank":197,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0905731056852254,"rank":203,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09025736846608028,"rank":204,"remainingConfigurations":398},{"removed":"automationbench","score":0.08988024100475124,"rank":203,"remainingConfigurations":398},{"removed":"critpt","score":0.08874027725280409,"rank":206,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08999432869505726,"rank":203,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09037552449594367,"rank":203,"remainingConfigurations":398},{"removed":"gdpval","score":0.08947566372893619,"rank":205,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09034476761307582,"rank":204,"remainingConfigurations":398},{"removed":"gpqa","score":0.10526788289343682,"rank":191,"remainingConfigurations":398},{"removed":"harvey","score":0.08892561370180885,"rank":203,"remainingConfigurations":398},{"removed":"hle","score":0.09327784418668723,"rank":206,"remainingConfigurations":398},{"removed":"ifbench","score":0.09011698406885549,"rank":202,"remainingConfigurations":398},{"removed":"itbench","score":0.08976585616930932,"rank":203,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09002953626986931,"rank":205,"remainingConfigurations":398},{"removed":"math500","score":0.09007247186433402,"rank":205,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09259448560272414,"rank":203,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0951913272518467,"rank":202,"remainingConfigurations":398},{"removed":"omniscience","score":0.0897668020315216,"rank":202,"remainingConfigurations":398},{"removed":"scicode","score":0.09075655797569382,"rank":204,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08700676014853703,"rank":207,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08973762899981663,"rank":208,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1064564065218143,"rank":205,"remainingConfigurations":398},{"removed":"deepswe","score":0.07675499261153808,"rank":205,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08992704063223445,"rank":203,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08945807249705391,"rank":203,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09520005814006893,"rank":203,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.09014770681998784,"rank":203,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08897954743843878,"rank":203,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08980131332080832,"rank":203,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08960155860207254,"rank":203,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0901429383209561,"rank":203,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08898252382858611,"rank":203,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09085682402029606,"rank":203,"remainingConfigurations":398},{"removed":"livebench-data","score":0.09014169929088256,"rank":203,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08869159007887893,"rank":203,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08932976504298994,"rank":203,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09121152868414723,"rank":203,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09114287231587953,"rank":206,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.057968851825556,"rank":242,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08912162240006637,"rank":211,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09305145459629928,"rank":203,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0894954182004369,"rank":203,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08965830887121658,"rank":203,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0894955482695885,"rank":203,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08978391271440189,"rank":203,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08941239533623783,"rank":203,"remainingConfigurations":398}]},"qwen3.5-9b--effort-reasoning":{"score":0.0896043900765382,"rank":204,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10642313383271396,"rank":205,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07685989111107792,"rank":203,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08884356968403505,"rank":204,"remainingConfigurations":398},{"removed":"Scale","score":0.09859195376374673,"rank":203,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08956645635249842,"rank":204,"remainingConfigurations":398},{"removed":"Cognition","score":0.09348870206014252,"rank":206,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09148135264344026,"rank":202,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0917717513956295,"rank":203,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09054263538940537,"rank":197,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08708774810298035,"rank":202,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08960905662178363,"rank":204,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08952286278082015,"rank":204,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08945459494539477,"rank":204,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0896043900765382,"rank":204,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08936415051288456,"rank":204,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08977689887079414,"rank":204,"remainingConfigurations":398},{"removed":"briefcase","score":0.08894188883307996,"rank":207,"remainingConfigurations":398},{"removed":"aime","score":0.09051012479872977,"rank":206,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09035526016649505,"rank":204,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0845150624175768,"rank":213,"remainingConfigurations":398},{"removed":"automationbench","score":0.0890989558676815,"rank":206,"remainingConfigurations":398},{"removed":"critpt","score":0.09000601598851043,"rank":204,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0894301952846401,"rank":205,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0902046392684218,"rank":205,"remainingConfigurations":398},{"removed":"gdpval","score":0.0967573370378614,"rank":196,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09020578989941752,"rank":205,"remainingConfigurations":398},{"removed":"gpqa","score":0.08610307816102968,"rank":212,"remainingConfigurations":398},{"removed":"harvey","score":0.08840818559591879,"rank":204,"remainingConfigurations":398},{"removed":"hle","score":0.09184591586590701,"rank":209,"remainingConfigurations":398},{"removed":"ifbench","score":0.08231412925966558,"rank":213,"remainingConfigurations":398},{"removed":"itbench","score":0.08918665901121592,"rank":205,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08992507531942538,"rank":206,"remainingConfigurations":398},{"removed":"math500","score":0.09008201596963848,"rank":204,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09236366129668455,"rank":204,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09370494627721898,"rank":208,"remainingConfigurations":398},{"removed":"omniscience","score":0.09689762017556836,"rank":195,"remainingConfigurations":398},{"removed":"scicode","score":0.09070439476260299,"rank":205,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0873687230043954,"rank":205,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09061315460001974,"rank":204,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10578694831621151,"rank":206,"remainingConfigurations":398},{"removed":"deepswe","score":0.0769149906327447,"rank":203,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08962846868141859,"rank":204,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08900260322255142,"rank":204,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09348870206014252,"rank":206,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08968052583262955,"rank":204,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08882398076768024,"rank":204,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08947432724865102,"rank":204,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08927763553464974,"rank":204,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08974822611090848,"rank":204,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08894616314654691,"rank":204,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09057983914895283,"rank":204,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0897694728695204,"rank":204,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0882919247973988,"rank":204,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08905623998420693,"rank":204,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09086089428491984,"rank":204,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0917717513956295,"rank":203,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08546808967033566,"rank":205,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09044281313191009,"rank":205,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09289945822505001,"rank":204,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08919536909801773,"rank":204,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08931760340650145,"rank":204,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08925886339009315,"rank":204,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08947170988089607,"rank":204,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08904342232211265,"rank":204,"remainingConfigurations":398}]},"o1--effort-reasoning":{"score":0.08934577810318838,"rank":205,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10633554839891914,"rank":206,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07676369128066489,"rank":204,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08846754814334144,"rank":205,"remainingConfigurations":398},{"removed":"Scale","score":0.09829086326341534,"rank":204,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08935292585391195,"rank":205,"remainingConfigurations":398},{"removed":"Cognition","score":0.09351622006867825,"rank":205,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0912060550228847,"rank":203,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09151442743151673,"rank":204,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08958240273294267,"rank":198,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08694168537999701,"rank":204,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0893508000166861,"rank":205,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08926507839778286,"rank":205,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08919972734435615,"rank":205,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08934577810318838,"rank":205,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0891105584346017,"rank":205,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08958023469495675,"rank":205,"remainingConfigurations":398},{"removed":"briefcase","score":0.0891665746596108,"rank":206,"remainingConfigurations":398},{"removed":"aime","score":0.08945684161962586,"rank":210,"remainingConfigurations":398},{"removed":"apex-agents","score":0.09021531861177627,"rank":205,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08614233989466359,"rank":210,"remainingConfigurations":398},{"removed":"automationbench","score":0.08928078162880247,"rank":205,"remainingConfigurations":398},{"removed":"critpt","score":0.08912340792642102,"rank":205,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08943946199779627,"rank":204,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.090360137688502,"rank":204,"remainingConfigurations":398},{"removed":"gdpval","score":0.089814874557527,"rank":204,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08991323506674558,"rank":206,"remainingConfigurations":398},{"removed":"gpqa","score":0.09046821812354683,"rank":204,"remainingConfigurations":398},{"removed":"harvey","score":0.08834781774379634,"rank":205,"remainingConfigurations":398},{"removed":"hle","score":0.10196035614608323,"rank":195,"remainingConfigurations":398},{"removed":"ifbench","score":0.08105208277369004,"rank":215,"remainingConfigurations":398},{"removed":"itbench","score":0.08919002279638917,"rank":204,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09295447914772496,"rank":200,"remainingConfigurations":398},{"removed":"math500","score":0.09229780146156143,"rank":201,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08761761746151565,"rank":215,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09489043584982869,"rank":204,"remainingConfigurations":398},{"removed":"omniscience","score":0.07651892219051253,"rank":218,"remainingConfigurations":398},{"removed":"scicode","score":0.09087751354231156,"rank":203,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08947968891181585,"rank":201,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09491342903214617,"rank":196,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10560740615401222,"rank":207,"remainingConfigurations":398},{"removed":"deepswe","score":0.07681882716032602,"rank":204,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08936953293248394,"rank":205,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08873535940643112,"rank":205,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09351622006867825,"rank":205,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08941630160222393,"rank":205,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08856480152230158,"rank":205,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08921367289356581,"rank":205,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08902586500666608,"rank":205,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08948955624305881,"rank":205,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08868663683048955,"rank":205,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09031664976818671,"rank":205,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08950782647679363,"rank":205,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08803844166837181,"rank":205,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0887994861341611,"rank":205,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09060348054978927,"rank":205,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09151442743151673,"rank":204,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08506872015620277,"rank":206,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09020792075485544,"rank":206,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09266482088914568,"rank":205,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08893854240850797,"rank":205,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08905835884228307,"rank":205,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0890022996030937,"rank":205,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08921125284604393,"rank":205,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0887869437775699,"rank":205,"remainingConfigurations":398}]},"gemini-2.5-flash--effort-reasoning":{"score":0.08910856077463679,"rank":206,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10578606550455473,"rank":207,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07648398476348849,"rank":206,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08818390944831166,"rank":207,"remainingConfigurations":398},{"removed":"Scale","score":0.09797895534524016,"rank":206,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08908781673778617,"rank":206,"remainingConfigurations":398},{"removed":"Cognition","score":0.09307914831843285,"rank":207,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09101032399128654,"rank":204,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09104528633252885,"rank":207,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0891089440496099,"rank":201,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0866811425587275,"rank":205,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08911349564965186,"rank":206,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08902686132685185,"rank":206,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08896297732181328,"rank":206,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08910856077463679,"rank":206,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08887274790789736,"rank":206,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08937314818971685,"rank":206,"remainingConfigurations":398},{"removed":"briefcase","score":0.08893660920905035,"rank":208,"remainingConfigurations":398},{"removed":"aime","score":0.09142782849505943,"rank":205,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08993960856753908,"rank":206,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08558425874652016,"rank":212,"remainingConfigurations":398},{"removed":"automationbench","score":0.08905543388506791,"rank":207,"remainingConfigurations":398},{"removed":"critpt","score":0.08417745181771068,"rank":215,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0891686560231613,"rank":206,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.09013654081407597,"rank":206,"remainingConfigurations":398},{"removed":"gdpval","score":0.08946423478031768,"rank":206,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08940760808052711,"rank":209,"remainingConfigurations":398},{"removed":"gpqa","score":0.08671874962078331,"rank":210,"remainingConfigurations":398},{"removed":"harvey","score":0.0880868994407268,"rank":206,"remainingConfigurations":398},{"removed":"hle","score":0.09405107786525636,"rank":205,"remainingConfigurations":398},{"removed":"ifbench","score":0.0886590966616192,"rank":206,"remainingConfigurations":398},{"removed":"itbench","score":0.08894488735184697,"rank":207,"remainingConfigurations":398},{"removed":"livecodebench","score":0.09071621910909204,"rank":204,"remainingConfigurations":398},{"removed":"math500","score":0.08773525949192477,"rank":210,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08932432578180022,"rank":209,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09384592476410065,"rank":207,"remainingConfigurations":398},{"removed":"omniscience","score":0.08148320666862556,"rank":216,"remainingConfigurations":398},{"removed":"scicode","score":0.09067116292945447,"rank":206,"remainingConfigurations":398},{"removed":"tau-bench","score":0.09592085582385652,"rank":195,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09351200591951386,"rank":198,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10513936415916836,"rank":208,"remainingConfigurations":398},{"removed":"deepswe","score":0.07653869907549472,"rank":206,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08913216515728052,"rank":206,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0885009969020286,"rank":206,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09307914831843285,"rank":207,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0891753788742607,"rank":206,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08833141973873421,"rank":206,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08897768843171748,"rank":206,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08878989935866795,"rank":206,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08925169413396551,"rank":206,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08845137668362246,"rank":206,"remainingConfigurations":398},{"removed":"livebench-language","score":0.09007719504582418,"rank":206,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08926979815273715,"rank":206,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08780433320552165,"rank":206,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08856377158033134,"rank":206,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09036340291697982,"rank":206,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09104528633252885,"rank":207,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08478484567644162,"rank":207,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08994249955065396,"rank":209,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09241821933033523,"rank":207,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08870229059100836,"rank":206,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08882158851204974,"rank":206,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08876598607478015,"rank":206,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0889735715898835,"rank":206,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08855066293247921,"rank":206,"remainingConfigurations":398}]},"qwen3.5-35b-a3b--effort-non-reasoning":{"score":0.08894864974984913,"rank":207,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10551708755870354,"rank":117,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10564465684172857,"rank":208,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07619621247414332,"rank":207,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08837286482891354,"rank":206,"remainingConfigurations":398},{"removed":"Scale","score":0.09743888856888538,"rank":208,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08904576293346654,"rank":207,"remainingConfigurations":398},{"removed":"Cognition","score":0.09376219491264393,"rank":204,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09052214524427997,"rank":206,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09033861888052575,"rank":210,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07800227878479174,"rank":209,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08650186272673739,"rank":206,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08895019992101443,"rank":207,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08885179027243706,"rank":207,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08882850185171413,"rank":207,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08894864974984913,"rank":207,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08872065515464383,"rank":207,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08913264047131038,"rank":207,"remainingConfigurations":398},{"removed":"briefcase","score":0.08867671478759669,"rank":209,"remainingConfigurations":398},{"removed":"aime","score":0.08950428146019562,"rank":209,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08968648924666661,"rank":207,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08764998708371267,"rank":206,"remainingConfigurations":398},{"removed":"automationbench","score":0.08878855569091193,"rank":208,"remainingConfigurations":398},{"removed":"critpt","score":0.08642535852133641,"rank":209,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08895493467770367,"rank":207,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08962696681397521,"rank":207,"remainingConfigurations":398},{"removed":"gdpval","score":0.08851354762951112,"rank":208,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08967797132493767,"rank":207,"remainingConfigurations":398},{"removed":"gpqa","score":0.08621505836041439,"rank":211,"remainingConfigurations":398},{"removed":"harvey","score":0.08789297920498174,"rank":207,"remainingConfigurations":398},{"removed":"hle","score":0.09193044696408843,"rank":208,"remainingConfigurations":398},{"removed":"ifbench","score":0.08979692355571495,"rank":203,"remainingConfigurations":398},{"removed":"itbench","score":0.08873970809078154,"rank":208,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08887417979736878,"rank":208,"remainingConfigurations":398},{"removed":"math500","score":0.0891464455538925,"rank":207,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09131439883819971,"rank":206,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09291209752607614,"rank":211,"remainingConfigurations":398},{"removed":"omniscience","score":0.09268161387991207,"rank":197,"remainingConfigurations":398},{"removed":"scicode","score":0.0900482773041769,"rank":207,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08757330103705423,"rank":204,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09001316790798207,"rank":206,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10505815661755562,"rank":209,"remainingConfigurations":398},{"removed":"deepswe","score":0.07625620383540922,"rank":207,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0889715274060706,"rank":207,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08838210014300707,"rank":207,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09376219491264393,"rank":204,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08907156732259543,"rank":207,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08814105110578015,"rank":207,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08882516293360739,"rank":207,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08862461669211147,"rank":207,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0891341284380973,"rank":207,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08818175574427728,"rank":207,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08991109574745206,"rank":207,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08914929130896648,"rank":207,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08767910847733001,"rank":207,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08839595180744951,"rank":207,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09020794371735495,"rank":207,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09033861888052575,"rank":210,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08109364197865068,"rank":212,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09018699858548294,"rank":207,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09242209705592219,"rank":206,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08854444302595534,"rank":207,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08868174513694388,"rank":207,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08857099091590152,"rank":207,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08882748035956149,"rank":207,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08842888316088972,"rank":207,"remainingConfigurations":398}]},"k-exaone-236b-a23b--effort-reasoning":{"score":0.0887780738609706,"rank":208,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10528324134738115,"rank":209,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07618226456099637,"rank":208,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08795493293361134,"rank":209,"remainingConfigurations":398},{"removed":"Scale","score":0.09769217303345801,"rank":207,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08875843471039223,"rank":208,"remainingConfigurations":398},{"removed":"Cognition","score":0.09274761773775202,"rank":210,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09060949711308745,"rank":205,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09067700346108865,"rank":208,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0890750234192823,"rank":202,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0863199585047356,"rank":207,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08878285424908834,"rank":208,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08869737617353819,"rank":208,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08863218862215268,"rank":208,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0887780738609706,"rank":208,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0885428235587844,"rank":208,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0889593337601991,"rank":208,"remainingConfigurations":398},{"removed":"briefcase","score":0.08827876164296794,"rank":211,"remainingConfigurations":398},{"removed":"aime","score":0.08524368139286471,"rank":218,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08952277549373872,"rank":208,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08771680656723106,"rank":205,"remainingConfigurations":398},{"removed":"automationbench","score":0.08842569768200921,"rank":210,"remainingConfigurations":398},{"removed":"critpt","score":0.08498759244275784,"rank":213,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08868262699795369,"rank":208,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08948474018065854,"rank":208,"remainingConfigurations":398},{"removed":"gdpval","score":0.0952794446783531,"rank":201,"remainingConfigurations":398},{"removed":"gmmlu","score":0.09642893519209877,"rank":197,"remainingConfigurations":398},{"removed":"gpqa","score":0.08701559029786993,"rank":208,"remainingConfigurations":398},{"removed":"harvey","score":0.0876506557688818,"rank":208,"remainingConfigurations":398},{"removed":"hle","score":0.09252212427283368,"rank":207,"remainingConfigurations":398},{"removed":"ifbench","score":0.08343681786971437,"rank":212,"remainingConfigurations":398},{"removed":"itbench","score":0.08851173766027526,"rank":209,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08528034511612875,"rank":215,"remainingConfigurations":398},{"removed":"math500","score":0.08916275362221876,"rank":206,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08882749592084155,"rank":211,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09418874898837958,"rank":206,"remainingConfigurations":398},{"removed":"omniscience","score":0.09258411534010969,"rank":198,"remainingConfigurations":398},{"removed":"scicode","score":0.08997204516640822,"rank":209,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08710865655028126,"rank":206,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08987224320860025,"rank":207,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10461674000806691,"rank":210,"remainingConfigurations":398},{"removed":"deepswe","score":0.07623705302645861,"rank":208,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0888018108316838,"rank":208,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08817299002328839,"rank":208,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09274761773775202,"rank":210,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08884350677389337,"rank":208,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08800106685503617,"rank":208,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0886476143812079,"rank":208,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08845780529723025,"rank":208,"remainingConfigurations":398},{"removed":"livebench-math","score":0.088921130728772,"rank":208,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08812305667326104,"rank":208,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08974461175140956,"rank":208,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08893981338903517,"rank":208,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08747673212935879,"rank":208,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08823457757284753,"rank":208,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.09002836882799058,"rank":208,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09067700346108865,"rank":208,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08442304867822364,"rank":208,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08961045553166065,"rank":210,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09206874406378422,"rank":208,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08837265584511252,"rank":208,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08849244021084883,"rank":208,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08843603076730899,"rank":208,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08864486326810095,"rank":208,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0882217144876229,"rank":208,"remainingConfigurations":398}]},"kimi-k2.6--effort-non-reasoning":{"score":0.08855555108764535,"rank":209,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.03605483629378873,"rank":147,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10509944452330372,"rank":210,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07596946762178518,"rank":209,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08799281771797608,"rank":208,"remainingConfigurations":398},{"removed":"Scale","score":0.09733032731287572,"rank":209,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08842081526524671,"rank":209,"remainingConfigurations":398},{"removed":"Cognition","score":0.09260601771718689,"rank":211,"remainingConfigurations":398},{"removed":"LiveBench","score":0.09037857369213013,"rank":208,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09145592657946018,"rank":205,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.13477635641589664,"rank":166,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08613937131020503,"rank":208,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08856664953133814,"rank":209,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08847753298370657,"rank":209,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08843348818663199,"rank":209,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08855555108764535,"rank":209,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08835368949839328,"rank":209,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08879741192114123,"rank":209,"remainingConfigurations":398},{"removed":"briefcase","score":0.08853382004185806,"rank":210,"remainingConfigurations":398},{"removed":"aime","score":0.08979325113188223,"rank":207,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0893803752313922,"rank":209,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0870734215062972,"rank":208,"remainingConfigurations":398},{"removed":"automationbench","score":0.0886003166792582,"rank":209,"remainingConfigurations":398},{"removed":"critpt","score":0.08510463011956353,"rank":212,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08865447957154697,"rank":209,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08941362021565341,"rank":209,"remainingConfigurations":398},{"removed":"gdpval","score":0.08895336648973852,"rank":207,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08944339787718536,"rank":208,"remainingConfigurations":398},{"removed":"gpqa","score":0.08712128948984339,"rank":207,"remainingConfigurations":398},{"removed":"harvey","score":0.08763558970512397,"rank":209,"remainingConfigurations":398},{"removed":"hle","score":0.09087935151458422,"rank":211,"remainingConfigurations":398},{"removed":"ifbench","score":0.09520834008245634,"rank":198,"remainingConfigurations":398},{"removed":"itbench","score":0.0884329628858589,"rank":210,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08911601293036814,"rank":207,"remainingConfigurations":398},{"removed":"math500","score":0.08908195340602564,"rank":208,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09156449530624856,"rank":205,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09459116327745641,"rank":205,"remainingConfigurations":398},{"removed":"omniscience","score":0.08677085154606841,"rank":209,"remainingConfigurations":398},{"removed":"scicode","score":0.08999178440114668,"rank":208,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08280203277638248,"rank":216,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08480267206948748,"rank":214,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10413696204227345,"rank":211,"remainingConfigurations":398},{"removed":"deepswe","score":0.0760207760589434,"rank":209,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08857696279359795,"rank":209,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08817147498265444,"rank":209,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09260601771718689,"rank":211,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08877106435492808,"rank":209,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08759451767686388,"rank":209,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08845740055698187,"rank":209,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08828135303964164,"rank":209,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08871290402704213,"rank":209,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08784656034644912,"rank":209,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08949391441279024,"rank":209,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08875524125422567,"rank":209,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08728373560874914,"rank":209,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08800947353412196,"rank":209,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08980937884419148,"rank":209,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09145592657946018,"rank":205,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.1285335339253307,"rank":172,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08995337981943445,"rank":208,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09156978588437015,"rank":209,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08814734202037854,"rank":209,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08828396980258273,"rank":209,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0881953341411338,"rank":209,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08841625627719786,"rank":209,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08801925387889353,"rank":209,"remainingConfigurations":398}]},"qwen3-235b-a22b-thinking-2507--effort-reasoning":{"score":0.08819885553963842,"rank":210,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10423756525656164,"rank":212,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07554015721605721,"rank":210,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08736106421755781,"rank":210,"remainingConfigurations":398},{"removed":"Scale","score":0.09706499193919009,"rank":210,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08814048109445628,"rank":210,"remainingConfigurations":398},{"removed":"Cognition","score":0.09195232031431366,"rank":213,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08999305417046555,"rank":209,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.09034613418252785,"rank":209,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08920864865432664,"rank":200,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08569746732015765,"rank":209,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08820335255456352,"rank":210,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08811798117498526,"rank":210,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08805061122169595,"rank":210,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08819885553963842,"rank":210,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0879608492641914,"rank":210,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08843839242521374,"rank":210,"remainingConfigurations":398},{"removed":"briefcase","score":0.09123022959178394,"rank":204,"remainingConfigurations":398},{"removed":"aime","score":0.08468757876944906,"rank":219,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0891202815664109,"rank":210,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08381936183098034,"rank":215,"remainingConfigurations":398},{"removed":"automationbench","score":0.08952570591841592,"rank":204,"remainingConfigurations":398},{"removed":"critpt","score":0.09505488830748458,"rank":200,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08823503494099076,"rank":210,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08841373876025586,"rank":211,"remainingConfigurations":398},{"removed":"gdpval","score":0.09278650688974116,"rank":203,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08690064191402665,"rank":213,"remainingConfigurations":398},{"removed":"gpqa","score":0.08593819617722646,"rank":213,"remainingConfigurations":398},{"removed":"harvey","score":0.08721741056805181,"rank":210,"remainingConfigurations":398},{"removed":"hle","score":0.09105713089377125,"rank":210,"remainingConfigurations":398},{"removed":"ifbench","score":0.08647854586533028,"rank":211,"remainingConfigurations":398},{"removed":"itbench","score":0.08801849143381792,"rank":211,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08543736702351494,"rank":214,"remainingConfigurations":398},{"removed":"math500","score":0.08650796299880958,"rank":214,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08804891553784612,"rank":214,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09350579764842543,"rank":209,"remainingConfigurations":398},{"removed":"omniscience","score":0.08486490414408931,"rank":213,"remainingConfigurations":398},{"removed":"scicode","score":0.0888616416965366,"rank":211,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08892037220355554,"rank":203,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.09190323358003989,"rank":202,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10358759944961281,"rank":213,"remainingConfigurations":398},{"removed":"deepswe","score":0.07559601683740079,"rank":210,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08822335779296779,"rank":210,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08760833974263517,"rank":210,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09195232031431366,"rank":213,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08826597563132232,"rank":210,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0874228666951223,"rank":210,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08807181186844189,"rank":210,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08787273583241428,"rank":210,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08833978531588559,"rank":210,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08755550638617741,"rank":210,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08916773099864632,"rank":210,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0883589246727452,"rank":210,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08689889723708294,"rank":210,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08765872924757649,"rank":210,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.089434162270015,"rank":210,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.09034613418252785,"rank":209,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08427635764444437,"rank":209,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08895980744344884,"rank":212,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09145821002587619,"rank":210,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08779373156659631,"rank":210,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08791604191957203,"rank":210,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08785767749763633,"rank":210,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08807114875822662,"rank":210,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08764335019736573,"rank":210,"remainingConfigurations":398}]},"glm-5.2--effort-non-reasoning":{"score":0.08791281135918054,"rank":211,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.07405946578932808,"rank":130,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10469097954309693,"rank":211,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07519117188140872,"rank":211,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08733825751127865,"rank":211,"remainingConfigurations":398},{"removed":"Scale","score":0.09636326012910966,"rank":211,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08786015241709894,"rank":211,"remainingConfigurations":398},{"removed":"Cognition","score":0.09228643126000703,"rank":212,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08945532240225694,"rank":210,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08968602387593005,"rank":211,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.09897556649705724,"rank":188,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08548719737411199,"rank":210,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08791612113313335,"rank":211,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08780215248370338,"rank":211,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08779351805400432,"rank":211,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08791281135918054,"rank":211,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08767362785631531,"rank":211,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08825437657166359,"rank":211,"remainingConfigurations":398},{"removed":"briefcase","score":0.08796401623366647,"rank":212,"remainingConfigurations":398},{"removed":"aime","score":0.09943484194160591,"rank":195,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08882039929302048,"rank":211,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.09363229636240883,"rank":198,"remainingConfigurations":398},{"removed":"automationbench","score":0.08812602816451158,"rank":211,"remainingConfigurations":398},{"removed":"critpt","score":0.08031124246744013,"rank":218,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08812655091829664,"rank":211,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08897322409705888,"rank":210,"remainingConfigurations":398},{"removed":"gdpval","score":0.07888229812605037,"rank":221,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08847970773814966,"rank":210,"remainingConfigurations":398},{"removed":"gpqa","score":0.10547109070945089,"rank":190,"remainingConfigurations":398},{"removed":"harvey","score":0.08709981331613949,"rank":211,"remainingConfigurations":398},{"removed":"hle","score":0.09585379230941347,"rank":204,"remainingConfigurations":398},{"removed":"ifbench","score":0.08700346271944738,"rank":209,"remainingConfigurations":398},{"removed":"itbench","score":0.08793047603687626,"rank":212,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08773614237947473,"rank":209,"remainingConfigurations":398},{"removed":"math500","score":0.0880582701941396,"rank":209,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.09023019267325842,"rank":207,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09350427965530049,"rank":210,"remainingConfigurations":398},{"removed":"omniscience","score":0.08918231219018041,"rank":204,"remainingConfigurations":398},{"removed":"scicode","score":0.0895761797469808,"rank":210,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08329520343556147,"rank":214,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08620364428306891,"rank":213,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10413350814639195,"rank":212,"remainingConfigurations":398},{"removed":"deepswe","score":0.07524523088500729,"rank":211,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08793530553629758,"rank":211,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08737453207209256,"rank":211,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09228643126000703,"rank":212,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08805963100390742,"rank":211,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08708042478835583,"rank":211,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.087796179418056,"rank":211,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08761445644619942,"rank":211,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08809138999546177,"rank":211,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0871598239015744,"rank":211,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0888612660019566,"rank":211,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08811108132882513,"rank":211,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08665827365432989,"rank":211,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08736527587231724,"rank":211,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.089162112671844,"rank":211,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08968602387593005,"rank":211,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07302443672483983,"rank":220,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07598034595763904,"rank":223,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09126490224624038,"rank":211,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08750572529778144,"rank":211,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08765201127202449,"rank":211,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08754333233517293,"rank":211,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08778600970858091,"rank":211,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08738629377147099,"rank":211,"remainingConfigurations":398}]},"qwen3.7-flash--effort-non-reasoning":{"score":0.08709382082340504,"rank":212,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0848689899673416,"rank":126,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10302686461838932,"rank":213,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07439132587505498,"rank":212,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08681564749445538,"rank":212,"remainingConfigurations":398},{"removed":"Scale","score":0.09499484863115244,"rank":212,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08722956465675206,"rank":212,"remainingConfigurations":398},{"removed":"Cognition","score":0.09278454802956428,"rank":209,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08849651615309384,"rank":211,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0881753411780279,"rank":213,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08499907469994794,"rank":211,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08709602840342469,"rank":212,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08698514870150968,"rank":212,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08701409521713499,"rank":212,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08709382082340504,"rank":212,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08689629046522468,"rank":212,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08728138965534636,"rank":212,"remainingConfigurations":398},{"removed":"briefcase","score":0.08698229644562187,"rank":213,"remainingConfigurations":398},{"removed":"aime","score":0.07270646033975885,"rank":229,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08772061708895074,"rank":213,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08746561981792227,"rank":207,"remainingConfigurations":398},{"removed":"automationbench","score":0.08703080567661503,"rank":212,"remainingConfigurations":398},{"removed":"critpt","score":0.08650217391967964,"rank":208,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08717421093873491,"rank":212,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0875468340058777,"rank":212,"remainingConfigurations":398},{"removed":"gdpval","score":0.08658504056162447,"rank":212,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0874657120250601,"rank":211,"remainingConfigurations":398},{"removed":"gpqa","score":0.08478265022075913,"rank":215,"remainingConfigurations":398},{"removed":"harvey","score":0.08612534870415445,"rank":212,"remainingConfigurations":398},{"removed":"hle","score":0.09020306541010364,"rank":212,"remainingConfigurations":398},{"removed":"ifbench","score":0.08752853819729955,"rank":207,"remainingConfigurations":398},{"removed":"itbench","score":0.08694598709607786,"rank":214,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08724847664891457,"rank":210,"remainingConfigurations":398},{"removed":"math500","score":0.08724847964818232,"rank":211,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08961912974643575,"rank":208,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09228372823833447,"rank":212,"remainingConfigurations":398},{"removed":"omniscience","score":0.0869753724978903,"rank":207,"remainingConfigurations":398},{"removed":"scicode","score":0.08791183064970028,"rank":213,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08429382926006242,"rank":211,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08698076337639284,"rank":211,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1026963952015726,"rank":214,"remainingConfigurations":398},{"removed":"deepswe","score":0.07445281577514913,"rank":212,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08711371155339022,"rank":212,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08661431713268397,"rank":212,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09278454802956428,"rank":209,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08731490954776576,"rank":212,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08620224147969822,"rank":212,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08698898223846928,"rank":212,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08680345234744691,"rank":212,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08731587289440983,"rank":212,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08622014790642228,"rank":212,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08801633541369049,"rank":212,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08734395934026358,"rank":212,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08589339412432434,"rank":212,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08654487507863368,"rank":212,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08833900831847824,"rank":212,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0881753411780279,"rank":213,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07604283598071133,"rank":216,"remainingConfigurations":398},{"removed":"frontiermath","score":0.10334802872833461,"rank":190,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09030435049204548,"rank":212,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08668903371049823,"rank":212,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08685616386911914,"rank":212,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08668686620373779,"rank":212,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08697667313699946,"rank":212,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08661649714425775,"rank":212,"remainingConfigurations":398}]},"gemma-4-26b-a4b-it--effort-minimal":{"score":0.08654390490711067,"rank":213,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08690080285692775,"rank":124,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10284630173844324,"rank":214,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07427776608981475,"rank":213,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0862583036639057,"rank":213,"remainingConfigurations":398},{"removed":"Scale","score":0.09444154489048166,"rank":214,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08661058849881893,"rank":213,"remainingConfigurations":398},{"removed":"Cognition","score":0.09281465770511792,"rank":208,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08745889463468205,"rank":214,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08726761683430632,"rank":216,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08428368984792382,"rank":212,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08654247181814474,"rank":213,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08643157983378462,"rank":213,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08645655388221547,"rank":213,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08654390490711067,"rank":213,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08633153394766596,"rank":213,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08673679185917486,"rank":213,"remainingConfigurations":398},{"removed":"briefcase","score":0.08644597364542513,"rank":214,"remainingConfigurations":398},{"removed":"aime","score":0.045730128012261374,"rank":271,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08718335915621533,"rank":214,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08692282528746954,"rank":209,"remainingConfigurations":398},{"removed":"automationbench","score":0.08651207506774856,"rank":213,"remainingConfigurations":398},{"removed":"critpt","score":0.08529763356654073,"rank":211,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08662311576493303,"rank":214,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08702231559082024,"rank":214,"remainingConfigurations":398},{"removed":"gdpval","score":0.0861470046494659,"rank":214,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08701242037132022,"rank":212,"remainingConfigurations":398},{"removed":"gpqa","score":0.13748263413416348,"rank":170,"remainingConfigurations":398},{"removed":"harvey","score":0.08556696590309765,"rank":213,"remainingConfigurations":398},{"removed":"hle","score":0.08991384406388662,"rank":214,"remainingConfigurations":398},{"removed":"ifbench","score":0.08659790835344609,"rank":210,"remainingConfigurations":398},{"removed":"itbench","score":0.0863886533524935,"rank":215,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0867240574110323,"rank":211,"remainingConfigurations":398},{"removed":"math500","score":0.08670346140254559,"rank":212,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08917271305030915,"rank":210,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09165022335261364,"rank":213,"remainingConfigurations":398},{"removed":"omniscience","score":0.08642842624525952,"rank":210,"remainingConfigurations":398},{"removed":"scicode","score":0.08734954106450223,"rank":215,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08363631920742615,"rank":213,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08660258097980718,"rank":212,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10253824868242185,"rank":215,"remainingConfigurations":398},{"removed":"deepswe","score":0.07434096198533639,"rank":213,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0865648730678344,"rank":213,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08603313913234865,"rank":213,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09281465770511792,"rank":208,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08674320142248464,"rank":213,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08570935324379342,"rank":213,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08643362116760257,"rank":213,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08623192420539318,"rank":213,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08678415108138192,"rank":213,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08562503386531228,"rank":213,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08747455075603948,"rank":213,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08676650588109787,"rank":213,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08537283705540684,"rank":213,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08598152784730728,"rank":213,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0878170509977489,"rank":213,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08726761683430632,"rank":216,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08638728192050166,"rank":204,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08708470659947397,"rank":213,"remainingConfigurations":398},{"removed":"simpleqa","score":0.09008581551605392,"rank":213,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08614761792649916,"rank":213,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08630357574568563,"rank":213,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08614479038150143,"rank":213,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08642943937615084,"rank":213,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08606830117179597,"rank":213,"remainingConfigurations":398}]},"gemma-4-26b-a4b-it--effort-reasoning":{"score":0.08623276197212953,"rank":214,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10229892471888037,"rank":215,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07387421089405644,"rank":214,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08550742086264868,"rank":215,"remainingConfigurations":398},{"removed":"Scale","score":0.09494439672862882,"rank":213,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08618359563277876,"rank":215,"remainingConfigurations":398},{"removed":"Cognition","score":0.08994387357521023,"rank":215,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08794997468993059,"rank":212,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08838216194690533,"rank":212,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0870680856525909,"rank":203,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08371342418766209,"rank":214,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08623722028533366,"rank":214,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08615607333424413,"rank":214,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08608759219066775,"rank":215,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08623276197212953,"rank":214,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08600204223624296,"rank":214,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08632628724780482,"rank":215,"remainingConfigurations":398},{"removed":"briefcase","score":0.08592441253088674,"rank":215,"remainingConfigurations":398},{"removed":"aime","score":0.08666702860372227,"rank":215,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08704398649362394,"rank":215,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08267589821496683,"rank":217,"remainingConfigurations":398},{"removed":"automationbench","score":0.08601652658088683,"rank":214,"remainingConfigurations":398},{"removed":"critpt","score":0.09696510416661501,"rank":195,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0861206721554328,"rank":216,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08709382296426603,"rank":213,"remainingConfigurations":398},{"removed":"gdpval","score":0.08705080606126087,"rank":211,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08684869538350289,"rank":214,"remainingConfigurations":398},{"removed":"gpqa","score":0.0832857317647465,"rank":217,"remainingConfigurations":398},{"removed":"harvey","score":0.08508075093560445,"rank":215,"remainingConfigurations":398},{"removed":"hle","score":0.08632052966655827,"rank":216,"remainingConfigurations":398},{"removed":"ifbench","score":0.0765251205481524,"rank":218,"remainingConfigurations":398},{"removed":"itbench","score":0.08726408318720706,"rank":213,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08622381868043112,"rank":212,"remainingConfigurations":398},{"removed":"math500","score":0.08651696313447253,"rank":213,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08860409066326543,"rank":212,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09009242742851702,"rank":215,"remainingConfigurations":398},{"removed":"omniscience","score":0.08714404397872122,"rank":206,"remainingConfigurations":398},{"removed":"scicode","score":0.08751100850286919,"rank":214,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08612625686978752,"rank":209,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08858610120949151,"rank":209,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10167552812004267,"rank":216,"remainingConfigurations":398},{"removed":"deepswe","score":0.07392843033118135,"rank":214,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0862557655965767,"rank":214,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08565671265729674,"rank":215,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08994387357521023,"rank":215,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08631166307151765,"rank":215,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08548171588318541,"rank":214,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08610790478703508,"rank":214,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08591683345800916,"rank":214,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0863704308125291,"rank":215,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08560119045307675,"rank":214,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08718165381070585,"rank":214,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08638584622060252,"rank":215,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08496206047606625,"rank":215,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0857037414794814,"rank":214,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08744614754957658,"rank":214,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08838216194690533,"rank":212,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08233220076717838,"rank":210,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0869963034331071,"rank":214,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08942261735685615,"rank":214,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08583825559717508,"rank":214,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08595287999043853,"rank":215,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08589843342523178,"rank":214,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08610321218825547,"rank":214,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08569286843302486,"rank":215,"remainingConfigurations":398}]},"qwen3.6-35b-a3b--effort-non-reasoning":{"score":0.08621496215962693,"rank":215,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.10411507875514381,"rank":118,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10182766537951195,"rank":216,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0737928962404834,"rank":215,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08570842971948074,"rank":214,"remainingConfigurations":398},{"removed":"Scale","score":0.09442389414039183,"rank":215,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08628668920118487,"rank":214,"remainingConfigurations":398},{"removed":"Cognition","score":0.09078165439145884,"rank":214,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08792231363883274,"rank":213,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08777923385124874,"rank":214,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0738537393806286,"rank":215,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08385575743835305,"rank":213,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08621826382266297,"rank":215,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08611153431511337,"rank":215,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0861031413304519,"rank":214,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08621496215962693,"rank":215,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08599090696963167,"rank":215,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08641564287053483,"rank":214,"remainingConfigurations":398},{"removed":"briefcase","score":0.0859167811061089,"rank":216,"remainingConfigurations":398},{"removed":"aime","score":0.08901044522057805,"rank":211,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08694500522664766,"rank":216,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0839859749633855,"rank":214,"remainingConfigurations":398},{"removed":"automationbench","score":0.08599279958927347,"rank":215,"remainingConfigurations":398},{"removed":"critpt","score":0.0917177649707152,"rank":203,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08625162014011915,"rank":215,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08682214592503078,"rank":215,"remainingConfigurations":398},{"removed":"gdpval","score":0.08355415083960131,"rank":216,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08661145353172256,"rank":215,"remainingConfigurations":398},{"removed":"gpqa","score":0.07314312872856213,"rank":230,"remainingConfigurations":398},{"removed":"harvey","score":0.0852189240972442,"rank":214,"remainingConfigurations":398},{"removed":"hle","score":0.08824155610131264,"rank":215,"remainingConfigurations":398},{"removed":"ifbench","score":0.09242894246401763,"rank":201,"remainingConfigurations":398},{"removed":"itbench","score":0.08604840140141341,"rank":216,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08583368594629971,"rank":213,"remainingConfigurations":398},{"removed":"math500","score":0.08623275685269538,"rank":215,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08813769020960986,"rank":213,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08835097488309307,"rank":217,"remainingConfigurations":398},{"removed":"omniscience","score":0.08867226113084563,"rank":205,"remainingConfigurations":398},{"removed":"scicode","score":0.08722999877156669,"rank":216,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08377231274310226,"rank":212,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0845992547663695,"rank":215,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10115649391734897,"rank":218,"remainingConfigurations":398},{"removed":"deepswe","score":0.07385031146337649,"rank":215,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08623649530809403,"rank":215,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08567512334263706,"rank":214,"remainingConfigurations":398},{"removed":"frontiercode","score":0.09078165439145884,"rank":214,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0863383551407383,"rank":214,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08540994623679164,"rank":215,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0860973370856246,"rank":215,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08591301102363864,"rank":215,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08639013079873527,"rank":214,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08547587196656971,"rank":215,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08714249943482338,"rank":215,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08642686121615573,"rank":214,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08497759536379902,"rank":214,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0856799227483677,"rank":215,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08743149224654179,"rank":215,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08777923385124874,"rank":214,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07726465005141352,"rank":214,"remainingConfigurations":398},{"removed":"frontiermath","score":0.09562510519367855,"rank":201,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0893866962831274,"rank":215,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08581810716646733,"rank":215,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08596046008336168,"rank":214,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08583950299641707,"rank":215,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08609685221785733,"rank":215,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08571304629739133,"rank":214,"remainingConfigurations":398}]},"deepseek-v4-flash-0424--effort-non-reasoning":{"score":0.08524087922623601,"rank":216,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.10181556869474108,"rank":217,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07309791529707764,"rank":216,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0844669920723692,"rank":216,"remainingConfigurations":398},{"removed":"Scale","score":0.09386584704639817,"rank":216,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08519904688608855,"rank":216,"remainingConfigurations":398},{"removed":"Cognition","score":0.08901408782855684,"rank":216,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08705915554621264,"rank":215,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08750725064511954,"rank":215,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08566334892326799,"rank":205,"remainingConfigurations":381},{"removed":"Vals AI","score":0.08289053223295853,"rank":216,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08524569326557825,"rank":216,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08516401169849679,"rank":216,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08510037584631969,"rank":216,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08524087922623601,"rank":216,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08501530076835466,"rank":216,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.085478772630324,"rank":216,"remainingConfigurations":398},{"removed":"briefcase","score":0.08488162512143833,"rank":217,"remainingConfigurations":398},{"removed":"aime","score":0.08594437745015894,"rank":217,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0860525922421397,"rank":217,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0929115426871918,"rank":200,"remainingConfigurations":398},{"removed":"automationbench","score":0.08504783168145667,"rank":216,"remainingConfigurations":398},{"removed":"critpt","score":0.08488229465538732,"rank":214,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08525552825170242,"rank":217,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08608631251545888,"rank":217,"remainingConfigurations":398},{"removed":"gdpval","score":0.08524424035193062,"rank":215,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0858707002255299,"rank":216,"remainingConfigurations":398},{"removed":"gpqa","score":0.0907852706389128,"rank":203,"remainingConfigurations":398},{"removed":"harvey","score":0.0842199361434332,"rank":216,"remainingConfigurations":398},{"removed":"hle","score":0.09751656679302832,"rank":202,"remainingConfigurations":398},{"removed":"ifbench","score":0.08740766805347411,"rank":208,"remainingConfigurations":398},{"removed":"itbench","score":0.08516027193245619,"rank":217,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08524207528586579,"rank":216,"remainingConfigurations":398},{"removed":"math500","score":0.0855932783834309,"rank":216,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08759373197547848,"rank":216,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.09061081954609812,"rank":214,"remainingConfigurations":398},{"removed":"omniscience","score":0.07588590423207962,"rank":219,"remainingConfigurations":398},{"removed":"scicode","score":0.086570846531784,"rank":217,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07285653436612083,"rank":224,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07837441016219676,"rank":221,"remainingConfigurations":398},{"removed":"arc-agi","score":0.10118591604717357,"rank":217,"remainingConfigurations":398},{"removed":"deepswe","score":0.07315049347073461,"rank":216,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08526367114619021,"rank":216,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08465958436631464,"rank":216,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08901408782855684,"rank":216,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.085309741718756,"rank":216,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08449693506330129,"rank":216,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08511502465955019,"rank":216,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0849330021979962,"rank":216,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08537898276240068,"rank":216,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08460520739854227,"rank":216,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08617477520531357,"rank":216,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08539890733564069,"rank":216,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08398354294889955,"rank":216,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08471458735716518,"rank":216,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08645209145782003,"rank":216,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08750725064511954,"rank":215,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08127278230621532,"rank":211,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08588544646111586,"rank":215,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08841864657247345,"rank":216,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08484936281869106,"rank":216,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08496448126166206,"rank":216,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08491007603866411,"rank":216,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08511082514447639,"rank":216,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08470366493688346,"rank":216,"remainingConfigurations":398}]},"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning":{"score":0.08439384572615083,"rank":217,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.09925932528389235,"rank":218,"remainingConfigurations":398},{"removed":"Datacurve","score":0.07207657751686412,"rank":217,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08376299313704251,"rank":217,"remainingConfigurations":398},{"removed":"Scale","score":0.09287492892929052,"rank":217,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08432585648107353,"rank":217,"remainingConfigurations":398},{"removed":"Cognition","score":0.08776399108464454,"rank":217,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08596078590873203,"rank":216,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08630086502474595,"rank":217,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08568450650765554,"rank":204,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0818573289112238,"rank":217,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08439888631703461,"rank":217,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0843204586917843,"rank":217,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08425340602699709,"rank":217,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08439384572615083,"rank":217,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08417185457694198,"rank":217,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08438551084549485,"rank":217,"remainingConfigurations":398},{"removed":"briefcase","score":0.09148792962557316,"rank":203,"remainingConfigurations":398},{"removed":"aime","score":0.08429161771360211,"rank":220,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08838932712487696,"rank":212,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08257260469500645,"rank":218,"remainingConfigurations":398},{"removed":"automationbench","score":0.0840740122993761,"rank":217,"remainingConfigurations":398},{"removed":"critpt","score":0.07852942149617113,"rank":221,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.08691860791486707,"rank":213,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08681871871558601,"rank":216,"remainingConfigurations":398},{"removed":"gdpval","score":0.08624463257416685,"rank":213,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08458971648194934,"rank":217,"remainingConfigurations":398},{"removed":"gpqa","score":0.08118458413547493,"rank":219,"remainingConfigurations":398},{"removed":"harvey","score":0.08314041113801192,"rank":217,"remainingConfigurations":398},{"removed":"hle","score":0.08425437985526825,"rank":219,"remainingConfigurations":398},{"removed":"ifbench","score":0.0760349217981948,"rank":221,"remainingConfigurations":398},{"removed":"itbench","score":0.08915554721875733,"rank":206,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08408928793090546,"rank":218,"remainingConfigurations":398},{"removed":"math500","score":0.0846740111068011,"rank":217,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08650070920720358,"rank":217,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08896981266473858,"rank":216,"remainingConfigurations":398},{"removed":"omniscience","score":0.08159644213870486,"rank":215,"remainingConfigurations":398},{"removed":"scicode","score":0.08829901605354862,"rank":212,"remainingConfigurations":398},{"removed":"tau-bench","score":0.08280718162113393,"rank":215,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08436907899571967,"rank":216,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0986527520734544,"rank":219,"remainingConfigurations":398},{"removed":"deepswe","score":0.07213262389495174,"rank":217,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08441686092583722,"rank":217,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08385002609836512,"rank":217,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08776399108464454,"rank":217,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0844673524267916,"rank":217,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08364747883045588,"rank":217,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08427368824340276,"rank":217,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08407691167386783,"rank":217,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08452538711010664,"rank":217,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08378745708229522,"rank":217,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08533874565806199,"rank":217,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08453816108123735,"rank":217,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.08313858108609891,"rank":217,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08387580476934538,"rank":217,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08557422777355768,"rank":217,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08630086502474595,"rank":217,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.08073366319218586,"rank":213,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08505669605757582,"rank":216,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08751119797816163,"rank":217,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08400606990610411,"rank":217,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08411919453002349,"rank":217,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08406215576054005,"rank":217,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08427289167611186,"rank":217,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08386154007394596,"rank":217,"remainingConfigurations":398}]},"deepseek-v3.2--effort-non-reasoning":{"score":0.08080195929723827,"rank":218,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.09645178240690234,"rank":219,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06923544657084657,"rank":218,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.08003543621633862,"rank":218,"remainingConfigurations":398},{"removed":"Scale","score":0.08899773218353679,"rank":218,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.08075762663531284,"rank":218,"remainingConfigurations":398},{"removed":"Cognition","score":0.08451062768809108,"rank":218,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08252318208601754,"rank":217,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0825449808465041,"rank":218,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08093976869774898,"rank":206,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07856161478965591,"rank":218,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.08080652219850952,"rank":218,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.08072776243892249,"rank":218,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.08066886295574045,"rank":218,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.08080195929723827,"rank":218,"remainingConfigurations":398},{"removed":"All provider reports","score":0.08058680194914117,"rank":218,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.08100961841962369,"rank":218,"remainingConfigurations":398},{"removed":"briefcase","score":0.08054434089818498,"rank":218,"remainingConfigurations":398},{"removed":"aime","score":0.08746531696536837,"rank":213,"remainingConfigurations":398},{"removed":"apex-agents","score":0.08157345198083892,"rank":218,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08324669826902721,"rank":216,"remainingConfigurations":398},{"removed":"automationbench","score":0.08066163990185375,"rank":218,"remainingConfigurations":398},{"removed":"critpt","score":0.07652670379698781,"rank":226,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0808128284204796,"rank":218,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0816527910289695,"rank":218,"remainingConfigurations":398},{"removed":"gdpval","score":0.08117898930570726,"rank":218,"remainingConfigurations":398},{"removed":"gmmlu","score":0.08165215329458257,"rank":218,"remainingConfigurations":398},{"removed":"gpqa","score":0.08058309337872357,"rank":221,"remainingConfigurations":398},{"removed":"harvey","score":0.07984547029701457,"rank":218,"remainingConfigurations":398},{"removed":"hle","score":0.08558754317421584,"rank":218,"remainingConfigurations":398},{"removed":"ifbench","score":0.08036984881934682,"rank":216,"remainingConfigurations":398},{"removed":"itbench","score":0.08064155075793616,"rank":218,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08519599469664461,"rank":217,"remainingConfigurations":398},{"removed":"math500","score":0.08104689944955357,"rank":218,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07958050222593341,"rank":221,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08583703712534589,"rank":219,"remainingConfigurations":398},{"removed":"omniscience","score":0.07457684714256252,"rank":222,"remainingConfigurations":398},{"removed":"scicode","score":0.08211127896525598,"rank":218,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07767694161529155,"rank":219,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.077417802440659,"rank":222,"remainingConfigurations":398},{"removed":"arc-agi","score":0.09583281640173792,"rank":220,"remainingConfigurations":398},{"removed":"deepswe","score":0.06928545761834591,"rank":218,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.08082372126509774,"rank":218,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.08024562371586852,"rank":218,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08451062768809108,"rank":218,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.08086108634127474,"rank":218,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.08008900853799768,"rank":218,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.08068211734743591,"rank":218,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.08051052986834471,"rank":218,"remainingConfigurations":398},{"removed":"livebench-math","score":0.08093426612611021,"rank":218,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.08019295762159047,"rank":218,"remainingConfigurations":398},{"removed":"livebench-language","score":0.081694423821485,"rank":218,"remainingConfigurations":398},{"removed":"livebench-data","score":0.08095210050956901,"rank":218,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07959994561331159,"rank":218,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.08029887773030299,"rank":218,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08196287075984526,"rank":218,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0825449808465041,"rank":218,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0767034613833336,"rank":215,"remainingConfigurations":398},{"removed":"frontiermath","score":0.08152139540854021,"rank":217,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08385282110814625,"rank":218,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.08042735395574738,"rank":218,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.08053703577247599,"rank":218,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.08048638618622823,"rank":218,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.08067626277333811,"rank":218,"remainingConfigurations":398},{"removed":"vibe-code","score":0.08028806098268895,"rank":218,"remainingConfigurations":398}]},"gpt-5.2--effort-non-reasoning":{"score":0.07919845348945133,"rank":219,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.09432935405418037,"rank":221,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06779427651482808,"rank":219,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07841226368563023,"rank":219,"remainingConfigurations":398},{"removed":"Scale","score":0.0872556216719539,"rank":219,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07914638924615114,"rank":219,"remainingConfigurations":398},{"removed":"Cognition","score":0.08275072043495892,"rank":219,"remainingConfigurations":398},{"removed":"LiveBench","score":0.08092455967281724,"rank":218,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08102734434138796,"rank":219,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07966646605763879,"rank":207,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07697963248345528,"rank":219,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0792028135655957,"rank":219,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07912418384526472,"rank":219,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07906634230045155,"rank":219,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07919845348945133,"rank":219,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07898420641107774,"rank":219,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07943991563623796,"rank":219,"remainingConfigurations":398},{"removed":"briefcase","score":0.07898566508028214,"rank":219,"remainingConfigurations":398},{"removed":"aime","score":0.08606751258424562,"rank":216,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07999999758135376,"rank":219,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.08064286720772273,"rank":219,"remainingConfigurations":398},{"removed":"automationbench","score":0.07911650279661754,"rank":219,"remainingConfigurations":398},{"removed":"critpt","score":0.07644440713144517,"rank":227,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07922087859671595,"rank":219,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.08008778239527072,"rank":219,"remainingConfigurations":398},{"removed":"gdpval","score":0.07946450723335008,"rank":219,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07257547949207203,"rank":226,"remainingConfigurations":398},{"removed":"gpqa","score":0.08098174955883726,"rank":220,"remainingConfigurations":398},{"removed":"harvey","score":0.078280215314643,"rank":219,"remainingConfigurations":398},{"removed":"hle","score":0.0862822804840815,"rank":217,"remainingConfigurations":398},{"removed":"ifbench","score":0.07880679446008378,"rank":217,"remainingConfigurations":398},{"removed":"itbench","score":0.0790747036819782,"rank":219,"remainingConfigurations":398},{"removed":"livecodebench","score":0.08060019772675772,"rank":219,"remainingConfigurations":398},{"removed":"math500","score":0.07936817202986511,"rank":220,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08206832980095206,"rank":218,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08457867546267185,"rank":220,"remainingConfigurations":398},{"removed":"omniscience","score":0.07046625585785246,"rank":230,"remainingConfigurations":398},{"removed":"scicode","score":0.08055281900085116,"rank":219,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07811944621189047,"rank":217,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07683557015246303,"rank":223,"remainingConfigurations":398},{"removed":"arc-agi","score":0.09374621011289232,"rank":222,"remainingConfigurations":398},{"removed":"deepswe","score":0.06784334572877014,"rank":219,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07921996272337628,"rank":219,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07865605391071724,"rank":219,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08275072043495892,"rank":219,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07925745179800453,"rank":219,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07849821052479712,"rank":219,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07908159521295278,"rank":219,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0789109217049224,"rank":219,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07932862984418777,"rank":219,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07860108848787441,"rank":219,"remainingConfigurations":398},{"removed":"livebench-language","score":0.08007705533513308,"rank":219,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07934625745318867,"rank":219,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07801595874690052,"rank":219,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07870421072404309,"rank":219,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.08033769673003759,"rank":219,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08102734434138796,"rank":219,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0754021593224,"rank":217,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07991855030482466,"rank":218,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08219123264830885,"rank":219,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07882949067177401,"rank":219,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07893843371593509,"rank":219,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07888793344710732,"rank":219,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07907535911882664,"rank":219,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07869288829483159,"rank":219,"remainingConfigurations":398}]},"amazon-nova-2-lite--effort-high":{"score":0.07878453807867682,"rank":220,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0945435863549965,"rank":220,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06744580854148234,"rank":220,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07807412986590183,"rank":220,"remainingConfigurations":398},{"removed":"Scale","score":0.08686895187310699,"rank":220,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07874105509020768,"rank":220,"remainingConfigurations":398},{"removed":"Cognition","score":0.08232842726210539,"rank":221,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0804782473484896,"rank":219,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.08070356233094732,"rank":220,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0792324725978523,"rank":208,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0765803139939145,"rank":220,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07878881603920791,"rank":220,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0787120003550055,"rank":220,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07865232004115091,"rank":220,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07878453807867682,"rank":220,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07857184919901854,"rank":220,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0789258694134879,"rank":220,"remainingConfigurations":398},{"removed":"briefcase","score":0.07830844559478661,"rank":220,"remainingConfigurations":398},{"removed":"aime","score":0.07462860974759095,"rank":226,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07948513996723149,"rank":220,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07749498547896568,"rank":221,"remainingConfigurations":398},{"removed":"automationbench","score":0.07848568675871272,"rank":220,"remainingConfigurations":398},{"removed":"critpt","score":0.07800450357120987,"rank":222,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07871063920635103,"rank":220,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07946426513401293,"rank":220,"remainingConfigurations":398},{"removed":"gdpval","score":0.08765419256640955,"rank":210,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07942074484101037,"rank":219,"remainingConfigurations":398},{"removed":"gpqa","score":0.07522803126236262,"rank":226,"remainingConfigurations":398},{"removed":"harvey","score":0.07778255091807945,"rank":220,"remainingConfigurations":398},{"removed":"hle","score":0.08281382988665892,"rank":221,"remainingConfigurations":398},{"removed":"ifbench","score":0.07203449449485755,"rank":226,"remainingConfigurations":398},{"removed":"itbench","score":0.0785356517936331,"rank":220,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07859420209103622,"rank":220,"remainingConfigurations":398},{"removed":"math500","score":0.07944908593104354,"rank":219,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0809639650963477,"rank":220,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08599759263989837,"rank":218,"remainingConfigurations":398},{"removed":"omniscience","score":0.07794647657936522,"rank":217,"remainingConfigurations":398},{"removed":"scicode","score":0.07995946226399754,"rank":220,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0767962949900191,"rank":221,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.08338704306073257,"rank":217,"remainingConfigurations":398},{"removed":"arc-agi","score":0.09392388260718443,"rank":221,"remainingConfigurations":398},{"removed":"deepswe","score":0.06749481998603479,"rank":220,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07880602796202392,"rank":220,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07824880007925808,"rank":220,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08232842726210539,"rank":221,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07885730938541753,"rank":220,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07808550830160123,"rank":220,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07867028372785882,"rank":220,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07849649891570963,"rank":220,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07891375801267686,"rank":220,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07819016511215653,"rank":220,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07966048752097271,"rank":220,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07893343386374797,"rank":220,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07760625443654538,"rank":220,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07829151638619906,"rank":220,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0799180242129726,"rank":220,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.08070356233094732,"rank":220,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07489472500698709,"rank":218,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07953628914041903,"rank":219,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08175942977555291,"rank":220,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07841721563258534,"rank":220,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07852598612639516,"rank":220,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0784747467911879,"rank":220,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07866305375390494,"rank":220,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07828111440247418,"rank":220,"remainingConfigurations":398}]},"gpt-5--effort-low":{"score":0.07766638319251114,"rank":221,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.036124687608952655,"rank":146,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.1801545944711752,"rank":155,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06602658981587169,"rank":221,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07731604319496914,"rank":221,"remainingConfigurations":398},{"removed":"Scale","score":0.08516023309017479,"rank":221,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07733915460911599,"rank":221,"remainingConfigurations":398},{"removed":"Cognition","score":0.0823360675971436,"rank":220,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07869917951356976,"rank":221,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07773579379386497,"rank":222,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07551885818327954,"rank":212,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0744377345863863,"rank":222,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07766979133312917,"rank":221,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07755777633343997,"rank":221,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0775664548873319,"rank":221,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07766638319251114,"rank":221,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07745002373651386,"rank":221,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07787625312256054,"rank":221,"remainingConfigurations":398},{"removed":"briefcase","score":0.07774369795438903,"rank":221,"remainingConfigurations":398},{"removed":"aime","score":0.07839285714362716,"rank":221,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07827137187787463,"rank":221,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07862027979698713,"rank":220,"remainingConfigurations":398},{"removed":"automationbench","score":0.07776576353853405,"rank":221,"remainingConfigurations":398},{"removed":"critpt","score":0.07716081383864513,"rank":225,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07774677203905007,"rank":221,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07841596722971428,"rank":221,"remainingConfigurations":398},{"removed":"gdpval","score":0.07846294603991079,"rank":222,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07835503479055163,"rank":220,"remainingConfigurations":398},{"removed":"gpqa","score":0.07826587786846258,"rank":223,"remainingConfigurations":398},{"removed":"harvey","score":0.07682772599191508,"rank":221,"remainingConfigurations":398},{"removed":"hle","score":0.08110455311283765,"rank":224,"remainingConfigurations":398},{"removed":"ifbench","score":0.07610849011615971,"rank":220,"remainingConfigurations":398},{"removed":"itbench","score":0.07757784211858697,"rank":221,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07767376527569667,"rank":221,"remainingConfigurations":398},{"removed":"math500","score":0.07687950241554854,"rank":222,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07915564420202034,"rank":223,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08067890320925603,"rank":224,"remainingConfigurations":398},{"removed":"omniscience","score":0.07231218267488103,"rank":228,"remainingConfigurations":398},{"removed":"scicode","score":0.07882214994344845,"rank":221,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07797331242585943,"rank":218,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07895083460909251,"rank":218,"remainingConfigurations":398},{"removed":"arc-agi","score":0.17926622300312114,"rank":156,"remainingConfigurations":398},{"removed":"deepswe","score":0.06606583548798821,"rank":221,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07768536179431587,"rank":221,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07663642132075864,"rank":221,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0823360675971436,"rank":220,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0777436671021885,"rank":221,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07700079741528902,"rank":221,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07755115206877022,"rank":221,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07737644782686266,"rank":221,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07777987016516348,"rank":221,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07708233202635711,"rank":221,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07849933102072312,"rank":221,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07776167510011552,"rank":221,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07649703303550472,"rank":221,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07720376883493374,"rank":221,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07885906720446735,"rank":221,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07773579379386497,"rank":222,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07221762884935413,"rank":222,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07866613661919282,"rank":220,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08051454502647985,"rank":221,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07730141692955121,"rank":221,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07737912046000323,"rank":221,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07742228992507462,"rank":221,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07749515753009968,"rank":221,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07713430173683855,"rank":221,"remainingConfigurations":398}]},"exaone-4.5-33b--effort-reasoning":{"score":0.07715761996044189,"rank":222,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.09187172144963866,"rank":222,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06598653910885968,"rank":222,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07643916695385537,"rank":222,"remainingConfigurations":398},{"removed":"Scale","score":0.08515661642081557,"rank":222,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07709912683491549,"rank":222,"remainingConfigurations":398},{"removed":"Cognition","score":0.08064005854381784,"rank":222,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07884336172461827,"rank":220,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07902364456207069,"rank":221,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0774798772984424,"rank":210,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07497120528207796,"rank":221,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07716204652132332,"rank":222,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0770871880763291,"rank":222,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07702757066913157,"rank":222,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07715761996044189,"rank":222,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07694956214189362,"rank":222,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07733850055369729,"rank":222,"remainingConfigurations":398},{"removed":"briefcase","score":0.07679131479990527,"rank":222,"remainingConfigurations":398},{"removed":"aime","score":0.077531880471632,"rank":222,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07786627535398853,"rank":222,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07692492509199987,"rank":222,"remainingConfigurations":398},{"removed":"automationbench","score":0.07691916491195096,"rank":222,"remainingConfigurations":398},{"removed":"critpt","score":0.0759501873649089,"rank":229,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07708498895992845,"rank":222,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07787124168322446,"rank":222,"remainingConfigurations":398},{"removed":"gdpval","score":0.0790449503325714,"rank":220,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07770377844378955,"rank":221,"remainingConfigurations":398},{"removed":"gpqa","score":0.07325971354925374,"rank":229,"remainingConfigurations":398},{"removed":"harvey","score":0.07620066121909398,"rank":222,"remainingConfigurations":398},{"removed":"hle","score":0.07989443414902586,"rank":225,"remainingConfigurations":398},{"removed":"ifbench","score":0.07276728118813197,"rank":224,"remainingConfigurations":398},{"removed":"itbench","score":0.07693912493753917,"rank":222,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07716797755713613,"rank":222,"remainingConfigurations":398},{"removed":"math500","score":0.0775444947654511,"rank":221,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0793767845966198,"rank":222,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08083847282730489,"rank":223,"remainingConfigurations":398},{"removed":"omniscience","score":0.08324030650159908,"rank":214,"remainingConfigurations":398},{"removed":"scicode","score":0.0783272707173046,"rank":222,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0733952060802166,"rank":223,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07854037382410156,"rank":220,"remainingConfigurations":398},{"removed":"arc-agi","score":0.09129683704740044,"rank":223,"remainingConfigurations":398},{"removed":"deepswe","score":0.06603448785496051,"rank":222,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07717862368262939,"rank":222,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07663551082217715,"rank":222,"remainingConfigurations":398},{"removed":"frontiercode","score":0.08064005854381784,"rank":222,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07721926925975282,"rank":222,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07647257811752112,"rank":222,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07704453016878957,"rank":222,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07687533779721212,"rank":222,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07728458308425078,"rank":222,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0765732754743057,"rank":222,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07801800870521336,"rank":222,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07730377911888793,"rank":222,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07600062344265458,"rank":222,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07667314928422715,"rank":222,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07827170025436858,"rank":222,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07902364456207069,"rank":221,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07344501563223639,"rank":219,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07788112706962884,"rank":221,"remainingConfigurations":398},{"removed":"simpleqa","score":0.08007432082133394,"rank":222,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07679696061252729,"rank":222,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07690338689597764,"rank":222,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07685311004711932,"rank":222,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07703762742343613,"rank":222,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07666387180785704,"rank":222,"remainingConfigurations":398}]},"claude-haiku-4-5-20251001--effort-reasoning":{"score":0.07549439719779046,"rank":223,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08946569917229182,"rank":224,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0644084567494872,"rank":223,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0747959231405081,"rank":223,"remainingConfigurations":398},{"removed":"Scale","score":0.08327155869514848,"rank":223,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07543419299527367,"rank":223,"remainingConfigurations":398},{"removed":"Cognition","score":0.07872462931513324,"rank":224,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07722925187544463,"rank":222,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07748074101217035,"rank":223,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07685483013812464,"rank":211,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07348096037117363,"rank":223,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07549923484369946,"rank":223,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07542208523621037,"rank":223,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07536414280048004,"rank":223,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07549439719779046,"rank":223,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07528481897874136,"rank":223,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07307280498680664,"rank":227,"remainingConfigurations":398},{"removed":"briefcase","score":0.07394432804726732,"rank":225,"remainingConfigurations":398},{"removed":"aime","score":0.07378198981951097,"rank":228,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07638260803542692,"rank":223,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07192042945407572,"rank":229,"remainingConfigurations":398},{"removed":"automationbench","score":0.07518669472556393,"rank":223,"remainingConfigurations":398},{"removed":"critpt","score":0.07959962876405263,"rank":219,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07463528311376778,"rank":224,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07613563786963971,"rank":223,"remainingConfigurations":398},{"removed":"gdpval","score":0.07445204327295052,"rank":225,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07498427128546532,"rank":224,"remainingConfigurations":398},{"removed":"gpqa","score":0.07653251595550865,"rank":224,"remainingConfigurations":398},{"removed":"harvey","score":0.07457215072543721,"rank":223,"remainingConfigurations":398},{"removed":"hle","score":0.0795250430365514,"rank":226,"remainingConfigurations":398},{"removed":"ifbench","score":0.07236304867433527,"rank":225,"remainingConfigurations":398},{"removed":"itbench","score":0.07465325919453278,"rank":224,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07681296885530892,"rank":223,"remainingConfigurations":398},{"removed":"math500","score":0.07553105792749311,"rank":223,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.08183124347428217,"rank":219,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08342119912615502,"rank":221,"remainingConfigurations":398},{"removed":"omniscience","score":0.07552977917002897,"rank":221,"remainingConfigurations":398},{"removed":"scicode","score":0.07535438140151736,"rank":224,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07450476124075701,"rank":222,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07478738519794535,"rank":225,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08889837422666554,"rank":225,"remainingConfigurations":398},{"removed":"deepswe","score":0.06445851817207109,"rank":223,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07551534034912982,"rank":223,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07499412843170715,"rank":223,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07872462931513324,"rank":224,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07556406161165534,"rank":223,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07482177413957945,"rank":223,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07538577368554093,"rank":223,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07521337287508262,"rank":223,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07561478028507808,"rank":223,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07493594796692028,"rank":223,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07635104340707441,"rank":223,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07562855379228707,"rank":223,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07435281726869615,"rank":223,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07502266621359867,"rank":223,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07657604880681101,"rank":223,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07748074101217035,"rank":223,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07231425876993892,"rank":221,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07612745918763054,"rank":222,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0783491108818321,"rank":223,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0751427739322906,"rank":223,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07524354641165644,"rank":223,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0751935710531458,"rank":223,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07538048096852855,"rank":223,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0750104093345605,"rank":223,"remainingConfigurations":398}]},"glm-4.5--effort-reasoning":{"score":0.07494241889121911,"rank":224,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08952583830665516,"rank":223,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06413999443356129,"rank":224,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07414135245135126,"rank":224,"remainingConfigurations":398},{"removed":"Scale","score":0.08277029996243808,"rank":224,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07490028166701852,"rank":224,"remainingConfigurations":398},{"removed":"Cognition","score":0.078483852392793,"rank":226,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07656552695572542,"rank":224,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07679662722347336,"rank":224,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07523296724257324,"rank":213,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07288270185779687,"rank":224,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07494672196727949,"rank":224,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07487339412374319,"rank":224,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0748180021493995,"rank":224,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07494241889121911,"rank":224,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07474162310587147,"rank":224,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07514106536027619,"rank":223,"remainingConfigurations":398},{"removed":"briefcase","score":0.07478254077693834,"rank":223,"remainingConfigurations":398},{"removed":"aime","score":0.07560233130481943,"rank":225,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07567353510626043,"rank":224,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07541382688383792,"rank":224,"remainingConfigurations":398},{"removed":"automationbench","score":0.0748731595088971,"rank":224,"remainingConfigurations":398},{"removed":"critpt","score":0.08248380823491028,"rank":217,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07497209469251015,"rank":223,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07580058315727256,"rank":224,"remainingConfigurations":398},{"removed":"gdpval","score":0.07534813595154417,"rank":223,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07545402954801451,"rank":223,"remainingConfigurations":398},{"removed":"gpqa","score":0.07227590481885392,"rank":233,"remainingConfigurations":398},{"removed":"harvey","score":0.07406565932818239,"rank":224,"remainingConfigurations":398},{"removed":"hle","score":0.07780427877835365,"rank":227,"remainingConfigurations":398},{"removed":"ifbench","score":0.0763167005640525,"rank":219,"remainingConfigurations":398},{"removed":"itbench","score":0.0747840257339464,"rank":223,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07272674248320253,"rank":227,"remainingConfigurations":398},{"removed":"math500","score":0.07386461367962398,"rank":225,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0733598029133901,"rank":231,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0796368935534423,"rank":225,"remainingConfigurations":398},{"removed":"omniscience","score":0.06716704364034036,"rank":237,"remainingConfigurations":398},{"removed":"scicode","score":0.07623385627662378,"rank":223,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07688964008045075,"rank":220,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07481874445598977,"rank":224,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08892425941529243,"rank":224,"remainingConfigurations":398},{"removed":"deepswe","score":0.06418678974432808,"rank":224,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07496286320656449,"rank":224,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07442560141476394,"rank":224,"remainingConfigurations":398},{"removed":"frontiercode","score":0.078483852392793,"rank":226,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07500034250719585,"rank":224,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07427450680471921,"rank":224,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07483199342294307,"rank":224,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07467085752795062,"rank":224,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07506648032710517,"rank":224,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07437028149491239,"rank":224,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07578044865319863,"rank":224,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0750842385434802,"rank":224,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0738144431938616,"rank":224,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07446982555616168,"rank":224,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0760327106377174,"rank":224,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07679662722347336,"rank":224,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0712530369866365,"rank":224,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07567872070826628,"rank":224,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07781418090072034,"rank":224,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07459070656270718,"rank":225,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07469374829964186,"rank":225,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07464630339805699,"rank":224,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07482414971841712,"rank":224,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0744603992444787,"rank":225,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-none":{"score":0.07423048860584286,"rank":225,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06925534996725623,"rank":133,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0873959354987781,"rank":227,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06330675619450445,"rank":225,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07396618258688277,"rank":225,"remainingConfigurations":398},{"removed":"Scale","score":0.08134560944426167,"rank":225,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07414913492018117,"rank":225,"remainingConfigurations":398},{"removed":"Cognition","score":0.07849788236186714,"rank":225,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07495330151612352,"rank":226,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07548764353794081,"rank":225,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07201466645443706,"rank":225,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07423328945621474,"rank":225,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0741396556947966,"rank":225,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07415627590784457,"rank":225,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07423048860584286,"rank":225,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07405812686862231,"rank":225,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07439590339224021,"rank":224,"remainingConfigurations":398},{"removed":"briefcase","score":0.07417351126194972,"rank":224,"remainingConfigurations":398},{"removed":"aime","score":0.08720911373128958,"rank":214,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07480850621779109,"rank":225,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07459836226052698,"rank":226,"remainingConfigurations":398},{"removed":"automationbench","score":0.0742167100197758,"rank":225,"remainingConfigurations":398},{"removed":"critpt","score":0.0736960404900164,"rank":231,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07430490282306781,"rank":225,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07464749924959356,"rank":225,"remainingConfigurations":398},{"removed":"gdpval","score":0.07383528534391917,"rank":227,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07459197255588682,"rank":225,"remainingConfigurations":398},{"removed":"gpqa","score":0.0875421607219884,"rank":206,"remainingConfigurations":398},{"removed":"harvey","score":0.07340529820697383,"rank":225,"remainingConfigurations":398},{"removed":"hle","score":0.07697193524950885,"rank":228,"remainingConfigurations":398},{"removed":"ifbench","score":0.07455821594516779,"rank":223,"remainingConfigurations":398},{"removed":"itbench","score":0.07411769443653544,"rank":225,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07429615418657108,"rank":225,"remainingConfigurations":398},{"removed":"math500","score":0.07437442802700021,"rank":224,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07651349490885212,"rank":225,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07880796797539863,"rank":226,"remainingConfigurations":398},{"removed":"omniscience","score":0.07405529478021626,"rank":223,"remainingConfigurations":398},{"removed":"scicode","score":0.07498364137861746,"rank":225,"remainingConfigurations":398},{"removed":"tau-bench","score":0.071593546253289,"rank":226,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07385168518623579,"rank":227,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08678615951800807,"rank":228,"remainingConfigurations":398},{"removed":"deepswe","score":0.0633582892624089,"rank":225,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0742480282356065,"rank":225,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07387134409967257,"rank":225,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07849788236186714,"rank":225,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0744502521241871,"rank":225,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07342753792600151,"rank":225,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07414701624340152,"rank":225,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07398319354230275,"rank":225,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07441992637026974,"rank":225,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07347057396176683,"rank":225,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07503657181848973,"rank":225,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07443870236884619,"rank":225,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07318509996975169,"rank":225,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0737451043173881,"rank":225,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07533485099194419,"rank":225,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07548764353794081,"rank":225,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.049302353577284956,"rank":256,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05594984493389938,"rank":253,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07720236009342464,"rank":225,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07387749381575637,"rank":226,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07401881309040027,"rank":226,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07388485529900318,"rank":225,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07412213572136193,"rank":226,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07380414270377356,"rank":226,"remainingConfigurations":398}]},"glm-5--effort-non-reasoning":{"score":0.0736086173457042,"rank":226,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08805338771316397,"rank":225,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06296648828805756,"rank":226,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0729213495813605,"rank":226,"remainingConfigurations":398},{"removed":"Scale","score":0.08134249214727707,"rank":226,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07354594080542916,"rank":226,"remainingConfigurations":398},{"removed":"Cognition","score":0.07704969080795437,"rank":227,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07521775848663959,"rank":225,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07537290847306338,"rank":226,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07436671064285134,"rank":214,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07154499138419403,"rank":226,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07361283781760601,"rank":226,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07354074088979633,"rank":226,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07348604827020579,"rank":226,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0736086173457042,"rank":226,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07341089051352859,"rank":226,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07380746096454739,"rank":225,"remainingConfigurations":398},{"removed":"briefcase","score":0.07330243069279763,"rank":226,"remainingConfigurations":398},{"removed":"aime","score":0.07392091781615363,"rank":227,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0743538985786583,"rank":226,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07648718903683548,"rank":223,"remainingConfigurations":398},{"removed":"automationbench","score":0.07340761350050766,"rank":226,"remainingConfigurations":398},{"removed":"critpt","score":0.08358618878499728,"rank":216,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07362382660552179,"rank":226,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07429135371150017,"rank":226,"remainingConfigurations":398},{"removed":"gdpval","score":0.0736212660804601,"rank":228,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07612361967361446,"rank":222,"remainingConfigurations":398},{"removed":"gpqa","score":0.07962057487846834,"rank":222,"remainingConfigurations":398},{"removed":"harvey","score":0.07276691165580822,"rank":226,"remainingConfigurations":398},{"removed":"hle","score":0.08197437757072108,"rank":222,"remainingConfigurations":398},{"removed":"ifbench","score":0.06977195707249166,"rank":230,"remainingConfigurations":398},{"removed":"itbench","score":0.07350394512926091,"rank":226,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07343698398698074,"rank":226,"remainingConfigurations":398},{"removed":"math500","score":0.07377396817884162,"rank":226,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07555744228554927,"rank":226,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07828717004252675,"rank":227,"remainingConfigurations":398},{"removed":"omniscience","score":0.06781804094232388,"rank":236,"remainingConfigurations":398},{"removed":"scicode","score":0.07472657549283619,"rank":226,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06242271077434233,"rank":239,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06559137034502188,"rank":239,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08747681572347547,"rank":226,"remainingConfigurations":398},{"removed":"deepswe","score":0.06301236618214136,"rank":226,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07362870742204658,"rank":226,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07310109341417606,"rank":226,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07704969080795437,"rank":227,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07366412591919791,"rank":226,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07295619316908931,"rank":226,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0734985910111743,"rank":226,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07334031204062519,"rank":226,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0737309118604327,"rank":226,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07304461228325014,"rank":226,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07443351070946379,"rank":226,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07374840914721702,"rank":226,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07249807587219913,"rank":226,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07314332695375035,"rank":226,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07468304137185643,"rank":226,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07537290847306338,"rank":226,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07012760258062123,"rank":226,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07440587745505602,"rank":225,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07641749403762584,"rank":226,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07326245253672926,"rank":227,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07336356985163077,"rank":227,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07331671050141382,"rank":226,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07349160487451736,"rank":227,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07313420625911672,"rank":227,"remainingConfigurations":398}]},"amazon-nova-2-pro-preview--effort-low":{"score":0.07329467736826006,"rank":227,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0879895358038964,"rank":226,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06274100614469945,"rank":227,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07259171418854367,"rank":227,"remainingConfigurations":398},{"removed":"Scale","score":0.08098441763758833,"rank":227,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07324824876091073,"rank":228,"remainingConfigurations":398},{"removed":"Cognition","score":0.07678230518971822,"rank":228,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07492411859753229,"rank":227,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07523782304032468,"rank":227,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0737801420454849,"rank":216,"remainingConfigurations":381},{"removed":"Vals AI","score":0.07127628565412657,"rank":227,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07329885112219826,"rank":227,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07322627824408033,"rank":227,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07317167449131869,"rank":227,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07329467736826006,"rank":227,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07309598523779189,"rank":227,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07351036044869765,"rank":226,"remainingConfigurations":398},{"removed":"briefcase","score":0.0730557717187462,"rank":227,"remainingConfigurations":398},{"removed":"aime","score":0.07609265012621257,"rank":224,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07404818352540744,"rank":227,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07026254958446738,"rank":231,"remainingConfigurations":398},{"removed":"automationbench","score":0.07314105091854728,"rank":227,"remainingConfigurations":398},{"removed":"critpt","score":0.07911505017832574,"rank":220,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07332337922004774,"rank":227,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07405105759831766,"rank":227,"remainingConfigurations":398},{"removed":"gdpval","score":0.07478942806858027,"rank":224,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0665907348097891,"rank":238,"remainingConfigurations":398},{"removed":"gpqa","score":0.0724105535251383,"rank":231,"remainingConfigurations":398},{"removed":"harvey","score":0.07246038611987789,"rank":227,"remainingConfigurations":398},{"removed":"hle","score":0.08370727536419727,"rank":220,"remainingConfigurations":398},{"removed":"ifbench","score":0.06372375725592928,"rank":236,"remainingConfigurations":398},{"removed":"itbench","score":0.07314356923347426,"rank":227,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07496307585361989,"rank":224,"remainingConfigurations":398},{"removed":"math500","score":0.07347660213532765,"rank":227,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07388204065235598,"rank":227,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.08116354803710792,"rank":222,"remainingConfigurations":398},{"removed":"omniscience","score":0.07337581084565732,"rank":225,"remainingConfigurations":398},{"removed":"scicode","score":0.07448489098479875,"rank":227,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06765357011144461,"rank":233,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0747548503433201,"rank":226,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08738814021760233,"rank":227,"remainingConfigurations":398},{"removed":"deepswe","score":0.06278660050261956,"rank":227,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07331469027924613,"rank":227,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07279039223784255,"rank":227,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07678230518971822,"rank":228,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07336041487426365,"rank":227,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07264809573586777,"rank":227,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07318656570585035,"rank":227,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0730274295121055,"rank":227,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07341634715001437,"rank":227,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07273324217649031,"rank":227,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07411688636891398,"rank":227,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07343405119383703,"rank":227,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07218802995500846,"rank":227,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07283100877670769,"rank":227,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07436469500321276,"rank":227,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07523782304032468,"rank":227,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06974627870854616,"rank":227,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07400662833851758,"rank":227,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07609799057847906,"rank":227,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0729495133888029,"rank":228,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07305068253001608,"rank":228,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07300410556883895,"rank":227,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07317802374875527,"rank":228,"remainingConfigurations":398},{"removed":"vibe-code","score":0.072821800337264,"rank":228,"remainingConfigurations":398}]},"mistral-medium-3.5--effort-high":{"score":0.0722190653459517,"rank":228,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.07355242035949366,"rank":131,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07239304796677605,"rank":247,"remainingConfigurations":398},{"removed":"Datacurve","score":0.060409705303853395,"rank":232,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07235999818019141,"rank":228,"remainingConfigurations":398},{"removed":"Scale","score":0.07943214615456387,"rank":228,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07338848668278404,"rank":227,"remainingConfigurations":398},{"removed":"Cognition","score":0.07968045134768022,"rank":223,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07675381089349508,"rank":223,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07073572791403267,"rank":233,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0713086054295132,"rank":217,"remainingConfigurations":381},{"removed":"Vals AI","score":null,"rank":null,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07221320394351392,"rank":228,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07221545522230412,"rank":228,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07201505216248237,"rank":228,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0722190653459517,"rank":228,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07200083001039838,"rank":228,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0723401878087938,"rank":228,"remainingConfigurations":398},{"removed":"briefcase","score":0.0721614747944929,"rank":228,"remainingConfigurations":398},{"removed":"aime","score":0.07162075800761349,"rank":231,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07236438854008509,"rank":228,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07216329507402765,"rank":227,"remainingConfigurations":398},{"removed":"automationbench","score":0.07224640272569198,"rank":228,"remainingConfigurations":398},{"removed":"critpt","score":0.07229025342122707,"rank":232,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07229345786786466,"rank":228,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07250133906027738,"rank":228,"remainingConfigurations":398},{"removed":"gdpval","score":0.07221617745236857,"rank":229,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07225515540631516,"rank":227,"remainingConfigurations":398},{"removed":"gpqa","score":0.07156954563612962,"rank":234,"remainingConfigurations":398},{"removed":"harvey","score":0.05556511299428759,"rank":252,"remainingConfigurations":398},{"removed":"hle","score":0.07474203801323222,"rank":232,"remainingConfigurations":398},{"removed":"ifbench","score":0.07177714097083135,"rank":227,"remainingConfigurations":398},{"removed":"itbench","score":0.07197258967195898,"rank":228,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07235627660972027,"rank":229,"remainingConfigurations":398},{"removed":"math500","score":0.07224757956061016,"rank":228,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07741964666391898,"rank":224,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07640295466622533,"rank":231,"remainingConfigurations":398},{"removed":"omniscience","score":0.07203126628335274,"rank":229,"remainingConfigurations":398},{"removed":"scicode","score":0.07236874153913118,"rank":229,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07197985664691749,"rank":225,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07884805453268826,"rank":219,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07153398319235985,"rank":247,"remainingConfigurations":398},{"removed":"deepswe","score":0.06049637686433737,"rank":232,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07225068588862077,"rank":228,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0718463830583297,"rank":228,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07968045134768022,"rank":223,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07249418036128313,"rank":228,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07160089582891978,"rank":228,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07218169329655043,"rank":228,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07186941379506331,"rank":228,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07255687719176805,"rank":228,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07163656178486795,"rank":228,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07300376783403843,"rank":228,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07239742075246787,"rank":228,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07104462168430381,"rank":228,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07197039178355676,"rank":228,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07292955852247889,"rank":228,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07073572791403267,"rank":233,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07031223036551483,"rank":225,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07268344043236138,"rank":228,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07401622442376912,"rank":229,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07459429737186374,"rank":224,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07494413063686198,"rank":224,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06997231590748289,"rank":232,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07443321866591963,"rank":225,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07493841721623919,"rank":224,"remainingConfigurations":398}]},"qwen3.5-9b--effort-non-reasoning":{"score":0.07152286835919733,"rank":229,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.08635956105020896,"rank":125,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08582377686350656,"rank":228,"remainingConfigurations":398},{"removed":"Datacurve","score":0.061102480314749276,"rank":228,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07105062985690236,"rank":229,"remainingConfigurations":398},{"removed":"Scale","score":0.078703502166278,"rank":229,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07156777610390089,"rank":229,"remainingConfigurations":398},{"removed":"Cognition","score":0.0756065764062971,"rank":230,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07289378271514384,"rank":228,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07278769671293435,"rank":229,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06175387612703085,"rank":232,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06963842161861837,"rank":228,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07152446736944132,"rank":229,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0714451828290879,"rank":229,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07142440949033065,"rank":229,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07152286835919733,"rank":229,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07133782932617354,"rank":229,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07170219211577239,"rank":229,"remainingConfigurations":398},{"removed":"briefcase","score":0.07128063819699075,"rank":229,"remainingConfigurations":398},{"removed":"aime","score":0.07648621431116025,"rank":223,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07213926262877023,"rank":229,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0720651248806325,"rank":228,"remainingConfigurations":398},{"removed":"automationbench","score":0.07137339416341727,"rank":229,"remainingConfigurations":398},{"removed":"critpt","score":0.06795900309678844,"rank":237,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07153347817946498,"rank":229,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0720621407634393,"rank":229,"remainingConfigurations":398},{"removed":"gdpval","score":0.07134329882568839,"rank":230,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0718953585866382,"rank":228,"remainingConfigurations":398},{"removed":"gpqa","score":0.07055898429719397,"rank":235,"remainingConfigurations":398},{"removed":"harvey","score":0.07066581032742919,"rank":228,"remainingConfigurations":398},{"removed":"hle","score":0.07551538097211784,"rank":230,"remainingConfigurations":398},{"removed":"ifbench","score":0.07548686746313371,"rank":222,"remainingConfigurations":398},{"removed":"itbench","score":0.07137211764009353,"rank":229,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0714218868249018,"rank":230,"remainingConfigurations":398},{"removed":"math500","score":0.07165019184126403,"rank":229,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07341271554761497,"rank":229,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07459389038590283,"rank":234,"remainingConfigurations":398},{"removed":"omniscience","score":0.07587188605854497,"rank":220,"remainingConfigurations":398},{"removed":"scicode","score":0.07242525559819096,"rank":228,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06616298764506452,"rank":236,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07160090356707866,"rank":230,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08534735681330909,"rank":230,"remainingConfigurations":398},{"removed":"deepswe","score":0.06115099772022576,"rank":228,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07154165025013276,"rank":229,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07106247757666456,"rank":229,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0756065764062971,"rank":230,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07163731372909056,"rank":229,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07086008107681646,"rank":229,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07142370987772258,"rank":229,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07125964892361114,"rank":229,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07167728606466219,"rank":229,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07087905431404848,"rank":229,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07232309427818381,"rank":229,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07169091742867675,"rank":229,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07046809759485038,"rank":229,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07106175575430791,"rank":229,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07257851570111658,"rank":229,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07278769671293435,"rank":229,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.05986985603477137,"rank":239,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07213984130291477,"rank":229,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07457231401227135,"rank":228,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07118629643677041,"rank":229,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07129951979187614,"rank":229,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07121049286645598,"rank":228,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07141785412489865,"rank":229,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07108989975472722,"rank":229,"remainingConfigurations":398}]},"hy3-preview--effort-non-reasoning":{"score":0.07113214824333573,"rank":230,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08522013039299703,"rank":231,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06078889674542696,"rank":229,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07045964656405247,"rank":230,"remainingConfigurations":398},{"removed":"Scale","score":0.07851121211375409,"rank":230,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0710615943501398,"rank":230,"remainingConfigurations":398},{"removed":"Cognition","score":0.0743776538733079,"rank":232,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07269204472308663,"rank":229,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07286316926562247,"rank":228,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07107663115077048,"rank":218,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06912182965720842,"rank":229,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07113628222089995,"rank":230,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0710669668699212,"rank":230,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07101312505058092,"rank":230,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07113214824333573,"rank":230,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07094088724909527,"rank":230,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07130157680968285,"rank":230,"remainingConfigurations":398},{"removed":"briefcase","score":0.07077183056138787,"rank":230,"remainingConfigurations":398},{"removed":"aime","score":0.07184447166053025,"rank":230,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07180313126373128,"rank":230,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07494169085094704,"rank":225,"remainingConfigurations":398},{"removed":"automationbench","score":0.0709247115487061,"rank":230,"remainingConfigurations":398},{"removed":"critpt","score":0.06865564367089143,"rank":235,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07112432675936771,"rank":230,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07180990696705399,"rank":230,"remainingConfigurations":398},{"removed":"gdpval","score":0.07110287457828741,"rank":232,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07152536340904873,"rank":229,"remainingConfigurations":398},{"removed":"gpqa","score":0.07238356589959886,"rank":232,"remainingConfigurations":398},{"removed":"harvey","score":0.07026346373835367,"rank":229,"remainingConfigurations":398},{"removed":"hle","score":0.08129781095321009,"rank":223,"remainingConfigurations":398},{"removed":"ifbench","score":0.07019576653178515,"rank":229,"remainingConfigurations":398},{"removed":"itbench","score":0.0709587598173299,"rank":230,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07131597576154013,"rank":231,"remainingConfigurations":398},{"removed":"math500","score":0.07161919122729232,"rank":230,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07339649107885049,"rank":230,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07565079991432193,"rank":232,"remainingConfigurations":398},{"removed":"omniscience","score":0.06423468545845636,"rank":240,"remainingConfigurations":398},{"removed":"scicode","score":0.07223898294294838,"rank":230,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06886451330276369,"rank":230,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06573337543242878,"rank":238,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08468334662047754,"rank":232,"remainingConfigurations":398},{"removed":"deepswe","score":0.060833301161493485,"rank":229,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0711516505681657,"rank":230,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07064420017466935,"rank":230,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0743776538733079,"rank":232,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07119160761179277,"rank":230,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07049651177623588,"rank":230,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07102737299686045,"rank":230,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0708718209421876,"rank":230,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0712506481644303,"rank":230,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07058368354859972,"rank":230,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07193368221711353,"rank":230,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07126963976002104,"rank":230,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.07005360212895224,"rank":230,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07067953749181766,"rank":230,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07217572822664124,"rank":230,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07286316926562247,"rank":228,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06746849042604938,"rank":228,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07161663831688865,"rank":231,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0738626810315945,"rank":230,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07079600964025912,"rank":230,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07089443585717148,"rank":230,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0708485219355433,"rank":229,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07101864996269894,"rank":230,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0706715545029249,"rank":230,"remainingConfigurations":398}]},"amazon-nova-2-lite--effort-medium":{"score":0.0710005072930514,"rank":231,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08565306348749785,"rank":230,"remainingConfigurations":398},{"removed":"Datacurve","score":0.06072068459144575,"rank":230,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0702781124787102,"rank":232,"remainingConfigurations":398},{"removed":"Scale","score":0.07840139867326365,"rank":231,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0709488800091064,"rank":231,"remainingConfigurations":398},{"removed":"Cognition","score":0.07436164630638457,"rank":233,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07256755911532936,"rank":230,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07262814606285163,"rank":230,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.07103382118841774,"rank":219,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06903199110303615,"rank":231,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07100460229652121,"rank":231,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07093420850247435,"rank":231,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.07088133681054724,"rank":231,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0710005072930514,"rank":231,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07080797636687422,"rank":231,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07119918998450726,"rank":231,"remainingConfigurations":398},{"removed":"briefcase","score":0.07071473444628291,"rank":231,"remainingConfigurations":398},{"removed":"aime","score":0.06683533958258195,"rank":237,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07167883838909979,"rank":231,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0690541518860532,"rank":235,"remainingConfigurations":398},{"removed":"automationbench","score":0.07083270853560349,"rank":231,"remainingConfigurations":398},{"removed":"critpt","score":0.07780047098909391,"rank":223,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07101802110316577,"rank":231,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07171844336700342,"rank":231,"remainingConfigurations":398},{"removed":"gdpval","score":0.07100700362073102,"rank":233,"remainingConfigurations":398},{"removed":"gmmlu","score":0.07142569552730343,"rank":230,"remainingConfigurations":398},{"removed":"gpqa","score":0.06859160615434982,"rank":237,"remainingConfigurations":398},{"removed":"harvey","score":0.07015139958006149,"rank":230,"remainingConfigurations":398},{"removed":"hle","score":0.07658306896141794,"rank":229,"remainingConfigurations":398},{"removed":"ifbench","score":0.06369516382522707,"rank":237,"remainingConfigurations":398},{"removed":"itbench","score":0.07079840406941869,"rank":231,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07237893956936833,"rank":228,"remainingConfigurations":398},{"removed":"math500","score":0.07140380810377421,"rank":231,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07355912413603705,"rank":228,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07823087916072913,"rank":228,"remainingConfigurations":398},{"removed":"omniscience","score":0.07009220133044476,"rank":232,"remainingConfigurations":398},{"removed":"scicode","score":0.07216344949246813,"rank":231,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0680021171066946,"rank":231,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07213357824292661,"rank":229,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08507363962166187,"rank":231,"remainingConfigurations":398},{"removed":"deepswe","score":0.06076490143913493,"rank":230,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07101993718970852,"rank":231,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07051055418329324,"rank":231,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07436164630638457,"rank":233,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.07106041384786617,"rank":231,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.07036661060583031,"rank":231,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.07089608939966396,"rank":231,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07074158432970934,"rank":231,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07111879321428845,"rank":231,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.07045315427321254,"rank":231,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07180031128520169,"rank":231,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07113690657905639,"rank":231,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0699239095714498,"rank":231,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.07054895598022883,"rank":231,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07204290110961702,"rank":231,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07262814606285163,"rank":230,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0672881773554989,"rank":229,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07168180403117365,"rank":230,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0737341299145302,"rank":231,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.07066472783308926,"rank":231,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07076298714838132,"rank":231,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.07071796482332139,"rank":230,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07088652075757544,"rank":231,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07054039565393351,"rank":231,"remainingConfigurations":398}]},"gemini-3.1-flash-lite--effort-low":{"score":0.07059500623815736,"rank":232,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0691242327922849,"rank":134,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0857174820419795,"rank":229,"remainingConfigurations":398},{"removed":"Datacurve","score":0.060652132884080556,"rank":231,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.07034476587570936,"rank":231,"remainingConfigurations":398},{"removed":"Scale","score":0.07746446623290174,"rank":232,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.07065599287212743,"rank":232,"remainingConfigurations":398},{"removed":"Cognition","score":0.07590668080826604,"rank":229,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0715867354572723,"rank":231,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07141963285694843,"rank":231,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06905755548338004,"rank":230,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.07059522299966182,"rank":232,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.07050546943611354,"rank":232,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0705236556665297,"rank":232,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.07059500623815736,"rank":232,"remainingConfigurations":398},{"removed":"All provider reports","score":0.07042468292290105,"rank":232,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.07075652864679179,"rank":232,"remainingConfigurations":398},{"removed":"briefcase","score":0.07052775159641737,"rank":232,"remainingConfigurations":398},{"removed":"aime","score":0.09509115819486012,"rank":201,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07114839677919328,"rank":232,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.07099898913342109,"rank":230,"remainingConfigurations":398},{"removed":"automationbench","score":0.07058194548524512,"rank":232,"remainingConfigurations":398},{"removed":"critpt","score":0.07006538542658976,"rank":234,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.07066164690880235,"rank":232,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07100395791809723,"rank":232,"remainingConfigurations":398},{"removed":"gdpval","score":0.07022697655823588,"rank":234,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0709937670318428,"rank":231,"remainingConfigurations":398},{"removed":"gpqa","score":0.08697546208341378,"rank":209,"remainingConfigurations":398},{"removed":"harvey","score":0.06978676845050384,"rank":231,"remainingConfigurations":398},{"removed":"hle","score":0.07336397310252389,"rank":233,"remainingConfigurations":398},{"removed":"ifbench","score":0.07072605952780155,"rank":228,"remainingConfigurations":398},{"removed":"itbench","score":0.07047205100949251,"rank":232,"remainingConfigurations":398},{"removed":"livecodebench","score":0.07068434691074116,"rank":232,"remainingConfigurations":398},{"removed":"math500","score":0.07073001457848709,"rank":232,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07282371444618481,"rank":232,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07497899888633866,"rank":233,"remainingConfigurations":398},{"removed":"omniscience","score":0.07042277824082589,"rank":231,"remainingConfigurations":398},{"removed":"scicode","score":0.07129790566711275,"rank":232,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06796428868929606,"rank":232,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07049486536433197,"rank":231,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08537512538509356,"rank":229,"remainingConfigurations":398},{"removed":"deepswe","score":0.06070324614228648,"rank":231,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.07061223257640237,"rank":232,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.07017907754099155,"rank":232,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07590668080826604,"rank":229,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0707767788713272,"rank":232,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06987901970890771,"rank":232,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.070507755319635,"rank":232,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.07034367592506748,"rank":232,"remainingConfigurations":398},{"removed":"livebench-math","score":0.07078246655555621,"rank":232,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06985114849892272,"rank":232,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07137497514855194,"rank":232,"remainingConfigurations":398},{"removed":"livebench-data","score":0.07078828377977242,"rank":232,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06959614789145165,"rank":232,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0701276570457514,"rank":232,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07166078123631309,"rank":232,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07141963285694843,"rank":231,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03513850463260724,"rank":285,"remainingConfigurations":398},{"removed":"frontiermath","score":0.07431381177855657,"rank":226,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07373007636290253,"rank":232,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0702578816963988,"rank":232,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.07039034056418372,"rank":232,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0702646830974996,"rank":231,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.07049186599900356,"rank":232,"remainingConfigurations":398},{"removed":"vibe-code","score":0.07018656640896692,"rank":232,"remainingConfigurations":398}]},"gemma-4-31b-it--effort-minimal":{"score":0.06956852224286685,"rank":233,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.0715204081785976,"rank":132,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08277393768613084,"rank":233,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05945608050411035,"rank":233,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06931712979387733,"rank":233,"remainingConfigurations":398},{"removed":"Scale","score":0.0762726900582514,"rank":236,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06957009613412098,"rank":233,"remainingConfigurations":398},{"removed":"Cognition","score":0.0746079077124688,"rank":231,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07046567020810401,"rank":234,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07023684484753973,"rank":236,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06791894222893576,"rank":232,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06956793808694298,"rank":233,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06947925928648249,"rank":233,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06949484856525184,"rank":233,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06956852224286685,"rank":233,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0693955115978733,"rank":233,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06973092998958814,"rank":233,"remainingConfigurations":398},{"removed":"briefcase","score":0.069491741310657,"rank":233,"remainingConfigurations":398},{"removed":"aime","score":0.05034523847883717,"rank":262,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07011250177760157,"rank":233,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06990695592836126,"rank":233,"remainingConfigurations":398},{"removed":"automationbench","score":0.06954854365892095,"rank":233,"remainingConfigurations":398},{"removed":"critpt","score":0.06845259329456399,"rank":236,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0696358233975835,"rank":233,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06997336792289903,"rank":234,"remainingConfigurations":398},{"removed":"gdpval","score":0.06925340585569875,"rank":236,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06997970416379004,"rank":232,"remainingConfigurations":398},{"removed":"gpqa","score":0.08240003906281965,"rank":218,"remainingConfigurations":398},{"removed":"harvey","score":0.06876344963619144,"rank":232,"remainingConfigurations":398},{"removed":"hle","score":0.07244214614315621,"rank":234,"remainingConfigurations":398},{"removed":"ifbench","score":0.06957274250020877,"rank":231,"remainingConfigurations":398},{"removed":"itbench","score":0.06944179871064346,"rank":233,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06974272438136235,"rank":233,"remainingConfigurations":398},{"removed":"math500","score":0.06970712034961041,"rank":234,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07180223588738677,"rank":233,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07384371924969525,"rank":235,"remainingConfigurations":398},{"removed":"omniscience","score":0.06943602083323712,"rank":234,"remainingConfigurations":398},{"removed":"scicode","score":0.07025342517366544,"rank":234,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06703057538455498,"rank":235,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06956530333806839,"rank":232,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08240083523939237,"rank":234,"remainingConfigurations":398},{"removed":"deepswe","score":0.0595069391681824,"rank":233,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0695859829223066,"rank":233,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06915155359994339,"rank":233,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0746079077124688,"rank":231,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06974047261903522,"rank":233,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06888397077451833,"rank":233,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06948005578519242,"rank":233,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0693123433034532,"rank":233,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0697640523551059,"rank":233,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06881376134647764,"rank":234,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07034316936061315,"rank":233,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0697512833812539,"rank":233,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06859089743621505,"rank":233,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0691021258743368,"rank":233,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07062922836814413,"rank":233,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07023684484753973,"rank":236,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.07147972779526753,"rank":223,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06849603782045367,"rank":236,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07241171781619898,"rank":233,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06923818081329382,"rank":233,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0693662135109746,"rank":233,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06924142103483007,"rank":233,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06946974237602978,"rank":233,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06916910220710985,"rank":233,"remainingConfigurations":398}]},"gemma-4-31b-it--effort-non-reasoning":{"score":0.06941550185365197,"rank":234,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08292323755265427,"rank":232,"remainingConfigurations":398},{"removed":"Datacurve","score":0.059283144127414145,"rank":234,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06879435705275416,"rank":234,"remainingConfigurations":398},{"removed":"Scale","score":0.07669798260932707,"rank":234,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06934410447925986,"rank":234,"remainingConfigurations":398},{"removed":"Cognition","score":0.07254092230024202,"rank":235,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07097694823735012,"rank":232,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07109534566378507,"rank":232,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06985309074701891,"rank":220,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06744380581294027,"rank":233,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06941942212878831,"rank":234,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06935112986818674,"rank":234,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06929786027695908,"rank":234,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06941550185365197,"rank":234,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06922644011687981,"rank":234,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06958522211958397,"rank":234,"remainingConfigurations":398},{"removed":"briefcase","score":0.0690284421488195,"rank":234,"remainingConfigurations":398},{"removed":"aime","score":0.06994173715730916,"rank":232,"remainingConfigurations":398},{"removed":"apex-agents","score":0.07008137388617573,"rank":234,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0702493258315116,"rank":232,"remainingConfigurations":398},{"removed":"automationbench","score":0.06918985638984902,"rank":234,"remainingConfigurations":398},{"removed":"critpt","score":0.0777904489940943,"rank":224,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06936583293615627,"rank":234,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.07006656096226102,"rank":233,"remainingConfigurations":398},{"removed":"gdpval","score":0.06902169477463926,"rank":237,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06980068431379037,"rank":233,"remainingConfigurations":398},{"removed":"gpqa","score":0.06720828813979567,"rank":241,"remainingConfigurations":398},{"removed":"harvey","score":0.0685212124563942,"rank":233,"remainingConfigurations":398},{"removed":"hle","score":0.07156939800291584,"rank":237,"remainingConfigurations":398},{"removed":"ifbench","score":0.06562309370045058,"rank":233,"remainingConfigurations":398},{"removed":"itbench","score":0.06918382639518328,"rank":234,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06947070064338798,"rank":234,"remainingConfigurations":398},{"removed":"math500","score":0.06976597649385484,"rank":233,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07143182853143072,"rank":235,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06904386214929141,"rank":238,"remainingConfigurations":398},{"removed":"omniscience","score":0.07232941524119335,"rank":227,"remainingConfigurations":398},{"removed":"scicode","score":0.07047500613706974,"rank":233,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0674702112652547,"rank":234,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0661415009005321,"rank":235,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0824165993753479,"rank":233,"remainingConfigurations":398},{"removed":"deepswe","score":0.05932645252848126,"rank":234,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06943469469873949,"rank":234,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06894209285589999,"rank":234,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07254092230024202,"rank":235,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06947799291414082,"rank":234,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06879361517649839,"rank":234,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06931426613382599,"rank":234,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06915981888764214,"rank":234,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06953152290380091,"rank":234,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06887918140684134,"rank":233,"remainingConfigurations":398},{"removed":"livebench-language","score":0.07020116850481158,"rank":234,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06955086522124708,"rank":234,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06835884015352371,"rank":234,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06897212250581171,"rank":234,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07043623293072877,"rank":234,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07109534566378507,"rank":232,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06601980478823027,"rank":230,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0700414806033442,"rank":232,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07208260884844808,"rank":234,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06908592933542314,"rank":234,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06918315881861027,"rank":234,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06913746019029339,"rank":234,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06930484816939318,"rank":234,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06896428973505885,"rank":234,"remainingConfigurations":398}]},"qwen3-next-80b-a3b-thinking--effort-reasoning":{"score":0.06904132691493144,"rank":235,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0824311773232879,"rank":235,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05896106336630747,"rank":235,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06830295729210821,"rank":236,"remainingConfigurations":398},{"removed":"Scale","score":0.0763524813707363,"rank":235,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06898928458554289,"rank":235,"remainingConfigurations":398},{"removed":"Cognition","score":0.07226954391786666,"rank":236,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07056866318761677,"rank":233,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07069157517603336,"rank":234,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0694488927644852,"rank":221,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06710957461266799,"rank":234,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06904519997162382,"rank":235,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06897709307003676,"rank":235,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06892524092468524,"rank":235,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06904132691493144,"rank":235,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06885399966558704,"rank":235,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0691752058005649,"rank":235,"remainingConfigurations":398},{"removed":"briefcase","score":0.06867419004860685,"rank":236,"remainingConfigurations":398},{"removed":"aime","score":0.06612489667378445,"rank":238,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06968355270617191,"rank":235,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06645813760209895,"rank":238,"remainingConfigurations":398},{"removed":"automationbench","score":0.06880510336824172,"rank":236,"remainingConfigurations":398},{"removed":"critpt","score":0.07487969245820857,"rank":230,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06898463170871981,"rank":236,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06963942754589542,"rank":235,"remainingConfigurations":398},{"removed":"gdpval","score":0.07412963293170154,"rank":226,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06954571460000046,"rank":234,"remainingConfigurations":398},{"removed":"gpqa","score":0.06746571733757346,"rank":238,"remainingConfigurations":398},{"removed":"harvey","score":0.06817654597043181,"rank":234,"remainingConfigurations":398},{"removed":"hle","score":0.07155564149297189,"rank":238,"remainingConfigurations":398},{"removed":"ifbench","score":0.06451133938293623,"rank":235,"remainingConfigurations":398},{"removed":"itbench","score":0.06885754453350934,"rank":236,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06485492128302815,"rank":238,"remainingConfigurations":398},{"removed":"math500","score":0.06921382328073053,"rank":236,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06895283358310834,"rank":237,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0734094635255788,"rank":236,"remainingConfigurations":398},{"removed":"omniscience","score":0.06708859050660375,"rank":238,"remainingConfigurations":398},{"removed":"scicode","score":0.07003906541090209,"rank":235,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07026381088159711,"rank":228,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.07290834744741628,"rank":228,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08187197938203601,"rank":236,"remainingConfigurations":398},{"removed":"deepswe","score":0.05900456147287625,"rank":235,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06906052477060952,"rank":235,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06856630715820408,"rank":235,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07226954391786666,"rank":236,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0690968835698534,"rank":235,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0684198551833149,"rank":235,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06894007743896247,"rank":235,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06878801636269753,"rank":235,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06915695373214238,"rank":235,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.068508610616008,"rank":235,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06982364268549963,"rank":235,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06917426995059811,"rank":235,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06798907889398874,"rank":235,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06860058806615747,"rank":235,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0700573444559574,"rank":235,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07069157517603336,"rank":234,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06563669821321648,"rank":231,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06969785875187545,"rank":234,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07170726180854971,"rank":235,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06871303646081399,"rank":235,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06880965202865248,"rank":235,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06876489961048277,"rank":235,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06893137731375339,"rank":235,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06859184431550112,"rank":235,"remainingConfigurations":398}]},"gpt-5.4-nano--effort-medium":{"score":0.06895178791295713,"rank":236,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.035473369859279215,"rank":149,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12607641292498162,"rank":185,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05859079269071459,"rank":237,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06869162187709253,"rank":235,"remainingConfigurations":398},{"removed":"Scale","score":0.07582307010884959,"rank":238,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06866430879723881,"rank":237,"remainingConfigurations":398},{"removed":"Cognition","score":0.07318232640175344,"rank":234,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07015585460451627,"rank":236,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06905711890820908,"rank":237,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0672980112229573,"rank":224,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06620292252909118,"rank":236,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06895500719670389,"rank":236,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06885771594270058,"rank":236,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06886030340769775,"rank":236,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06895178791295713,"rank":236,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06875918992114277,"rank":236,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06913668142925022,"rank":236,"remainingConfigurations":398},{"removed":"briefcase","score":0.06892609467399866,"rank":235,"remainingConfigurations":398},{"removed":"aime","score":0.0697584150244718,"rank":233,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06951232084865276,"rank":236,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06740171860453434,"rank":237,"remainingConfigurations":398},{"removed":"automationbench","score":0.06896915799495208,"rank":235,"remainingConfigurations":398},{"removed":"critpt","score":0.06465795335468108,"rank":241,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06899061661076257,"rank":235,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06958698353804747,"rank":236,"remainingConfigurations":398},{"removed":"gdpval","score":0.06957710813407446,"rank":235,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06949011298729972,"rank":235,"remainingConfigurations":398},{"removed":"gpqa","score":0.06970733773952104,"rank":236,"remainingConfigurations":398},{"removed":"harvey","score":0.06817262520838036,"rank":235,"remainingConfigurations":398},{"removed":"hle","score":0.07093237243464424,"rank":239,"remainingConfigurations":398},{"removed":"ifbench","score":0.0657810175567018,"rank":232,"remainingConfigurations":398},{"removed":"itbench","score":0.06885764391826364,"rank":235,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06940873397114926,"rank":235,"remainingConfigurations":398},{"removed":"math500","score":0.06936278717857843,"rank":235,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07149249719944945,"rank":234,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07744337442100445,"rank":229,"remainingConfigurations":398},{"removed":"omniscience","score":0.06697427745225212,"rank":239,"remainingConfigurations":398},{"removed":"scicode","score":0.0699699943598503,"rank":236,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07020711519843292,"rank":229,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06717407331234172,"rank":234,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1253838691028102,"rank":186,"remainingConfigurations":398},{"removed":"deepswe","score":0.05862651446118714,"rank":237,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06896901543515775,"rank":236,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06818308082516285,"rank":237,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07318232640175344,"rank":234,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06902141820751194,"rank":236,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06835427483061025,"rank":236,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06884953623178203,"rank":236,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06869222176081848,"rank":236,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06906164782108579,"rank":236,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0684085142016594,"rank":236,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06969440975832733,"rank":236,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06905357234785271,"rank":236,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0678992170826522,"rank":236,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06853016909712589,"rank":236,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.07003435342560811,"rank":236,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06905711890820908,"rank":237,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06410430543691636,"rank":233,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06984220050935691,"rank":233,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07153429899874138,"rank":236,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06862243789059362,"rank":236,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06870933975236998,"rank":236,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06871020542004856,"rank":236,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06881214178968241,"rank":236,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06848015843947826,"rank":236,"remainingConfigurations":398}]},"gemma-4-12b-it--effort-reasoning":{"score":0.06873894909681973,"rank":237,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08250216256108485,"rank":234,"remainingConfigurations":398},{"removed":"Datacurve","score":0.058754610078119836,"rank":236,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06814268038055225,"rank":237,"remainingConfigurations":398},{"removed":"Scale","score":0.07599663297640488,"rank":237,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.068680844973431,"rank":236,"remainingConfigurations":398},{"removed":"Cognition","score":0.07193239500352598,"rank":237,"remainingConfigurations":398},{"removed":"LiveBench","score":0.07029623802651001,"rank":235,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.07049130155816458,"rank":235,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06921021752855909,"rank":222,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06681716487072083,"rank":235,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06874288023753498,"rank":237,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06867555965379904,"rank":237,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06862235927383971,"rank":237,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06873894909681973,"rank":237,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0685520141158121,"rank":237,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06891423441194848,"rank":237,"remainingConfigurations":398},{"removed":"briefcase","score":0.06837708822697781,"rank":237,"remainingConfigurations":398},{"removed":"aime","score":0.06922487223369629,"rank":234,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06939942939100689,"rank":237,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06549472533593016,"rank":240,"remainingConfigurations":398},{"removed":"automationbench","score":0.06851759886025884,"rank":237,"remainingConfigurations":398},{"removed":"critpt","score":0.07633378775563986,"rank":228,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06869965695872836,"rank":237,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06937953089056685,"rank":237,"remainingConfigurations":398},{"removed":"gdpval","score":0.07133282761208816,"rank":231,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06917592623138803,"rank":236,"remainingConfigurations":398},{"removed":"gpqa","score":0.06736475276858296,"rank":240,"remainingConfigurations":398},{"removed":"harvey","score":0.06787928237442645,"rank":236,"remainingConfigurations":398},{"removed":"hle","score":0.06831210053656159,"rank":241,"remainingConfigurations":398},{"removed":"ifbench","score":0.05800667675035063,"rank":245,"remainingConfigurations":398},{"removed":"itbench","score":0.0684986859529414,"rank":237,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06882977615415006,"rank":236,"remainingConfigurations":398},{"removed":"math500","score":0.06901009467269678,"rank":237,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.07077405180696512,"rank":236,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06968285919386906,"rank":237,"remainingConfigurations":398},{"removed":"omniscience","score":0.07389774692099793,"rank":224,"remainingConfigurations":398},{"removed":"scicode","score":0.0698099083072518,"rank":237,"remainingConfigurations":398},{"removed":"tau-bench","score":0.07109319400378286,"rank":227,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06908557522095203,"rank":233,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0819496741087274,"rank":235,"remainingConfigurations":398},{"removed":"deepswe","score":0.05879763450260075,"rank":236,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06875796474174158,"rank":237,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06827082012411505,"rank":236,"remainingConfigurations":398},{"removed":"frontiercode","score":0.07193239500352598,"rank":237,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06880702660278026,"rank":237,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06812757600098941,"rank":237,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06863892335447755,"rank":237,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06848542136854542,"rank":237,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06885390589356201,"rank":237,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06820733776984868,"rank":237,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0695183186663897,"rank":237,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06887305338165652,"rank":237,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06769103123546676,"rank":237,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06829929912100507,"rank":237,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06975104683931488,"rank":237,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.07049130155816458,"rank":235,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0652936716565367,"rank":232,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06939581865863338,"rank":235,"remainingConfigurations":398},{"removed":"simpleqa","score":0.07138309549469775,"rank":237,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06841222307564995,"rank":237,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06850844813304391,"rank":237,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06846321806310256,"rank":237,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06862921063892936,"rank":237,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06829167329282518,"rank":237,"remainingConfigurations":398}]},"gpt-5.6-luna--effort-non-reasoning":{"score":0.0669094362917369,"rank":238,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07982553197853602,"rank":238,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05712174756453283,"rank":238,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06629024025137109,"rank":238,"remainingConfigurations":398},{"removed":"Scale","score":0.07390556313222384,"rank":239,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06683087227039493,"rank":238,"remainingConfigurations":398},{"removed":"Cognition","score":0.06986115263464583,"rank":238,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06847240796490354,"rank":237,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06858195308314745,"rank":238,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06737368000551948,"rank":223,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06501103025605248,"rank":237,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06691293660717224,"rank":238,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06684542182145743,"rank":238,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06679390794765479,"rank":238,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0669094362917369,"rank":238,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06672276639797388,"rank":238,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06714274011687715,"rank":238,"remainingConfigurations":398},{"removed":"briefcase","score":0.06415845116965371,"rank":239,"remainingConfigurations":398},{"removed":"aime","score":0.06700464606331145,"rank":236,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0677090265077858,"rank":238,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06935504016469209,"rank":234,"remainingConfigurations":398},{"removed":"automationbench","score":0.06708777322427291,"rank":238,"remainingConfigurations":398},{"removed":"critpt","score":0.06435237227348459,"rank":242,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06707626869930343,"rank":238,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06796827947925299,"rank":238,"remainingConfigurations":398},{"removed":"gdpval","score":0.062155329938014085,"rank":244,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06729185560659875,"rank":237,"remainingConfigurations":398},{"removed":"gpqa","score":0.07452191092187185,"rank":228,"remainingConfigurations":398},{"removed":"harvey","score":0.06617475443200281,"rank":237,"remainingConfigurations":398},{"removed":"hle","score":0.07485119921815607,"rank":231,"remainingConfigurations":398},{"removed":"ifbench","score":0.06486055148601921,"rank":234,"remainingConfigurations":398},{"removed":"itbench","score":0.06688210812813666,"rank":238,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06674033006188157,"rank":237,"remainingConfigurations":398},{"removed":"math500","score":0.0671636711788946,"rank":238,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06867772668817039,"rank":238,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.07709175921889998,"rank":230,"remainingConfigurations":398},{"removed":"omniscience","score":0.05612349472439097,"rank":251,"remainingConfigurations":398},{"removed":"scicode","score":0.06842648425428624,"rank":238,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06503107751149813,"rank":237,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0659589974491866,"rank":237,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07931639017058714,"rank":238,"remainingConfigurations":398},{"removed":"deepswe","score":0.05716398352395997,"rank":238,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06692828138072775,"rank":238,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06645391707385273,"rank":238,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06986115263464583,"rank":238,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06697574247651795,"rank":238,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0663089738020111,"rank":238,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06681258914894832,"rank":238,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06666042820376662,"rank":238,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06702123400643747,"rank":238,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0663907635283074,"rank":238,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06767219167531019,"rank":238,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06704309160003256,"rank":238,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06588409110977955,"rank":238,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06647918563075295,"rank":238,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06789686231169804,"rank":238,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06858195308314745,"rank":238,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.063746010954224,"rank":234,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06757472861190181,"rank":237,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06948659111300072,"rank":238,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06658971320775746,"rank":238,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06668529076727715,"rank":238,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0666394370948363,"rank":238,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06680362064886196,"rank":238,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06647177948199205,"rank":238,"remainingConfigurations":398}]},"glm-4.7-flash--effort-reasoning":{"score":0.06465097479270353,"rank":239,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07753599829873425,"rank":239,"remainingConfigurations":398},{"removed":"Datacurve","score":0.055218110582346214,"rank":239,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06403885635075829,"rank":239,"remainingConfigurations":398},{"removed":"Scale","score":0.07162319585441217,"rank":240,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06458965724899667,"rank":239,"remainingConfigurations":398},{"removed":"Cognition","score":0.06772954863767379,"rank":239,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06612341780645731,"rank":238,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06647624343853749,"rank":239,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06523630331816872,"rank":225,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06285612779444406,"rank":238,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06465477990568455,"rank":239,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06459127285284078,"rank":239,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06454196725423621,"rank":239,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06465097479270353,"rank":239,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06447576135710709,"rank":239,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06484302776665747,"rank":239,"remainingConfigurations":398},{"removed":"briefcase","score":0.06437121462820729,"rank":238,"remainingConfigurations":398},{"removed":"aime","score":0.0648922888895805,"rank":240,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06536214375225728,"rank":239,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06802084118917301,"rank":236,"remainingConfigurations":398},{"removed":"automationbench","score":0.06445662371344962,"rank":240,"remainingConfigurations":398},{"removed":"critpt","score":0.06161610119347913,"rank":246,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06468104533612362,"rank":239,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0652732576286144,"rank":240,"remainingConfigurations":398},{"removed":"gdpval","score":0.06465750847310035,"rank":239,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06514741034063755,"rank":239,"remainingConfigurations":398},{"removed":"gpqa","score":0.07482589918650946,"rank":227,"remainingConfigurations":398},{"removed":"harvey","score":0.06388058261031448,"rank":238,"remainingConfigurations":398},{"removed":"hle","score":0.07219605089783938,"rank":236,"remainingConfigurations":398},{"removed":"ifbench","score":0.057477672659667946,"rank":246,"remainingConfigurations":398},{"removed":"itbench","score":0.06451460492754267,"rank":239,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0644694359812021,"rank":239,"remainingConfigurations":398},{"removed":"math500","score":0.0648530515480351,"rank":239,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06632472139162854,"rank":239,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06893880794395017,"rank":240,"remainingConfigurations":398},{"removed":"omniscience","score":0.069359695207932,"rank":235,"remainingConfigurations":398},{"removed":"scicode","score":0.06565830522466759,"rank":239,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05101913475566112,"rank":258,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0634397506355358,"rank":241,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07700160412197096,"rank":239,"remainingConfigurations":398},{"removed":"deepswe","score":0.05525871317782724,"rank":239,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06466890621327495,"rank":239,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06420596268150762,"rank":239,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06772954863767379,"rank":239,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06471183524629229,"rank":239,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06407198439747915,"rank":239,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06455583754652358,"rank":239,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06441285119128189,"rank":239,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0647599830658095,"rank":239,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06414502044628759,"rank":239,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06538884286462333,"rank":239,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0647783439759982,"rank":239,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.063658252440098,"rank":239,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06423391786264493,"rank":239,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06561339056088876,"rank":239,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06647624343853749,"rank":239,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.061537105980955305,"rank":235,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06535245169937022,"rank":239,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06716392092888579,"rank":239,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06434147249633224,"rank":239,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0644319128105118,"rank":239,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06439003805689807,"rank":239,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06454567731151432,"rank":239,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06422708178999327,"rank":239,"remainingConfigurations":398}]},"qwen3.5-4b--effort-reasoning":{"score":0.06380973906523132,"rank":240,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0766257267410937,"rank":240,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05446694706764545,"rank":240,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0632208707638713,"rank":240,"remainingConfigurations":398},{"removed":"Scale","score":0.07061905164912582,"rank":242,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06373995839882386,"rank":241,"remainingConfigurations":398},{"removed":"Cognition","score":0.0667925278575585,"rank":241,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06527771558782548,"rank":240,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06548457084932625,"rank":240,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06418543236483587,"rank":228,"remainingConfigurations":381},{"removed":"Vals AI","score":0.06200960154917187,"rank":240,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06381340750869911,"rank":240,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0637500284329148,"rank":240,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06370106159391477,"rank":240,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06380973906523132,"rank":240,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06363482283943982,"rank":240,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06399904003754787,"rank":240,"remainingConfigurations":398},{"removed":"briefcase","score":0.06348528598387874,"rank":241,"remainingConfigurations":398},{"removed":"aime","score":0.06418357948741683,"rank":241,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06443789893986082,"rank":241,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06023309933306755,"rank":245,"remainingConfigurations":398},{"removed":"automationbench","score":0.06360809955517079,"rank":242,"remainingConfigurations":398},{"removed":"critpt","score":0.07139010498622436,"rank":233,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0637902910014762,"rank":240,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06441109015890982,"rank":241,"remainingConfigurations":398},{"removed":"gdpval","score":0.06362042663708901,"rank":241,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06414591607216931,"rank":240,"remainingConfigurations":398},{"removed":"gpqa","score":0.06034958613264565,"rank":247,"remainingConfigurations":398},{"removed":"harvey","score":0.06301069842367758,"rank":239,"remainingConfigurations":398},{"removed":"hle","score":0.06761257241118687,"rank":242,"remainingConfigurations":398},{"removed":"ifbench","score":0.05999140728867386,"rank":242,"remainingConfigurations":398},{"removed":"itbench","score":0.06358431824528185,"rank":241,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06383040128599714,"rank":240,"remainingConfigurations":398},{"removed":"math500","score":0.06404988713569386,"rank":241,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06565272549332546,"rank":240,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06724829843261015,"rank":244,"remainingConfigurations":398},{"removed":"omniscience","score":0.06965485671797221,"rank":233,"remainingConfigurations":398},{"removed":"scicode","score":0.06482383624522317,"rank":240,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05714357606187611,"rank":249,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06371922076009373,"rank":240,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07611636377380403,"rank":240,"remainingConfigurations":398},{"removed":"deepswe","score":0.05450693436348703,"rank":240,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06382751409511284,"rank":240,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06337181025587091,"rank":241,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0667925278575585,"rank":241,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06387029698451531,"rank":240,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06323732716163127,"rank":240,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06371632440137424,"rank":240,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06357404349153088,"rank":240,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06391753194334428,"rank":240,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06331025976342557,"rank":240,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0645395128763316,"rank":240,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06393587335972835,"rank":240,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0628280979130537,"rank":240,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06339749677712272,"rank":240,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06476026228794804,"rank":240,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06548457084932625,"rank":240,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.06066991723298725,"rank":238,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06443366358729845,"rank":240,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06629124577937998,"rank":240,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06350344256418837,"rank":240,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.063593457451723,"rank":240,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06355166232795856,"rank":240,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06370587120254534,"rank":240,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0633905106056775,"rank":240,"remainingConfigurations":398}]},"command-a-plus-05-2026--effort-reasoning":{"score":0.06380291792130503,"rank":241,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07589102057518517,"rank":242,"remainingConfigurations":398},{"removed":"Datacurve","score":0.054349144923966246,"rank":241,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06321627248646637,"rank":241,"remainingConfigurations":398},{"removed":"Scale","score":0.07063317995999387,"rank":241,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06374936283786826,"rank":240,"remainingConfigurations":398},{"removed":"Cognition","score":0.0666290157574201,"rank":242,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06528460118149246,"rank":239,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06543569201333643,"rank":241,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06481873284026701,"rank":226,"remainingConfigurations":381},{"removed":"Vals AI","score":0.062062528662319406,"rank":239,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0638063928615323,"rank":241,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.063743334758904,"rank":241,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06369243598488943,"rank":241,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06380291792130503,"rank":241,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06362610420562863,"rank":241,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06394089044496842,"rank":241,"remainingConfigurations":398},{"removed":"briefcase","score":0.06409056718456128,"rank":240,"remainingConfigurations":398},{"removed":"aime","score":0.06386809450701228,"rank":242,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06448481373395919,"rank":240,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06419576888693301,"rank":241,"remainingConfigurations":398},{"removed":"automationbench","score":0.06387348563311192,"rank":241,"remainingConfigurations":398},{"removed":"critpt","score":0.061896306037648625,"rank":245,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06374883418649357,"rank":241,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06772586069224845,"rank":239,"remainingConfigurations":398},{"removed":"gdpval","score":0.06374655997525565,"rank":240,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06411255239054504,"rank":241,"remainingConfigurations":398},{"removed":"gpqa","score":0.061520259772916336,"rank":244,"remainingConfigurations":398},{"removed":"harvey","score":0.06296102074955383,"rank":240,"remainingConfigurations":398},{"removed":"hle","score":0.06564228035914245,"rank":245,"remainingConfigurations":398},{"removed":"ifbench","score":0.05447402167175248,"rank":251,"remainingConfigurations":398},{"removed":"itbench","score":0.06363740295304438,"rank":240,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06362830339793137,"rank":241,"remainingConfigurations":398},{"removed":"math500","score":0.06407711006745301,"rank":240,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0655763386136189,"rank":241,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0689632291231281,"rank":239,"remainingConfigurations":398},{"removed":"omniscience","score":0.07330600543774884,"rank":226,"remainingConfigurations":398},{"removed":"scicode","score":0.06481815962702926,"rank":241,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06189149417272577,"rank":240,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06183452541293485,"rank":245,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07538233990271793,"rank":243,"remainingConfigurations":398},{"removed":"deepswe","score":0.05439020770356795,"rank":241,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06382131633834903,"rank":241,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06338041908343582,"rank":240,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0666290157574201,"rank":242,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.063862443697469,"rank":241,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06322087438305436,"rank":241,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06371220355758976,"rank":241,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06356420253387572,"rank":241,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06390927364441444,"rank":241,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.063310120003939,"rank":241,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06453927222405773,"rank":241,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06392836169654177,"rank":241,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06281678529819477,"rank":241,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06339083354025642,"rank":241,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06474657828621463,"rank":241,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06543569201333643,"rank":241,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.060915677753345776,"rank":236,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0643639377068479,"rank":241,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06627341646727251,"rank":241,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06349573193787748,"rank":241,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06358744368527691,"rank":241,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06354345489885124,"rank":241,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06370282614318822,"rank":241,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06338241088020515,"rank":241,"remainingConfigurations":398}]},"grok-4.3--effort-non-reasoning":{"score":0.06361649252819462,"rank":242,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07584980497024042,"rank":243,"remainingConfigurations":398},{"removed":"Datacurve","score":0.054217290631032505,"rank":242,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0630553992116991,"rank":242,"remainingConfigurations":398},{"removed":"Scale","score":0.07045573231616141,"rank":243,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.063541612614132,"rank":242,"remainingConfigurations":398},{"removed":"Cognition","score":0.06637453600293013,"rank":243,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0651310386510609,"rank":241,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06530366005409562,"rank":242,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0644755895416441,"rank":227,"remainingConfigurations":381},{"removed":"Vals AI","score":0.061820076410228464,"rank":241,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06361996879061893,"rank":242,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06355665360209593,"rank":242,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06350596915961192,"rank":242,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06361649252819462,"rank":242,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06343938769910223,"rank":242,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06381609574094856,"rank":242,"remainingConfigurations":398},{"removed":"briefcase","score":0.05963406604810248,"rank":248,"remainingConfigurations":398},{"removed":"aime","score":0.06374818366348348,"rank":244,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06439379728992163,"rank":242,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06594702374917277,"rank":239,"remainingConfigurations":398},{"removed":"automationbench","score":0.06583235840112886,"rank":239,"remainingConfigurations":398},{"removed":"critpt","score":0.06769887030529019,"rank":239,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06370039921165865,"rank":242,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06410735720495041,"rank":242,"remainingConfigurations":398},{"removed":"gdpval","score":0.05826469289695,"rank":250,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06399317234226795,"rank":242,"remainingConfigurations":398},{"removed":"gpqa","score":0.06573149048291725,"rank":242,"remainingConfigurations":398},{"removed":"harvey","score":0.06288946875300087,"rank":241,"remainingConfigurations":398},{"removed":"hle","score":0.06927915431479431,"rank":240,"remainingConfigurations":398},{"removed":"ifbench","score":0.06123863066106817,"rank":240,"remainingConfigurations":398},{"removed":"itbench","score":0.06351935444470029,"rank":242,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06354928734359495,"rank":242,"remainingConfigurations":398},{"removed":"math500","score":0.06387706404731587,"rank":242,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06547735803820419,"rank":242,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06738271846073321,"rank":243,"remainingConfigurations":398},{"removed":"omniscience","score":0.059893274381672905,"rank":244,"remainingConfigurations":398},{"removed":"scicode","score":0.06413023293200718,"rank":242,"remainingConfigurations":398},{"removed":"tau-bench","score":0.061771580327847464,"rank":241,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06257894195032142,"rank":244,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0754055019127592,"rank":242,"remainingConfigurations":398},{"removed":"deepswe","score":0.05425772816950301,"rank":242,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06363483703972717,"rank":242,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06319366321901665,"rank":242,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06637453600293013,"rank":243,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06368727541268819,"rank":242,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06304478249546559,"rank":242,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0635258964862393,"rank":242,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06337772679638294,"rank":242,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06372272599991534,"rank":242,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0631212504753274,"rank":242,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06435006365448342,"rank":242,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06374418862409316,"rank":242,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06263313939085148,"rank":242,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06320416677766777,"rank":242,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06456094831368989,"rank":242,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06530366005409562,"rank":242,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.060681966030917626,"rank":237,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06410812210051946,"rank":242,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06607392174251442,"rank":242,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06330880628527907,"rank":242,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06340197992367523,"rank":242,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06335884344808725,"rank":242,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06351497412252201,"rank":242,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06319537187314542,"rank":242,"remainingConfigurations":398}]},"qwen3-vl-32b-thinking--effort-reasoning":{"score":0.0627221293081783,"rank":243,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07514171034713478,"rank":244,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05351280672514885,"rank":244,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06201086416351186,"rank":244,"remainingConfigurations":398},{"removed":"Scale","score":0.06947543469651553,"rank":244,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06266802839651148,"rank":244,"remainingConfigurations":398},{"removed":"Cognition","score":0.06575348545930702,"rank":244,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06413705521816522,"rank":242,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06429277829651037,"rank":243,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06295540628477266,"rank":229,"remainingConfigurations":381},{"removed":"Vals AI","score":0.060977097192172,"rank":243,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06272584171717495,"rank":243,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06266327066887534,"rank":243,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06261576244928155,"rank":244,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0627221293081783,"rank":243,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06255059832429555,"rank":243,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06288229364168359,"rank":243,"remainingConfigurations":398},{"removed":"briefcase","score":0.06249484076046691,"rank":243,"remainingConfigurations":398},{"removed":"aime","score":0.05883263160823898,"rank":247,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06334048533576851,"rank":243,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06132434016798254,"rank":243,"remainingConfigurations":398},{"removed":"automationbench","score":0.06260692742847597,"rank":244,"remainingConfigurations":398},{"removed":"critpt","score":0.06772119614649945,"rank":238,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06271055951305896,"rank":244,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06338042156989136,"rank":243,"remainingConfigurations":398},{"removed":"gdpval","score":0.06298250023124234,"rank":242,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06322669706081581,"rank":243,"remainingConfigurations":398},{"removed":"gpqa","score":0.06219328606310184,"rank":243,"remainingConfigurations":398},{"removed":"harvey","score":0.06196262278850879,"rank":243,"remainingConfigurations":398},{"removed":"hle","score":0.06649191245369508,"rank":243,"remainingConfigurations":398},{"removed":"ifbench","score":0.05822212658994428,"rank":244,"remainingConfigurations":398},{"removed":"itbench","score":0.06259290432925808,"rank":243,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05987767618825157,"rank":246,"remainingConfigurations":398},{"removed":"math500","score":0.06292183758409184,"rank":243,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06294501949204354,"rank":245,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06765482141003129,"rank":242,"remainingConfigurations":398},{"removed":"omniscience","score":0.06210313360008019,"rank":243,"remainingConfigurations":398},{"removed":"scicode","score":0.06376266894773155,"rank":243,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06249413995809353,"rank":238,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06613812557778492,"rank":236,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07461879332764254,"rank":244,"remainingConfigurations":398},{"removed":"deepswe","score":0.053552247663003705,"rank":244,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06273956930111235,"rank":243,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.062288536359489284,"rank":244,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06575348545930702,"rank":244,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06277428637694972,"rank":244,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.06215397686643693,"rank":243,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06262991703728192,"rank":243,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.062491870693285136,"rank":243,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06282834256210185,"rank":244,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.062229882359822734,"rank":243,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06344064441748148,"rank":243,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0628450369573736,"rank":244,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.061755596497091975,"rank":244,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06231629050243994,"rank":243,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06365964186964583,"rank":243,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06429277829651037,"rank":243,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.059584104633211434,"rank":240,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06334567786067241,"rank":243,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06518063427005934,"rank":244,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06242047345529703,"rank":243,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06250857354448504,"rank":244,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.062468468243875086,"rank":243,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06261905534978986,"rank":243,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06230936529797317,"rank":244,"remainingConfigurations":398}]},"gemini-3.1-flash-lite--effort-minimal":{"score":0.06269597405272669,"rank":244,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.06237337314589327,"rank":136,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07621322047552397,"rank":241,"remainingConfigurations":398},{"removed":"Datacurve","score":0.053919549821963675,"rank":243,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06246413004750964,"rank":243,"remainingConfigurations":398},{"removed":"Scale","score":0.06894951517560564,"rank":245,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06276298167899207,"rank":243,"remainingConfigurations":398},{"removed":"Cognition","score":0.06766086399481089,"rank":240,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06369225742145439,"rank":243,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0634661550984096,"rank":244,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.061307778611773465,"rank":242,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06269639504161499,"rank":244,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06261668716511735,"rank":244,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06263106475488546,"rank":243,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06269597405272669,"rank":244,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06254344180152445,"rank":244,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06284255069633128,"rank":244,"remainingConfigurations":398},{"removed":"briefcase","score":0.06263755796284781,"rank":242,"remainingConfigurations":398},{"removed":"aime","score":0.088025359744533,"rank":212,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06320036998210433,"rank":244,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06306811833116195,"rank":242,"remainingConfigurations":398},{"removed":"automationbench","score":0.06268721764239056,"rank":243,"remainingConfigurations":398},{"removed":"critpt","score":0.06217912422145317,"rank":244,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06275674321192695,"rank":243,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06306764785235035,"rank":244,"remainingConfigurations":398},{"removed":"gdpval","score":0.06237206077930955,"rank":243,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06306580507789745,"rank":244,"remainingConfigurations":398},{"removed":"gpqa","score":0.07593597015165178,"rank":225,"remainingConfigurations":398},{"removed":"harvey","score":0.061969838005373035,"rank":242,"remainingConfigurations":398},{"removed":"hle","score":0.06522564786740569,"rank":246,"remainingConfigurations":398},{"removed":"ifbench","score":0.06279370768692281,"rank":238,"remainingConfigurations":398},{"removed":"itbench","score":0.06258600784447642,"rank":244,"remainingConfigurations":398},{"removed":"livecodebench","score":0.06278497654821817,"rank":243,"remainingConfigurations":398},{"removed":"math500","score":0.06282036109257075,"rank":244,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06472741501098501,"rank":243,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06666225324832971,"rank":245,"remainingConfigurations":398},{"removed":"omniscience","score":0.0625271104566829,"rank":242,"remainingConfigurations":398},{"removed":"scicode","score":0.06333588945836488,"rank":244,"remainingConfigurations":398},{"removed":"tau-bench","score":0.06027249787079958,"rank":244,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06262173581486784,"rank":243,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07585789937049577,"rank":241,"remainingConfigurations":398},{"removed":"deepswe","score":0.05396510207548561,"rank":243,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06271154068722247,"rank":244,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.06232454812497831,"rank":243,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06766086399481089,"rank":240,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.06286231749862263,"rank":243,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.062054294473036016,"rank":244,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06261862218229515,"rank":244,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06247035527426309,"rank":244,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06286353283381062,"rank":243,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06202839664478876,"rank":244,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06339998891018807,"rank":244,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06286927751656271,"rank":243,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.06179348474268087,"rank":243,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06227464230450951,"rank":244,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06365860350790745,"rank":244,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0634661550984096,"rank":244,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.029183484185864472,"rank":306,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06722485951663958,"rank":238,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0656343924153988,"rank":243,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06239172515153887,"rank":244,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.06251029613400773,"rank":243,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06239984831230025,"rank":244,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06260158836005413,"rank":244,"remainingConfigurations":398},{"removed":"vibe-code","score":0.062326152432977205,"rank":243,"remainingConfigurations":398}]},"magistral-medium-2509--effort-reasoning":{"score":0.06176191255563992,"rank":245,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07390882014048544,"rank":245,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05265082727879459,"rank":245,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06107774997441153,"rank":245,"remainingConfigurations":398},{"removed":"Scale","score":0.0684128646918444,"rank":246,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06169537073867925,"rank":245,"remainingConfigurations":398},{"removed":"Cognition","score":0.06467929382716515,"rank":245,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06316947808133183,"rank":244,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06328945929655681,"rank":246,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.06215382604562252,"rank":230,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0600227723884913,"rank":244,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.06176546843544602,"rank":245,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06170369488613376,"rank":245,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06165660617398966,"rank":245,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06176191255563992,"rank":245,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06159205869074538,"rank":245,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06188901777167802,"rank":245,"remainingConfigurations":398},{"removed":"briefcase","score":0.061501266670603676,"rank":244,"remainingConfigurations":398},{"removed":"aime","score":0.059830997394853314,"rank":246,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0623469745915079,"rank":245,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.06088425085121274,"rank":244,"remainingConfigurations":398},{"removed":"automationbench","score":0.0616298630405861,"rank":245,"remainingConfigurations":398},{"removed":"critpt","score":0.05961687085551488,"rank":249,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0617231116745889,"rank":245,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06238311535245853,"rank":245,"remainingConfigurations":398},{"removed":"gdpval","score":0.06536187978654111,"rank":238,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06257488007136808,"rank":245,"remainingConfigurations":398},{"removed":"gpqa","score":0.060761749389383314,"rank":246,"remainingConfigurations":398},{"removed":"harvey","score":0.060991380093413726,"rank":244,"remainingConfigurations":398},{"removed":"hle","score":0.06508418075027277,"rank":247,"remainingConfigurations":398},{"removed":"ifbench","score":0.06164521426359499,"rank":239,"remainingConfigurations":398},{"removed":"itbench","score":0.06161032269206309,"rank":245,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05884135397396797,"rank":247,"remainingConfigurations":398},{"removed":"math500","score":0.06195952851821357,"rank":245,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0628517821782833,"rank":246,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06829439120019995,"rank":241,"remainingConfigurations":398},{"removed":"omniscience","score":0.05804437547608444,"rank":247,"remainingConfigurations":398},{"removed":"scicode","score":0.06274710717453541,"rank":245,"remainingConfigurations":398},{"removed":"tau-bench","score":0.061748125124821286,"rank":242,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06335970049570396,"rank":242,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07339847649262797,"rank":245,"remainingConfigurations":398},{"removed":"deepswe","score":0.05268988463291623,"rank":245,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06177925341723609,"rank":245,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.061335287754364,"rank":245,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06467929382716515,"rank":245,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.061813508473032686,"rank":245,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.061200603631641766,"rank":245,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06167150773206414,"rank":245,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.06153417038018711,"rank":245,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06186667807750246,"rank":245,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.06127772760351851,"rank":245,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06247184651838663,"rank":245,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06188291143460825,"rank":245,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0608074744543291,"rank":245,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.06136170569572027,"rank":245,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06268546960066836,"rank":245,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06328945929655681,"rank":246,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.058688288800055444,"rank":241,"remainingConfigurations":398},{"removed":"frontiermath","score":0.062353221981186986,"rank":244,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06418137638454656,"rank":246,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06146396021818202,"rank":245,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.061551394103500384,"rank":245,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.06151134117103113,"rank":245,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06166097698858533,"rank":245,"remainingConfigurations":398},{"removed":"vibe-code","score":0.06135438730266841,"rank":245,"remainingConfigurations":398}]},"claude-sonnet-4-5-20250929--effort-non-reasoning":{"score":0.06035033102260783,"rank":246,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07266949672318367,"rank":246,"remainingConfigurations":398},{"removed":"Datacurve","score":0.051485175102908974,"rank":246,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.059770704933713024,"rank":248,"remainingConfigurations":398},{"removed":"Scale","score":0.06680792542388757,"rank":247,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.06028234569297531,"rank":246,"remainingConfigurations":398},{"removed":"Cognition","score":0.06325848157121107,"rank":247,"remainingConfigurations":398},{"removed":"LiveBench","score":0.061738938378262026,"rank":245,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06189143331482764,"rank":247,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0604286500966728,"rank":233,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05865857019980994,"rank":245,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.060353896270805334,"rank":246,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.06029344377930013,"rank":246,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.060248069040638404,"rank":246,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.06035033102260783,"rank":246,"remainingConfigurations":398},{"removed":"All provider reports","score":0.06018505433672994,"rank":246,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.06054012340437529,"rank":246,"remainingConfigurations":398},{"removed":"briefcase","score":0.06020102196623653,"rank":246,"remainingConfigurations":398},{"removed":"aime","score":0.06850980181459497,"rank":235,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06097722157960692,"rank":246,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05883676530139251,"rank":250,"remainingConfigurations":398},{"removed":"automationbench","score":0.06030195171089355,"rank":246,"remainingConfigurations":398},{"removed":"critpt","score":0.06487793523311072,"rank":240,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06040591594769521,"rank":246,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06106912503911999,"rank":247,"remainingConfigurations":398},{"removed":"gdpval","score":0.06065495074127833,"rank":245,"remainingConfigurations":398},{"removed":"gmmlu","score":0.06080071658126884,"rank":246,"remainingConfigurations":398},{"removed":"gpqa","score":0.05980831606147526,"rank":248,"remainingConfigurations":398},{"removed":"harvey","score":0.05965989629470972,"rank":245,"remainingConfigurations":398},{"removed":"hle","score":0.06580278341146033,"rank":244,"remainingConfigurations":398},{"removed":"ifbench","score":0.06108220336977766,"rank":241,"remainingConfigurations":398},{"removed":"itbench","score":0.060266727519593825,"rank":246,"remainingConfigurations":398},{"removed":"livecodebench","score":0.062091167382314565,"rank":244,"remainingConfigurations":398},{"removed":"math500","score":0.06062956266669603,"rank":246,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05642155643328939,"rank":251,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06355462093503679,"rank":247,"remainingConfigurations":398},{"removed":"omniscience","score":0.05189647585079828,"rank":257,"remainingConfigurations":398},{"removed":"scicode","score":0.06145887251373531,"rank":247,"remainingConfigurations":398},{"removed":"tau-bench","score":0.057695093779287894,"rank":248,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.057581333164025895,"rank":251,"remainingConfigurations":398},{"removed":"arc-agi","score":0.07217579941827867,"rank":246,"remainingConfigurations":398},{"removed":"deepswe","score":0.05152309074785782,"rank":246,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.060367153325243235,"rank":246,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.059932288772610816,"rank":246,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06325848157121107,"rank":247,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0604047547254268,"rank":246,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0598043028602492,"rank":246,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06026171993133953,"rank":246,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.060128099849085764,"rank":246,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06045304035477303,"rank":246,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05987326735960108,"rank":246,"remainingConfigurations":398},{"removed":"livebench-language","score":0.061044531344933976,"rank":246,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06046984362712273,"rank":246,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05941624798741344,"rank":246,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05995779519815508,"rank":246,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.06125788162227785,"rank":246,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06189143331482764,"rank":247,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.057240399507318844,"rank":243,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06095321751353583,"rank":245,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06272676659355496,"rank":247,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.06005881310088008,"rank":246,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.060143809521946624,"rank":246,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.060105274388686986,"rank":246,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.060250164143856394,"rank":246,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0599512940264015,"rank":246,"remainingConfigurations":398}]},"gpt-5-nano--effort-high":{"score":0.060152935965066795,"rank":247,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05555614485756152,"rank":137,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0693100008837851,"rank":250,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05111477420536584,"rank":247,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.060301270747655726,"rank":247,"remainingConfigurations":398},{"removed":"Scale","score":0.06680230506066269,"rank":248,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05993331120431272,"rank":247,"remainingConfigurations":398},{"removed":"Cognition","score":0.063953810668385,"rank":246,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06115726200675645,"rank":246,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06051151567703517,"rank":248,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05855924748609634,"rank":235,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05785975893222719,"rank":246,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.060155858041581224,"rank":247,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.060074575627212023,"rank":247,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.06006862083670602,"rank":247,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.060152935965066795,"rank":247,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05998400568281548,"rank":247,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0602913126851033,"rank":247,"remainingConfigurations":398},{"removed":"briefcase","score":0.05999515184426096,"rank":247,"remainingConfigurations":398},{"removed":"aime","score":0.05850019125873243,"rank":248,"remainingConfigurations":398},{"removed":"apex-agents","score":0.06064594388786235,"rank":247,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.060157361471294774,"rank":246,"remainingConfigurations":398},{"removed":"automationbench","score":0.06003351284725253,"rank":247,"remainingConfigurations":398},{"removed":"critpt","score":0.06253722919089373,"rank":243,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.06016641323600169,"rank":247,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06059592739305694,"rank":248,"remainingConfigurations":398},{"removed":"gdpval","score":0.06037262170597246,"rank":246,"remainingConfigurations":398},{"removed":"gmmlu","score":0.060685055373205794,"rank":247,"remainingConfigurations":398},{"removed":"gpqa","score":0.06099596428843306,"rank":245,"remainingConfigurations":398},{"removed":"harvey","score":0.05945856817163453,"rank":246,"remainingConfigurations":398},{"removed":"hle","score":0.06360145128717501,"rank":248,"remainingConfigurations":398},{"removed":"ifbench","score":0.05601114192816977,"rank":249,"remainingConfigurations":398},{"removed":"itbench","score":0.06005539887328923,"rank":247,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05798498483929862,"rank":248,"remainingConfigurations":398},{"removed":"math500","score":0.06027974443676235,"rank":247,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.06345290998927752,"rank":244,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06532101991836432,"rank":246,"remainingConfigurations":398},{"removed":"omniscience","score":0.057565217736590256,"rank":249,"remainingConfigurations":398},{"removed":"scicode","score":0.060917063245288484,"rank":248,"remainingConfigurations":398},{"removed":"tau-bench","score":0.060490269160153105,"rank":243,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06063191600461391,"rank":246,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06881912425818405,"rank":250,"remainingConfigurations":398},{"removed":"deepswe","score":0.05114738102499986,"rank":247,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.06016852499528799,"rank":247,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05960354589092171,"rank":247,"remainingConfigurations":398},{"removed":"frontiercode","score":0.063953810668385,"rank":246,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.060214630809373317,"rank":247,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05962500387880804,"rank":247,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.06006393990379036,"rank":247,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.059925283325415434,"rank":247,"remainingConfigurations":398},{"removed":"livebench-math","score":0.06024707660176013,"rank":247,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.059680506967904945,"rank":247,"remainingConfigurations":398},{"removed":"livebench-language","score":0.06082750341282661,"rank":247,"remainingConfigurations":398},{"removed":"livebench-data","score":0.06024081061107323,"rank":247,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05921738268009901,"rank":247,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05977637123170917,"rank":247,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.061098948309848106,"rank":247,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06051151567703517,"rank":248,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.055919774130630456,"rank":244,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06091189554247465,"rank":246,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06246087215753724,"rank":248,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05986055182632529,"rank":247,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05992701496399327,"rank":247,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05994668786189139,"rank":247,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.06002250486285504,"rank":247,"remainingConfigurations":398},{"removed":"vibe-code","score":0.059733449791948535,"rank":247,"remainingConfigurations":398}]},"claude-haiku-4-5-20251001--effort-thinking-32k":{"score":0.059489553281670944,"rank":248,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05448494053127579,"rank":139,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.051364152592161726,"rank":279,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04977090918433296,"rank":249,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.06041865338658548,"rank":246,"remainingConfigurations":398},{"removed":"Scale","score":0.06636247686952199,"rank":249,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05909779418378053,"rank":248,"remainingConfigurations":398},{"removed":"Cognition","score":0.06322032172560015,"rank":248,"remainingConfigurations":398},{"removed":"LiveBench","score":0.060085229168334135,"rank":247,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05890595791002307,"rank":250,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.08940079447017153,"rank":199,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05637491705130063,"rank":248,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05947680450911914,"rank":248,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05939127347345607,"rank":248,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0595295592681308,"rank":248,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.059489553281670944,"rank":248,"remainingConfigurations":398},{"removed":"All provider reports","score":0.059410057059873976,"rank":248,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05959676987699505,"rank":248,"remainingConfigurations":398},{"removed":"briefcase","score":0.05941099450882204,"rank":249,"remainingConfigurations":398},{"removed":"aime","score":0.06381399666690662,"rank":243,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0598173767032728,"rank":248,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05941237730008706,"rank":248,"remainingConfigurations":398},{"removed":"automationbench","score":0.05939692707249724,"rank":248,"remainingConfigurations":398},{"removed":"critpt","score":0.059721039121550586,"rank":248,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05949499537038074,"rank":248,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05973253985385942,"rank":249,"remainingConfigurations":398},{"removed":"gdpval","score":0.059576664968284454,"rank":248,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05951693971976551,"rank":249,"remainingConfigurations":398},{"removed":"gpqa","score":0.0674035766333951,"rank":239,"remainingConfigurations":398},{"removed":"harvey","score":0.058751280993328714,"rank":247,"remainingConfigurations":398},{"removed":"hle","score":0.06288916691939184,"rank":249,"remainingConfigurations":398},{"removed":"ifbench","score":0.05882797800168806,"rank":243,"remainingConfigurations":398},{"removed":"itbench","score":0.05939116714043308,"rank":248,"remainingConfigurations":398},{"removed":"livecodebench","score":0.060396230820666585,"rank":245,"remainingConfigurations":398},{"removed":"math500","score":0.05955377400505966,"rank":248,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.061303187783765346,"rank":248,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06340745712868712,"rank":248,"remainingConfigurations":398},{"removed":"omniscience","score":0.058438781241374894,"rank":245,"remainingConfigurations":398},{"removed":"scicode","score":0.059936244828733075,"rank":249,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05918382945007205,"rank":245,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05916013163807047,"rank":249,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05113731527463539,"rank":279,"remainingConfigurations":398},{"removed":"deepswe","score":0.04980580024955939,"rank":249,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.059502930565686535,"rank":248,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.058410067789446886,"rank":248,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06322032172560015,"rank":248,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0595705886624851,"rank":248,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05895992969833045,"rank":248,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05939948647899725,"rank":248,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05926334035743211,"rank":248,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05955878185987939,"rank":248,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05894070149549424,"rank":248,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0601879523013946,"rank":248,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05959812896957841,"rank":248,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05858370955763887,"rank":248,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.059107538195723126,"rank":248,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.060466125150996086,"rank":248,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05890595791002307,"rank":250,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.048266595222245086,"rank":259,"remainingConfigurations":398},{"removed":"frontiermath","score":0.06072294429897299,"rank":247,"remainingConfigurations":398},{"removed":"simpleqa","score":0.06423322715562059,"rank":245,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05918956497541262,"rank":248,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05928474633050635,"rank":248,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.059283987235525255,"rank":248,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05936842695144029,"rank":248,"remainingConfigurations":398},{"removed":"vibe-code","score":0.059077420827160804,"rank":248,"remainingConfigurations":398}]},"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning":{"score":0.05869867271256985,"rank":249,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07011590775346839,"rank":249,"remainingConfigurations":398},{"removed":"Datacurve","score":0.05000926282994484,"rank":248,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.058162198535087466,"rank":249,"remainingConfigurations":398},{"removed":"Scale","score":0.06504910444050564,"rank":250,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.058632203189833,"rank":249,"remainingConfigurations":398},{"removed":"Cognition","score":0.06141767199804818,"rank":250,"remainingConfigurations":398},{"removed":"LiveBench","score":0.06006180178187017,"rank":248,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06019352076474888,"rank":249,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05958091268355827,"rank":234,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05704884859769518,"rank":247,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0587019057531094,"rank":249,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05864325097092298,"rank":249,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0585972719218975,"rank":249,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05869867271256985,"rank":249,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05853557531133519,"rank":249,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05882624599683256,"rank":249,"remainingConfigurations":398},{"removed":"briefcase","score":0.06034169150383408,"rank":245,"remainingConfigurations":398},{"removed":"aime","score":0.054696422567077574,"rank":253,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05931250138115187,"rank":249,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05983686255014969,"rank":247,"remainingConfigurations":398},{"removed":"automationbench","score":0.059271572752353875,"rank":249,"remainingConfigurations":398},{"removed":"critpt","score":0.0552191877936593,"rank":256,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05867420652967248,"rank":249,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.06197038233464106,"rank":246,"remainingConfigurations":398},{"removed":"gdpval","score":0.06027746077356216,"rank":247,"remainingConfigurations":398},{"removed":"gmmlu","score":0.058967125849753464,"rank":250,"remainingConfigurations":398},{"removed":"gpqa","score":0.05694347742861189,"rank":251,"remainingConfigurations":398},{"removed":"harvey","score":0.05794650161724637,"rank":248,"remainingConfigurations":398},{"removed":"hle","score":0.06089684846063912,"rank":250,"remainingConfigurations":398},{"removed":"ifbench","score":0.05261895213715295,"rank":253,"remainingConfigurations":398},{"removed":"itbench","score":0.058524039217997974,"rank":249,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05633031800606772,"rank":252,"remainingConfigurations":398},{"removed":"math500","score":0.05903423799927326,"rank":249,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.061811431146551465,"rank":247,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06268237752240945,"rank":249,"remainingConfigurations":398},{"removed":"omniscience","score":0.05830357079756052,"rank":246,"remainingConfigurations":398},{"removed":"scicode","score":0.06230014384262114,"rank":246,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05916064080439296,"rank":246,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.06052975512862654,"rank":247,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06962737279289001,"rank":249,"remainingConfigurations":398},{"removed":"deepswe","score":0.05004707082660561,"rank":248,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.058715718544799754,"rank":249,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0583040619984476,"rank":249,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06141767199804818,"rank":250,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.058761411768543714,"rank":249,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05816697913010796,"rank":249,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05861483671470349,"rank":249,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05847964329996456,"rank":249,"remainingConfigurations":398},{"removed":"livebench-math","score":0.058797961621480606,"rank":249,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05823766665199581,"rank":249,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05938152968451735,"rank":249,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05881630394811619,"rank":249,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05778320289565032,"rank":249,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.058315275449814595,"rank":249,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05957889536096863,"rank":249,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06019352076474888,"rank":249,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.05591746691051317,"rank":245,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05922442352639804,"rank":248,"remainingConfigurations":398},{"removed":"simpleqa","score":0.061005699123294434,"rank":249,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.058413237873634276,"rank":249,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05849836440645384,"rank":249,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05845819495225252,"rank":249,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05860461735285446,"rank":249,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05830804306199953,"rank":249,"remainingConfigurations":398}]},"o3-mini--effort-high":{"score":0.057997227152157695,"rank":250,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04928505695375659,"rank":142,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06001798570817857,"rank":263,"remainingConfigurations":398},{"removed":"Datacurve","score":0.049259303160658574,"rank":250,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05794142412164947,"rank":250,"remainingConfigurations":398},{"removed":"Scale","score":0.07688708401182463,"rank":233,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.057627734540949827,"rank":250,"remainingConfigurations":398},{"removed":"Cognition","score":0.06166892498325353,"rank":249,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05885562121431195,"rank":249,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.058750583053814386,"rank":251,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05735084536495661,"rank":237,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05580001162027357,"rank":249,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05800059481824624,"rank":250,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05791788648706036,"rank":250,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0579233607743549,"rank":250,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.057997227152157695,"rank":250,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05783893822645922,"rank":250,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.058142627933330256,"rank":250,"remainingConfigurations":398},{"removed":"briefcase","score":0.058606275555791974,"rank":250,"remainingConfigurations":398},{"removed":"aime","score":0.05811690144840592,"rank":249,"remainingConfigurations":398},{"removed":"apex-agents","score":0.058429627876952744,"rank":250,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.058401703430354356,"rank":251,"remainingConfigurations":398},{"removed":"automationbench","score":0.05912484336287164,"rank":250,"remainingConfigurations":398},{"removed":"critpt","score":0.057377798494447387,"rank":251,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.058037409470588906,"rank":250,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.058763423793090575,"rank":250,"remainingConfigurations":398},{"removed":"gdpval","score":0.05946540863445383,"rank":249,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05784810342448896,"rank":251,"remainingConfigurations":398},{"removed":"gpqa","score":0.05701394119313604,"rank":250,"remainingConfigurations":398},{"removed":"harvey","score":0.05736542225916099,"rank":249,"remainingConfigurations":398},{"removed":"hle","score":0.07232545269599268,"rank":235,"remainingConfigurations":398},{"removed":"ifbench","score":0.055689617419897995,"rank":250,"remainingConfigurations":398},{"removed":"itbench","score":0.05791508598634861,"rank":250,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05740943143644495,"rank":249,"remainingConfigurations":398},{"removed":"math500","score":0.05672329015858323,"rank":251,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.060150670911112016,"rank":249,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06173489858842641,"rank":250,"remainingConfigurations":398},{"removed":"omniscience","score":0.05539050411662491,"rank":252,"remainingConfigurations":398},{"removed":"scicode","score":0.05758653836721756,"rank":251,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0591365865447897,"rank":247,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.059018079206330516,"rank":250,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05963333378849452,"rank":263,"remainingConfigurations":398},{"removed":"deepswe","score":0.04929129114566851,"rank":250,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05801217993215085,"rank":250,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.057625106706343625,"rank":250,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06166892498325353,"rank":249,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05698716779261153,"rank":251,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05756777771482422,"rank":250,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05791412208129488,"rank":250,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0578312259757393,"rank":250,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05808690149452356,"rank":250,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.057561583799455564,"rank":250,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05862942273048266,"rank":250,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05808665005237181,"rank":250,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05712491838451537,"rank":250,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.057647461591637465,"rank":250,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05886043391357904,"rank":250,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.058750583053814386,"rank":251,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.05465285978890811,"rank":246,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05857183602662994,"rank":249,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0601186600443244,"rank":250,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05772339589879172,"rank":250,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05779485260055117,"rank":250,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05779623803236716,"rank":250,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05788392236854667,"rank":250,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05760628437123235,"rank":250,"remainingConfigurations":398}]},"gpt-5.6-terra--effort-none":{"score":0.05710018538229856,"rank":251,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05441414169927908,"rank":140,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.07035120982829492,"rank":248,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0487855228000679,"rank":251,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.056876775014778114,"rank":251,"remainingConfigurations":398},{"removed":"Scale","score":0.0628812434512515,"rank":251,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.057043287898849444,"rank":251,"remainingConfigurations":398},{"removed":"Cognition","score":0.06087438758168104,"rank":251,"remainingConfigurations":398},{"removed":"LiveBench","score":0.057588573601248354,"rank":250,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.058256473832732865,"rank":252,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.055546980789036186,"rank":250,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05710289322387069,"rank":251,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05703033328272251,"rank":251,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05703822443992124,"rank":251,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05710018538229856,"rank":251,"remainingConfigurations":398},{"removed":"All provider reports","score":0.056962929014686414,"rank":251,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.057234103272902424,"rank":251,"remainingConfigurations":398},{"removed":"briefcase","score":0.057076031910312526,"rank":251,"remainingConfigurations":398},{"removed":"aime","score":0.060806280272300374,"rank":245,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05757550923632606,"rank":251,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.057352801268139554,"rank":253,"remainingConfigurations":398},{"removed":"automationbench","score":0.05711200241471917,"rank":251,"remainingConfigurations":398},{"removed":"critpt","score":0.05625135209091492,"rank":254,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.057164584073211185,"rank":251,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.057431524137112305,"rank":251,"remainingConfigurations":398},{"removed":"gdpval","score":0.05685390095138621,"rank":251,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05742283483157381,"rank":252,"remainingConfigurations":398},{"removed":"gpqa","score":0.050315079680075626,"rank":259,"remainingConfigurations":398},{"removed":"harvey","score":0.05645587804090496,"rank":250,"remainingConfigurations":398},{"removed":"hle","score":0.05943880373037114,"rank":251,"remainingConfigurations":398},{"removed":"ifbench","score":0.05721668882721196,"rank":247,"remainingConfigurations":398},{"removed":"itbench","score":0.05701748573643419,"rank":251,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05716451644979901,"rank":251,"remainingConfigurations":398},{"removed":"math500","score":0.05722398475240276,"rank":250,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05899201590252496,"rank":250,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.06075046894544483,"rank":251,"remainingConfigurations":398},{"removed":"omniscience","score":0.05695559920166004,"rank":250,"remainingConfigurations":398},{"removed":"scicode","score":0.0577104705561888,"rank":250,"remainingConfigurations":398},{"removed":"tau-bench","score":0.054944074426562746,"rank":251,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05690929811691505,"rank":252,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06999151324087209,"rank":248,"remainingConfigurations":398},{"removed":"deepswe","score":0.0488251193297666,"rank":251,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05711435231948487,"rank":251,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05677329875048554,"rank":251,"remainingConfigurations":398},{"removed":"frontiercode","score":0.06087438758168104,"rank":251,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05728034369748952,"rank":250,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.056472797960341325,"rank":251,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05703664118753812,"rank":251,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.056902543482299,"rank":251,"remainingConfigurations":398},{"removed":"livebench-math","score":0.057250216898737015,"rank":251,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.056494709585483555,"rank":251,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05774394284999556,"rank":251,"remainingConfigurations":398},{"removed":"livebench-data","score":0.057259114856670734,"rank":251,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.056268713054509305,"rank":251,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.056711841696125316,"rank":251,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05798898504924724,"rank":251,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.058256473832732865,"rank":252,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04982854280376132,"rank":254,"remainingConfigurations":398},{"removed":"frontiermath","score":0.058282373726075726,"rank":250,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05940741879256808,"rank":251,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0568210722607396,"rank":251,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05692788788113626,"rank":251,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05683047785791722,"rank":251,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05701020921443728,"rank":251,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05675835307380605,"rank":251,"remainingConfigurations":398}]},"seed-oss-36b-instruct--effort-reasoning":{"score":0.05625797060958851,"rank":252,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06744396207349608,"rank":251,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04792685728710594,"rank":252,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05565310920766033,"rank":252,"remainingConfigurations":398},{"removed":"Scale","score":0.06241601485277634,"rank":252,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05618980485976008,"rank":252,"remainingConfigurations":398},{"removed":"Cognition","score":0.05900223276282008,"rank":252,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05755670973078334,"rank":251,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.057663022282154856,"rank":253,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05653060812360653,"rank":238,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05467188373321765,"rank":251,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05626130096719161,"rank":252,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05620489327170871,"rank":252,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.056162594467937345,"rank":252,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05625797060958851,"rank":252,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0561037505382718,"rank":252,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.056404847614642845,"rank":252,"remainingConfigurations":398},{"removed":"briefcase","score":0.05605137088437818,"rank":252,"remainingConfigurations":398},{"removed":"aime","score":0.05218294083450543,"rank":258,"remainingConfigurations":398},{"removed":"apex-agents","score":0.056832070297447024,"rank":252,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05356012978662906,"rank":255,"remainingConfigurations":398},{"removed":"automationbench","score":0.05615689993361142,"rank":252,"remainingConfigurations":398},{"removed":"critpt","score":0.06002820340247723,"rank":247,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05627473582786594,"rank":252,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05684851377193506,"rank":252,"remainingConfigurations":398},{"removed":"gdpval","score":0.05648853404001667,"rank":252,"remainingConfigurations":398},{"removed":"gmmlu","score":0.060273048304269106,"rank":248,"remainingConfigurations":398},{"removed":"gpqa","score":0.05556064315780516,"rank":253,"remainingConfigurations":398},{"removed":"harvey","score":0.0555831173234439,"rank":251,"remainingConfigurations":398},{"removed":"hle","score":0.0593628330692553,"rank":252,"remainingConfigurations":398},{"removed":"ifbench","score":0.05664056475103651,"rank":248,"remainingConfigurations":398},{"removed":"itbench","score":0.056143636047807415,"rank":252,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05231688706415278,"rank":256,"remainingConfigurations":398},{"removed":"math500","score":0.05642058629508751,"rank":252,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05641888187457675,"rank":252,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05995292195916221,"rank":252,"remainingConfigurations":398},{"removed":"omniscience","score":0.05412706180396757,"rank":253,"remainingConfigurations":398},{"removed":"scicode","score":0.057195949441868704,"rank":252,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05478371375215917,"rank":252,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05952031833976129,"rank":248,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06696898120597165,"rank":251,"remainingConfigurations":398},{"removed":"deepswe","score":0.04796251614763374,"rank":252,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.056273827503578344,"rank":252,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05586673753032579,"rank":252,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05900223276282008,"rank":252,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.056304871235467326,"rank":252,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05574450041035008,"rank":252,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05617484983517857,"rank":252,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.056050241521167894,"rank":252,"remainingConfigurations":398},{"removed":"livebench-math","score":0.056354619950139774,"rank":252,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05580930427967296,"rank":252,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05691053917361245,"rank":252,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05637029102654038,"rank":252,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05538010567452212,"rank":252,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05588899857124558,"rank":252,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05711160481940813,"rank":252,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.057663022282154856,"rank":253,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.05339913099352377,"rank":248,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05682159948106407,"rank":251,"remainingConfigurations":398},{"removed":"simpleqa","score":0.058493987183647726,"rank":252,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.055983935190820185,"rank":252,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.056063720245979755,"rank":252,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05602757377712598,"rank":252,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05616372385621052,"rank":252,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05588306937979017,"rank":252,"remainingConfigurations":398}]},"qwen3-235b-a22b-instruct-2507--effort-non-reasoning":{"score":0.05547438510299708,"rank":253,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06660302735327314,"rank":252,"remainingConfigurations":398},{"removed":"Datacurve","score":0.047265801523041516,"rank":253,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05484307612714152,"rank":253,"remainingConfigurations":398},{"removed":"Scale","score":0.06150416566340194,"rank":253,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05541135200456886,"rank":253,"remainingConfigurations":398},{"removed":"Cognition","score":0.0582020083705136,"rank":253,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05676592876895687,"rank":252,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05691175697342415,"rank":254,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05575442011068818,"rank":239,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05392444232597455,"rank":252,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05547767780572908,"rank":253,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05542204047492286,"rank":253,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05538030024537241,"rank":253,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05547438510299708,"rank":253,"remainingConfigurations":398},{"removed":"All provider reports","score":0.055322263097677064,"rank":253,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05563176425005744,"rank":253,"remainingConfigurations":398},{"removed":"briefcase","score":0.055358774890789504,"rank":253,"remainingConfigurations":398},{"removed":"aime","score":0.0551356679262071,"rank":252,"remainingConfigurations":398},{"removed":"apex-agents","score":0.056047914195341254,"rank":253,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.057356996635731655,"rank":252,"remainingConfigurations":398},{"removed":"automationbench","score":0.05543981011162241,"rank":253,"remainingConfigurations":398},{"removed":"critpt","score":0.05895945791247333,"rank":250,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05552002823227562,"rank":253,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0561423835562024,"rank":253,"remainingConfigurations":398},{"removed":"gdpval","score":0.055796778013211736,"rank":253,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05590588546670336,"rank":253,"remainingConfigurations":398},{"removed":"gpqa","score":0.053259246799187275,"rank":256,"remainingConfigurations":398},{"removed":"harvey","score":0.054819596991685364,"rank":253,"remainingConfigurations":398},{"removed":"hle","score":0.057096949172694554,"rank":254,"remainingConfigurations":398},{"removed":"ifbench","score":0.0537696337401303,"rank":252,"remainingConfigurations":398},{"removed":"itbench","score":0.05536644979435312,"rank":253,"remainingConfigurations":398},{"removed":"livecodebench","score":0.057370075318064616,"rank":250,"remainingConfigurations":398},{"removed":"math500","score":0.05270356240379282,"rank":255,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.053693949005831375,"rank":257,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05920518720532191,"rank":253,"remainingConfigurations":398},{"removed":"omniscience","score":0.052435567514663384,"rank":256,"remainingConfigurations":398},{"removed":"scicode","score":0.056486352333058855,"rank":254,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05687855580165052,"rank":250,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.055633056924691955,"rank":254,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06612889365126438,"rank":252,"remainingConfigurations":398},{"removed":"deepswe","score":0.0473009910320439,"rank":253,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0554900432758903,"rank":253,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05508887614072592,"rank":253,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0582020083705136,"rank":253,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05552364914420979,"rank":253,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05496765466045945,"rank":253,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.055392964736378995,"rank":253,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05526966414012106,"rank":253,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05556980407583716,"rank":253,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.055030910160710565,"rank":253,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05611895017756507,"rank":253,"remainingConfigurations":398},{"removed":"livebench-data","score":0.055585802260969326,"rank":253,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.054607455742288404,"rank":253,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05510980511187697,"rank":253,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05631750987686357,"rank":253,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05691175697342415,"rank":254,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.052644947129204554,"rank":249,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05603267972350314,"rank":252,"remainingConfigurations":398},{"removed":"simpleqa","score":0.057688389085242174,"rank":253,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05520374891490706,"rank":253,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05528264087175671,"rank":253,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05524686488322292,"rank":253,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05538133773738365,"rank":253,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05510415581775491,"rank":253,"remainingConfigurations":398}]},"glm-4.7--effort-non-reasoning":{"score":0.05353275853788129,"rank":254,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06445665292427487,"rank":253,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04561213341404017,"rank":254,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05299707527573965,"rank":254,"remainingConfigurations":398},{"removed":"Scale","score":0.059459606944535275,"rank":254,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05346154390405255,"rank":254,"remainingConfigurations":398},{"removed":"Cognition","score":0.05619136927833716,"rank":255,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05479081886194956,"rank":253,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05495323788836398,"rank":255,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.054229113634464844,"rank":240,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05202427847821068,"rank":253,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.053535929614746264,"rank":254,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05348190523420205,"rank":254,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.053441863115611575,"rank":254,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05353275853788129,"rank":254,"remainingConfigurations":398},{"removed":"All provider reports","score":0.053385471294815585,"rank":254,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05369454944911003,"rank":254,"remainingConfigurations":398},{"removed":"briefcase","score":0.05340011427043239,"rank":254,"remainingConfigurations":398},{"removed":"aime","score":0.05707530773386175,"rank":250,"remainingConfigurations":398},{"removed":"apex-agents","score":0.054116794445383094,"rank":254,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05440397876733557,"rank":254,"remainingConfigurations":398},{"removed":"automationbench","score":0.05348957774038282,"rank":255,"remainingConfigurations":398},{"removed":"critpt","score":0.056670817009766145,"rank":253,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05358314289546673,"rank":254,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.054161302601440246,"rank":256,"remainingConfigurations":398},{"removed":"gdpval","score":0.05385721994276577,"rank":255,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0555252890501762,"rank":254,"remainingConfigurations":398},{"removed":"gpqa","score":0.05515580415677846,"rank":254,"remainingConfigurations":398},{"removed":"harvey","score":0.0529243402215564,"rank":254,"remainingConfigurations":398},{"removed":"hle","score":0.05867061591656878,"rank":253,"remainingConfigurations":398},{"removed":"ifbench","score":0.04986454107613648,"rank":259,"remainingConfigurations":398},{"removed":"itbench","score":0.05344930632466836,"rank":254,"remainingConfigurations":398},{"removed":"livecodebench","score":0.054500826812509,"rank":253,"remainingConfigurations":398},{"removed":"math500","score":0.05369384669046054,"rank":253,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05571352571753977,"rank":253,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05731999300056904,"rank":254,"remainingConfigurations":398},{"removed":"omniscience","score":0.04763665184979629,"rank":262,"remainingConfigurations":398},{"removed":"scicode","score":0.05449929261162562,"rank":256,"remainingConfigurations":398},{"removed":"tau-bench","score":0.046855523242021156,"rank":269,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05045568982529378,"rank":261,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06399124512502193,"rank":253,"remainingConfigurations":398},{"removed":"deepswe","score":0.04564606174574401,"rank":254,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05354788879173721,"rank":254,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05315951153182944,"rank":254,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05619136927833716,"rank":255,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.053581287381999236,"rank":254,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.053045731091856806,"rank":254,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.053453593449214264,"rank":254,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05333436143601633,"rank":254,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05362525539420992,"rank":254,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05310265775834311,"rank":254,"remainingConfigurations":398},{"removed":"livebench-language","score":0.054156689103521984,"rank":254,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05364057195420526,"rank":254,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05269321487282153,"rank":254,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05317968318379895,"rank":254,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.054350492125856374,"rank":254,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05495323788836398,"rank":255,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.050883457061426274,"rank":250,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0540609639021527,"rank":254,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05567077148167732,"rank":254,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05327065387512677,"rank":254,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05334680607617415,"rank":254,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05331251752647644,"rank":254,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.053442024447286705,"rank":254,"remainingConfigurations":398},{"removed":"vibe-code","score":0.053174131765137723,"rank":254,"remainingConfigurations":398}]},"minicpm5-2b--effort-reasoning":{"score":0.052925727492042385,"rank":255,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06319809317617407,"rank":254,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04499965261007921,"rank":255,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05243103898230894,"rank":255,"remainingConfigurations":398},{"removed":"Scale","score":0.058752143913394866,"rank":255,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.052871869031987796,"rank":255,"remainingConfigurations":398},{"removed":"Cognition","score":0.05530440240687787,"rank":256,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05421679678949281,"rank":254,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.054343111371036375,"rank":256,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.054126159485746554,"rank":241,"remainingConfigurations":381},{"removed":"Vals AI","score":0.051486809235172175,"rank":254,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05292851294415773,"rank":255,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05287530149208267,"rank":255,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05283270773182161,"rank":255,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.052925727492042385,"rank":255,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05277639203684013,"rank":255,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.053104718732008095,"rank":255,"remainingConfigurations":398},{"removed":"briefcase","score":0.051668093083480186,"rank":256,"remainingConfigurations":398},{"removed":"aime","score":0.05298606193582189,"rank":254,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05355927246361821,"rank":255,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.049879491499905525,"rank":261,"remainingConfigurations":398},{"removed":"automationbench","score":0.05252633450795536,"rank":256,"remainingConfigurations":398},{"removed":"critpt","score":0.04952748967320625,"rank":262,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05295836022307824,"rank":256,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.054334523209070805,"rank":255,"remainingConfigurations":398},{"removed":"gdpval","score":0.049620330259427727,"rank":264,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05330884944543477,"rank":255,"remainingConfigurations":398},{"removed":"gpqa","score":0.052647258900038206,"rank":257,"remainingConfigurations":398},{"removed":"harvey","score":0.05231233254763587,"rank":255,"remainingConfigurations":398},{"removed":"hle","score":0.05562409126658114,"rank":255,"remainingConfigurations":398},{"removed":"ifbench","score":0.05118966316692731,"rank":255,"remainingConfigurations":398},{"removed":"itbench","score":0.052831502984877425,"rank":255,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05281796057761503,"rank":254,"remainingConfigurations":398},{"removed":"math500","score":0.05309000126531358,"rank":254,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05450539311753184,"rank":254,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05650791090973348,"rank":256,"remainingConfigurations":398},{"removed":"omniscience","score":0.06369106807928025,"rank":241,"remainingConfigurations":398},{"removed":"scicode","score":0.05713963967775474,"rank":253,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04711911021677822,"rank":267,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05422203158749472,"rank":256,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06276189609252315,"rank":254,"remainingConfigurations":398},{"removed":"deepswe","score":0.04503388400528965,"rank":255,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05294140049135541,"rank":255,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05257253775305965,"rank":255,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05530440240687787,"rank":256,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.052984149785256646,"rank":255,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05243984657697706,"rank":255,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05285064932138306,"rank":255,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05272700012908892,"rank":255,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05301616270993582,"rank":255,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05250436845878448,"rank":255,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05354962756346909,"rank":255,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05303520811603448,"rank":255,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05208992513918794,"rank":255,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05257515179075297,"rank":255,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05372902069627983,"rank":255,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.054343111371036375,"rank":256,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.05052756351211644,"rank":252,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05339804739781582,"rank":255,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05502286910082088,"rank":255,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.052665181800442086,"rank":255,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05274340952540738,"rank":255,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.052705841230946494,"rank":255,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05284025906632234,"rank":255,"remainingConfigurations":398},{"removed":"vibe-code","score":0.052569387826270776,"rank":255,"remainingConfigurations":398}]},"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning":{"score":0.05237181401569465,"rank":256,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.062481431162612594,"rank":256,"remainingConfigurations":398},{"removed":"Datacurve","score":0.044502331428563295,"rank":257,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05188744698404061,"rank":256,"remainingConfigurations":398},{"removed":"Scale","score":0.058169108456462316,"rank":256,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.052325838317223476,"rank":256,"remainingConfigurations":398},{"removed":"Cognition","score":0.054690809233041066,"rank":258,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05364932373663139,"rank":255,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0537693071103123,"rank":257,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05364927012742196,"rank":242,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05091508297895864,"rank":255,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.052374954585259224,"rank":256,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.052322003838458996,"rank":256,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05228145866419257,"rank":256,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05237181401569465,"rank":256,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05222616970218178,"rank":256,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05249800074358548,"rank":256,"remainingConfigurations":398},{"removed":"briefcase","score":0.04988371622989713,"rank":262,"remainingConfigurations":398},{"removed":"aime","score":0.05252080550857672,"rank":255,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05295486106392736,"rank":256,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.050652576168239115,"rank":258,"remainingConfigurations":398},{"removed":"automationbench","score":0.0537856498258282,"rank":254,"remainingConfigurations":398},{"removed":"critpt","score":0.057093035230585086,"rank":252,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05316939040364077,"rank":255,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05144211980938412,"rank":261,"remainingConfigurations":398},{"removed":"gdpval","score":0.04972123454018145,"rank":263,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05276939576635852,"rank":256,"remainingConfigurations":398},{"removed":"gpqa","score":0.049919426777554676,"rank":261,"remainingConfigurations":398},{"removed":"harvey","score":0.05168734942830522,"rank":257,"remainingConfigurations":398},{"removed":"hle","score":0.0532880695945413,"rank":260,"remainingConfigurations":398},{"removed":"ifbench","score":0.05055994773268286,"rank":258,"remainingConfigurations":398},{"removed":"itbench","score":0.052222767451588874,"rank":257,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05236605765274665,"rank":255,"remainingConfigurations":398},{"removed":"math500","score":0.05264146259563993,"rank":256,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0540485896169109,"rank":255,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.055831937640083706,"rank":257,"remainingConfigurations":398},{"removed":"omniscience","score":0.0576943328358862,"rank":248,"remainingConfigurations":398},{"removed":"scicode","score":0.05510498524236076,"rank":255,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0507793595294378,"rank":260,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05034932678791948,"rank":262,"remainingConfigurations":398},{"removed":"arc-agi","score":0.062047950536389805,"rank":256,"remainingConfigurations":398},{"removed":"deepswe","score":0.04453673855354765,"rank":257,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05238730359029898,"rank":256,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05202497949537437,"rank":256,"remainingConfigurations":398},{"removed":"frontiercode","score":0.054690809233041066,"rank":258,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.052430765209653486,"rank":256,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05188924605320805,"rank":256,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.052298045680545586,"rank":256,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05217485702008764,"rank":256,"remainingConfigurations":398},{"removed":"livebench-math","score":0.052460446207059024,"rank":256,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.051957075019412054,"rank":256,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05299224795898235,"rank":256,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05247872812069451,"rank":256,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.051542713569443364,"rank":256,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.052024977788974136,"rank":256,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.053165655849823745,"rank":256,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0537693071103123,"rank":257,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.049964454402123666,"rank":253,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05282857016584611,"rank":257,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05444846674740599,"rank":256,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05211417406206439,"rank":256,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.052191100635100594,"rank":256,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05215308886416256,"rank":256,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.052288312007900434,"rank":256,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05201816409495077,"rank":256,"remainingConfigurations":398}]},"diffusiongemma-26b-a4b--effort-reasoning":{"score":0.05234657672201513,"rank":257,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06284972358942573,"rank":255,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04455757497475488,"rank":256,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05181605319638685,"rank":257,"remainingConfigurations":398},{"removed":"Scale","score":0.058113430846783436,"rank":257,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05228305456570764,"rank":257,"remainingConfigurations":398},{"removed":"Cognition","score":0.0548858404692933,"rank":257,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05361058763002697,"rank":256,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.053690503655878345,"rank":258,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.052571831056503926,"rank":243,"remainingConfigurations":381},{"removed":"Vals AI","score":0.05087111872767441,"rank":256,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.052349660405826164,"rank":257,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05229707771631459,"rank":257,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05225616471413128,"rank":257,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05234657672201513,"rank":257,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05220118045604807,"rank":257,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05249028896433943,"rank":257,"remainingConfigurations":398},{"removed":"briefcase","score":0.05211506957477904,"rank":255,"remainingConfigurations":398},{"removed":"aime","score":0.05244355719380545,"rank":256,"remainingConfigurations":398},{"removed":"apex-agents","score":0.052868576595603956,"rank":257,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05908359861661266,"rank":249,"remainingConfigurations":398},{"removed":"automationbench","score":0.05223887077885719,"rank":257,"remainingConfigurations":398},{"removed":"critpt","score":0.048398540546703034,"rank":266,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05235319305190689,"rank":257,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05289869269274027,"rank":257,"remainingConfigurations":398},{"removed":"gdpval","score":0.05419865390779017,"rank":254,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05271646662198335,"rank":257,"remainingConfigurations":398},{"removed":"gpqa","score":0.054482552359760066,"rank":255,"remainingConfigurations":398},{"removed":"harvey","score":0.05171577551143902,"rank":256,"remainingConfigurations":398},{"removed":"hle","score":0.052877551457329454,"rank":262,"remainingConfigurations":398},{"removed":"ifbench","score":0.04525570025634142,"rank":268,"remainingConfigurations":398},{"removed":"itbench","score":0.052222788710093754,"rank":256,"remainingConfigurations":398},{"removed":"livecodebench","score":0.052269367512728225,"rank":257,"remainingConfigurations":398},{"removed":"math500","score":0.052638026719589365,"rank":257,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05389070277464253,"rank":256,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05276310578656731,"rank":262,"remainingConfigurations":398},{"removed":"omniscience","score":0.05349106199455391,"rank":254,"remainingConfigurations":398},{"removed":"scicode","score":0.05324213315027449,"rank":257,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0511460822697918,"rank":257,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05344205745292568,"rank":257,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06242202879129,"rank":255,"remainingConfigurations":398},{"removed":"deepswe","score":0.04459077801999208,"rank":256,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05236148975789299,"rank":257,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.051988037032937424,"rank":257,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0548858404692933,"rank":257,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05239948110487807,"rank":257,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05186871080905297,"rank":257,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05227048324169369,"rank":257,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05215124677153701,"rank":257,"remainingConfigurations":398},{"removed":"livebench-math","score":0.052437028702866616,"rank":257,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05192591082480627,"rank":257,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05295959306406412,"rank":257,"remainingConfigurations":398},{"removed":"livebench-data","score":0.052453617976297856,"rank":257,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05152296247843292,"rank":257,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05200004500344824,"rank":257,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05314601321360407,"rank":257,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.053690503655878345,"rank":258,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04971603652010689,"rank":255,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05284245186590227,"rank":256,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05443091741118664,"rank":257,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.052089466210051054,"rank":257,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05216494641639968,"rank":257,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05212995263860631,"rank":257,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.052258639792276664,"rank":257,"remainingConfigurations":398},{"removed":"vibe-code","score":0.051995303664667064,"rank":257,"remainingConfigurations":398}]},"gemini-3.5-flash-lite--effort-low":{"score":0.05159565471280456,"rank":258,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.04781030556244739,"rank":143,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.12130244635985095,"rank":190,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04396834780087284,"rank":258,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.051273861887858034,"rank":258,"remainingConfigurations":398},{"removed":"Scale","score":0.056869896838165256,"rank":259,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05136557764568084,"rank":258,"remainingConfigurations":398},{"removed":"Cognition","score":0.056817635114107166,"rank":254,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05220633170049447,"rank":258,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.051334397438174,"rank":263,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.025826712554681785,"rank":302,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04966579393908683,"rank":258,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.051596752826909814,"rank":258,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05151098303200257,"rank":258,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.051542239427034675,"rank":258,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05159565471280456,"rank":258,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05145126203910805,"rank":258,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05169574927584747,"rank":259,"remainingConfigurations":398},{"removed":"briefcase","score":0.051539031847994195,"rank":257,"remainingConfigurations":398},{"removed":"aime","score":0.05591000395924169,"rank":251,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05193740938919114,"rank":258,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.051599272599657194,"rank":256,"remainingConfigurations":398},{"removed":"automationbench","score":0.05153413838811139,"rank":259,"remainingConfigurations":398},{"removed":"critpt","score":0.05167376564870929,"rank":260,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05161337477107867,"rank":258,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0518314557082005,"rank":258,"remainingConfigurations":398},{"removed":"gdpval","score":0.05161787887993222,"rank":257,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05169314621133659,"rank":258,"remainingConfigurations":398},{"removed":"gpqa","score":0.0580586773506535,"rank":249,"remainingConfigurations":398},{"removed":"harvey","score":0.05099504505620519,"rank":258,"remainingConfigurations":398},{"removed":"hle","score":0.053778733043700816,"rank":257,"remainingConfigurations":398},{"removed":"ifbench","score":0.05104838958644237,"rank":256,"remainingConfigurations":398},{"removed":"itbench","score":0.05151402250417911,"rank":258,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05129642866104758,"rank":258,"remainingConfigurations":398},{"removed":"math500","score":0.051671743677960486,"rank":258,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05327656199946685,"rank":259,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05504489592130646,"rank":258,"remainingConfigurations":398},{"removed":"omniscience","score":0.050733556214815324,"rank":258,"remainingConfigurations":398},{"removed":"scicode","score":0.05204174988495458,"rank":259,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05095867061594986,"rank":259,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.051409161849324335,"rank":258,"remainingConfigurations":398},{"removed":"arc-agi","score":0.1212596456983383,"rank":191,"remainingConfigurations":398},{"removed":"deepswe","score":0.04399708510689948,"rank":258,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05160823668342568,"rank":258,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05129655012040949,"rank":258,"remainingConfigurations":398},{"removed":"frontiercode","score":0.056817635114107166,"rank":254,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05170420946933777,"rank":258,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05111999141279792,"rank":258,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0515260872806823,"rank":258,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0513885090024043,"rank":258,"remainingConfigurations":398},{"removed":"livebench-math","score":0.051682818351966725,"rank":258,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.051118511782881286,"rank":258,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05217448886899783,"rank":258,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05168209713085323,"rank":258,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05080440628428057,"rank":258,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05125239060664455,"rank":258,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05247055066959069,"rank":258,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.051334397438174,"rank":263,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03478091799104783,"rank":287,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0524445125138153,"rank":258,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05378426555814588,"rank":258,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05135105748439044,"rank":258,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05139786604676395,"rank":258,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05141325533499347,"rank":258,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05147291481530671,"rank":258,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0512454703798082,"rank":258,"remainingConfigurations":398}]},"mistral-small-4--effort-reasoning":{"score":0.05125607216903435,"rank":259,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06120208913701596,"rank":260,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04355554907228238,"rank":259,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0507860350454816,"rank":259,"remainingConfigurations":398},{"removed":"Scale","score":0.056931471497933234,"rank":258,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05119706746543967,"rank":259,"remainingConfigurations":398},{"removed":"Cognition","score":0.05358497506741628,"rank":259,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05250059177058127,"rank":257,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05257080851222414,"rank":259,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05217158112896112,"rank":245,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04980297471032796,"rank":257,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05125889613020836,"rank":259,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05120552770065411,"rank":259,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05116589974981722,"rank":259,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05125607216903435,"rank":259,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05110975745236899,"rank":259,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.052261595486646516,"rank":258,"remainingConfigurations":398},{"removed":"briefcase","score":0.051069047663253035,"rank":258,"remainingConfigurations":398},{"removed":"aime","score":0.05142668639331672,"rank":260,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05182052814078978,"rank":259,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05032202155237525,"rank":259,"remainingConfigurations":398},{"removed":"automationbench","score":0.05198264389565838,"rank":258,"remainingConfigurations":398},{"removed":"critpt","score":0.049108287760858606,"rank":263,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0512078328412856,"rank":259,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05594176865857078,"rank":254,"remainingConfigurations":398},{"removed":"gdpval","score":0.05192537089566721,"rank":256,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05146388974072113,"rank":259,"remainingConfigurations":398},{"removed":"gpqa","score":0.04854812122584944,"rank":263,"remainingConfigurations":398},{"removed":"harvey","score":0.05056452650032569,"rank":259,"remainingConfigurations":398},{"removed":"hle","score":0.05353705355462718,"rank":259,"remainingConfigurations":398},{"removed":"ifbench","score":0.048529789360137486,"rank":264,"remainingConfigurations":398},{"removed":"itbench","score":0.05109089205218496,"rank":259,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05128451164844403,"rank":259,"remainingConfigurations":398},{"removed":"math500","score":0.05158303102349754,"rank":259,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.052902112483020264,"rank":260,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05656053303342515,"rank":255,"remainingConfigurations":398},{"removed":"omniscience","score":0.04812349122423973,"rank":261,"remainingConfigurations":398},{"removed":"scicode","score":0.05084001104774033,"rank":263,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05191132336065859,"rank":255,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05101850346454217,"rank":259,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0607876715395849,"rank":259,"remainingConfigurations":398},{"removed":"deepswe","score":0.043588892561002235,"rank":259,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05127112031989572,"rank":259,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05091304144114928,"rank":259,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05358497506741628,"rank":259,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.051311197386362674,"rank":259,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.050784014970480594,"rank":259,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.051183204808328685,"rank":259,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05106388429573703,"rank":259,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05134379138775271,"rank":259,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.050847526563225685,"rank":259,"remainingConfigurations":398},{"removed":"livebench-language","score":0.051861388183227906,"rank":259,"remainingConfigurations":398},{"removed":"livebench-data","score":0.051360827616506066,"rank":259,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05044481712190028,"rank":259,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0509165738221496,"rank":259,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05203650805122532,"rank":259,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05257080851222414,"rank":259,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.048884301412284455,"rank":257,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05170688090004221,"rank":259,"remainingConfigurations":398},{"removed":"simpleqa","score":0.053293983766130516,"rank":259,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.051004240604628964,"rank":259,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05107808706667217,"rank":259,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0510424490947149,"rank":259,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05117191942599567,"rank":259,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05091090503591303,"rank":259,"remainingConfigurations":398}]},"gemma-4-26b-a4b-it--effort-non-reasoning":{"score":0.050968515421893894,"rank":260,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.061531033958811134,"rank":258,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04338585045290522,"rank":260,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.05046125241400597,"rank":260,"remainingConfigurations":398},{"removed":"Scale","score":0.056569846412083215,"rank":260,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.050891263610409514,"rank":260,"remainingConfigurations":398},{"removed":"Cognition","score":0.05346087330769572,"rank":260,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0521910267064325,"rank":259,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05224466739202526,"rank":260,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05107280008486875,"rank":247,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04951428875563527,"rank":259,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05097159522020861,"rank":260,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05092023504669523,"rank":260,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.050880921884958685,"rank":260,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.050968515421893894,"rank":260,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05082736548906727,"rank":260,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05111767532334618,"rank":260,"remainingConfigurations":398},{"removed":"briefcase","score":0.050759225484066306,"rank":260,"remainingConfigurations":398},{"removed":"aime","score":0.05150811113968059,"rank":259,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05150384381725783,"rank":260,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05104970261840754,"rank":257,"remainingConfigurations":398},{"removed":"automationbench","score":0.050862533269928865,"rank":260,"remainingConfigurations":398},{"removed":"critpt","score":0.05541023614850488,"rank":255,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05099369944818553,"rank":260,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05150989837610733,"rank":259,"remainingConfigurations":398},{"removed":"gdpval","score":0.05093035375630305,"rank":259,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05119527768519358,"rank":261,"remainingConfigurations":398},{"removed":"gpqa","score":0.05031195823454859,"rank":260,"remainingConfigurations":398},{"removed":"harvey","score":0.05034702950781451,"rank":260,"remainingConfigurations":398},{"removed":"hle","score":0.050659342180018774,"rank":265,"remainingConfigurations":398},{"removed":"ifbench","score":0.04905082214123385,"rank":260,"remainingConfigurations":398},{"removed":"itbench","score":0.05083282734582937,"rank":260,"remainingConfigurations":398},{"removed":"livecodebench","score":0.05109133492091422,"rank":260,"remainingConfigurations":398},{"removed":"math500","score":0.05132320676001681,"rank":260,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.052617515942162185,"rank":261,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.051025211511437386,"rank":265,"remainingConfigurations":398},{"removed":"omniscience","score":0.05318218162697582,"rank":255,"remainingConfigurations":398},{"removed":"scicode","score":0.05183590518128867,"rank":260,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05063274976974531,"rank":261,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04794591215067206,"rank":268,"remainingConfigurations":398},{"removed":"arc-agi","score":0.061105522034934405,"rank":258,"remainingConfigurations":398},{"removed":"deepswe","score":0.04341812862146124,"rank":260,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.05098296643449932,"rank":260,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.050615497695471266,"rank":260,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05346087330769572,"rank":260,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.051017395981166724,"rank":260,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.05050216648326641,"rank":260,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.05089376833942541,"rank":260,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05077842839830141,"rank":260,"remainingConfigurations":398},{"removed":"livebench-math","score":0.051056792185770694,"rank":260,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05055685514450433,"rank":260,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05156591859230856,"rank":260,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05107274279313597,"rank":260,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05016522400459553,"rank":260,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.05063027500944311,"rank":260,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05175066933701152,"rank":260,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05224466739202526,"rank":260,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04827043095365539,"rank":258,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0513918878209377,"rank":261,"remainingConfigurations":398},{"removed":"simpleqa","score":0.053007437371412836,"rank":260,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05071775272633978,"rank":260,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05079077762841613,"rank":260,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05075752683030216,"rank":260,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.050881680301137495,"rank":260,"remainingConfigurations":398},{"removed":"vibe-code","score":0.05062563851209529,"rank":260,"remainingConfigurations":398}]},"minimax-m1-80k--effort-reasoning":{"score":0.05088668577264525,"rank":261,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.061222136748481086,"rank":259,"remainingConfigurations":398},{"removed":"Datacurve","score":0.043313184884796914,"rank":261,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.050303196733477516,"rank":261,"remainingConfigurations":398},{"removed":"Scale","score":0.056511263055860676,"rank":261,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.050822141473958256,"rank":261,"remainingConfigurations":398},{"removed":"Cognition","score":0.05341319880190542,"rank":261,"remainingConfigurations":398},{"removed":"LiveBench","score":0.052091787880969964,"rank":260,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05224223832495473,"rank":261,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05111226784877249,"rank":246,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04946169379763577,"rank":260,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.050889729491863545,"rank":261,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.050838387398205474,"rank":261,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.05079994674934618,"rank":261,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05088668577264525,"rank":261,"remainingConfigurations":398},{"removed":"All provider reports","score":0.05074637205748974,"rank":261,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05103321611217914,"rank":261,"remainingConfigurations":398},{"removed":"briefcase","score":0.05077326903984175,"rank":259,"remainingConfigurations":398},{"removed":"aime","score":0.05224584871577274,"rank":257,"remainingConfigurations":398},{"removed":"apex-agents","score":0.051423342931737975,"rank":261,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04861096921454261,"rank":266,"remainingConfigurations":398},{"removed":"automationbench","score":0.0508414277937597,"rank":261,"remainingConfigurations":398},{"removed":"critpt","score":0.05356215172710338,"rank":257,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.05092276585312266,"rank":261,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.051497805827119124,"rank":260,"remainingConfigurations":398},{"removed":"gdpval","score":0.051142271800948595,"rank":258,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05128270894063444,"rank":260,"remainingConfigurations":398},{"removed":"gpqa","score":0.05065574711952984,"rank":258,"remainingConfigurations":398},{"removed":"harvey","score":0.05028671599480119,"rank":261,"remainingConfigurations":398},{"removed":"hle","score":0.053840520296460886,"rank":256,"remainingConfigurations":398},{"removed":"ifbench","score":0.05086383524492926,"rank":257,"remainingConfigurations":398},{"removed":"itbench","score":0.05079334338760414,"rank":261,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04848484220890623,"rank":264,"remainingConfigurations":398},{"removed":"math500","score":0.04809062281371001,"rank":264,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05031580095896413,"rank":262,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05434289485609053,"rank":259,"remainingConfigurations":398},{"removed":"omniscience","score":0.0451994931166818,"rank":268,"remainingConfigurations":398},{"removed":"scicode","score":0.05181882483738326,"rank":261,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05162486560862209,"rank":256,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05647071532612886,"rank":253,"remainingConfigurations":398},{"removed":"arc-agi","score":0.06078023163749935,"rank":260,"remainingConfigurations":398},{"removed":"deepswe","score":0.04334558480650822,"rank":261,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.050901164385363046,"rank":261,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.05053249110803614,"rank":261,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05341319880190542,"rank":261,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.05093335569412971,"rank":261,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.050419196535796344,"rank":261,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.050812084092430605,"rank":261,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.05069808215953547,"rank":261,"remainingConfigurations":398},{"removed":"livebench-math","score":0.050975006202706064,"rank":261,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.05047547897243104,"rank":261,"remainingConfigurations":398},{"removed":"livebench-language","score":0.05148326215368832,"rank":261,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05099032261252168,"rank":261,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.05008444903618483,"rank":261,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0505490149485777,"rank":261,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05166801548569122,"rank":261,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05224223832495473,"rank":261,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04826492908402163,"rank":260,"remainingConfigurations":398},{"removed":"frontiermath","score":0.051401988284729194,"rank":260,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05293730822632171,"rank":261,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.05063617443875423,"rank":261,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.05070911737127915,"rank":261,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.05067615256313726,"rank":261,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05080012386587863,"rank":261,"remainingConfigurations":398},{"removed":"vibe-code","score":0.050544132391828644,"rank":261,"remainingConfigurations":398}]},"o3-mini--effort-reasoning":{"score":0.05010757291585585,"rank":262,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06036287978590966,"rank":261,"remainingConfigurations":398},{"removed":"Datacurve","score":0.042664690139816615,"rank":262,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04954989825688957,"rank":262,"remainingConfigurations":398},{"removed":"Scale","score":0.055618036260233504,"rank":262,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.05004162181397503,"rank":262,"remainingConfigurations":398},{"removed":"Cognition","score":0.052609689631254695,"rank":262,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05130061438017832,"rank":261,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05139400813340389,"rank":262,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.050016447065067034,"rank":249,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04870533652524383,"rank":261,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.05011055576380801,"rank":262,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.05005964945129815,"rank":262,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0500223094014319,"rank":262,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.05010757291585585,"rank":262,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04996916243561066,"rank":262,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.05025288268589648,"rank":262,"remainingConfigurations":398},{"removed":"briefcase","score":0.04997889522669402,"rank":261,"remainingConfigurations":398},{"removed":"aime","score":0.050479821674240755,"rank":261,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05063757541159473,"rank":262,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04964388294968253,"rank":262,"remainingConfigurations":398},{"removed":"automationbench","score":0.050067297734596033,"rank":263,"remainingConfigurations":398},{"removed":"critpt","score":0.04909628547137193,"rank":264,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.050156133256218934,"rank":262,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05069342088727973,"rank":262,"remainingConfigurations":398},{"removed":"gdpval","score":0.05023534572242567,"rank":261,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05027606464284345,"rank":263,"remainingConfigurations":398},{"removed":"gpqa","score":0.04662161012887959,"rank":266,"remainingConfigurations":398},{"removed":"harvey","score":0.049527658282975444,"rank":262,"remainingConfigurations":398},{"removed":"hle","score":0.05298816830436415,"rank":261,"remainingConfigurations":398},{"removed":"ifbench","score":0.04903709184679165,"rank":261,"remainingConfigurations":398},{"removed":"itbench","score":0.04999619328973787,"rank":262,"remainingConfigurations":398},{"removed":"livecodebench","score":0.045337427361699996,"rank":268,"remainingConfigurations":398},{"removed":"math500","score":0.04778217694070879,"rank":266,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05341562699601667,"rank":258,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.053320977555755274,"rank":261,"remainingConfigurations":398},{"removed":"omniscience","score":0.04727184405402216,"rank":264,"remainingConfigurations":398},{"removed":"scicode","score":0.05101036394011261,"rank":262,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05467174035714504,"rank":253,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.05489723595914584,"rank":255,"remainingConfigurations":398},{"removed":"arc-agi","score":0.059927839568653794,"rank":261,"remainingConfigurations":398},{"removed":"deepswe","score":0.042696535512906364,"rank":262,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.050121813219506074,"rank":262,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04975772044742669,"rank":262,"remainingConfigurations":398},{"removed":"frontiercode","score":0.052609689631254695,"rank":262,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.050157285159820514,"rank":262,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04964813885529785,"rank":262,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.050034109381108076,"rank":262,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.049921597680891404,"rank":262,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05019476003023226,"rank":262,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.049701372384973824,"rank":262,"remainingConfigurations":398},{"removed":"livebench-language","score":0.050695483159820004,"rank":262,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05020991695513421,"rank":262,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04931669367850113,"rank":262,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04977458546275345,"rank":262,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.050878815159648254,"rank":262,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05139400813340389,"rank":262,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.047327729485350196,"rank":262,"remainingConfigurations":398},{"removed":"frontiermath","score":0.05053311293901356,"rank":262,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05213408258161431,"rank":262,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04986053855354954,"rank":262,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.049932366025978815,"rank":262,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04990014511076126,"rank":262,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.05002180282099794,"rank":262,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04976965366239663,"rank":262,"remainingConfigurations":398}]},"glm-4.5-air--effort-reasoning":{"score":0.049952971815906376,"rank":263,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06013382308910422,"rank":262,"remainingConfigurations":398},{"removed":"Datacurve","score":0.042509750584336294,"rank":263,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0493984984316529,"rank":263,"remainingConfigurations":398},{"removed":"Scale","score":0.05548059654958062,"rank":263,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04988828191415681,"rank":263,"remainingConfigurations":398},{"removed":"Cognition","score":0.05243810127196127,"rank":263,"remainingConfigurations":398},{"removed":"LiveBench","score":0.05114008044931534,"rank":262,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.05127394563174479,"rank":264,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.05026713730535282,"rank":248,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04855353618978997,"rank":262,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.049955964346183684,"rank":263,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04990550263475995,"rank":263,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.049867737259253996,"rank":263,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.049952971815906376,"rank":263,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04981507763346982,"rank":263,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.050099198223901,"rank":263,"remainingConfigurations":398},{"removed":"briefcase","score":0.04980261396104708,"rank":263,"remainingConfigurations":398},{"removed":"aime","score":0.04722989996220637,"rank":266,"remainingConfigurations":398},{"removed":"apex-agents","score":0.05048131315349083,"rank":263,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04925775555254308,"rank":263,"remainingConfigurations":398},{"removed":"automationbench","score":0.04988539328978955,"rank":264,"remainingConfigurations":398},{"removed":"critpt","score":0.05249802837086648,"rank":258,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04998501571544498,"rank":263,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.05051637954561706,"rank":263,"remainingConfigurations":398},{"removed":"gdpval","score":0.050195670419168704,"rank":262,"remainingConfigurations":398},{"removed":"gmmlu","score":0.05037466295801956,"rank":262,"remainingConfigurations":398},{"removed":"gpqa","score":0.04856003472414549,"rank":262,"remainingConfigurations":398},{"removed":"harvey","score":0.049359077113438,"rank":263,"remainingConfigurations":398},{"removed":"hle","score":0.053757339449389485,"rank":258,"remainingConfigurations":398},{"removed":"ifbench","score":0.052271842966423156,"rank":254,"remainingConfigurations":398},{"removed":"itbench","score":0.049860817239105605,"rank":263,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0486780000657075,"rank":261,"remainingConfigurations":398},{"removed":"math500","score":0.04993336471127557,"rank":261,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.049818182698030976,"rank":265,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0533604280855213,"rank":260,"remainingConfigurations":398},{"removed":"omniscience","score":0.04911907560971334,"rank":259,"remainingConfigurations":398},{"removed":"scicode","score":0.050832453992171595,"rank":264,"remainingConfigurations":398},{"removed":"tau-bench","score":0.048652212140765566,"rank":263,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04862614934657785,"rank":265,"remainingConfigurations":398},{"removed":"arc-agi","score":0.059698545677625864,"rank":262,"remainingConfigurations":398},{"removed":"deepswe","score":0.042541580150983194,"rank":263,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04996720789907591,"rank":263,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04960516678753601,"rank":263,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05243810127196127,"rank":263,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04999908656562935,"rank":263,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04949352820200967,"rank":263,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04987975679078955,"rank":263,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04976766639022237,"rank":263,"remainingConfigurations":398},{"removed":"livebench-math","score":0.05003983089353092,"rank":263,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.049548425339076885,"rank":263,"remainingConfigurations":398},{"removed":"livebench-language","score":0.050539667459875016,"rank":263,"remainingConfigurations":398},{"removed":"livebench-data","score":0.05005499549446044,"rank":263,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.049164052194173184,"rank":263,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.049620846863401354,"rank":263,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.05072155576855042,"rank":263,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.05127394563174479,"rank":264,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.047384238106188116,"rank":261,"remainingConfigurations":398},{"removed":"frontiermath","score":0.050459473767599204,"rank":263,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05196994085178081,"rank":263,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04970660474356223,"rank":263,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.049778324651560374,"rank":263,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.049745934924304375,"rank":263,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04986775566415711,"rank":263,"remainingConfigurations":398},{"removed":"vibe-code","score":0.049616114377129046,"rank":263,"remainingConfigurations":398}]},"solar-pro3-260323--effort-reasoning":{"score":0.04878652067740269,"rank":264,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.058350316428939904,"rank":265,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04146010614263831,"rank":265,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04834801147701851,"rank":264,"remainingConfigurations":398},{"removed":"Scale","score":0.05416777836354244,"rank":264,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04874201185125185,"rank":264,"remainingConfigurations":398},{"removed":"Cognition","score":0.051069631663016514,"rank":265,"remainingConfigurations":398},{"removed":"LiveBench","score":0.049994073879564116,"rank":263,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.050088899956277716,"rank":265,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.049625838774555515,"rank":250,"remainingConfigurations":381},{"removed":"Vals AI","score":0.047443904049989855,"rank":264,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04878926549207918,"rank":264,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.048740552877456135,"rank":264,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04870148869032278,"rank":264,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04878652067740269,"rank":264,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0486502073248801,"rank":264,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04888338739586328,"rank":264,"remainingConfigurations":398},{"removed":"briefcase","score":0.0497042737974435,"rank":264,"remainingConfigurations":398},{"removed":"aime","score":0.04873596069878083,"rank":263,"remainingConfigurations":398},{"removed":"apex-agents","score":0.049317289610878806,"rank":264,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.05004599983661808,"rank":260,"remainingConfigurations":398},{"removed":"automationbench","score":0.05081895199122908,"rank":262,"remainingConfigurations":398},{"removed":"critpt","score":0.05210902796936976,"rank":259,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04876116372752295,"rank":264,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.049386101983469044,"rank":264,"remainingConfigurations":398},{"removed":"gdpval","score":0.05038521576586965,"rank":260,"remainingConfigurations":398},{"removed":"gmmlu","score":0.048993842368427874,"rank":264,"remainingConfigurations":398},{"removed":"gpqa","score":0.04748231826901659,"rank":264,"remainingConfigurations":398},{"removed":"harvey","score":0.04816737329955326,"rank":264,"remainingConfigurations":398},{"removed":"hle","score":0.05000570016814807,"rank":267,"remainingConfigurations":398},{"removed":"ifbench","score":0.04063763746134523,"rank":278,"remainingConfigurations":398},{"removed":"itbench","score":0.04865934550284351,"rank":264,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04860299195467177,"rank":263,"remainingConfigurations":398},{"removed":"math500","score":0.048966696101332086,"rank":262,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05014211181494387,"rank":264,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.05190041436156012,"rank":263,"remainingConfigurations":398},{"removed":"omniscience","score":0.04745572385949353,"rank":263,"remainingConfigurations":398},{"removed":"scicode","score":0.05236980083218057,"rank":258,"remainingConfigurations":398},{"removed":"tau-bench","score":0.044434521722343086,"rank":272,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.049958234559770505,"rank":264,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05792407502883531,"rank":265,"remainingConfigurations":398},{"removed":"deepswe","score":0.041491876816762745,"rank":265,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04880092676117879,"rank":264,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04846011354826679,"rank":264,"remainingConfigurations":398},{"removed":"frontiercode","score":0.051069631663016514,"rank":265,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.048840757531506775,"rank":264,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04833726613443659,"rank":264,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04871716787261987,"rank":264,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.048604011732952423,"rank":264,"remainingConfigurations":398},{"removed":"livebench-math","score":0.048870384256665365,"rank":264,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04839516634879495,"rank":264,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04936587489930702,"rank":264,"remainingConfigurations":398},{"removed":"livebench-data","score":0.048887013100133096,"rank":264,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04801075970792782,"rank":264,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0484611223830362,"rank":264,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04953375760608055,"rank":264,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.050088899956277716,"rank":265,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04649124382901713,"rank":263,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04923179957159644,"rank":264,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05073976717172427,"rank":265,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.048544780421165674,"rank":264,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04861640101113398,"rank":264,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04858239016818564,"rank":264,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.048706081349796725,"rank":264,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04845587937161777,"rank":264,"remainingConfigurations":398}]},"minimax-m3--effort-non-reasoning":{"score":0.048523551151277905,"rank":265,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.05044439069275491,"rank":141,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05925749778167414,"rank":264,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04175091116287724,"rank":264,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04832543552645713,"rank":265,"remainingConfigurations":398},{"removed":"Scale","score":0.053540796045562146,"rank":265,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04862602541159858,"rank":265,"remainingConfigurations":398},{"removed":"Cognition","score":0.05240978268777183,"rank":264,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04929641542001739,"rank":264,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04930051649726886,"rank":266,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0475270326637147,"rank":263,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04852544443798401,"rank":265,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.048464374159553146,"rank":265,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04846979365202778,"rank":265,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.048523551151277905,"rank":265,"remainingConfigurations":398},{"removed":"All provider reports","score":0.048405458101406285,"rank":265,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04864181775651852,"rank":265,"remainingConfigurations":398},{"removed":"briefcase","score":0.048475602574815674,"rank":265,"remainingConfigurations":398},{"removed":"aime","score":0.06500199370193337,"rank":239,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04893002027054625,"rank":265,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.048774579950713964,"rank":265,"remainingConfigurations":398},{"removed":"automationbench","score":0.0485086553522359,"rank":265,"remainingConfigurations":398},{"removed":"critpt","score":0.04768821385415783,"rank":268,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04857700367304163,"rank":265,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04881112926620093,"rank":266,"remainingConfigurations":398},{"removed":"gdpval","score":0.04828446733207926,"rank":265,"remainingConfigurations":398},{"removed":"gmmlu","score":0.048809760762417526,"rank":265,"remainingConfigurations":398},{"removed":"gpqa","score":0.028221289902693427,"rank":313,"remainingConfigurations":398},{"removed":"harvey","score":0.04795795531352124,"rank":265,"remainingConfigurations":398},{"removed":"hle","score":0.05063460588011115,"rank":266,"remainingConfigurations":398},{"removed":"ifbench","score":0.04859752550949615,"rank":263,"remainingConfigurations":398},{"removed":"itbench","score":0.04844259228515419,"rank":265,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0486706972286819,"rank":262,"remainingConfigurations":398},{"removed":"math500","score":0.048633164548695734,"rank":263,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.05016496888754443,"rank":263,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.051660134417710384,"rank":264,"remainingConfigurations":398},{"removed":"omniscience","score":0.04837498243011357,"rank":260,"remainingConfigurations":398},{"removed":"scicode","score":0.0490454961731434,"rank":265,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04663314395955744,"rank":270,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04854498487513304,"rank":266,"remainingConfigurations":398},{"removed":"arc-agi","score":0.058916556190237244,"rank":264,"remainingConfigurations":398},{"removed":"deepswe","score":0.04178543978223249,"rank":264,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04853593590779707,"rank":265,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04825727703286442,"rank":265,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05240978268777183,"rank":264,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04866972463055044,"rank":265,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04800881305345583,"rank":265,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04846582020756226,"rank":265,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04834860782607859,"rank":265,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04865492188024473,"rank":265,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04800038493588855,"rank":265,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04908232004538829,"rank":265,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04865983808250185,"rank":265,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0478032721007054,"rank":265,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04818899281673244,"rank":265,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04928970856658268,"rank":265,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04930051649726886,"rank":266,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.050579559641055094,"rank":251,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04864769774083644,"rank":265,"remainingConfigurations":398},{"removed":"simpleqa","score":0.05089802317690875,"rank":264,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04828175395665219,"rank":265,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04837400559911978,"rank":265,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04828990754382365,"rank":265,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04844659466766576,"rank":265,"remainingConfigurations":398},{"removed":"vibe-code","score":0.048229177529113126,"rank":265,"remainingConfigurations":398}]},"qwen3-vl-235b-a22b-instruct--effort-non-reasoning":{"score":0.04787945329809313,"rank":266,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05767616891870644,"rank":266,"remainingConfigurations":398},{"removed":"Datacurve","score":0.04071808656361822,"rank":266,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04734614198513589,"rank":266,"remainingConfigurations":398},{"removed":"Scale","score":0.05320275632362086,"rank":266,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04781369089437736,"rank":266,"remainingConfigurations":398},{"removed":"Cognition","score":0.05026190776069855,"rank":266,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04904168962572573,"rank":265,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04914646730467384,"rank":267,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.048133907386874696,"rank":251,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04653116798358956,"rank":265,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04788235284554737,"rank":266,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.047833714732816224,"rank":266,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0477970767765668,"rank":266,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04787945329809313,"rank":266,"remainingConfigurations":398},{"removed":"All provider reports","score":0.047746354828390875,"rank":266,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04802401394698689,"rank":266,"remainingConfigurations":398},{"removed":"briefcase","score":0.047762601571265974,"rank":266,"remainingConfigurations":398},{"removed":"aime","score":0.04701059245317473,"rank":268,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04838387348376608,"rank":266,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04911887288261633,"rank":264,"remainingConfigurations":398},{"removed":"automationbench","score":0.04783995699369731,"rank":266,"remainingConfigurations":398},{"removed":"critpt","score":0.050191272737760494,"rank":261,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04791725418583686,"rank":266,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04846414022829684,"rank":267,"remainingConfigurations":398},{"removed":"gdpval","score":0.04812515483088616,"rank":267,"remainingConfigurations":398},{"removed":"gmmlu","score":0.048246940229182446,"rank":266,"remainingConfigurations":398},{"removed":"gpqa","score":0.047059341009625576,"rank":265,"remainingConfigurations":398},{"removed":"harvey","score":0.04732003158902931,"rank":266,"remainingConfigurations":398},{"removed":"hle","score":0.05188226799656015,"rank":263,"remainingConfigurations":398},{"removed":"ifbench","score":0.047164696950106964,"rank":265,"remainingConfigurations":398},{"removed":"itbench","score":0.04779369729492492,"rank":266,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04774448999588746,"rank":265,"remainingConfigurations":398},{"removed":"math500","score":0.04808965197509218,"rank":265,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.046122206744478644,"rank":270,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04835698801850591,"rank":268,"remainingConfigurations":398},{"removed":"omniscience","score":0.04374286243199991,"rank":269,"remainingConfigurations":398},{"removed":"scicode","score":0.048771982754820115,"rank":266,"remainingConfigurations":398},{"removed":"tau-bench","score":0.047929831469019864,"rank":265,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04997723762062219,"rank":263,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05725588127764128,"rank":266,"remainingConfigurations":398},{"removed":"deepswe","score":0.04074857659316954,"rank":266,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04789312288979521,"rank":266,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.047546556930528394,"rank":266,"remainingConfigurations":398},{"removed":"frontiercode","score":0.05026190776069855,"rank":266,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.047923845807722555,"rank":266,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04743768706386436,"rank":266,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04780929905992301,"rank":266,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04770120734844896,"rank":266,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04796293500084257,"rank":266,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.047490278770885706,"rank":266,"remainingConfigurations":398},{"removed":"livebench-language","score":0.048444094942070914,"rank":266,"remainingConfigurations":398},{"removed":"livebench-data","score":0.047977630122439774,"rank":266,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.047120341746838684,"rank":266,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04755980144730462,"rank":266,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04861924520881564,"rank":266,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04914646730467384,"rank":267,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04542729388388756,"rank":264,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04836493677875393,"rank":266,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04981571328025131,"rank":266,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04764234055878733,"rank":266,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04771132014480112,"rank":266,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.047680263188751515,"rank":266,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04779713038226988,"rank":266,"remainingConfigurations":398},{"removed":"vibe-code","score":0.047555404772485994,"rank":266,"remainingConfigurations":398}]},"qwen3-coder-next--effort-non-reasoning":{"score":0.046604000016587176,"rank":267,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05579818260441841,"rank":267,"remainingConfigurations":398},{"removed":"Datacurve","score":0.039567537199858616,"rank":267,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.046162075671143256,"rank":267,"remainingConfigurations":398},{"removed":"Scale","score":0.05186395284517407,"rank":267,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04653990152958063,"rank":267,"remainingConfigurations":398},{"removed":"Cognition","score":0.04877434729864331,"rank":267,"remainingConfigurations":398},{"removed":"LiveBench","score":0.047756157208418394,"rank":266,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0478601358223039,"rank":268,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04750747480999517,"rank":252,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04530087545056286,"rank":266,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04660666934251878,"rank":267,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.046559822796219,"rank":267,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.046522346350808715,"rank":267,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.046604000016587176,"rank":267,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04647311090505568,"rank":267,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04674251542033538,"rank":267,"remainingConfigurations":398},{"removed":"briefcase","score":0.04554323165840119,"rank":270,"remainingConfigurations":398},{"removed":"aime","score":0.04676149058154363,"rank":269,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04715563406423067,"rank":267,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04549171437539004,"rank":267,"remainingConfigurations":398},{"removed":"automationbench","score":0.04641385696285267,"rank":268,"remainingConfigurations":398},{"removed":"critpt","score":0.049004912855438586,"rank":265,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04662722676157293,"rank":267,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0462671059085366,"rank":269,"remainingConfigurations":398},{"removed":"gdpval","score":0.045328031531940406,"rank":270,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04804507653963336,"rank":267,"remainingConfigurations":398},{"removed":"gpqa","score":0.04476619613416896,"rank":270,"remainingConfigurations":398},{"removed":"harvey","score":0.04602759165441405,"rank":267,"remainingConfigurations":398},{"removed":"hle","score":0.048010869992389245,"rank":272,"remainingConfigurations":398},{"removed":"ifbench","score":0.04872031321933155,"rank":262,"remainingConfigurations":398},{"removed":"itbench","score":0.04651367720923621,"rank":267,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04661731463376028,"rank":267,"remainingConfigurations":398},{"removed":"math500","score":0.04685238368608457,"rank":268,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.048126370540114975,"rank":266,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.049806879666647846,"rank":266,"remainingConfigurations":398},{"removed":"omniscience","score":0.047247053537473015,"rank":265,"remainingConfigurations":398},{"removed":"scicode","score":0.047131882188684644,"rank":268,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04444265153118784,"rank":271,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04526915117130392,"rank":273,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05540658814795007,"rank":267,"remainingConfigurations":398},{"removed":"deepswe","score":0.039597829251794,"rank":267,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04661776302811368,"rank":267,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04628814123833643,"rank":267,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04877434729864331,"rank":267,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04664956421181341,"rank":267,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.046170596597427484,"rank":267,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04653703645564905,"rank":267,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.046429946465319,"rank":267,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04668472498827284,"rank":267,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04622771762740808,"rank":267,"remainingConfigurations":398},{"removed":"livebench-language","score":0.047158951070424844,"rank":267,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04670015040084249,"rank":267,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04586036037705521,"rank":267,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.046291927409604756,"rank":267,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04732210993628171,"rank":267,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0478601358223039,"rank":268,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04438955214825668,"rank":265,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04703349164347798,"rank":267,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04847917918028327,"rank":267,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04637206751017015,"rank":267,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04644061437319191,"rank":267,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04640855559734199,"rank":267,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.046526162038528725,"rank":267,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04628703317077736,"rank":267,"remainingConfigurations":398}]},"qwen3-30b-a3b-thinking-2507--effort-reasoning":{"score":0.046402764140352666,"rank":268,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05559181566075455,"rank":268,"remainingConfigurations":398},{"removed":"Datacurve","score":0.039414823945218676,"rank":268,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.045910604882530986,"rank":268,"remainingConfigurations":398},{"removed":"Scale","score":0.05155739516767757,"rank":268,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.046336984564358974,"rank":268,"remainingConfigurations":398},{"removed":"Cognition","score":0.048611393249829986,"rank":268,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04754068512376886,"rank":267,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04762969961868446,"rank":269,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.046990685384498944,"rank":253,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04510989456959049,"rank":267,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04640544708993118,"rank":268,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0463585895126194,"rank":268,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04632191914234677,"rank":268,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.046402764140352666,"rank":268,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04627274309089205,"rank":268,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04654384668133928,"rank":268,"remainingConfigurations":398},{"removed":"briefcase","score":0.04734715195709315,"rank":267,"remainingConfigurations":398},{"removed":"aime","score":0.047239082572131365,"rank":265,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04692687368911991,"rank":268,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04402771349841853,"rank":270,"remainingConfigurations":398},{"removed":"automationbench","score":0.047096249647047526,"rank":267,"remainingConfigurations":398},{"removed":"critpt","score":0.04388420087508823,"rank":274,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04644809210448536,"rank":268,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04888610077494062,"rank":265,"remainingConfigurations":398},{"removed":"gdpval","score":0.048235458372015615,"rank":266,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04668634315389447,"rank":268,"remainingConfigurations":398},{"removed":"gpqa","score":0.04554841775858398,"rank":268,"remainingConfigurations":398},{"removed":"harvey","score":0.045859956698794564,"rank":268,"remainingConfigurations":398},{"removed":"hle","score":0.048014204525205474,"rank":271,"remainingConfigurations":398},{"removed":"ifbench","score":0.04353302550573432,"rank":270,"remainingConfigurations":398},{"removed":"itbench","score":0.046321504005849855,"rank":268,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0446681887574562,"rank":272,"remainingConfigurations":398},{"removed":"math500","score":0.04487058183015988,"rank":270,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.047389872648078014,"rank":267,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04954462197072527,"rank":267,"remainingConfigurations":398},{"removed":"omniscience","score":0.0456598165464307,"rank":267,"remainingConfigurations":398},{"removed":"scicode","score":0.04741492459841257,"rank":267,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04715060508429885,"rank":266,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04842158357436701,"rank":267,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05520031003607118,"rank":268,"remainingConfigurations":398},{"removed":"deepswe","score":0.03944498035831393,"rank":268,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04641641582246133,"rank":268,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04608517950653334,"rank":268,"remainingConfigurations":398},{"removed":"frontiercode","score":0.048611393249829986,"rank":268,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04644974228427481,"rank":268,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04597219239654574,"rank":268,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04633628408840706,"rank":268,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.046230291480065154,"rank":268,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04648323192221011,"rank":268,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04602763560261904,"rank":268,"remainingConfigurations":398},{"removed":"livebench-language","score":0.046955002617443814,"rank":268,"remainingConfigurations":398},{"removed":"livebench-data","score":0.046498206741952895,"rank":268,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.045662538815276654,"rank":268,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.046092030970247326,"rank":268,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04711851499742798,"rank":268,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04762969961868446,"rank":269,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04411567049174272,"rank":266,"remainingConfigurations":398},{"removed":"frontiermath","score":0.046832129228329404,"rank":268,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04828077487690118,"rank":268,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04617173715403524,"rank":268,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04623992445296395,"rank":268,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04620850117704717,"rank":268,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04632488016202313,"rank":268,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04608704557171651,"rank":268,"remainingConfigurations":398}]},"gemini-2.5-flash--effort-non-reasoning":{"score":0.045615101785798244,"rank":269,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05518300316146007,"rank":269,"remainingConfigurations":398},{"removed":"Datacurve","score":0.038810288956362717,"rank":269,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.045138569797436266,"rank":269,"remainingConfigurations":398},{"removed":"Scale","score":0.05072049696140899,"rank":269,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04554824689135197,"rank":269,"remainingConfigurations":398},{"removed":"Cognition","score":0.047915301469379196,"rank":269,"remainingConfigurations":398},{"removed":"LiveBench","score":0.046753087603922834,"rank":268,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04684509348879431,"rank":270,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04601558978315773,"rank":254,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0443436074858489,"rank":268,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04561784216193616,"rank":269,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04557123866085303,"rank":269,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04553691128617154,"rank":269,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.045615101785798244,"rank":269,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04548824524321957,"rank":269,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04579420917357426,"rank":269,"remainingConfigurations":398},{"removed":"briefcase","score":0.04565265821684334,"rank":269,"remainingConfigurations":398},{"removed":"aime","score":0.0460712002062826,"rank":270,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04614361848869369,"rank":269,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.043479035466468634,"rank":273,"remainingConfigurations":398},{"removed":"automationbench","score":0.04573463956864587,"rank":270,"remainingConfigurations":398},{"removed":"critpt","score":0.039915146435125747,"rank":283,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.045730075167441535,"rank":269,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.046322268636196505,"rank":268,"remainingConfigurations":398},{"removed":"gdpval","score":0.04604419677646988,"rank":268,"remainingConfigurations":398},{"removed":"gmmlu","score":0.045987399396146565,"rank":269,"remainingConfigurations":398},{"removed":"gpqa","score":0.04536861126208877,"rank":269,"remainingConfigurations":398},{"removed":"harvey","score":0.0451293143160836,"rank":269,"remainingConfigurations":398},{"removed":"hle","score":0.051790214043138744,"rank":264,"remainingConfigurations":398},{"removed":"ifbench","score":0.046324925656166444,"rank":267,"remainingConfigurations":398},{"removed":"itbench","score":0.04557680726485449,"rank":269,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04705575351115441,"rank":266,"remainingConfigurations":398},{"removed":"math500","score":0.04752369714993477,"rank":267,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.045207521396424734,"rank":273,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0468920637380939,"rank":274,"remainingConfigurations":398},{"removed":"omniscience","score":0.03899706256528113,"rank":280,"remainingConfigurations":398},{"removed":"scicode","score":0.04664735055582755,"rank":269,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05058758937522886,"rank":262,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.045730942289535524,"rank":271,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05477318541475731,"rank":269,"remainingConfigurations":398},{"removed":"deepswe","score":0.038839386153625984,"rank":269,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04562816782661334,"rank":269,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04529814741732371,"rank":269,"remainingConfigurations":398},{"removed":"frontiercode","score":0.047915301469379196,"rank":269,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.045661269658122276,"rank":269,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04519527981454594,"rank":269,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04554848553852737,"rank":269,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.045444721725808566,"rank":269,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04569496946248742,"rank":269,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.045242105265152203,"rank":269,"remainingConfigurations":398},{"removed":"livebench-language","score":0.046155364624811256,"rank":269,"remainingConfigurations":398},{"removed":"livebench-data","score":0.045709381280647284,"rank":269,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04488876944667414,"rank":269,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04530915547971646,"rank":269,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.046323651397734616,"rank":269,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04684509348879431,"rank":270,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04327897885132095,"rank":267,"remainingConfigurations":398},{"removed":"frontiermath","score":0.046083968384409375,"rank":269,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04747066672187104,"rank":269,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.045388251330254877,"rank":269,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04545412156947489,"rank":269,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04542453696715728,"rank":269,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04553602572569498,"rank":269,"remainingConfigurations":398},{"removed":"vibe-code","score":0.045304909507154205,"rank":269,"remainingConfigurations":398}]},"qwen3.5-omni-flash--effort-non-reasoning":{"score":0.04474253082529738,"rank":270,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.054080481670883494,"rank":270,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03805178406396826,"rank":270,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.044291489370038815,"rank":271,"remainingConfigurations":398},{"removed":"Scale","score":0.049761489368645294,"rank":270,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04467167013850167,"rank":270,"remainingConfigurations":398},{"removed":"Cognition","score":0.04701275948806829,"rank":270,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04583061427618301,"rank":269,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0459713838412795,"rank":271,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04500311037036476,"rank":257,"remainingConfigurations":381},{"removed":"Vals AI","score":0.043474828588361276,"rank":269,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.044745274219803115,"rank":270,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04469988079958564,"rank":270,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.044665168507713494,"rank":270,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04474253082529738,"rank":270,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04461783331433521,"rank":270,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04488088800509832,"rank":270,"remainingConfigurations":398},{"removed":"briefcase","score":0.044613044837276926,"rank":271,"remainingConfigurations":398},{"removed":"aime","score":0.044832644485015144,"rank":272,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04522575187239151,"rank":271,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.042694443048890536,"rank":276,"remainingConfigurations":398},{"removed":"automationbench","score":0.044697159885603154,"rank":271,"remainingConfigurations":398},{"removed":"critpt","score":0.04782310911323845,"rank":267,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.044777681794934576,"rank":271,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04527243079203697,"rank":270,"remainingConfigurations":398},{"removed":"gdpval","score":0.04491593022423604,"rank":271,"remainingConfigurations":398},{"removed":"gmmlu","score":0.045106088687008494,"rank":271,"remainingConfigurations":398},{"removed":"gpqa","score":0.042029230942126884,"rank":277,"remainingConfigurations":398},{"removed":"harvey","score":0.04421351865680259,"rank":271,"remainingConfigurations":398},{"removed":"hle","score":0.04740482463517998,"rank":273,"remainingConfigurations":398},{"removed":"ifbench","score":0.047054704952441746,"rank":266,"remainingConfigurations":398},{"removed":"itbench","score":0.04467107683123567,"rank":271,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04470350465879053,"rank":271,"remainingConfigurations":398},{"removed":"math500","score":0.044918004382734994,"rank":269,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.046080729351608174,"rank":271,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.045483119572421384,"rank":277,"remainingConfigurations":398},{"removed":"omniscience","score":0.046980917745332175,"rank":266,"remainingConfigurations":398},{"removed":"scicode","score":0.04556629387917566,"rank":271,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03853581438070696,"rank":282,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.045617019359409046,"rank":272,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05367004858327471,"rank":270,"remainingConfigurations":398},{"removed":"deepswe","score":0.03808031666577992,"rank":270,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04475535748105156,"rank":270,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04443295430998059,"rank":270,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04701275948806829,"rank":270,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04478927288776633,"rank":270,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.044330608821835454,"rank":270,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.044676886273283,"rank":270,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04457496027662209,"rank":270,"remainingConfigurations":398},{"removed":"livebench-math","score":0.044821029399338186,"rank":270,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04437606601155813,"rank":270,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04527346212522229,"rank":270,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04483550149723786,"rank":270,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04402897141132226,"rank":270,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04444180268140308,"rank":270,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04543839861996437,"rank":270,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0459713838412795,"rank":271,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04247710476020908,"rank":268,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04519397588823462,"rank":270,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04655665105093414,"rank":270,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.044519670030543586,"rank":270,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04458448566544948,"rank":270,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04455507889738381,"rank":270,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04466493672695269,"rank":270,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04443812200457076,"rank":270,"remainingConfigurations":398}]},"gpt-oss-120b--effort-high":{"score":0.044556730926555405,"rank":271,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.015742405193032303,"rank":157,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05326893954076339,"rank":274,"remainingConfigurations":398},{"removed":"Datacurve","score":0.037604115757570916,"rank":273,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.044331946627689967,"rank":270,"remainingConfigurations":398},{"removed":"Scale","score":0.049523327607965184,"rank":271,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.044377042823949366,"rank":273,"remainingConfigurations":398},{"removed":"Cognition","score":0.04676791758120341,"rank":271,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04531082807988917,"rank":272,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.06329495219330557,"rank":245,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.057465832367635895,"rank":236,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04309304676044354,"rank":272,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04456151075209397,"rank":271,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04451348881352462,"rank":271,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.044492635790412065,"rank":271,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.044556730926555405,"rank":271,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04444704133888264,"rank":271,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04468181254356062,"rank":271,"remainingConfigurations":398},{"removed":"briefcase","score":0.04615629090968163,"rank":268,"remainingConfigurations":398},{"removed":"aime","score":0.042897118830804236,"rank":277,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04533086748578289,"rank":270,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0445212564154222,"rank":268,"remainingConfigurations":398},{"removed":"automationbench","score":0.04598076572349478,"rank":269,"remainingConfigurations":398},{"removed":"critpt","score":0.043605377785422374,"rank":276,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0451881646262958,"rank":270,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04471454490832431,"rank":274,"remainingConfigurations":398},{"removed":"gdpval","score":0.04453507172583441,"rank":273,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04438500338274889,"rank":274,"remainingConfigurations":398},{"removed":"gpqa","score":0.04290977533434533,"rank":275,"remainingConfigurations":398},{"removed":"harvey","score":0.044879523798108806,"rank":270,"remainingConfigurations":398},{"removed":"hle","score":0.045881993081824446,"rank":276,"remainingConfigurations":398},{"removed":"ifbench","score":0.04235642830837132,"rank":272,"remainingConfigurations":398},{"removed":"itbench","score":0.04541569623499699,"rank":270,"remainingConfigurations":398},{"removed":"livecodebench","score":0.043101733032030104,"rank":275,"remainingConfigurations":398},{"removed":"math500","score":0.0446857049191387,"rank":273,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0462172874450607,"rank":269,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04764101242674617,"rank":269,"remainingConfigurations":398},{"removed":"omniscience","score":0.0431411122934633,"rank":270,"remainingConfigurations":398},{"removed":"scicode","score":0.04600568112954235,"rank":270,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04364541460351288,"rank":274,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04475639632583183,"rank":274,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0528159134444631,"rank":274,"remainingConfigurations":398},{"removed":"deepswe","score":0.03763160452008254,"rank":273,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.044568779169310374,"rank":271,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.044208503081308304,"rank":271,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04676791758120341,"rank":271,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04463929240674977,"rank":271,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04409862194850243,"rank":271,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04449897329446312,"rank":271,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0443940315349838,"rank":271,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04463354208964689,"rank":271,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0441873611891831,"rank":271,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04506758181057982,"rank":271,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04464724768554514,"rank":271,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04385368501509047,"rank":271,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.044250932161093215,"rank":271,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04527374899178066,"rank":271,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.06329495219330557,"rank":245,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.054158715060572904,"rank":247,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04432013333249465,"rank":275,"remainingConfigurations":398},{"removed":"simpleqa","score":0.046288148566352945,"rank":272,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.044334185142959885,"rank":271,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04439857968410771,"rank":271,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.044372959293689,"rank":271,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.044472929720086575,"rank":271,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04425276544310854,"rank":271,"remainingConfigurations":398}]},"gpt-oss-120b--effort-low":{"score":0.04450311124998657,"rank":272,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.053611949539591974,"rank":271,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03783423215617467,"rank":271,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04404035312479551,"rank":272,"remainingConfigurations":398},{"removed":"Scale","score":0.049501774112202274,"rank":273,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.044433577358604336,"rank":271,"remainingConfigurations":398},{"removed":"Cognition","score":0.046723855445360424,"rank":272,"remainingConfigurations":398},{"removed":"LiveBench","score":0.045586487616628646,"rank":270,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04566118046492917,"rank":272,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.045045971045772897,"rank":255,"remainingConfigurations":381},{"removed":"Vals AI","score":0.043245457200245474,"rank":270,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04450574273581795,"rank":272,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04446049044201939,"rank":272,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04442644542541563,"rank":272,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04450311124998657,"rank":272,"remainingConfigurations":398},{"removed":"All provider reports","score":0.044379072517313066,"rank":272,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04462671193330121,"rank":272,"remainingConfigurations":398},{"removed":"briefcase","score":0.04430281088783322,"rank":273,"remainingConfigurations":398},{"removed":"aime","score":0.04391020345786004,"rank":274,"remainingConfigurations":398},{"removed":"apex-agents","score":0.044978750084756026,"rank":272,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04351376914870825,"rank":272,"remainingConfigurations":398},{"removed":"automationbench","score":0.04440098577812656,"rank":273,"remainingConfigurations":398},{"removed":"critpt","score":0.046141910133870055,"rank":270,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04453152517512523,"rank":272,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04497582095879043,"rank":272,"remainingConfigurations":398},{"removed":"gdpval","score":0.04586280163147855,"rank":269,"remainingConfigurations":398},{"removed":"gmmlu","score":0.044885889719134826,"rank":272,"remainingConfigurations":398},{"removed":"gpqa","score":0.044558333583465344,"rank":272,"remainingConfigurations":398},{"removed":"harvey","score":0.04397858775884184,"rank":272,"remainingConfigurations":398},{"removed":"hle","score":0.048613040709785164,"rank":268,"remainingConfigurations":398},{"removed":"ifbench","score":0.04003881527037688,"rank":282,"remainingConfigurations":398},{"removed":"itbench","score":0.04441183568716864,"rank":272,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04211148185732694,"rank":276,"remainingConfigurations":398},{"removed":"math500","score":0.0448218247554024,"rank":271,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04725020313640394,"rank":268,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.047509386467725845,"rank":271,"remainingConfigurations":398},{"removed":"omniscience","score":0.04078607198820322,"rank":278,"remainingConfigurations":398},{"removed":"scicode","score":0.04527014117632,"rank":273,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04427298739238883,"rank":273,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.046449190464954125,"rank":270,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05322478181933543,"rank":271,"remainingConfigurations":398},{"removed":"deepswe","score":0.03786269188695315,"rank":271,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.044515953655250684,"rank":272,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04419400293929069,"rank":272,"remainingConfigurations":398},{"removed":"frontiercode","score":0.046723855445360424,"rank":272,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.044547916245553106,"rank":272,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04409221914904412,"rank":272,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.044438097640238074,"rank":272,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04433654172147523,"rank":272,"remainingConfigurations":398},{"removed":"livebench-math","score":0.044581323778812215,"rank":272,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.044138296773814985,"rank":272,"remainingConfigurations":398},{"removed":"livebench-language","score":0.045031599789854444,"rank":272,"remainingConfigurations":398},{"removed":"livebench-data","score":0.044595857038693267,"rank":272,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04379264534133522,"rank":272,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04420376844985596,"rank":272,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04519578079918952,"rank":272,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04566118046492917,"rank":272,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.042238824223870236,"rank":269,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04494698043848546,"rank":271,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04631279369779385,"rank":271,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04428119144810586,"rank":272,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04434590195402832,"rank":272,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04431655011786411,"rank":272,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04442618481036298,"rank":272,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04419979702719199,"rank":272,"remainingConfigurations":398}]},"gpt-5--effort-non-reasoning":{"score":0.044474629776370816,"rank":273,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05351594553277577,"rank":272,"remainingConfigurations":398},{"removed":"Datacurve","score":0.037813791141431415,"rank":272,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.044018487618101974,"rank":273,"remainingConfigurations":398},{"removed":"Scale","score":0.049508125452647274,"rank":272,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.044403483867806424,"rank":272,"remainingConfigurations":398},{"removed":"Cognition","score":0.046695132623673107,"rank":273,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04555271017950669,"rank":271,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04565764870744588,"rank":273,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04502957319755741,"rank":256,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04321559277532261,"rank":271,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0444773386213714,"rank":273,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04443221213514728,"rank":273,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04439807170164246,"rank":273,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.044474629776370816,"rank":273,"remainingConfigurations":398},{"removed":"All provider reports","score":0.044350983976759684,"rank":273,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04460755666810217,"rank":273,"remainingConfigurations":398},{"removed":"briefcase","score":0.04435586792196364,"rank":272,"remainingConfigurations":398},{"removed":"aime","score":0.04717278582632332,"rank":267,"remainingConfigurations":398},{"removed":"apex-agents","score":0.044953065956714,"rank":273,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03598607745657532,"rank":290,"remainingConfigurations":398},{"removed":"automationbench","score":0.04443103676988714,"rank":272,"remainingConfigurations":398},{"removed":"critpt","score":0.043684177448739786,"rank":275,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.044509651859624196,"rank":273,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04500698499585485,"rank":271,"remainingConfigurations":398},{"removed":"gdpval","score":0.04470031458076961,"rank":272,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04484828293741183,"rank":273,"remainingConfigurations":398},{"removed":"gpqa","score":0.044379496984241845,"rank":273,"remainingConfigurations":398},{"removed":"harvey","score":0.043948383670323665,"rank":273,"remainingConfigurations":398},{"removed":"hle","score":0.0483767173049631,"rank":269,"remainingConfigurations":398},{"removed":"ifbench","score":0.042683935598381774,"rank":271,"remainingConfigurations":398},{"removed":"itbench","score":0.04437512079014516,"rank":273,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04528079438063599,"rank":269,"remainingConfigurations":398},{"removed":"math500","score":0.04473416262558358,"rank":272,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04204069620941627,"rank":279,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04761914296866968,"rank":270,"remainingConfigurations":398},{"removed":"omniscience","score":0.04220779511575564,"rank":271,"remainingConfigurations":398},{"removed":"scicode","score":0.04530740906349942,"rank":272,"remainingConfigurations":398},{"removed":"tau-bench","score":0.05300297439189617,"rank":254,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04422816692257293,"rank":276,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05312756697367566,"rank":272,"remainingConfigurations":398},{"removed":"deepswe","score":0.03784221163957736,"rank":272,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.044487406185948736,"rank":273,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.044166276300247165,"rank":273,"remainingConfigurations":398},{"removed":"frontiercode","score":0.046695132623673107,"rank":273,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04451895332160027,"rank":273,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04406388544806375,"rank":273,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.044409516115920915,"rank":273,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.044308204036659526,"rank":273,"remainingConfigurations":398},{"removed":"livebench-math","score":0.044552831995354814,"rank":273,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04410950442215058,"rank":273,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04500240531604835,"rank":273,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0445673558409079,"rank":273,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04376502540218596,"rank":273,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04417541172942551,"rank":273,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04516734833242634,"rank":273,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04565764870744588,"rank":273,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04220564495034115,"rank":270,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0449422563218436,"rank":272,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04628782255061282,"rank":273,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04425296163678844,"rank":273,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04431742164279493,"rank":273,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04428829860258604,"rank":273,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.044397444112193284,"rank":273,"remainingConfigurations":398},{"removed":"vibe-code","score":0.044171719186879045,"rank":273,"remainingConfigurations":398}]},"solar-open-100b--effort-reasoning":{"score":0.0442092575795106,"rank":274,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.053345144468591676,"rank":273,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03756596835266058,"rank":274,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04375333351917655,"rank":274,"remainingConfigurations":398},{"removed":"Scale","score":0.04917402617293928,"rank":274,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04413444004989472,"rank":274,"remainingConfigurations":398},{"removed":"Cognition","score":0.046420156499756456,"rank":274,"remainingConfigurations":398},{"removed":"LiveBench","score":0.045274090593208687,"rank":273,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04532069164190606,"rank":274,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04445395685457366,"rank":258,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0429470998225935,"rank":273,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04421194753633134,"rank":274,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04416719848830583,"rank":274,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04413322318213756,"rank":274,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0442092575795106,"rank":274,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0440865127258879,"rank":274,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.044344775204483045,"rank":274,"remainingConfigurations":398},{"removed":"briefcase","score":0.0441022620131483,"rank":274,"remainingConfigurations":398},{"removed":"aime","score":0.04429190434495838,"rank":273,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04468580963225416,"rank":274,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.044196882239974096,"rank":269,"remainingConfigurations":398},{"removed":"automationbench","score":0.04418548962364042,"rank":274,"remainingConfigurations":398},{"removed":"critpt","score":0.047189248641593746,"rank":269,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.044241386115923376,"rank":274,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.044743539533031625,"rank":273,"remainingConfigurations":398},{"removed":"gdpval","score":0.04437397190857422,"rank":274,"remainingConfigurations":398},{"removed":"gmmlu","score":0.042880949507254844,"rank":279,"remainingConfigurations":398},{"removed":"gpqa","score":0.045848722521759304,"rank":267,"remainingConfigurations":398},{"removed":"harvey","score":0.043684504451933726,"rank":274,"remainingConfigurations":398},{"removed":"hle","score":0.044184470610046885,"rank":279,"remainingConfigurations":398},{"removed":"ifbench","score":0.03856718154460078,"rank":283,"remainingConfigurations":398},{"removed":"itbench","score":0.04413105243771535,"rank":274,"remainingConfigurations":398},{"removed":"livecodebench","score":0.044116255652179685,"rank":273,"remainingConfigurations":398},{"removed":"math500","score":0.04433233266596859,"rank":274,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0455159289323851,"rank":272,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04721968698844309,"rank":273,"remainingConfigurations":398},{"removed":"omniscience","score":0.04103921991677945,"rank":277,"remainingConfigurations":398},{"removed":"scicode","score":0.045032134278179314,"rank":274,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04154467079270121,"rank":278,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.050734995957161654,"rank":260,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05296208112337952,"rank":273,"remainingConfigurations":398},{"removed":"deepswe","score":0.037594238618848815,"rank":274,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04422196969848505,"rank":274,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04390217310959904,"rank":274,"remainingConfigurations":398},{"removed":"frontiercode","score":0.046420156499756456,"rank":274,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04425009662146317,"rank":274,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04380138814491649,"rank":274,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04414393613027778,"rank":274,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04404368679452449,"rank":274,"remainingConfigurations":398},{"removed":"livebench-math","score":0.044287032316212456,"rank":274,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04384648274135745,"rank":274,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04473430681581797,"rank":274,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0443011782602215,"rank":274,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04350342083557018,"rank":274,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04391182472365778,"rank":274,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04489795794924648,"rank":274,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04532069164190606,"rank":274,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.041896471820811264,"rank":271,"remainingConfigurations":398},{"removed":"frontiermath","score":0.044654819377814015,"rank":273,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04600444763631222,"rank":274,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04398882894423469,"rank":274,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04405286033010123,"rank":274,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04402379953593186,"rank":274,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.044132535230479074,"rank":274,"remainingConfigurations":398},{"removed":"vibe-code","score":0.043908100552685174,"rank":274,"remainingConfigurations":398}]},"qwen3-vl-30b-a3b-thinking--effort-reasoning":{"score":0.043951887574566646,"rank":275,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.053032334166198035,"rank":275,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03735055207607358,"rank":275,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04346720226996665,"rank":275,"remainingConfigurations":398},{"removed":"Scale","score":0.048884448850534945,"rank":275,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.043886055543944515,"rank":275,"remainingConfigurations":398},{"removed":"Cognition","score":0.04616656092975615,"rank":275,"remainingConfigurations":398},{"removed":"LiveBench","score":0.045016226365097056,"rank":274,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04511441533325838,"rank":275,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04416517161097291,"rank":259,"remainingConfigurations":381},{"removed":"Vals AI","score":0.042711238431050215,"rank":274,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04395457039053105,"rank":275,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04390966698764132,"rank":275,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04387612173545913,"rank":275,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.043951887574566646,"rank":275,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0438292894284898,"rank":275,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0440816562083684,"rank":275,"remainingConfigurations":398},{"removed":"briefcase","score":0.0438236637129967,"rank":275,"remainingConfigurations":398},{"removed":"aime","score":0.04024555767503049,"rank":281,"remainingConfigurations":398},{"removed":"apex-agents","score":0.044419567734249606,"rank":275,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.043514313040881526,"rank":271,"remainingConfigurations":398},{"removed":"automationbench","score":0.043907310449424676,"rank":275,"remainingConfigurations":398},{"removed":"critpt","score":0.04588134198035019,"rank":271,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04398752447220603,"rank":275,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04447103610685501,"rank":275,"remainingConfigurations":398},{"removed":"gdpval","score":0.04419098900561508,"rank":275,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0442881102790644,"rank":275,"remainingConfigurations":398},{"removed":"gpqa","score":0.042523370332241274,"rank":276,"remainingConfigurations":398},{"removed":"harvey","score":0.04343086209715267,"rank":275,"remainingConfigurations":398},{"removed":"hle","score":0.045708937815229354,"rank":277,"remainingConfigurations":398},{"removed":"ifbench","score":0.041825958594319645,"rank":274,"remainingConfigurations":398},{"removed":"itbench","score":0.04387438839751051,"rank":275,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04146738980806655,"rank":279,"remainingConfigurations":398},{"removed":"math500","score":0.04423349883553773,"rank":275,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.043902958179684044,"rank":277,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.047220776102703636,"rank":272,"remainingConfigurations":398},{"removed":"omniscience","score":0.04193220048890638,"rank":272,"remainingConfigurations":398},{"removed":"scicode","score":0.04475731309266807,"rank":275,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04802426893365037,"rank":264,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04696826738652768,"rank":269,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05264040645635193,"rank":275,"remainingConfigurations":398},{"removed":"deepswe","score":0.03737862284029407,"rank":275,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04396450776899119,"rank":275,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04364610254648733,"rank":275,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04616656092975615,"rank":275,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.043994276900464806,"rank":275,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.043545020138481876,"rank":275,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.043887534467878214,"rank":275,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.043787586375099226,"rank":275,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04402910119888271,"rank":275,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04359130621660299,"rank":275,"remainingConfigurations":398},{"removed":"livebench-language","score":0.044474090394875876,"rank":275,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04404300134118851,"rank":275,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.043249909931380066,"rank":275,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.043656086993270504,"rank":275,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04463700204344646,"rank":275,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04511441533325838,"rank":275,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.041667639422644544,"rank":272,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0444011954341798,"rank":274,"remainingConfigurations":398},{"removed":"simpleqa","score":0.045744260736155534,"rank":275,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.043732582970864624,"rank":275,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.043796240797839885,"rank":275,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04376770917284709,"rank":275,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.043875319035442756,"rank":275,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04365221759104351,"rank":275,"remainingConfigurations":398}]},"qwen3-next-80b-a3b-instruct--effort-non-reasoning":{"score":0.04358756757528543,"rank":276,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0525935559712569,"rank":277,"remainingConfigurations":398},{"removed":"Datacurve","score":0.037040106335614977,"rank":276,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04310928517315307,"rank":277,"remainingConfigurations":398},{"removed":"Scale","score":0.04849905926087372,"rank":276,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04352057510754937,"rank":276,"remainingConfigurations":398},{"removed":"Cognition","score":0.04578183623988242,"rank":276,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04464593380330311,"rank":275,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.044761738167226124,"rank":276,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.043860127341463086,"rank":261,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04235669645668805,"rank":275,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04359021267609228,"rank":276,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.043545871664508434,"rank":276,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04351263957868934,"rank":276,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04358756757528543,"rank":276,"remainingConfigurations":398},{"removed":"All provider reports","score":0.043466351560124766,"rank":276,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.043717914526684415,"rank":276,"remainingConfigurations":398},{"removed":"briefcase","score":0.04347946671843169,"rank":277,"remainingConfigurations":398},{"removed":"aime","score":0.04297487371596253,"rank":275,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04405813474001785,"rank":276,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04174579692462771,"rank":279,"remainingConfigurations":398},{"removed":"automationbench","score":0.0435495040015916,"rank":277,"remainingConfigurations":398},{"removed":"critpt","score":0.04546134843071863,"rank":272,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.043628400978375226,"rank":276,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.044123149551264805,"rank":277,"remainingConfigurations":398},{"removed":"gdpval","score":0.04381599074715559,"rank":277,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04391901132863058,"rank":276,"remainingConfigurations":398},{"removed":"gpqa","score":0.04154641159222942,"rank":280,"remainingConfigurations":398},{"removed":"harvey","score":0.043072865768464697,"rank":276,"remainingConfigurations":398},{"removed":"hle","score":0.04598961175817425,"rank":274,"remainingConfigurations":398},{"removed":"ifbench","score":0.04383111765189283,"rank":269,"remainingConfigurations":398},{"removed":"itbench","score":0.04351076861974251,"rank":276,"remainingConfigurations":398},{"removed":"livecodebench","score":0.041647615054668165,"rank":278,"remainingConfigurations":398},{"removed":"math500","score":0.043820425317591914,"rank":276,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04173104209942571,"rank":280,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04661438905592199,"rank":275,"remainingConfigurations":398},{"removed":"omniscience","score":0.041295664454460174,"rank":276,"remainingConfigurations":398},{"removed":"scicode","score":0.044407871453679366,"rank":277,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04710995229353777,"rank":268,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.044725864686781525,"rank":275,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05220730728828424,"rank":277,"remainingConfigurations":398},{"removed":"deepswe","score":0.037068009519340556,"rank":276,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04360012415840234,"rank":276,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.043284084676217034,"rank":276,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04578183623988242,"rank":276,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.043629995531822376,"rank":276,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04318392171008417,"rank":276,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.043523724727624113,"rank":276,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.043424686678613746,"rank":276,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04366428665909414,"rank":276,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04322929442431911,"rank":276,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04410585004786252,"rank":276,"remainingConfigurations":398},{"removed":"livebench-data","score":0.043678404036051506,"rank":276,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0428907948283123,"rank":276,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.043293843048891854,"rank":276,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04426772498194026,"rank":276,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.044761738167226124,"rank":276,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.04133973243466981,"rank":273,"remainingConfigurations":398},{"removed":"frontiermath","score":0.044030937596876076,"rank":276,"remainingConfigurations":398},{"removed":"simpleqa","score":0.045367963422188,"rank":276,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.043369909623190955,"rank":276,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04343316599523078,"rank":276,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04340469549801109,"rank":276,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0435117601604522,"rank":276,"remainingConfigurations":398},{"removed":"vibe-code","score":0.043290129972532586,"rank":276,"remainingConfigurations":398}]},"gpt-5.1--effort-non-reasoning":{"score":0.04355609227980487,"rank":277,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.052737154585581016,"rank":276,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03703236170245554,"rank":277,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04311335283514072,"rank":276,"remainingConfigurations":398},{"removed":"Scale","score":0.04843934272233804,"rank":277,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.043486498073714554,"rank":277,"remainingConfigurations":398},{"removed":"Cognition","score":0.04576227345015618,"rank":277,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04462159343127678,"rank":276,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04467710121220577,"rank":277,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04386802955798128,"rank":260,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04232558928756073,"rank":276,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04355873724443086,"rank":277,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04351423975985677,"rank":277,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04348096205483673,"rank":277,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04355609227980487,"rank":277,"remainingConfigurations":398},{"removed":"All provider reports","score":0.043434515786477335,"rank":277,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04370432050625947,"rank":277,"remainingConfigurations":398},{"removed":"briefcase","score":0.04348185628941042,"rank":276,"remainingConfigurations":398},{"removed":"aime","score":0.04745705952732446,"rank":264,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04404115636918591,"rank":277,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.042698625990271376,"rank":275,"remainingConfigurations":398},{"removed":"automationbench","score":0.04355886578835563,"rank":276,"remainingConfigurations":398},{"removed":"critpt","score":0.045180730140361926,"rank":273,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.043621329420782035,"rank":277,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.044134128995896166,"rank":276,"remainingConfigurations":398},{"removed":"gdpval","score":0.043844762245498325,"rank":276,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04387526219339691,"rank":277,"remainingConfigurations":398},{"removed":"gpqa","score":0.04465486182762448,"rank":271,"remainingConfigurations":398},{"removed":"harvey","score":0.043062312367055294,"rank":277,"remainingConfigurations":398},{"removed":"hle","score":0.048276171901798635,"rank":270,"remainingConfigurations":398},{"removed":"ifbench","score":0.04220119410100915,"rank":273,"remainingConfigurations":398},{"removed":"itbench","score":0.04350609419440684,"rank":277,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0451794327205168,"rank":270,"remainingConfigurations":398},{"removed":"math500","score":0.04377760273857496,"rank":277,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0439388889772362,"rank":276,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.046207238647558053,"rank":276,"remainingConfigurations":398},{"removed":"omniscience","score":0.03579704511262939,"rank":284,"remainingConfigurations":398},{"removed":"scicode","score":0.04443191236447011,"rank":276,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04188964353184189,"rank":277,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04154844218747493,"rank":280,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05235196226381158,"rank":276,"remainingConfigurations":398},{"removed":"deepswe","score":0.03706014927783021,"rank":277,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04356860887819631,"rank":277,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.043253835389909685,"rank":277,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04576227345015618,"rank":277,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04360014547196542,"rank":277,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0431538553514025,"rank":277,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04349239430646767,"rank":277,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04339292119927935,"rank":277,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04363271048113828,"rank":277,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.043198020072529014,"rank":277,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04407387577380811,"rank":277,"remainingConfigurations":398},{"removed":"livebench-data","score":0.043646871945189236,"rank":277,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04285990222616278,"rank":277,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04326260088416453,"rank":277,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04423590094301949,"rank":277,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04467710121220577,"rank":277,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.041284662046217446,"rank":274,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04399646874142309,"rank":277,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04533259725518657,"rank":277,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04333860191128616,"rank":277,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04340176578642705,"rank":277,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.043373459176736164,"rank":277,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04348009419686611,"rank":277,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04325884796520161,"rank":277,"remainingConfigurations":398}]},"gpt-oss-20b--effort-medium":{"score":0.041662787391579116,"rank":278,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.046895582660612306,"rank":145,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.05200632383505579,"rank":278,"remainingConfigurations":398},{"removed":"Datacurve","score":0.035577414250283025,"rank":278,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.04149640165730565,"rank":278,"remainingConfigurations":398},{"removed":"Scale","score":0.04604154145609644,"rank":278,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04166885314524041,"rank":278,"remainingConfigurations":398},{"removed":"Cognition","score":0.04476805531519871,"rank":278,"remainingConfigurations":398},{"removed":"LiveBench","score":0.042029149234072444,"rank":279,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04215325215632803,"rank":280,"remainingConfigurations":398},{"removed":"Epoch AI","score":null,"rank":null,"remainingConfigurations":381},{"removed":"Vals AI","score":0.04065606714154568,"rank":277,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.041663018970491614,"rank":278,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.041608268688247414,"rank":278,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04161593341753723,"rank":278,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.041662787391579116,"rank":278,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04155553534205741,"rank":278,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04176579369939187,"rank":278,"remainingConfigurations":398},{"removed":"briefcase","score":0.041590006426067985,"rank":279,"remainingConfigurations":398},{"removed":"aime","score":0.025976611385268484,"rank":318,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04200160317647588,"rank":279,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.041900333652593824,"rank":277,"remainingConfigurations":398},{"removed":"automationbench","score":0.04162165153922811,"rank":279,"remainingConfigurations":398},{"removed":"critpt","score":0.040933413182470964,"rank":280,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0417060212654231,"rank":278,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.041920988182635836,"rank":278,"remainingConfigurations":398},{"removed":"gdpval","score":0.041481584246268556,"rank":279,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04188059411797231,"rank":281,"remainingConfigurations":398},{"removed":"gpqa","score":0.056611815757389265,"rank":252,"remainingConfigurations":398},{"removed":"harvey","score":0.041163702932257934,"rank":278,"remainingConfigurations":398},{"removed":"hle","score":0.0435173465199614,"rank":281,"remainingConfigurations":398},{"removed":"ifbench","score":0.04176512325223477,"rank":275,"remainingConfigurations":398},{"removed":"itbench","score":0.041586140223425966,"rank":278,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04187917394540467,"rank":277,"remainingConfigurations":398},{"removed":"math500","score":0.0417551001579814,"rank":278,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.043052508163485693,"rank":278,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04441245333120065,"rank":278,"remainingConfigurations":398},{"removed":"omniscience","score":0.04154150068955195,"rank":274,"remainingConfigurations":398},{"removed":"scicode","score":0.04211437933375717,"rank":278,"remainingConfigurations":398},{"removed":"tau-bench","score":0.039892995130043,"rank":280,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04162343781790757,"rank":279,"remainingConfigurations":398},{"removed":"arc-agi","score":0.05177292240738642,"rank":278,"remainingConfigurations":398},{"removed":"deepswe","score":0.03560793166293038,"rank":278,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.04167375933711979,"rank":278,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04141209510068721,"rank":278,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04476805531519871,"rank":278,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04178181567328109,"rank":278,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04123420281039875,"rank":278,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04161081766191179,"rank":278,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04150388123509179,"rank":278,"remainingConfigurations":398},{"removed":"livebench-math","score":0.041779349453551246,"rank":278,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04119635976646793,"rank":278,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04215209486306301,"rank":278,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04177878324840666,"rank":278,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0410392888800492,"rank":278,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04136802471955968,"rank":278,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04233886072042517,"rank":278,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04215325215632803,"rank":280,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0372136792197,"rank":280,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04137142342633518,"rank":280,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04364833605082174,"rank":278,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04145391725835855,"rank":278,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.041531632895529545,"rank":278,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.04146061640767097,"rank":278,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.041595160287921026,"rank":278,"remainingConfigurations":398},{"removed":"vibe-code","score":0.04140581521002038,"rank":278,"remainingConfigurations":398}]},"gpt-oss-20b--effort-high":{"score":0.04140804953605689,"rank":279,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01905408903798275,"rank":154,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.049790566741377794,"rank":280,"remainingConfigurations":398},{"removed":"Datacurve","score":0.035205814313922994,"rank":279,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.041062640294455506,"rank":279,"remainingConfigurations":398},{"removed":"Scale","score":0.04602592886405093,"rank":279,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.04137105489346286,"rank":279,"remainingConfigurations":398},{"removed":"Cognition","score":0.04367909365666256,"rank":279,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04222759111439611,"rank":277,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04232310489462526,"rank":278,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0524324909953687,"rank":244,"remainingConfigurations":381},{"removed":"Vals AI","score":0.040287323252058284,"rank":278,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.04141009173871323,"rank":279,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.04136594863253621,"rank":279,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04134424021978954,"rank":279,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04140804953605689,"rank":279,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04129748694642585,"rank":279,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.04154210053266987,"rank":279,"remainingConfigurations":398},{"removed":"briefcase","score":0.04290487126829553,"rank":278,"remainingConfigurations":398},{"removed":"aime","score":0.03639882389419121,"rank":288,"remainingConfigurations":398},{"removed":"apex-agents","score":0.042592637476908585,"rank":278,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04185361180000863,"rank":278,"remainingConfigurations":398},{"removed":"automationbench","score":0.04321408650671191,"rank":278,"remainingConfigurations":398},{"removed":"critpt","score":0.038471729211846266,"rank":287,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04146981454563354,"rank":279,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04184895832671981,"rank":279,"remainingConfigurations":398},{"removed":"gdpval","score":0.041952842030143773,"rank":278,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04341521201862116,"rank":278,"remainingConfigurations":398},{"removed":"gpqa","score":0.04329313032248546,"rank":274,"remainingConfigurations":398},{"removed":"harvey","score":0.04093953741602549,"rank":279,"remainingConfigurations":398},{"removed":"hle","score":0.04291446887178172,"rank":283,"remainingConfigurations":398},{"removed":"ifbench","score":0.03844611390198022,"rank":285,"remainingConfigurations":398},{"removed":"itbench","score":0.04135180030147093,"rank":279,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03939924758584938,"rank":283,"remainingConfigurations":398},{"removed":"math500","score":0.041548463756609574,"rank":280,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04458914308424492,"rank":275,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.044254155829664736,"rank":279,"remainingConfigurations":398},{"removed":"omniscience","score":0.04138618351076362,"rank":275,"remainingConfigurations":398},{"removed":"scicode","score":0.04162198674241482,"rank":280,"remainingConfigurations":398},{"removed":"tau-bench","score":0.040002567728579325,"rank":279,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04176045436363194,"rank":277,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04946395577684932,"rank":280,"remainingConfigurations":398},{"removed":"deepswe","score":0.03523431097041801,"rank":279,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.041419997807221894,"rank":279,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04113254336178883,"rank":279,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04367909365666256,"rank":279,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.04147034563649551,"rank":279,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04101274322590543,"rank":279,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.041350499315300035,"rank":279,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.04125367819405964,"rank":279,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04149103258718282,"rank":279,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.04104198759257216,"rank":279,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04190558099993879,"rank":279,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04149705086372423,"rank":279,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04075250587552383,"rank":279,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04112589272991252,"rank":279,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.042057494653691685,"rank":279,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04232310489462526,"rank":278,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03995975926538047,"rank":275,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04150465254788193,"rank":278,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04315294114802598,"rank":279,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.04119980131021991,"rank":279,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.04126503984622368,"rank":279,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0412264193528687,"rank":279,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04133893820411553,"rank":279,"remainingConfigurations":398},{"removed":"vibe-code","score":0.041131696431970156,"rank":279,"remainingConfigurations":398}]},"mimo-v2-flash--effort-non-reasoning":{"score":0.04107013709432023,"rank":280,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.049616309682700595,"rank":281,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03489561105211043,"rank":280,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0406656936700792,"rank":280,"remainingConfigurations":398},{"removed":"Scale","score":0.045719257834903874,"rank":280,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0410033962938482,"rank":280,"remainingConfigurations":398},{"removed":"Cognition","score":0.0431551700451018,"rank":280,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04209569340854413,"rank":278,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0421797778066371,"rank":279,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04151077212914555,"rank":262,"remainingConfigurations":381},{"removed":"Vals AI","score":0.039917960052010516,"rank":279,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0410725964405618,"rank":280,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.041030732838014554,"rank":280,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.04099912784027858,"rank":280,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.04107013709432023,"rank":280,"remainingConfigurations":398},{"removed":"All provider reports","score":0.04095531897606665,"rank":280,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0412110537962786,"rank":280,"remainingConfigurations":398},{"removed":"briefcase","score":0.04099015316236642,"rank":280,"remainingConfigurations":398},{"removed":"aime","score":0.04003947353942413,"rank":282,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04155968681883765,"rank":280,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.04118359715264173,"rank":280,"remainingConfigurations":398},{"removed":"automationbench","score":0.041049054805343266,"rank":280,"remainingConfigurations":398},{"removed":"critpt","score":0.04209999368160736,"rank":277,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.04114824592480027,"rank":280,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04159384723768578,"rank":280,"remainingConfigurations":398},{"removed":"gdpval","score":0.0381140522026129,"rank":285,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04530855615265272,"rank":270,"remainingConfigurations":398},{"removed":"gpqa","score":0.04162720796968705,"rank":279,"remainingConfigurations":398},{"removed":"harvey","score":0.04060736442279873,"rank":280,"remainingConfigurations":398},{"removed":"hle","score":0.04269373867440989,"rank":284,"remainingConfigurations":398},{"removed":"ifbench","score":0.04059472634062309,"rank":279,"remainingConfigurations":398},{"removed":"itbench","score":0.041021951231700916,"rank":280,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04384862972616995,"rank":274,"remainingConfigurations":398},{"removed":"math500","score":0.04125597212731764,"rank":281,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04481485427685542,"rank":274,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04385191823997155,"rank":280,"remainingConfigurations":398},{"removed":"omniscience","score":0.04035347228170126,"rank":279,"remainingConfigurations":398},{"removed":"scicode","score":0.04186807203381288,"rank":279,"remainingConfigurations":398},{"removed":"tau-bench","score":0.036938170258400516,"rank":287,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.036092272759373094,"rank":292,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04924002112648068,"rank":281,"remainingConfigurations":398},{"removed":"deepswe","score":0.034921982735062605,"rank":280,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.041082052208084634,"rank":280,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.04078462865105655,"rank":280,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0431551700451018,"rank":280,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.041113464477437245,"rank":280,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.04068880568307627,"rank":280,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.04101025108396495,"rank":280,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.040916041125703156,"rank":280,"remainingConfigurations":398},{"removed":"livebench-math","score":0.04114275837601213,"rank":280,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.040730941824889656,"rank":280,"remainingConfigurations":398},{"removed":"livebench-language","score":0.041561179809895744,"rank":280,"remainingConfigurations":398},{"removed":"livebench-data","score":0.04115645331970046,"rank":280,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.04041018572678683,"rank":280,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.04079194525502301,"rank":280,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04171414038458913,"rank":280,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0421797778066371,"rank":279,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.038939286233345825,"rank":276,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04147116676609122,"rank":279,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04275215811062022,"rank":280,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.040863978900575824,"rank":280,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.040923982723659866,"rank":280,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.040896865898865875,"rank":280,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.04099840434919477,"rank":280,"remainingConfigurations":398},{"removed":"vibe-code","score":0.040788463258469874,"rank":280,"remainingConfigurations":398}]},"gpt-5.4-mini--effort-non-reasoning":{"score":0.03991459695581715,"rank":281,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04820976065141273,"rank":284,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03391219174542393,"rank":281,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03953671795819252,"rank":281,"remainingConfigurations":398},{"removed":"Scale","score":0.04442295376461919,"rank":281,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03984561775362148,"rank":281,"remainingConfigurations":398},{"removed":"Cognition","score":0.04192439789514881,"rank":282,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04088993607597491,"rank":280,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04103050156016501,"rank":281,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.04030530894306926,"rank":263,"remainingConfigurations":381},{"removed":"Vals AI","score":0.038775905592062364,"rank":280,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.039917015575062026,"rank":281,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03987680948150262,"rank":281,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.039844846124098915,"rank":281,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03991459695581715,"rank":281,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03980274774068773,"rank":281,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.040041464915718916,"rank":281,"remainingConfigurations":398},{"removed":"briefcase","score":0.03991515289733225,"rank":281,"remainingConfigurations":398},{"removed":"aime","score":0.039920581641922144,"rank":283,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04041107867227568,"rank":281,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03993326950196161,"rank":282,"remainingConfigurations":398},{"removed":"automationbench","score":0.03999618058267059,"rank":281,"remainingConfigurations":398},{"removed":"critpt","score":0.04153189458623371,"rank":278,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.039996996499773535,"rank":281,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04052364423846631,"rank":281,"remainingConfigurations":398},{"removed":"gdpval","score":0.03703339783656109,"rank":290,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04014949359370095,"rank":282,"remainingConfigurations":398},{"removed":"gpqa","score":0.04168776461184235,"rank":278,"remainingConfigurations":398},{"removed":"harvey","score":0.03946198138577778,"rank":281,"remainingConfigurations":398},{"removed":"hle","score":0.04333782612384762,"rank":282,"remainingConfigurations":398},{"removed":"ifbench","score":0.04027500226659809,"rank":280,"remainingConfigurations":398},{"removed":"itbench","score":0.03975587934758314,"rank":281,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03982199897429301,"rank":281,"remainingConfigurations":398},{"removed":"math500","score":0.04015813137394942,"rank":282,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.041096433578388755,"rank":281,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04276560569857846,"rank":281,"remainingConfigurations":398},{"removed":"omniscience","score":0.03327340677685242,"rank":294,"remainingConfigurations":398},{"removed":"scicode","score":0.0407784303276079,"rank":281,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04199251438641429,"rank":276,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03794175084075211,"rank":285,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04785435554539171,"rank":284,"remainingConfigurations":398},{"removed":"deepswe","score":0.033938035083735156,"rank":281,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03992611376679193,"rank":281,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.039638820499235505,"rank":281,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04192439789514881,"rank":282,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03995845821730902,"rank":281,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03954475350462521,"rank":281,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0398565538914945,"rank":281,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0397637388315047,"rank":281,"remainingConfigurations":398},{"removed":"livebench-math","score":0.039984438199013074,"rank":281,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03958542370370074,"rank":281,"remainingConfigurations":398},{"removed":"livebench-language","score":0.040394011869792065,"rank":281,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03999902707949438,"rank":281,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03927206137869444,"rank":281,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.039643426234049726,"rank":281,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04054013546813489,"rank":281,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04103050156016501,"rank":281,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03794562899650569,"rank":277,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04030662990362031,"rank":281,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04154598785242057,"rank":281,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03971447758323312,"rank":281,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.039771859413848,"rank":281,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.039745434726818435,"rank":281,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.039844809653836195,"rank":281,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03964157571016121,"rank":281,"remainingConfigurations":398}]},"glm-4.6--effort-non-reasoning":{"score":0.039727250758612706,"rank":282,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04823713614598965,"rank":283,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03375163205620676,"rank":282,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.039329256693994855,"rank":282,"remainingConfigurations":398},{"removed":"Scale","score":0.044221622515219466,"rank":282,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03965849788286792,"rank":282,"remainingConfigurations":398},{"removed":"Cognition","score":0.04177202718869074,"rank":284,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04071042743788651,"rank":281,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04080835505012759,"rank":282,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.040094978871964775,"rank":264,"remainingConfigurations":381},{"removed":"Vals AI","score":0.038600968606862164,"rank":281,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03972967190470866,"rank":282,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03968900321137067,"rank":282,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.039658691582958795,"rank":282,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.039727250758612706,"rank":282,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03961621390915135,"rank":282,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03985200984811849,"rank":282,"remainingConfigurations":398},{"removed":"briefcase","score":0.03963592935268538,"rank":282,"remainingConfigurations":398},{"removed":"aime","score":0.041707986599219794,"rank":278,"remainingConfigurations":398},{"removed":"apex-agents","score":0.04017029828241083,"rank":282,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.041181930455599876,"rank":281,"remainingConfigurations":398},{"removed":"automationbench","score":0.03970548461115817,"rank":282,"remainingConfigurations":398},{"removed":"critpt","score":0.04095891723113535,"rank":279,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.039783301698724904,"rank":282,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.040232271862253484,"rank":282,"remainingConfigurations":398},{"removed":"gdpval","score":0.03999170842039881,"rank":280,"remainingConfigurations":398},{"removed":"gmmlu","score":0.04001111383206445,"rank":283,"remainingConfigurations":398},{"removed":"gpqa","score":0.04066744284832169,"rank":282,"remainingConfigurations":398},{"removed":"harvey","score":0.039270590091512285,"rank":282,"remainingConfigurations":398},{"removed":"hle","score":0.043532808395237675,"rank":280,"remainingConfigurations":398},{"removed":"ifbench","score":0.04103767636765427,"rank":277,"remainingConfigurations":398},{"removed":"itbench","score":0.03967512760405803,"rank":282,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03947300348169566,"rank":282,"remainingConfigurations":398},{"removed":"math500","score":0.03998815662714216,"rank":284,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.04103003727757763,"rank":282,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04259258165534408,"rank":282,"remainingConfigurations":398},{"removed":"omniscience","score":0.034461780497350276,"rank":291,"remainingConfigurations":398},{"removed":"scicode","score":0.04050587208673489,"rank":282,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03568008533520376,"rank":293,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.036334315303187835,"rank":291,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04787414916201164,"rank":283,"remainingConfigurations":398},{"removed":"deepswe","score":0.033777099770738624,"rank":282,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.039738756614694865,"rank":282,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03945007673559952,"rank":282,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04177202718869074,"rank":284,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03976848406104756,"rank":282,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03935837673124643,"rank":282,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03966920800553691,"rank":282,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03957794314968675,"rank":282,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03979768782522307,"rank":282,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03939752968046291,"rank":282,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04020301263461661,"rank":282,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0398111473879282,"rank":282,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.039087586776606474,"rank":282,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03945735371026722,"rank":282,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04035273134843175,"rank":282,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04080835505012759,"rank":282,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03762983646467085,"rank":278,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04011166305100336,"rank":282,"remainingConfigurations":398},{"removed":"simpleqa","score":0.041362259951951474,"rank":282,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0395274008987646,"rank":282,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03958537808405709,"rank":282,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03955944032350655,"rank":282,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.039657205274928116,"rank":282,"remainingConfigurations":398},{"removed":"vibe-code","score":0.039454140505264204,"rank":282,"remainingConfigurations":398}]},"gpt-4.1--effort-non-reasoning":{"score":0.03959665727818621,"rank":283,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.047904142618402916,"rank":285,"remainingConfigurations":398},{"removed":"Datacurve","score":0.033620840708689315,"rank":284,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03917175702797391,"rank":284,"remainingConfigurations":398},{"removed":"Scale","score":0.04411647332983587,"rank":283,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.039535995780649695,"rank":283,"remainingConfigurations":398},{"removed":"Cognition","score":0.04160816938348851,"rank":285,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04058382844303853,"rank":282,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04068865985410763,"rank":283,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03989987687126839,"rank":265,"remainingConfigurations":381},{"removed":"Vals AI","score":0.038489634966565024,"rank":282,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03959908074966417,"rank":283,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0395583929168279,"rank":283,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03952800451783988,"rank":283,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03959665727818621,"rank":283,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03948553718503174,"rank":283,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.039735950551591355,"rank":283,"remainingConfigurations":398},{"removed":"briefcase","score":0.039548289444146324,"rank":283,"remainingConfigurations":398},{"removed":"aime","score":0.04290572053070757,"rank":276,"remainingConfigurations":398},{"removed":"apex-agents","score":0.040050010687770206,"rank":283,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.035718388595752805,"rank":291,"remainingConfigurations":398},{"removed":"automationbench","score":0.03960878970067627,"rank":283,"remainingConfigurations":398},{"removed":"critpt","score":0.04045834266840715,"rank":281,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.039665112915602506,"rank":283,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.04012661410925985,"rank":283,"remainingConfigurations":398},{"removed":"gdpval","score":0.039908719372214164,"rank":281,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03998630659078797,"rank":284,"remainingConfigurations":398},{"removed":"gpqa","score":0.039593258665834255,"rank":283,"remainingConfigurations":398},{"removed":"harvey","score":0.039152124851034385,"rank":283,"remainingConfigurations":398},{"removed":"hle","score":0.045927892673876806,"rank":275,"remainingConfigurations":398},{"removed":"ifbench","score":0.03808060713262534,"rank":286,"remainingConfigurations":398},{"removed":"itbench","score":0.03954817099037524,"rank":283,"remainingConfigurations":398},{"removed":"livecodebench","score":0.04129661723654984,"rank":280,"remainingConfigurations":398},{"removed":"math500","score":0.04173475959293397,"rank":279,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03952882293606174,"rank":285,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04220672383501358,"rank":283,"remainingConfigurations":398},{"removed":"omniscience","score":0.03295360143154475,"rank":297,"remainingConfigurations":398},{"removed":"scicode","score":0.04039042321253078,"rank":283,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03771639448616598,"rank":284,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.039016988227948184,"rank":283,"remainingConfigurations":398},{"removed":"arc-agi","score":0.047543494166121684,"rank":285,"remainingConfigurations":398},{"removed":"deepswe","score":0.03364625274006786,"rank":284,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03960813271382541,"rank":283,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03932006121117344,"rank":283,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04160816938348851,"rank":285,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03963560492745388,"rank":283,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03922758406383657,"rank":283,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.039538816551405155,"rank":283,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.039448304883819466,"rank":283,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03966684635651901,"rank":283,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.039268488980985006,"rank":283,"remainingConfigurations":398},{"removed":"livebench-language","score":0.04007121001983494,"rank":283,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03967985494719308,"rank":283,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03895890882840724,"rank":283,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03932771624627659,"rank":283,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04021977563671887,"rank":283,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04068865985410763,"rank":283,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.037532417444037465,"rank":279,"remainingConfigurations":398},{"removed":"frontiermath","score":0.04000507823977357,"rank":283,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04122915174829107,"rank":284,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.039397346793044845,"rank":283,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03945521886870922,"rank":283,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.039429344849090026,"rank":283,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03952687826961041,"rank":283,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03932446387910875,"rank":283,"remainingConfigurations":398}]},"qwen3.5-4b--effort-non-reasoning":{"score":0.03950448090854901,"rank":284,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.054528688660189485,"rank":138,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04829857810841117,"rank":282,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03364485844318894,"rank":283,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03917947533207531,"rank":283,"remainingConfigurations":398},{"removed":"Scale","score":0.04389836409874518,"rank":284,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03947523215196384,"rank":284,"remainingConfigurations":398},{"removed":"Cognition","score":0.041838742208323725,"rank":283,"remainingConfigurations":398},{"removed":"LiveBench","score":0.04030966733253286,"rank":283,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.04040876701420032,"rank":284,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03649231003429013,"rank":272,"remainingConfigurations":381},{"removed":"Vals AI","score":0.038445857075255864,"rank":283,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03950550931154665,"rank":284,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03946197603493289,"rank":284,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03944286702909176,"rank":284,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03950448090854901,"rank":284,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03939500427770449,"rank":284,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.039624196480330554,"rank":284,"remainingConfigurations":398},{"removed":"briefcase","score":0.03938005311057947,"rank":284,"remainingConfigurations":398},{"removed":"aime","score":0.03642119990160026,"rank":287,"remainingConfigurations":398},{"removed":"apex-agents","score":0.039912491676087035,"rank":284,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.039531436328327015,"rank":283,"remainingConfigurations":398},{"removed":"automationbench","score":0.03943665102868253,"rank":284,"remainingConfigurations":398},{"removed":"critpt","score":0.04033406550521426,"rank":282,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.039537478991646606,"rank":284,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.039869497721964395,"rank":284,"remainingConfigurations":398},{"removed":"gdpval","score":0.03949302692740671,"rank":282,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03972635432209929,"rank":285,"remainingConfigurations":398},{"removed":"gpqa","score":0.03857721414393977,"rank":284,"remainingConfigurations":398},{"removed":"harvey","score":0.03903680252280626,"rank":284,"remainingConfigurations":398},{"removed":"hle","score":0.04047028790410152,"rank":286,"remainingConfigurations":398},{"removed":"ifbench","score":0.041493410151108086,"rank":276,"remainingConfigurations":398},{"removed":"itbench","score":0.03943517806559424,"rank":284,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03925980445696863,"rank":285,"remainingConfigurations":398},{"removed":"math500","score":0.039564409291869274,"rank":285,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.040525740044737746,"rank":283,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04157765375829262,"rank":285,"remainingConfigurations":398},{"removed":"omniscience","score":0.041868114468744576,"rank":273,"remainingConfigurations":398},{"removed":"scicode","score":0.04010880970276833,"rank":284,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03582150586864808,"rank":292,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03866595545034071,"rank":284,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04796104901724366,"rank":282,"remainingConfigurations":398},{"removed":"deepswe","score":0.03367123406589525,"rank":283,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03951565889842592,"rank":284,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03924156713722308,"rank":284,"remainingConfigurations":398},{"removed":"frontiercode","score":0.041838742208323725,"rank":283,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03956912875818245,"rank":284,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03912868795836182,"rank":284,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03944927107625185,"rank":284,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03935553586295603,"rank":284,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03958690581351044,"rank":284,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03914330242174449,"rank":284,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03997567997238439,"rank":284,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0395956587177022,"rank":284,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03888061871426279,"rank":284,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.039232884900923505,"rank":284,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.04013138832448336,"rank":284,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.04040876701420032,"rank":284,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0366528495605322,"rank":282,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03977116744905906,"rank":284,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04123442233617931,"rank":283,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03930528061694164,"rank":284,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.039368649282398076,"rank":284,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.039329685707967306,"rank":284,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.039436892791786936,"rank":284,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03924116541025661,"rank":284,"remainingConfigurations":398}]},"exaone-4.0-32b--effort-reasoning":{"score":0.03892443070030866,"rank":285,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04709298211969535,"rank":287,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03305115914681502,"rank":285,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03850961562134066,"rank":285,"remainingConfigurations":398},{"removed":"Scale","score":0.04335756570119925,"rank":285,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03885532287972533,"rank":285,"remainingConfigurations":398},{"removed":"Cognition","score":0.040908619735305386,"rank":286,"remainingConfigurations":398},{"removed":"LiveBench","score":0.039882579612318524,"rank":284,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03997441873211603,"rank":285,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03905784659690527,"rank":266,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03781690642938029,"rank":284,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03892679463582144,"rank":285,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.038886709450396025,"rank":285,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.038857344423519465,"rank":285,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03892443070030866,"rank":285,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03881546645179556,"rank":285,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.039041133775781243,"rank":285,"remainingConfigurations":398},{"removed":"briefcase","score":0.038836863314332414,"rank":285,"remainingConfigurations":398},{"removed":"aime","score":0.03626467213078353,"rank":291,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03934981200967404,"rank":285,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03865422286968789,"rank":285,"remainingConfigurations":398},{"removed":"automationbench","score":0.03887726792549374,"rank":285,"remainingConfigurations":398},{"removed":"critpt","score":0.03970025355022038,"rank":284,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.038970204686845845,"rank":285,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03938376456046703,"rank":285,"remainingConfigurations":398},{"removed":"gdpval","score":0.03908232972441258,"rank":283,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0427928775911789,"rank":280,"remainingConfigurations":398},{"removed":"gpqa","score":0.0369136083740506,"rank":287,"remainingConfigurations":398},{"removed":"harvey","score":0.0384687711786233,"rank":285,"remainingConfigurations":398},{"removed":"hle","score":0.038781564597229375,"rank":292,"remainingConfigurations":398},{"removed":"ifbench","score":0.040189827666581426,"rank":281,"remainingConfigurations":398},{"removed":"itbench","score":0.038862146827052683,"rank":285,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03533148938136345,"rank":295,"remainingConfigurations":398},{"removed":"math500","score":0.03670914289188066,"rank":289,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.037672734929672776,"rank":289,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04161952574033715,"rank":284,"remainingConfigurations":398},{"removed":"omniscience","score":0.038903152009635004,"rank":281,"remainingConfigurations":398},{"removed":"scicode","score":0.03964200459049212,"rank":285,"remainingConfigurations":398},{"removed":"tau-bench","score":0.04232625084923786,"rank":275,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04162555345586553,"rank":278,"remainingConfigurations":398},{"removed":"arc-agi","score":0.046742514238685605,"rank":287,"remainingConfigurations":398},{"removed":"deepswe","score":0.033076134010743226,"rank":285,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.038935716199139186,"rank":285,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0386515895238233,"rank":285,"remainingConfigurations":398},{"removed":"frontiercode","score":0.040908619735305386,"rank":286,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03896252114238507,"rank":285,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03856258623396559,"rank":285,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.038867204782565605,"rank":285,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03877810350545213,"rank":285,"remainingConfigurations":398},{"removed":"livebench-math","score":0.038993632620380116,"rank":285,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03860088992140994,"rank":285,"remainingConfigurations":398},{"removed":"livebench-language","score":0.039391173870598,"rank":285,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03900631070889315,"rank":285,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03829680350265432,"rank":285,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03865977211119047,"rank":285,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03953848012438497,"rank":285,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03997441873211603,"rank":285,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03682241886607183,"rank":281,"remainingConfigurations":398},{"removed":"frontiermath","score":0.039315325267415706,"rank":285,"remainingConfigurations":398},{"removed":"simpleqa","score":0.04053058749592925,"rank":285,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03872829416128091,"rank":285,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03878507604719603,"rank":285,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03875984323159724,"rank":285,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.038855479892424334,"rank":285,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03865640424241789,"rank":285,"remainingConfigurations":398}]},"qwen3-235b-a22b--effort-reasoning":{"score":0.0382339900208146,"rank":286,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04633164838337864,"rank":288,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03247147933321915,"rank":286,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.037821991379065445,"rank":286,"remainingConfigurations":398},{"removed":"Scale","score":0.042579309196969846,"rank":286,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.038168022015892054,"rank":286,"remainingConfigurations":398},{"removed":"Cognition","score":0.04019238825460575,"rank":288,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0391824187647949,"rank":285,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03929372499806514,"rank":286,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03847875539596235,"rank":267,"remainingConfigurations":381},{"removed":"Vals AI","score":0.037152561539854814,"rank":285,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03823632126859765,"rank":286,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03819704423205417,"rank":286,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.038167956931674664,"rank":286,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0382339900208146,"rank":286,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03812692439649336,"rank":286,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03835833523639306,"rank":286,"remainingConfigurations":398},{"removed":"briefcase","score":0.0381565961909369,"rank":286,"remainingConfigurations":398},{"removed":"aime","score":0.03490571440547483,"rank":297,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03865880425846959,"rank":286,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.042718369239395614,"rank":274,"remainingConfigurations":398},{"removed":"automationbench","score":0.038219358380815666,"rank":286,"remainingConfigurations":398},{"removed":"critpt","score":0.039061551521706046,"rank":285,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03829254886049955,"rank":286,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.038712362864958036,"rank":286,"remainingConfigurations":398},{"removed":"gdpval","score":0.03842734219982302,"rank":284,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03854836877914401,"rank":286,"remainingConfigurations":398},{"removed":"gpqa","score":0.037037589100132884,"rank":286,"remainingConfigurations":398},{"removed":"harvey","score":0.03779206159036529,"rank":286,"remainingConfigurations":398},{"removed":"hle","score":0.03813687148116368,"rank":294,"remainingConfigurations":398},{"removed":"ifbench","score":0.03855604474462255,"rank":284,"remainingConfigurations":398},{"removed":"itbench","score":0.03817522859087715,"rank":286,"remainingConfigurations":398},{"removed":"livecodebench","score":0.037035356094150866,"rank":289,"remainingConfigurations":398},{"removed":"math500","score":0.040092631971207764,"rank":283,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03576148594386227,"rank":296,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04101830200739986,"rank":286,"remainingConfigurations":398},{"removed":"omniscience","score":0.034865215753982416,"rank":287,"remainingConfigurations":398},{"removed":"scicode","score":0.03896669299642117,"rank":286,"remainingConfigurations":398},{"removed":"tau-bench","score":0.039731796127211345,"rank":281,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03982350901773158,"rank":282,"remainingConfigurations":398},{"removed":"arc-agi","score":0.045984404740043255,"rank":288,"remainingConfigurations":398},{"removed":"deepswe","score":0.0324960222797915,"rank":286,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.038245092988863166,"rank":286,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.037966800225894715,"rank":286,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04019238825460575,"rank":288,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.038273953230056675,"rank":286,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03787831816319546,"rank":286,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.038178171412524366,"rank":286,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0380902247650041,"rank":286,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03830201860618931,"rank":286,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.037915487152996426,"rank":286,"remainingConfigurations":398},{"removed":"livebench-language","score":0.038693174907001235,"rank":286,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03831505052298488,"rank":286,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03761665496244123,"rank":286,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.037973460861453597,"rank":286,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03883796381923548,"rank":286,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03929372499806514,"rank":286,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03616451001945426,"rank":283,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03861450099183648,"rank":287,"remainingConfigurations":398},{"removed":"simpleqa","score":0.039815297173404145,"rank":286,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.038041077466246076,"rank":286,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0380970335440014,"rank":286,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.038072055149212636,"rank":286,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03816626521312746,"rank":286,"remainingConfigurations":398},{"removed":"vibe-code","score":0.037970409437096515,"rank":286,"remainingConfigurations":398}]},"gemini-3.5-flash-lite--effort-minimal":{"score":0.0377492921821457,"rank":287,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.035876145050416,"rank":148,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.08108922129215175,"rank":236,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0323681328599932,"rank":287,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03759809890384084,"rank":287,"remainingConfigurations":398},{"removed":"Scale","score":0.04184613066587465,"rank":288,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.037614366602159076,"rank":287,"remainingConfigurations":398},{"removed":"Cognition","score":0.042145681129693524,"rank":281,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03830244876928853,"rank":287,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03778763468857886,"rank":289,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.018360173379784062,"rank":322,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03647952101833623,"rank":287,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.037750242217940155,"rank":287,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.037687742801162286,"rank":287,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03770879425499326,"rank":287,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0377492921821457,"rank":287,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03764258524813207,"rank":287,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.037825826670050626,"rank":287,"remainingConfigurations":398},{"removed":"briefcase","score":0.03770829222802669,"rank":287,"remainingConfigurations":398},{"removed":"aime","score":0.041623856658629534,"rank":279,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03801184167071777,"rank":287,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03776119453805829,"rank":286,"remainingConfigurations":398},{"removed":"automationbench","score":0.03770680353502447,"rank":287,"remainingConfigurations":398},{"removed":"critpt","score":0.03781307850346676,"rank":289,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.037764061691978025,"rank":287,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.037932029879835294,"rank":288,"remainingConfigurations":398},{"removed":"gdpval","score":0.0377730547362678,"rank":288,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03782920527801735,"rank":288,"remainingConfigurations":398},{"removed":"gpqa","score":0.04143238021017595,"rank":281,"remainingConfigurations":398},{"removed":"harvey","score":0.03730023624017304,"rank":287,"remainingConfigurations":398},{"removed":"hle","score":0.039476846700247474,"rank":288,"remainingConfigurations":398},{"removed":"ifbench","score":0.03731190848386776,"rank":287,"remainingConfigurations":398},{"removed":"itbench","score":0.03768828113732466,"rank":287,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03762439976304905,"rank":287,"remainingConfigurations":398},{"removed":"math500","score":0.03781247538293454,"rank":286,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0390460840697108,"rank":286,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04036201632789361,"rank":289,"remainingConfigurations":398},{"removed":"omniscience","score":0.037069377034476624,"rank":282,"remainingConfigurations":398},{"removed":"scicode","score":0.03809267576704063,"rank":288,"remainingConfigurations":398},{"removed":"tau-bench","score":0.037218247245976485,"rank":286,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03766777397315307,"rank":287,"remainingConfigurations":398},{"removed":"arc-agi","score":0.08091600881750577,"rank":237,"remainingConfigurations":398},{"removed":"deepswe","score":0.03238959187879268,"rank":287,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03775878938903023,"rank":287,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03771438464270711,"rank":287,"remainingConfigurations":398},{"removed":"frontiercode","score":0.042145681129693524,"rank":281,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.037835519242713576,"rank":287,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03739954405403701,"rank":287,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.037698750133583384,"rank":287,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03759528473901464,"rank":287,"remainingConfigurations":398},{"removed":"livebench-math","score":0.037815058175314914,"rank":287,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.037391435219490204,"rank":287,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03818568990324739,"rank":287,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03781533677693629,"rank":287,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03715390437985377,"rank":287,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03749155643088099,"rank":287,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03840530950904434,"rank":287,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03778763468857886,"rank":289,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.026108787058179594,"rank":316,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03865606927442129,"rank":286,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0395402266938054,"rank":287,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.037564546829858714,"rank":287,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03759966607952015,"rank":287,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0376131632693502,"rank":287,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.037655875132749005,"rank":287,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03748501082488811,"rank":287,"remainingConfigurations":398}]},"amazon-nova-2-lite--effort-low":{"score":0.03757937696013005,"rank":288,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04549877613346174,"rank":289,"remainingConfigurations":398},{"removed":"Datacurve","score":0.031913149030636766,"rank":288,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03719353609169993,"rank":288,"remainingConfigurations":398},{"removed":"Scale","score":0.04189326131233548,"rank":287,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.037513966267883524,"rank":288,"remainingConfigurations":398},{"removed":"Cognition","score":0.039520523222656756,"rank":289,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03851296378389642,"rank":286,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03858169972734892,"rank":287,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.038037782350388655,"rank":268,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03651383832089779,"rank":286,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03758167514733036,"rank":288,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03754292068358871,"rank":288,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.037514101894705526,"rank":288,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03757937696013005,"rank":288,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03747362299209616,"rank":288,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03771351137550238,"rank":288,"remainingConfigurations":398},{"removed":"briefcase","score":0.037514617215954955,"rank":288,"remainingConfigurations":398},{"removed":"aime","score":0.03875820101805755,"rank":284,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03800586264041565,"rank":288,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03518928883459867,"rank":293,"remainingConfigurations":398},{"removed":"automationbench","score":0.03758060745075948,"rank":288,"remainingConfigurations":398},{"removed":"critpt","score":0.03845017246063951,"rank":288,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.037631493884844776,"rank":288,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03807395107356638,"rank":287,"remainingConfigurations":398},{"removed":"gdpval","score":0.03781181393042799,"rank":287,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03789509152499124,"rank":287,"remainingConfigurations":398},{"removed":"gpqa","score":0.036505676808356986,"rank":288,"remainingConfigurations":398},{"removed":"harvey","score":0.03713721164051634,"rank":288,"remainingConfigurations":398},{"removed":"hle","score":0.04457355005202379,"rank":278,"remainingConfigurations":398},{"removed":"ifbench","score":0.03249642026457855,"rank":298,"remainingConfigurations":398},{"removed":"itbench","score":0.037514873392808616,"rank":288,"remainingConfigurations":398},{"removed":"livecodebench","score":0.038869187841568564,"rank":286,"remainingConfigurations":398},{"removed":"math500","score":0.037728405617099385,"rank":287,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03840514134168978,"rank":287,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.040822056205100335,"rank":287,"remainingConfigurations":398},{"removed":"omniscience","score":0.03480997911678743,"rank":288,"remainingConfigurations":398},{"removed":"scicode","score":0.038335312976485514,"rank":287,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03420957514043613,"rank":294,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.04020163359901873,"rank":281,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04515454937035213,"rank":289,"remainingConfigurations":398},{"removed":"deepswe","score":0.03193725018991246,"rank":288,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03759029425526309,"rank":288,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03731690738152993,"rank":288,"remainingConfigurations":398},{"removed":"frontiercode","score":0.039520523222656756,"rank":289,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03761902593006718,"rank":288,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03722983714378895,"rank":288,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03752450313306296,"rank":288,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.037437618506405514,"rank":288,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03764622810130785,"rank":288,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03726613260211756,"rank":288,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03803130407869497,"rank":288,"remainingConfigurations":398},{"removed":"livebench-data","score":0.037659193757326535,"rank":288,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.036971831061122104,"rank":288,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03732297284501807,"rank":288,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03817369957555695,"rank":288,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03858169972734892,"rank":287,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.035594025445156406,"rank":284,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03801502890119735,"rank":288,"remainingConfigurations":398},{"removed":"simpleqa","score":0.039130871474576966,"rank":288,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.037389518522718795,"rank":288,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.037444584749445634,"rank":288,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0374200250613309,"rank":288,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03751262458569844,"rank":288,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03731999227421979,"rank":288,"remainingConfigurations":398}]},"gpt-5-nano--effort-medium":{"score":0.037423022669022775,"rank":289,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.018125777580546735,"rank":156,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.06176595748907035,"rank":257,"remainingConfigurations":398},{"removed":"Datacurve","score":0.031803605411072806,"rank":289,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03711206317658782,"rank":289,"remainingConfigurations":398},{"removed":"Scale","score":0.04162017339149143,"rank":289,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03729653080330075,"rank":289,"remainingConfigurations":398},{"removed":"Cognition","score":0.04021395726727584,"rank":287,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03818570001750529,"rank":288,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03798244030125563,"rank":288,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.036630363503334186,"rank":271,"remainingConfigurations":381},{"removed":"Vals AI","score":0.036091718258206396,"rank":288,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03742494659503073,"rank":289,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03737446403212962,"rank":289,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03736853991410276,"rank":289,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.037423022669022775,"rank":289,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03731589629211632,"rank":289,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03752536158012925,"rank":289,"remainingConfigurations":398},{"removed":"briefcase","score":0.03739958743768882,"rank":290,"remainingConfigurations":398},{"removed":"aime","score":0.03638188368825699,"rank":289,"remainingConfigurations":398},{"removed":"apex-agents","score":0.037762199098386316,"rank":289,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0373466360163908,"rank":287,"remainingConfigurations":398},{"removed":"automationbench","score":0.0374347408481984,"rank":289,"remainingConfigurations":398},{"removed":"critpt","score":0.03874476489783293,"rank":286,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03745370754558738,"rank":289,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.037806602122217654,"rank":289,"remainingConfigurations":398},{"removed":"gdpval","score":0.03770111307335673,"rank":289,"remainingConfigurations":398},{"removed":"gmmlu","score":0.037669973486090254,"rank":289,"remainingConfigurations":398},{"removed":"gpqa","score":0.03799028402716397,"rank":285,"remainingConfigurations":398},{"removed":"harvey","score":0.036984850517446884,"rank":289,"remainingConfigurations":398},{"removed":"hle","score":0.039440388880578985,"rank":289,"remainingConfigurations":398},{"removed":"ifbench","score":0.03432202591598927,"rank":293,"remainingConfigurations":398},{"removed":"itbench","score":0.037366916256700335,"rank":289,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03537583731842317,"rank":294,"remainingConfigurations":398},{"removed":"math500","score":0.037685004660354814,"rank":288,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.039596377433604356,"rank":284,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.04079864634593093,"rank":288,"remainingConfigurations":398},{"removed":"omniscience","score":0.035949386618699564,"rank":283,"remainingConfigurations":398},{"removed":"scicode","score":0.03802098453052644,"rank":289,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0381756084428355,"rank":283,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.037124799031636506,"rank":288,"remainingConfigurations":398},{"removed":"arc-agi","score":0.061317875285867095,"rank":257,"remainingConfigurations":398},{"removed":"deepswe","score":0.03182464688104614,"rank":289,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.037433195148407386,"rank":289,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.037287797464147246,"rank":289,"remainingConfigurations":398},{"removed":"frontiercode","score":0.04021395726727584,"rank":287,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03747121550390512,"rank":289,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.037088983321238084,"rank":289,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03736856295394266,"rank":289,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.037277946571437855,"rank":289,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03748482274191606,"rank":289,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03711248259907012,"rank":289,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03786332705358291,"rank":289,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0374842929818514,"rank":289,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03681558467265449,"rank":289,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03717627717175333,"rank":289,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03803857750712789,"rank":289,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03798244030125563,"rank":288,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.034625323783903796,"rank":289,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03792087850296145,"rank":289,"remainingConfigurations":398},{"removed":"simpleqa","score":0.038937139146583755,"rank":289,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03723288528504654,"rank":289,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03727602551537119,"rank":289,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.037287941164580764,"rank":289,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.037337754331891966,"rank":289,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0371516543360356,"rank":289,"remainingConfigurations":398}]},"qwen3-32b--effort-reasoning":{"score":0.036724459273009526,"rank":290,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.044213421884302384,"rank":291,"remainingConfigurations":398},{"removed":"Datacurve","score":0.03114664433916554,"rank":290,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.036347897402556846,"rank":291,"remainingConfigurations":398},{"removed":"Scale","score":0.040914519543431366,"rank":290,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03666744467228889,"rank":290,"remainingConfigurations":398},{"removed":"Cognition","score":0.0385275537471119,"rank":291,"remainingConfigurations":398},{"removed":"LiveBench","score":0.037665176187825535,"rank":289,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03774950933936149,"rank":290,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03731778298223518,"rank":269,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03571425110031643,"rank":289,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03672662713430336,"rank":290,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.036689071065039734,"rank":290,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.036659912583367434,"rank":290,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.036724459273009526,"rank":290,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03662048450142097,"rank":290,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03684466302107186,"rank":290,"remainingConfigurations":398},{"removed":"briefcase","score":0.03748922826116421,"rank":289,"remainingConfigurations":398},{"removed":"aime","score":0.0352949322918887,"rank":296,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03715985766247199,"rank":290,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.039308906125907726,"rank":284,"remainingConfigurations":398},{"removed":"automationbench","score":0.036455045336904586,"rank":291,"remainingConfigurations":398},{"removed":"critpt","score":0.033722509411463326,"rank":300,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03677348413123426,"rank":290,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.036614176936024694,"rank":292,"remainingConfigurations":398},{"removed":"gdpval","score":0.037945797717238654,"rank":286,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03694926317269367,"rank":290,"remainingConfigurations":398},{"removed":"gpqa","score":0.03626696212565741,"rank":289,"remainingConfigurations":398},{"removed":"harvey","score":0.03630338658779887,"rank":290,"remainingConfigurations":398},{"removed":"hle","score":0.03847059710139528,"rank":293,"remainingConfigurations":398},{"removed":"ifbench","score":0.036800638393666686,"rank":288,"remainingConfigurations":398},{"removed":"itbench","score":0.03666702647292631,"rank":290,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03652217201527858,"rank":290,"remainingConfigurations":398},{"removed":"math500","score":0.036353019045661274,"rank":292,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.037225826891042056,"rank":292,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03930222228020966,"rank":292,"remainingConfigurations":398},{"removed":"omniscience","score":0.03462024024339238,"rank":289,"remainingConfigurations":398},{"removed":"scicode","score":0.036953260345737184,"rank":291,"remainingConfigurations":398},{"removed":"tau-bench","score":0.036573525267810096,"rank":288,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03792670137544534,"rank":286,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04389025387130662,"rank":292,"remainingConfigurations":398},{"removed":"deepswe","score":0.03117065546968691,"rank":290,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.036735419702168697,"rank":290,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0364726433694467,"rank":290,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0385275537471119,"rank":291,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.036764724579517405,"rank":290,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03638012710991035,"rank":290,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03667192774969446,"rank":290,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03658792849593142,"rank":290,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03678935466249528,"rank":290,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03642060332019609,"rank":290,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03716957663956453,"rank":290,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03680226613589646,"rank":290,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03612793927544707,"rank":290,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.036473515238655815,"rank":290,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03730337087379019,"rank":290,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03774950933936149,"rank":290,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.034910253765926345,"rank":286,"remainingConfigurations":398},{"removed":"frontiermath","score":0.037069761025595734,"rank":290,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03824059323789089,"rank":290,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0365382198919944,"rank":290,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03659296258997824,"rank":290,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03656789976844009,"rank":290,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03666083706118369,"rank":290,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03647010528962171,"rank":290,"remainingConfigurations":398}]},"gpt-5-mini--effort-minimal":{"score":0.036557974125622165,"rank":291,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.028001775805689102,"rank":151,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04509635040838226,"rank":290,"remainingConfigurations":398},{"removed":"Datacurve","score":0.031069479867400066,"rank":291,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.036396715779114665,"rank":290,"remainingConfigurations":398},{"removed":"Scale","score":0.040660961423728985,"rank":292,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.036434088293353574,"rank":291,"remainingConfigurations":398},{"removed":"Cognition","score":0.03929539034594299,"rank":290,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03731310509734923,"rank":291,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03719370663397853,"rank":292,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03567690121653542,"rank":274,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03526322944703958,"rank":291,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.036559855604948586,"rank":291,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03651059866907455,"rank":291,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03650460446611876,"rank":291,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.036557974125622165,"rank":291,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03645322737527968,"rank":291,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03665707138212442,"rank":291,"remainingConfigurations":398},{"removed":"briefcase","score":0.036509530540399404,"rank":291,"remainingConfigurations":398},{"removed":"aime","score":0.03740253097455795,"rank":286,"remainingConfigurations":398},{"removed":"apex-agents","score":0.036889841322529905,"rank":292,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.036273273809453895,"rank":288,"remainingConfigurations":398},{"removed":"automationbench","score":0.036546411909247754,"rank":290,"remainingConfigurations":398},{"removed":"critpt","score":0.03721312792770374,"rank":290,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03658632613851182,"rank":291,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03691849568281102,"rank":291,"remainingConfigurations":398},{"removed":"gdpval","score":0.03677697714464711,"rank":291,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03672889856800537,"rank":292,"remainingConfigurations":398},{"removed":"gpqa","score":0.03617372035318105,"rank":290,"remainingConfigurations":398},{"removed":"harvey","score":0.03612676506995828,"rank":291,"remainingConfigurations":398},{"removed":"hle","score":0.039433566484914584,"rank":290,"remainingConfigurations":398},{"removed":"ifbench","score":0.03486258815991258,"rank":292,"remainingConfigurations":398},{"removed":"itbench","score":0.036501474645332814,"rank":291,"remainingConfigurations":398},{"removed":"livecodebench","score":0.036413246982619496,"rank":291,"remainingConfigurations":398},{"removed":"math500","score":0.036704291742577604,"rank":290,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.038030105301915536,"rank":288,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03934277359672452,"rank":291,"remainingConfigurations":398},{"removed":"omniscience","score":0.03382955456255005,"rank":293,"remainingConfigurations":398},{"removed":"scicode","score":0.03713135173391632,"rank":290,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03644500212865549,"rank":290,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03591010332193927,"rank":295,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04475812644465064,"rank":290,"remainingConfigurations":398},{"removed":"deepswe","score":0.031090088247806378,"rank":291,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.036567934129218715,"rank":291,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.036441886995600296,"rank":291,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03929539034594299,"rank":290,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.036605492320800105,"rank":291,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03623170978298374,"rank":291,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03650478921113424,"rank":291,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.036416189870822326,"rank":291,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0366185159133587,"rank":291,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.036253992830784315,"rank":291,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03698917001608793,"rank":291,"remainingConfigurations":398},{"removed":"livebench-data","score":0.036618096603025015,"rank":291,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03596355449245846,"rank":291,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.036316590882188214,"rank":291,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03715989193959972,"rank":291,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03719370663397853,"rank":292,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03380929009117153,"rank":291,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03704663356880907,"rank":291,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03804094387410379,"rank":291,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03637192918390611,"rank":291,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03641415592938895,"rank":291,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.036425650983318576,"rank":291,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0364746109780841,"rank":291,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03629257651258439,"rank":291,"remainingConfigurations":398}]},"mistral-large-3--effort-non-reasoning":{"score":0.036464954392584924,"rank":292,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0439389427584155,"rank":293,"remainingConfigurations":398},{"removed":"Datacurve","score":0.030914785696589075,"rank":292,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03609162886758972,"rank":292,"remainingConfigurations":398},{"removed":"Scale","score":0.0406895537289809,"rank":291,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03640482600272237,"rank":292,"remainingConfigurations":398},{"removed":"Cognition","score":0.038249764881576845,"rank":292,"remainingConfigurations":398},{"removed":"LiveBench","score":0.037395759514903204,"rank":290,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03748080619695346,"rank":291,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0370968079081709,"rank":270,"remainingConfigurations":381},{"removed":"Vals AI","score":0.035476644484271264,"rank":290,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03646712819168287,"rank":292,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.036429719498477,"rank":292,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03640066560513911,"rank":292,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.036464954392584924,"rank":292,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03636144376212505,"rank":292,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03659166450271759,"rank":292,"remainingConfigurations":398},{"removed":"briefcase","score":0.03590476940530544,"rank":292,"remainingConfigurations":398},{"removed":"aime","score":0.03799132324411711,"rank":285,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03690862738973238,"rank":291,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.036083950210309516,"rank":289,"remainingConfigurations":398},{"removed":"automationbench","score":0.03579053615418138,"rank":293,"remainingConfigurations":398},{"removed":"critpt","score":0.03688948108859543,"rank":291,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.036522149649852335,"rank":292,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03696530330103663,"rank":290,"remainingConfigurations":398},{"removed":"gdpval","score":0.03602224838301205,"rank":293,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03602014741794344,"rank":294,"remainingConfigurations":398},{"removed":"gpqa","score":0.03577824768983424,"rank":291,"remainingConfigurations":398},{"removed":"harvey","score":0.03605856827893151,"rank":292,"remainingConfigurations":398},{"removed":"hle","score":0.04133565528783165,"rank":285,"remainingConfigurations":398},{"removed":"ifbench","score":0.03668364996043697,"rank":289,"remainingConfigurations":398},{"removed":"itbench","score":0.036414422148811555,"rank":292,"remainingConfigurations":398},{"removed":"livecodebench","score":0.037291317619428964,"rank":288,"remainingConfigurations":398},{"removed":"math500","score":0.036641158821773955,"rank":291,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03643858084379228,"rank":293,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.039521750105538954,"rank":290,"remainingConfigurations":398},{"removed":"omniscience","score":0.032043363567886896,"rank":299,"remainingConfigurations":398},{"removed":"scicode","score":0.03628679451471195,"rank":293,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03654068019886766,"rank":289,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03596832435852901,"rank":293,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04362036886820686,"rank":293,"remainingConfigurations":398},{"removed":"deepswe","score":0.03093858991999171,"rank":292,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.036475802982264105,"rank":292,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03621326461511374,"rank":292,"remainingConfigurations":398},{"removed":"frontiercode","score":0.038249764881576845,"rank":292,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.036502825387414256,"rank":292,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03612250190463239,"rank":292,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03641248037998084,"rank":292,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.036329407492112296,"rank":292,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03652943375163009,"rank":292,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.036163351463585465,"rank":292,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03690693453065137,"rank":292,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03654162314122803,"rank":292,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.035872569026931006,"rank":292,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.036215839092390574,"rank":292,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.037040222038469885,"rank":292,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03748080619695346,"rank":291,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03465757854067264,"rank":288,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0368080790889798,"rank":292,"remainingConfigurations":398},{"removed":"simpleqa","score":0.037970060354133583,"rank":292,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0362799179088354,"rank":292,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.036334166147354324,"rank":292,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03630958182627209,"rank":292,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03640142523615581,"rank":292,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03621235969746529,"rank":292,"remainingConfigurations":398}]},"qwen3-vl-32b-instruct--effort-non-reasoning":{"score":0.03588013897324267,"rank":293,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04342817247224321,"rank":294,"remainingConfigurations":398},{"removed":"Datacurve","score":0.030440699218892933,"rank":293,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.035489309636416035,"rank":293,"remainingConfigurations":398},{"removed":"Scale","score":0.03998386573470945,"rank":293,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.035818927718364764,"rank":293,"remainingConfigurations":398},{"removed":"Cognition","score":0.03772358886154334,"rank":293,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03677687107083912,"rank":292,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.036861351781910134,"rank":293,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03610165452124082,"rank":273,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03486627353008024,"rank":292,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0358823552417502,"rank":293,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03584532259319378,"rank":293,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03581777723883311,"rank":293,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03588013897324267,"rank":293,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03577912495966804,"rank":293,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03599223453883778,"rank":293,"remainingConfigurations":398},{"removed":"briefcase","score":0.03579972971363286,"rank":293,"remainingConfigurations":398},{"removed":"aime","score":0.034191113491875515,"rank":300,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0362746466448428,"rank":293,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.035560677087492526,"rank":292,"remainingConfigurations":398},{"removed":"automationbench","score":0.035866935427963195,"rank":292,"remainingConfigurations":398},{"removed":"critpt","score":0.03660695197653797,"rank":292,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03592334522352381,"rank":293,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03633997628900617,"rank":293,"remainingConfigurations":398},{"removed":"gdpval","score":0.03612763478303687,"rank":292,"remainingConfigurations":398},{"removed":"gmmlu","score":0.036176178916537925,"rank":293,"remainingConfigurations":398},{"removed":"gpqa","score":0.03530970524513714,"rank":293,"remainingConfigurations":398},{"removed":"harvey","score":0.03545792302230474,"rank":293,"remainingConfigurations":398},{"removed":"hle","score":0.03781332259891811,"rank":296,"remainingConfigurations":398},{"removed":"ifbench","score":0.03565212067029565,"rank":291,"remainingConfigurations":398},{"removed":"itbench","score":0.035823026257211885,"rank":293,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03594649491132613,"rank":292,"remainingConfigurations":398},{"removed":"math500","score":0.036090223663944467,"rank":293,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.036207504516976026,"rank":295,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0366000372919694,"rank":299,"remainingConfigurations":398},{"removed":"omniscience","score":0.03552219592583145,"rank":285,"remainingConfigurations":398},{"removed":"scicode","score":0.03658133694150554,"rank":292,"remainingConfigurations":398},{"removed":"tau-bench","score":0.036143836196883154,"rank":291,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03579994826261591,"rank":296,"remainingConfigurations":398},{"removed":"arc-agi","score":0.043097862753731675,"rank":294,"remainingConfigurations":398},{"removed":"deepswe","score":0.030463774518137615,"rank":293,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03589059175201029,"rank":293,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03562988363449268,"rank":293,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03772358886154334,"rank":293,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03591686372548596,"rank":293,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03554474390734405,"rank":293,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0358277300848775,"rank":293,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0357449647882978,"rank":293,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03594418507562278,"rank":293,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03558015645985519,"rank":293,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03631315333865843,"rank":293,"remainingConfigurations":398},{"removed":"livebench-data","score":0.035956378694462894,"rank":293,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0352982446248744,"rank":293,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03563455773217887,"rank":293,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03644948437989527,"rank":293,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.036861351781910134,"rank":293,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.033994018066203,"rank":290,"remainingConfigurations":398},{"removed":"frontiermath","score":0.036251415053129836,"rank":293,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03736882848809713,"rank":293,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03569826289396,"rank":293,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.035750960799203806,"rank":293,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03572747595554918,"rank":293,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03581612490043879,"rank":293,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03563178523145172,"rank":293,"remainingConfigurations":398}]},"gemini-2.5-flash-lite--effort-reasoning":{"score":0.035006963760360894,"rank":294,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.042384174859897865,"rank":295,"remainingConfigurations":398},{"removed":"Datacurve","score":0.029710574530341483,"rank":294,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.034632163899299316,"rank":294,"remainingConfigurations":398},{"removed":"Scale","score":0.039037781840831884,"rank":294,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.034946906447811794,"rank":294,"remainingConfigurations":398},{"removed":"Cognition","score":0.03681645709580978,"rank":294,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03588810163204113,"rank":293,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.035970106015257956,"rank":294,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0353096172359151,"rank":276,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03402080409041251,"rank":293,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.035009101462756625,"rank":294,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03497288566927627,"rank":294,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.034946384881712485,"rank":294,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.035006963760360894,"rank":294,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03490853122266751,"rank":294,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03512625150322989,"rank":294,"remainingConfigurations":398},{"removed":"briefcase","score":0.03496354787266264,"rank":294,"remainingConfigurations":398},{"removed":"aime","score":0.035344517717895964,"rank":294,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03540312850723038,"rank":294,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.032737282514993124,"rank":301,"remainingConfigurations":398},{"removed":"automationbench","score":0.035022486285422344,"rank":294,"remainingConfigurations":398},{"removed":"critpt","score":0.035309286901101015,"rank":293,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.035055232635155496,"rank":294,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03547968148510002,"rank":294,"remainingConfigurations":398},{"removed":"gdpval","score":0.035220803593564325,"rank":294,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03525348989058147,"rank":296,"remainingConfigurations":398},{"removed":"gpqa","score":0.035314986881388274,"rank":292,"remainingConfigurations":398},{"removed":"harvey","score":0.034602979767739496,"rank":294,"remainingConfigurations":398},{"removed":"hle","score":0.03681376966133911,"rank":299,"remainingConfigurations":398},{"removed":"ifbench","score":0.03196206288291711,"rank":300,"remainingConfigurations":398},{"removed":"itbench","score":0.034949354846838886,"rank":294,"remainingConfigurations":398},{"removed":"livecodebench","score":0.034069348061892,"rank":299,"remainingConfigurations":398},{"removed":"math500","score":0.033753727928155536,"rank":299,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03723104618303554,"rank":291,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.037712070230971166,"rank":294,"remainingConfigurations":398},{"removed":"omniscience","score":0.03213804965573038,"rank":298,"remainingConfigurations":398},{"removed":"scicode","score":0.03572251397805127,"rank":294,"remainingConfigurations":398},{"removed":"tau-bench","score":0.037328722827266944,"rank":285,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03666366220716887,"rank":290,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04205931714995389,"rank":295,"remainingConfigurations":398},{"removed":"deepswe","score":0.029733130215699302,"rank":294,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03501718426015706,"rank":294,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.034763345673245016,"rank":294,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03681645709580978,"rank":294,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03504507021183755,"rank":294,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03468039795447266,"rank":294,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03495603184024398,"rank":294,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0348747595963958,"rank":294,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03506950344144628,"rank":294,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.034713700043391194,"rank":294,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03543029916877572,"rank":294,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03508161029007618,"rank":294,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03443817663213684,"rank":294,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03476693284802902,"rank":294,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03556346851381968,"rank":294,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.035970106015257956,"rank":294,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03316558932787442,"rank":292,"remainingConfigurations":398},{"removed":"frontiermath","score":0.035362369728537145,"rank":294,"remainingConfigurations":398},{"removed":"simpleqa","score":0.036463463278141185,"rank":294,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03482923600127726,"rank":294,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.034880687951406204,"rank":294,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.034857704958486266,"rank":294,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0349443813339618,"rank":294,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03476412855812412,"rank":294,"remainingConfigurations":398}]},"devstral-2512--effort-non-reasoning":{"score":0.034657235545589464,"rank":295,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04180141157854627,"rank":297,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02937002271323186,"rank":295,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.034296181886167246,"rank":295,"remainingConfigurations":398},{"removed":"Scale","score":0.038696359943134966,"rank":295,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.034600200118274464,"rank":295,"remainingConfigurations":398},{"removed":"Cognition","score":0.03636152653183567,"rank":296,"remainingConfigurations":398},{"removed":"LiveBench","score":0.035550407529584487,"rank":294,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0356311485443675,"rank":295,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03533908097365485,"rank":275,"remainingConfigurations":381},{"removed":"Vals AI","score":0.033717658533909414,"rank":294,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.034659299789655255,"rank":295,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03462376298624629,"rank":295,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.034596239513562305,"rank":295,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.034657235545589464,"rank":295,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03455895622796055,"rank":295,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03479373838580759,"rank":295,"remainingConfigurations":398},{"removed":"briefcase","score":0.03308281034795517,"rank":300,"remainingConfigurations":398},{"removed":"aime","score":0.036330232385921056,"rank":290,"remainingConfigurations":398},{"removed":"apex-agents","score":0.035099765349457204,"rank":295,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.034605352360016654,"rank":295,"remainingConfigurations":398},{"removed":"automationbench","score":0.033124240841110195,"rank":300,"remainingConfigurations":398},{"removed":"critpt","score":0.034976366171474614,"rank":294,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03472764142068175,"rank":295,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03419340305169588,"rank":298,"remainingConfigurations":398},{"removed":"gdpval","score":0.03317700436761103,"rank":301,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03545685083041479,"rank":295,"remainingConfigurations":398},{"removed":"gpqa","score":0.03506847839418461,"rank":295,"remainingConfigurations":398},{"removed":"harvey","score":0.03428198790688749,"rank":295,"remainingConfigurations":398},{"removed":"hle","score":0.04025357746058156,"rank":287,"remainingConfigurations":398},{"removed":"ifbench","score":0.03425285659418199,"rank":294,"remainingConfigurations":398},{"removed":"itbench","score":0.03461580051374532,"rank":295,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03554903296450173,"rank":293,"remainingConfigurations":398},{"removed":"math500","score":0.03485790291147105,"rank":295,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03632263767840186,"rank":294,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03725757397237282,"rank":295,"remainingConfigurations":398},{"removed":"omniscience","score":0.03126394803611252,"rank":303,"remainingConfigurations":398},{"removed":"scicode","score":0.03504098042367537,"rank":296,"remainingConfigurations":398},{"removed":"tau-bench","score":0.033619095184170195,"rank":296,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03337846485077531,"rank":300,"remainingConfigurations":398},{"removed":"arc-agi","score":0.041496519178232896,"rank":297,"remainingConfigurations":398},{"removed":"deepswe","score":0.02939270090787,"rank":295,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03466759304126675,"rank":295,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.034418053035773784,"rank":295,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03636152653183567,"rank":296,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.034693815764365636,"rank":295,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.034330985392979206,"rank":295,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03460739604817557,"rank":295,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03452841412373717,"rank":295,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03471879007234872,"rank":295,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.034369055135558955,"rank":295,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03507873349651339,"rank":295,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03473078293352246,"rank":295,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0340922485718961,"rank":295,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03441948272629491,"rank":295,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.035206352936294545,"rank":295,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0356311485443675,"rank":295,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03291845720904015,"rank":293,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03498492439694476,"rank":295,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03609433514214292,"rank":295,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03448078546111607,"rank":295,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03453248876745786,"rank":295,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.034508983599315625,"rank":295,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.034596608630093915,"rank":295,"remainingConfigurations":398},{"removed":"vibe-code","score":0.034416324885634474,"rank":295,"remainingConfigurations":398}]},"qwen3-coder-480b-a35b-instruct--effort-non-reasoning":{"score":0.03459081069028119,"rank":296,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04189796569063901,"rank":296,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02934037986639701,"rank":296,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03421891100548923,"rank":296,"remainingConfigurations":398},{"removed":"Scale","score":0.03857073251813715,"rank":296,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03453162093666704,"rank":296,"remainingConfigurations":398},{"removed":"Cognition","score":0.03637220130812203,"rank":295,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03546184300398949,"rank":295,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03554935647881103,"rank":296,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03485759258917554,"rank":277,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03361757552559833,"rank":295,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03459293586019102,"rank":296,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03455727118165955,"rank":296,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03453079087479027,"rank":296,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03459081069028119,"rank":296,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03449353101616167,"rank":296,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03470792193641705,"rank":296,"remainingConfigurations":398},{"removed":"briefcase","score":0.03453348735802461,"rank":295,"remainingConfigurations":398},{"removed":"aime","score":0.036130930966472914,"rank":292,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03497933887620405,"rank":296,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03325796711718219,"rank":297,"remainingConfigurations":398},{"removed":"automationbench","score":0.03459115058452935,"rank":296,"remainingConfigurations":398},{"removed":"critpt","score":0.03494345669338931,"rank":295,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03464083491732376,"rank":296,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.035047861398383624,"rank":295,"remainingConfigurations":398},{"removed":"gdpval","score":0.03483618547111157,"rank":296,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03494225243756784,"rank":298,"remainingConfigurations":398},{"removed":"gpqa","score":0.03496593107169998,"rank":296,"remainingConfigurations":398},{"removed":"harvey","score":0.03418802943724235,"rank":296,"remainingConfigurations":398},{"removed":"hle","score":0.039108268222372684,"rank":291,"remainingConfigurations":398},{"removed":"ifbench","score":0.03365306664482926,"rank":296,"remainingConfigurations":398},{"removed":"itbench","score":0.03453671094195781,"rank":296,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03370775007956794,"rank":300,"remainingConfigurations":398},{"removed":"math500","score":0.03413247627038512,"rank":297,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.035046856676807424,"rank":299,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.037154013431571174,"rank":296,"remainingConfigurations":398},{"removed":"omniscience","score":0.03318092018865012,"rank":295,"remainingConfigurations":398},{"removed":"scicode","score":0.03528134448654189,"rank":295,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03290352090377183,"rank":299,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03278730246432905,"rank":301,"remainingConfigurations":398},{"removed":"arc-agi","score":0.041579369775757234,"rank":296,"remainingConfigurations":398},{"removed":"deepswe","score":0.02936269901515748,"rank":296,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03460093527019115,"rank":296,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03434887473674614,"rank":296,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03637220130812203,"rank":295,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03462640199316493,"rank":296,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03426661364431074,"rank":296,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03454034066685908,"rank":296,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03446066597029692,"rank":296,"remainingConfigurations":398},{"removed":"livebench-math","score":0.034652805116849324,"rank":296,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03430043825640074,"rank":296,"remainingConfigurations":398},{"removed":"livebench-language","score":0.035009341889316516,"rank":296,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03466481493589997,"rank":296,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.034028388927142474,"rank":296,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03435333743495142,"rank":296,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03514136500886101,"rank":296,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03554935647881103,"rank":296,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03275915119751598,"rank":294,"remainingConfigurations":398},{"removed":"frontiermath","score":0.034949926512184724,"rank":296,"remainingConfigurations":398},{"removed":"simpleqa","score":0.036034144249589097,"rank":296,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03441500560155109,"rank":296,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03446600059677594,"rank":296,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0344432183229008,"rank":296,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03452900807744928,"rank":296,"remainingConfigurations":398},{"removed":"vibe-code","score":0.034350773886772205,"rank":296,"remainingConfigurations":398}]},"k-exaone-236b-a23b--effort-non-reasoning":{"score":0.03430216433974306,"rank":297,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04167737478866481,"rank":298,"remainingConfigurations":398},{"removed":"Datacurve","score":0.029102177559789364,"rank":297,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.033955888594876533,"rank":297,"remainingConfigurations":398},{"removed":"Scale","score":0.03825786175976093,"rank":297,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03423562194744685,"rank":297,"remainingConfigurations":398},{"removed":"Cognition","score":0.036084383324301035,"rank":297,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03516230484830634,"rank":296,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03522265523989353,"rank":297,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03455307498890802,"rank":278,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03332221387594809,"rank":296,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.034304273473527984,"rank":297,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.034268906170109976,"rank":297,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03424257873046719,"rank":297,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03430216433974306,"rank":297,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03420562375119209,"rank":297,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03441228011260745,"rank":297,"remainingConfigurations":398},{"removed":"briefcase","score":0.03421210685298023,"rank":296,"remainingConfigurations":398},{"removed":"aime","score":0.03576210596491162,"rank":293,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03468955214230013,"rank":297,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03176003501542016,"rank":306,"remainingConfigurations":398},{"removed":"automationbench","score":0.034267371149901776,"rank":297,"remainingConfigurations":398},{"removed":"critpt","score":0.03486163627397932,"rank":296,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03434474467003016,"rank":297,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03472037134639979,"rank":296,"remainingConfigurations":398},{"removed":"gdpval","score":0.034434512555085596,"rank":297,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0368008892673929,"rank":291,"remainingConfigurations":398},{"removed":"gpqa","score":0.032992388634128504,"rank":300,"remainingConfigurations":398},{"removed":"harvey","score":0.033901420600999266,"rank":297,"remainingConfigurations":398},{"removed":"hle","score":0.036887213297261495,"rank":298,"remainingConfigurations":398},{"removed":"ifbench","score":0.0338206154518351,"rank":295,"remainingConfigurations":398},{"removed":"itbench","score":0.03425410096107071,"rank":297,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03431195951634321,"rank":297,"remainingConfigurations":398},{"removed":"math500","score":0.03459536852283264,"rank":296,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.032841623467560095,"rank":306,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03678425916585045,"rank":298,"remainingConfigurations":398},{"removed":"omniscience","score":0.03454891093392274,"rank":290,"remainingConfigurations":398},{"removed":"scicode","score":0.034954332072060966,"rank":297,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03131870024412612,"rank":306,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03492167739137115,"rank":298,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04136272101597411,"rank":298,"remainingConfigurations":398},{"removed":"deepswe","score":0.02912427067810075,"rank":297,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03431219495468577,"rank":297,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.034062205690914164,"rank":297,"remainingConfigurations":398},{"removed":"frontiercode","score":0.036084383324301035,"rank":297,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.034337712789255716,"rank":297,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03398158058086442,"rank":297,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03425190151021742,"rank":297,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.034172480713700264,"rank":297,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03436364925778871,"rank":297,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.034013986378374765,"rank":297,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03471727492379443,"rank":297,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0343756518859648,"rank":297,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.033744163256639294,"rank":297,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.034066549622468544,"rank":297,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.034848645887982824,"rank":297,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03522265523989353,"rank":297,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03246314631123759,"rank":295,"remainingConfigurations":398},{"removed":"frontiermath","score":0.034650820426309556,"rank":297,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03572797752281399,"rank":297,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03412777098284344,"rank":297,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03417827574592363,"rank":297,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03415574981240423,"rank":297,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.034240693323705836,"rank":297,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03406398331720058,"rank":297,"remainingConfigurations":398}]},"gpt-4.1-mini--effort-non-reasoning":{"score":0.03381827207983502,"rank":298,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04091673987574743,"rank":299,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02867164685143998,"rank":298,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03344416150283847,"rank":298,"remainingConfigurations":398},{"removed":"Scale","score":0.03773480386027093,"rank":298,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03376311663796271,"rank":298,"remainingConfigurations":398},{"removed":"Cognition","score":0.03553892576840687,"rank":298,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03468363010613072,"rank":297,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03475423183649678,"rank":298,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.034118332042908206,"rank":280,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03287691157650512,"rank":297,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03382033344162596,"rank":298,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0337853909732425,"rank":298,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03375912550130839,"rank":298,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03381827207983502,"rank":298,"remainingConfigurations":398},{"removed":"All provider reports","score":0.033722576167065275,"rank":298,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03393133497991164,"rank":298,"remainingConfigurations":398},{"removed":"briefcase","score":0.03376951198186448,"rank":297,"remainingConfigurations":398},{"removed":"aime","score":0.034526928608504856,"rank":298,"remainingConfigurations":398},{"removed":"apex-agents","score":0.034195755115270156,"rank":298,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03268098528614471,"rank":303,"remainingConfigurations":398},{"removed":"automationbench","score":0.03384718892684188,"rank":298,"remainingConfigurations":398},{"removed":"critpt","score":0.03400805756290675,"rank":297,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03385946795718176,"rank":298,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03428857086967392,"rank":297,"remainingConfigurations":398},{"removed":"gdpval","score":0.03390859358299383,"rank":298,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03418095512300113,"rank":299,"remainingConfigurations":398},{"removed":"gpqa","score":0.033480645162714866,"rank":299,"remainingConfigurations":398},{"removed":"harvey","score":0.03342661963449547,"rank":298,"remainingConfigurations":398},{"removed":"hle","score":0.036763659298137824,"rank":300,"remainingConfigurations":398},{"removed":"ifbench","score":0.03345253425380532,"rank":297,"remainingConfigurations":398},{"removed":"itbench","score":0.03376400538267572,"rank":298,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03411128960416971,"rank":298,"remainingConfigurations":398},{"removed":"math500","score":0.03489121829318478,"rank":294,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.034495585880025964,"rank":300,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.036041234198399094,"rank":301,"remainingConfigurations":398},{"removed":"omniscience","score":0.030131100390707457,"rank":306,"remainingConfigurations":398},{"removed":"scicode","score":0.03451385111086901,"rank":298,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03241111210493864,"rank":301,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03398421401394893,"rank":299,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04060618734516518,"rank":299,"remainingConfigurations":398},{"removed":"deepswe","score":0.028693520028379934,"rank":298,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03382822140965001,"rank":298,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03358237672020822,"rank":298,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03553892576840687,"rank":298,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03385387317892819,"rank":298,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.033500307149649404,"rank":298,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.033769277767793364,"rank":298,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03369137059400136,"rank":298,"remainingConfigurations":398},{"removed":"livebench-math","score":0.033878850093694186,"rank":298,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03353473868535629,"rank":298,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0342285848284863,"rank":298,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03389061503861918,"rank":298,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03326728277215748,"rank":298,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.033585801125583785,"rank":298,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03435660545836878,"rank":298,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03475423183649678,"rank":298,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0320422865762946,"rank":296,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03415939001078076,"rank":298,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03522815665630933,"rank":298,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.033646028629606695,"rank":298,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.033696161587329194,"rank":298,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03367364478597781,"rank":298,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.033758022567488936,"rank":298,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03358320594170506,"rank":298,"remainingConfigurations":398}]},"magistral-small-2509--effort-reasoning":{"score":0.03378990462330259,"rank":299,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.040765705518386215,"rank":300,"remainingConfigurations":398},{"removed":"Datacurve","score":0.028635339316485573,"rank":299,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.033428349563886274,"rank":299,"remainingConfigurations":398},{"removed":"Scale","score":0.03766397789326325,"rank":299,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03373191205148231,"rank":299,"remainingConfigurations":398},{"removed":"Cognition","score":0.03548770946416726,"rank":299,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03465584860638075,"rank":298,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03470515937161959,"rank":299,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03413932700733109,"rank":279,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0328465608841694,"rank":298,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.033791956482904874,"rank":299,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0337570721329847,"rank":299,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03373062461798292,"rank":299,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03378990462330259,"rank":299,"remainingConfigurations":398},{"removed":"All provider reports","score":0.033694114547282585,"rank":299,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03389436838463178,"rank":299,"remainingConfigurations":398},{"removed":"briefcase","score":0.03360760615007307,"rank":298,"remainingConfigurations":398},{"removed":"aime","score":0.031217319733935992,"rank":305,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03416811962157202,"rank":299,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.034913809480789086,"rank":294,"remainingConfigurations":398},{"removed":"automationbench","score":0.0350089739979711,"rank":295,"remainingConfigurations":398},{"removed":"critpt","score":0.0308933991539275,"rank":308,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03382031196869844,"rank":299,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03412371067029332,"rank":299,"remainingConfigurations":398},{"removed":"gdpval","score":0.034883013846291125,"rank":295,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03507809462847328,"rank":297,"remainingConfigurations":398},{"removed":"gpqa","score":0.03354343227057085,"rank":298,"remainingConfigurations":398},{"removed":"harvey","score":0.033393871912068614,"rank":299,"remainingConfigurations":398},{"removed":"hle","score":0.03562282224807809,"rank":303,"remainingConfigurations":398},{"removed":"ifbench","score":0.03167263980482846,"rank":302,"remainingConfigurations":398},{"removed":"itbench","score":0.03373318300556381,"rank":299,"remainingConfigurations":398},{"removed":"livecodebench","score":0.031150019491939285,"rank":305,"remainingConfigurations":398},{"removed":"math500","score":0.03391133311422464,"rank":298,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.035158643714271735,"rank":297,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03681509597439541,"rank":297,"remainingConfigurations":398},{"removed":"omniscience","score":0.03389387010521295,"rank":292,"remainingConfigurations":398},{"removed":"scicode","score":0.034352608240334766,"rank":299,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03402569445582917,"rank":295,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03507520859001017,"rank":297,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04046120937962134,"rank":300,"remainingConfigurations":398},{"removed":"deepswe","score":0.028657244618229282,"rank":299,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03379988133009149,"rank":299,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.033554614603576456,"rank":299,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03548770946416726,"rank":299,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03382475991510455,"rank":299,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03347197799584134,"rank":299,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03374088352239328,"rank":299,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03366324489859917,"rank":299,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03385032037841924,"rank":299,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0335071764191208,"rank":299,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03420026353266741,"rank":299,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03386190192487427,"rank":299,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03323906113671596,"rank":299,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.033557696288629583,"rank":299,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03432746952158978,"rank":299,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03470515937161959,"rank":299,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.032030199183355,"rank":297,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03412357452060575,"rank":299,"remainingConfigurations":398},{"removed":"simpleqa","score":0.035194781475629516,"rank":299,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03361774197350844,"rank":299,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03366788245185273,"rank":299,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03364534549077211,"rank":299,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.033729853856294435,"rank":299,"remainingConfigurations":398},{"removed":"vibe-code","score":0.033554926842770214,"rank":299,"remainingConfigurations":398}]},"glm-4.6v--effort-reasoning":{"score":0.033581884810177244,"rank":300,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04074427836663997,"rank":301,"remainingConfigurations":398},{"removed":"Datacurve","score":0.028487967080520028,"rank":300,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03322956872833576,"rank":300,"remainingConfigurations":398},{"removed":"Scale","score":0.03745448735071873,"rank":300,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03351775485118732,"rank":300,"remainingConfigurations":398},{"removed":"Cognition","score":0.0353207352790045,"rank":300,"remainingConfigurations":398},{"removed":"LiveBench","score":0.034426495893915894,"rank":299,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.034474527730604755,"rank":300,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03387972003516819,"rank":282,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03262450651677636,"rank":299,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03358395408151895,"rank":300,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.033549131958681234,"rank":300,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03352338505665903,"rank":300,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.033581884810177244,"rank":300,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0334870099302687,"rank":300,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03368400161096731,"rank":300,"remainingConfigurations":398},{"removed":"briefcase","score":0.03348628731754869,"rank":299,"remainingConfigurations":398},{"removed":"aime","score":0.029511805514740353,"rank":307,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03396195749133359,"rank":300,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03188883084372031,"rank":305,"remainingConfigurations":398},{"removed":"automationbench","score":0.033554715302804856,"rank":299,"remainingConfigurations":398},{"removed":"critpt","score":0.03394131448359849,"rank":298,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03362587522574608,"rank":300,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0339882962056168,"rank":300,"remainingConfigurations":398},{"removed":"gdpval","score":0.03374203386314511,"rank":299,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03303576801736815,"rank":304,"remainingConfigurations":398},{"removed":"gpqa","score":0.03191298813756766,"rank":305,"remainingConfigurations":398},{"removed":"harvey","score":0.03318964976952286,"rank":300,"remainingConfigurations":398},{"removed":"hle","score":0.034029723145148634,"rank":306,"remainingConfigurations":398},{"removed":"ifbench","score":0.0360473820639117,"rank":290,"remainingConfigurations":398},{"removed":"itbench","score":0.033532668269134286,"rank":300,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03934948670770685,"rank":284,"remainingConfigurations":398},{"removed":"math500","score":0.03368086753337921,"rank":300,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.033386555473576766,"rank":303,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0380646966393284,"rank":293,"remainingConfigurations":398},{"removed":"omniscience","score":0.03204036852386662,"rank":300,"remainingConfigurations":398},{"removed":"scicode","score":0.03421711672955613,"rank":300,"remainingConfigurations":398},{"removed":"tau-bench","score":0.033160932338184575,"rank":297,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03255114381514986,"rank":303,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04043329324585034,"rank":301,"remainingConfigurations":398},{"removed":"deepswe","score":0.02850958045224036,"rank":300,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.033591708706417964,"rank":300,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03334700799057367,"rank":300,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0353207352790045,"rank":300,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03361698412442074,"rank":300,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03326801160517127,"rank":300,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.033532719529640036,"rank":300,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03345479965828428,"rank":300,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03364214100432802,"rank":300,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03329941904686933,"rank":300,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0339888219139025,"rank":300,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03365382851889743,"rank":300,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0330348897384854,"rank":300,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03335093687737109,"rank":300,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.034117692237590556,"rank":300,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.034474527730604755,"rank":300,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.031787484148923136,"rank":298,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0339230870928643,"rank":300,"remainingConfigurations":398},{"removed":"simpleqa","score":0.034980030597749366,"rank":300,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0334108893472734,"rank":300,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.033460398156060465,"rank":300,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03343843233935594,"rank":300,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03352148961405548,"rank":300,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03334838428736427,"rank":300,"remainingConfigurations":398}]},"mistral-medium-2508--effort-non-reasoning":{"score":0.03328777687561441,"rank":301,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.040196112930539936,"rank":302,"remainingConfigurations":398},{"removed":"Datacurve","score":0.028204452899376235,"rank":301,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.032938626343176645,"rank":301,"remainingConfigurations":398},{"removed":"Scale","score":0.037166929936898005,"rank":301,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03323569912099054,"rank":301,"remainingConfigurations":398},{"removed":"Cognition","score":0.03493256117779494,"rank":301,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03415720722497884,"rank":300,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03423671608373266,"rank":301,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03388627814963414,"rank":281,"remainingConfigurations":381},{"removed":"Vals AI","score":0.032395223303507976,"rank":300,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03328977802259086,"rank":301,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03325551997767632,"rank":301,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03322890949210623,"rank":301,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03328777687561441,"rank":301,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03319299066503612,"rank":301,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03342957835889512,"rank":301,"remainingConfigurations":398},{"removed":"briefcase","score":0.031058637104909522,"rank":307,"remainingConfigurations":398},{"removed":"aime","score":0.03449251227682057,"rank":299,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03370534788778318,"rank":301,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03309208025105374,"rank":298,"remainingConfigurations":398},{"removed":"automationbench","score":0.03134620029520423,"rank":307,"remainingConfigurations":398},{"removed":"critpt","score":0.03353725872105411,"rank":301,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03337081247052486,"rank":301,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03360059721142042,"rank":301,"remainingConfigurations":398},{"removed":"gdpval","score":0.03268573725748058,"rank":303,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0336687148992616,"rank":300,"remainingConfigurations":398},{"removed":"gpqa","score":0.03371768386765959,"rank":297,"remainingConfigurations":398},{"removed":"harvey","score":0.032940697592705626,"rank":301,"remainingConfigurations":398},{"removed":"hle","score":0.03660627576858536,"rank":301,"remainingConfigurations":398},{"removed":"ifbench","score":0.032168708595496386,"rank":299,"remainingConfigurations":398},{"removed":"itbench","score":0.03326282226609554,"rank":301,"remainingConfigurations":398},{"removed":"livecodebench","score":0.034391344066020554,"rank":296,"remainingConfigurations":398},{"removed":"math500","score":0.03353480205141828,"rank":301,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.037535417319897076,"rank":290,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03623006842810932,"rank":300,"remainingConfigurations":398},{"removed":"omniscience","score":0.02986458549201433,"rank":307,"remainingConfigurations":398},{"removed":"scicode","score":0.03374324567888557,"rank":301,"remainingConfigurations":398},{"removed":"tau-bench","score":0.031706721095865,"rank":304,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03275050713611904,"rank":302,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03989903390592756,"rank":302,"remainingConfigurations":398},{"removed":"deepswe","score":0.0282262233453752,"rank":301,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03329772839624789,"rank":301,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.033058725082561,"rank":301,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03493256117779494,"rank":301,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.033324068567944,"rank":301,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03297364610169785,"rank":301,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03324011387264122,"rank":301,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03316388229757216,"rank":301,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03334696378290744,"rank":301,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.033010220165337244,"rank":301,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03369373473083389,"rank":301,"remainingConfigurations":398},{"removed":"livebench-data","score":0.033358772840558826,"rank":301,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.032743771053089704,"rank":301,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03305874182112333,"rank":301,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03381661728860495,"rank":301,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03423671608373266,"rank":301,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03161952373883218,"rank":299,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03360413601455393,"rank":301,"remainingConfigurations":398},{"removed":"simpleqa","score":0.034671809511135944,"rank":301,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.033117881865229105,"rank":301,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.033167649746834324,"rank":301,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03314501870516257,"rank":301,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03322926023215517,"rank":301,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0330558491473619,"rank":301,"remainingConfigurations":398}]},"gemma-4-12b-it--effort-non-reasoning":{"score":0.03304995790460006,"rank":302,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.04003132784303155,"rank":304,"remainingConfigurations":398},{"removed":"Datacurve","score":0.028045464325974327,"rank":302,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.032710819666697914,"rank":302,"remainingConfigurations":398},{"removed":"Scale","score":0.036900589422039394,"rank":302,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03298590112865748,"rank":303,"remainingConfigurations":398},{"removed":"Cognition","score":0.034763094394516296,"rank":303,"remainingConfigurations":398},{"removed":"LiveBench","score":0.033886090941661104,"rank":301,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03394589176252351,"rank":303,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03322610268881431,"rank":284,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03210657640728875,"rank":302,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03305201031143773,"rank":302,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03301792927530454,"rank":302,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03299215474961372,"rank":302,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03304995790460006,"rank":302,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03295656307936708,"rank":302,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03315850987708505,"rank":303,"remainingConfigurations":398},{"removed":"briefcase","score":0.032945318992935575,"rank":302,"remainingConfigurations":398},{"removed":"aime","score":0.033243234834157434,"rank":302,"remainingConfigurations":398},{"removed":"apex-agents","score":0.033427383375547425,"rank":302,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0325998476122269,"rank":304,"remainingConfigurations":398},{"removed":"automationbench","score":0.033006351672172494,"rank":302,"remainingConfigurations":398},{"removed":"critpt","score":0.03379348555036503,"rank":299,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03308817267569257,"rank":303,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.033442759692192355,"rank":303,"remainingConfigurations":398},{"removed":"gdpval","score":0.033105707584575754,"rank":302,"remainingConfigurations":398},{"removed":"gmmlu","score":0.033255914442955004,"rank":302,"remainingConfigurations":398},{"removed":"gpqa","score":0.03284432210331739,"rank":301,"remainingConfigurations":398},{"removed":"harvey","score":0.032659536708989995,"rank":303,"remainingConfigurations":398},{"removed":"hle","score":0.03476352197681989,"rank":304,"remainingConfigurations":398},{"removed":"ifbench","score":0.029889909915241236,"rank":306,"remainingConfigurations":398},{"removed":"itbench","score":0.032982712780685354,"rank":303,"remainingConfigurations":398},{"removed":"livecodebench","score":0.033147944635983174,"rank":302,"remainingConfigurations":398},{"removed":"math500","score":0.03333171762846496,"rank":302,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03421290189286814,"rank":301,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03402337136264687,"rank":308,"remainingConfigurations":398},{"removed":"omniscience","score":0.0350147995948991,"rank":286,"remainingConfigurations":398},{"removed":"scicode","score":0.03366407434122713,"rank":303,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03231770319226964,"rank":302,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03197789177041752,"rank":304,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03972466092539985,"rank":304,"remainingConfigurations":398},{"removed":"deepswe","score":0.028066741333695952,"rank":302,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03305963208400998,"rank":302,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03281947290741979,"rank":302,"remainingConfigurations":398},{"removed":"frontiercode","score":0.034763094394516296,"rank":303,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.033086044513116426,"rank":302,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.032741191299215426,"rank":302,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.033001726260432705,"rank":302,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03292467129741714,"rank":302,"remainingConfigurations":398},{"removed":"livebench-math","score":0.033109246668804264,"rank":302,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03277167940843314,"rank":302,"remainingConfigurations":398},{"removed":"livebench-language","score":0.033451012490094925,"rank":302,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03312119310052856,"rank":302,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03251105609613906,"rank":302,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.032822301174420025,"rank":302,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.033577623753399545,"rank":302,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03394589176252351,"rank":303,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03134312054511002,"rank":300,"remainingConfigurations":398},{"removed":"frontiermath","score":0.033365059201095046,"rank":303,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03442355067926702,"rank":303,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03288154700085969,"rank":302,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03293035472128387,"rank":302,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03290847272824069,"rank":302,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03299055090179927,"rank":302,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03282003022373479,"rank":302,"remainingConfigurations":398}]},"minimax-m1-40k--effort-reasoning":{"score":0.033048301803810604,"rank":303,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.040116977875821504,"rank":303,"remainingConfigurations":398},{"removed":"Datacurve","score":0.028030729019074992,"rank":303,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03268388129846668,"rank":303,"remainingConfigurations":398},{"removed":"Scale","score":0.03687870437767216,"rank":303,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03298794898270289,"rank":302,"remainingConfigurations":398},{"removed":"Cognition","score":0.03477632320885121,"rank":302,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03388053115132784,"rank":302,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.033972634639388787,"rank":302,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03314993368434733,"rank":285,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03211513269120456,"rank":301,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.033050351652026494,"rank":303,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03301614215553816,"rank":303,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03299104239226001,"rank":303,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.033048301803810604,"rank":303,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03295532994494402,"rank":303,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.033161780698338104,"rank":302,"remainingConfigurations":398},{"removed":"briefcase","score":0.03297599039279581,"rank":301,"remainingConfigurations":398},{"removed":"aime","score":0.04148158098192606,"rank":280,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03342462781200961,"rank":303,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03269159545039806,"rank":302,"remainingConfigurations":398},{"removed":"automationbench","score":0.03301910644941181,"rank":301,"remainingConfigurations":398},{"removed":"critpt","score":0.03223321488960727,"rank":306,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03309992949730465,"rank":302,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03344804209560582,"rank":302,"remainingConfigurations":398},{"removed":"gdpval","score":0.03320309009667261,"rank":300,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03330101155578821,"rank":301,"remainingConfigurations":398},{"removed":"gpqa","score":0.03187848341741378,"rank":306,"remainingConfigurations":398},{"removed":"harvey","score":0.032673944866851656,"rank":302,"remainingConfigurations":398},{"removed":"hle","score":0.03362689962221078,"rank":307,"remainingConfigurations":398},{"removed":"ifbench","score":0.03185408473506564,"rank":301,"remainingConfigurations":398},{"removed":"itbench","score":0.033002515299584576,"rank":302,"remainingConfigurations":398},{"removed":"livecodebench","score":0.030744649476220864,"rank":306,"remainingConfigurations":398},{"removed":"math500","score":0.030354311972398376,"rank":310,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03141572850478817,"rank":308,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03542751440597696,"rank":304,"remainingConfigurations":398},{"removed":"omniscience","score":0.031082659621944092,"rank":304,"remainingConfigurations":398},{"removed":"scicode","score":0.03366964424327401,"rank":302,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03283511935624626,"rank":300,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03667216351968303,"rank":289,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03980824743771957,"rank":303,"remainingConfigurations":398},{"removed":"deepswe","score":0.02805205074865011,"rank":303,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03305797226920197,"rank":303,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03281704902196333,"rank":303,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03477632320885121,"rank":302,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03308358316949941,"rank":303,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03273907845105334,"rank":303,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03300006566640764,"rank":303,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03292352271557413,"rank":303,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03310773340114938,"rank":303,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03276973456456991,"rank":303,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03344910844035332,"rank":303,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03311916111082425,"rank":303,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03250959475358884,"rank":303,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03282078952301786,"rank":303,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03357632776334298,"rank":303,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.033972634639388787,"rank":302,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.031258459589305364,"rank":301,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03339624936841767,"rank":302,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03443377646543505,"rank":302,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03287987761394682,"rank":303,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03292858332360841,"rank":303,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03290702743446289,"rank":303,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03298877027568179,"rank":303,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03281830561063946,"rank":303,"remainingConfigurations":398}]},"amazon-nova-2-pro-preview--effort-non-reasoning":{"score":0.032736965097685956,"rank":304,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03957364297506109,"rank":305,"remainingConfigurations":398},{"removed":"Datacurve","score":0.027773514869449425,"rank":304,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03241540607022851,"rank":304,"remainingConfigurations":398},{"removed":"Scale","score":0.03655411510539721,"rank":304,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0326734111239552,"rank":304,"remainingConfigurations":398},{"removed":"Cognition","score":0.03445019498275161,"rank":304,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03356596321736988,"rank":303,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.033608452547156366,"rank":304,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.033229523938003755,"rank":283,"remainingConfigurations":381},{"removed":"Vals AI","score":0.031804594550184744,"rank":303,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.032738969432072385,"rank":304,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03270513143588491,"rank":304,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03267992783984507,"rank":304,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.032736965097685956,"rank":304,"remainingConfigurations":398},{"removed":"All provider reports","score":0.032644539058123874,"rank":304,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.032842683286386044,"rank":304,"remainingConfigurations":398},{"removed":"briefcase","score":0.03266327642038119,"rank":303,"remainingConfigurations":398},{"removed":"aime","score":0.03531070413746187,"rank":295,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03311297872224909,"rank":304,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03295105804119336,"rank":299,"remainingConfigurations":398},{"removed":"automationbench","score":0.03273481766122784,"rank":303,"remainingConfigurations":398},{"removed":"critpt","score":0.03293965256244557,"rank":302,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.032781802284583376,"rank":304,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03315624124390441,"rank":304,"remainingConfigurations":398},{"removed":"gdpval","score":0.032656489833441854,"rank":304,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03319382682336986,"rank":303,"remainingConfigurations":398},{"removed":"gpqa","score":0.032811019488772235,"rank":302,"remainingConfigurations":398},{"removed":"harvey","score":0.032355981505681815,"rank":304,"remainingConfigurations":398},{"removed":"hle","score":0.03810840348769483,"rank":295,"remainingConfigurations":398},{"removed":"ifbench","score":0.029133091492500266,"rank":307,"remainingConfigurations":398},{"removed":"itbench","score":0.03267493332866055,"rank":304,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03317004479196194,"rank":301,"remainingConfigurations":398},{"removed":"math500","score":0.03293194000230635,"rank":303,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03385035906916565,"rank":302,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03515248162691208,"rank":305,"remainingConfigurations":398},{"removed":"omniscience","score":0.030469100080485086,"rank":305,"remainingConfigurations":398},{"removed":"scicode","score":0.03338289660705273,"rank":304,"remainingConfigurations":398},{"removed":"tau-bench","score":0.029572354940897477,"rank":312,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03121396057069061,"rank":308,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03927049023072768,"rank":305,"remainingConfigurations":398},{"removed":"deepswe","score":0.027794650224772403,"rank":304,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.032746582228942556,"rank":304,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03250810044219255,"rank":304,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03445019498275161,"rank":304,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.032771810327810916,"rank":304,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.032430374399699806,"rank":304,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03268915035629197,"rank":304,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.032613066698626327,"rank":304,"remainingConfigurations":398},{"removed":"livebench-math","score":0.032795817558491536,"rank":304,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0324610408956069,"rank":304,"remainingConfigurations":398},{"removed":"livebench-language","score":0.033134479432718036,"rank":304,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03280749338714272,"rank":304,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03220273551257965,"rank":304,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03251134236752415,"rank":304,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.033260146391295334,"rank":304,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.033608452547156366,"rank":304,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.031012717594273514,"rank":302,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03308804060491379,"rank":304,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03410200730854953,"rank":304,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.032569983645474414,"rank":304,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.032618398785186666,"rank":304,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03259675822026379,"rank":304,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03267814219018753,"rank":304,"remainingConfigurations":398},{"removed":"vibe-code","score":0.032508949974200424,"rank":304,"remainingConfigurations":398}]},"qwen3-4b-thinking-2507--effort-reasoning":{"score":0.03243620114874294,"rank":305,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.039302006842920484,"rank":307,"remainingConfigurations":398},{"removed":"Datacurve","score":0.027501371069223544,"rank":305,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03208609653547499,"rank":305,"remainingConfigurations":398},{"removed":"Scale","score":0.03617688014298625,"rank":305,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03237706359404533,"rank":305,"remainingConfigurations":398},{"removed":"Cognition","score":0.03411453482282469,"rank":305,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03325819454887726,"rank":304,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03334002568874172,"rank":305,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.03262271874947306,"rank":287,"remainingConfigurations":381},{"removed":"Vals AI","score":0.03151914843834896,"rank":304,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03243820507909959,"rank":305,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03240470414703745,"rank":305,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.032379763297957366,"rank":305,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03243620114874294,"rank":305,"remainingConfigurations":398},{"removed":"All provider reports","score":0.032344762601597625,"rank":305,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03254196261114334,"rank":305,"remainingConfigurations":398},{"removed":"briefcase","score":0.03234169442895813,"rank":305,"remainingConfigurations":398},{"removed":"aime","score":0.028335826161241136,"rank":311,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03279897191768098,"rank":305,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03175863636001267,"rank":307,"remainingConfigurations":398},{"removed":"automationbench","score":0.032395467132665334,"rank":305,"remainingConfigurations":398},{"removed":"critpt","score":0.03272715476099262,"rank":303,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.032478570374604485,"rank":305,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.032829903111861077,"rank":306,"remainingConfigurations":398},{"removed":"gdpval","score":0.03260404712468529,"rank":305,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03275376905767647,"rank":305,"remainingConfigurations":398},{"removed":"gpqa","score":0.03187160200880967,"rank":307,"remainingConfigurations":398},{"removed":"harvey","score":0.03205660066974278,"rank":305,"remainingConfigurations":398},{"removed":"hle","score":0.03433444146967281,"rank":305,"remainingConfigurations":398},{"removed":"ifbench","score":0.029105669763955396,"rank":308,"remainingConfigurations":398},{"removed":"itbench","score":0.03238581165243739,"rank":305,"remainingConfigurations":398},{"removed":"livecodebench","score":0.030561468914716217,"rank":308,"remainingConfigurations":398},{"removed":"math500","score":0.03264549644893074,"rank":304,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03506885870968218,"rank":298,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03482132172528401,"rank":306,"remainingConfigurations":398},{"removed":"omniscience","score":0.03299394408851266,"rank":296,"remainingConfigurations":398},{"removed":"scicode","score":0.033051956614076186,"rank":306,"remainingConfigurations":398},{"removed":"tau-bench","score":0.033128663059794554,"rank":298,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03596500578556456,"rank":294,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03900109243415919,"rank":307,"remainingConfigurations":398},{"removed":"deepswe","score":0.02752232792986381,"rank":305,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03244572805951635,"rank":305,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.032209618383823545,"rank":305,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03411453482282469,"rank":305,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.032470411593929556,"rank":305,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.032131764122444416,"rank":305,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03238886385794026,"rank":305,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03231378509969362,"rank":305,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03249455782273935,"rank":305,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03216257833071461,"rank":305,"remainingConfigurations":398},{"removed":"livebench-language","score":0.032830278785390764,"rank":305,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03250609044139974,"rank":305,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03190666333220798,"rank":305,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.032212503063974794,"rank":305,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03295490715469981,"rank":305,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03334002568874172,"rank":305,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.030704229174980568,"rank":303,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03277210051714061,"rank":305,"remainingConfigurations":398},{"removed":"simpleqa","score":0.033793271697290295,"rank":305,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0322706664583142,"rank":305,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03231864791969942,"rank":305,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0322972308089349,"rank":305,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03237787154213138,"rank":305,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03221022062903075,"rank":305,"remainingConfigurations":398}]},"claude-haiku-4-5-20251001--effort-non-reasoning":{"score":0.03240557994038452,"rank":306,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03933138853347139,"rank":306,"remainingConfigurations":398},{"removed":"Datacurve","score":0.027492954816009097,"rank":306,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.032073392643008465,"rank":306,"remainingConfigurations":398},{"removed":"Scale","score":0.03615645190978704,"rank":306,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03234559011290382,"rank":306,"remainingConfigurations":398},{"removed":"Cognition","score":0.03409859355668728,"rank":306,"remainingConfigurations":398},{"removed":"LiveBench","score":0.033230296761501514,"rank":305,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03328587549198767,"rank":306,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.032701478212197176,"rank":286,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0314903437012495,"rank":305,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03240757494368076,"rank":306,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03237397555267677,"rank":306,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.03234918181503926,"rank":306,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03240557994038452,"rank":306,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03231406751038155,"rank":306,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.032521657345040686,"rank":306,"remainingConfigurations":398},{"removed":"briefcase","score":0.03237195947964407,"rank":304,"remainingConfigurations":398},{"removed":"aime","score":0.03396300132071965,"rank":301,"remainingConfigurations":398},{"removed":"apex-agents","score":0.032785818388322265,"rank":306,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03038872583920942,"rank":311,"remainingConfigurations":398},{"removed":"automationbench","score":0.03242477444019073,"rank":304,"remainingConfigurations":398},{"removed":"critpt","score":0.03258909025547019,"rank":304,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03247156688436472,"rank":306,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.03285945709260169,"rank":305,"remainingConfigurations":398},{"removed":"gdpval","score":0.03260327353209563,"rank":306,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03266530173026528,"rank":306,"remainingConfigurations":398},{"removed":"gpqa","score":0.032301439478355475,"rank":303,"remainingConfigurations":398},{"removed":"harvey","score":0.032033038630666484,"rank":306,"remainingConfigurations":398},{"removed":"hle","score":0.037237677483415645,"rank":297,"remainingConfigurations":398},{"removed":"ifbench","score":0.030853126164704064,"rank":304,"remainingConfigurations":398},{"removed":"itbench","score":0.032370180187815345,"rank":306,"remainingConfigurations":398},{"removed":"livecodebench","score":0.032393308346821435,"rank":303,"remainingConfigurations":398},{"removed":"math500","score":0.03259389476039023,"rank":305,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.031887691359119175,"rank":307,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03546294160225311,"rank":303,"remainingConfigurations":398},{"removed":"omniscience","score":0.03189149754055336,"rank":301,"remainingConfigurations":398},{"removed":"scicode","score":0.033089618919848476,"rank":305,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03168126855479537,"rank":305,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02950753280336511,"rank":313,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03902628876300535,"rank":306,"remainingConfigurations":398},{"removed":"deepswe","score":0.027513849269518987,"rank":306,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.032415080877420975,"rank":306,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03217959179861935,"rank":306,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03409859355668728,"rank":306,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0324415636072017,"rank":306,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03210266457862665,"rank":306,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0323583972168432,"rank":306,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.03228283234713067,"rank":306,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0324637892853199,"rank":306,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.032132360885517006,"rank":306,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03279929343779274,"rank":306,"remainingConfigurations":398},{"removed":"livebench-data","score":0.032475319683660346,"rank":306,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.03187651401787268,"rank":306,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03218213903719846,"rank":306,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03292381444971254,"rank":306,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03328587549198767,"rank":306,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.03067012213234605,"rank":304,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03273450089056544,"rank":306,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03375917395416863,"rank":306,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03224021537866873,"rank":306,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.032288077813231154,"rank":306,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03226678764299718,"rank":306,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03234715999771373,"rank":306,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03217972822385068,"rank":306,"remainingConfigurations":398}]},"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning":{"score":0.03194174308061126,"rank":307,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03871891990445562,"rank":308,"remainingConfigurations":398},{"removed":"Datacurve","score":0.027097639276449707,"rank":307,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03161209859984021,"rank":307,"remainingConfigurations":398},{"removed":"Scale","score":0.035652630175909035,"rank":307,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03189279917230827,"rank":307,"remainingConfigurations":398},{"removed":"Cognition","score":0.03360937094054342,"rank":307,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03276347810400305,"rank":306,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03285512289916995,"rank":307,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.032223452875546815,"rank":288,"remainingConfigurations":381},{"removed":"Vals AI","score":0.031051907096703038,"rank":306,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.03194372060473529,"rank":307,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.03191088111286688,"rank":307,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.031885691521870055,"rank":307,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.03194174308061126,"rank":307,"remainingConfigurations":398},{"removed":"All provider reports","score":0.031851364871965215,"rank":307,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0320489018847336,"rank":307,"remainingConfigurations":398},{"removed":"briefcase","score":0.03183556353842533,"rank":306,"remainingConfigurations":398},{"removed":"aime","score":0.03195912698286223,"rank":304,"remainingConfigurations":398},{"removed":"apex-agents","score":0.032303729918347734,"rank":307,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.030989148711432647,"rank":309,"remainingConfigurations":398},{"removed":"automationbench","score":0.03190917352188652,"rank":306,"remainingConfigurations":398},{"removed":"critpt","score":0.03252591462228754,"rank":305,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.03198674070896683,"rank":307,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.032331528255033666,"rank":307,"remainingConfigurations":398},{"removed":"gdpval","score":0.03228892452691454,"rank":307,"remainingConfigurations":398},{"removed":"gmmlu","score":0.03221688432729161,"rank":307,"remainingConfigurations":398},{"removed":"gpqa","score":0.03519453333379653,"rank":294,"remainingConfigurations":398},{"removed":"harvey","score":0.03157420633698476,"rank":307,"remainingConfigurations":398},{"removed":"hle","score":0.03564823360821786,"rank":302,"remainingConfigurations":398},{"removed":"ifbench","score":0.025541849295582907,"rank":318,"remainingConfigurations":398},{"removed":"itbench","score":0.03189142104630705,"rank":307,"remainingConfigurations":398},{"removed":"livecodebench","score":0.03189320154148676,"rank":304,"remainingConfigurations":398},{"removed":"math500","score":0.03214783381017303,"rank":306,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.032937187706765146,"rank":305,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03546671500169493,"rank":302,"remainingConfigurations":398},{"removed":"omniscience","score":0.031653765462698207,"rank":302,"remainingConfigurations":398},{"removed":"scicode","score":0.03255533071222664,"rank":307,"remainingConfigurations":398},{"removed":"tau-bench","score":0.029385963373395458,"rank":313,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.031847881699472044,"rank":305,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03840819221663352,"rank":308,"remainingConfigurations":398},{"removed":"deepswe","score":0.02711829147473069,"rank":307,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.031951143865057416,"rank":307,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0317203347006315,"rank":307,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03360937094054342,"rank":307,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03197731531589837,"rank":307,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.031642701002017756,"rank":307,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.03189531668491232,"rank":307,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.031821143178360836,"rank":307,"remainingConfigurations":398},{"removed":"livebench-math","score":0.03199917853331378,"rank":307,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03167248752084371,"rank":307,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03233060712143368,"rank":307,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03201079004902207,"rank":307,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0314196125055395,"rank":307,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.03172120724875245,"rank":307,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.032452353189494645,"rank":307,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03285512289916995,"rank":307,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.030289812902988197,"rank":305,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03226468753317013,"rank":307,"remainingConfigurations":398},{"removed":"simpleqa","score":0.033272144369566735,"rank":307,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0317785717075067,"rank":307,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.03182600338002033,"rank":307,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.03180450133527012,"rank":307,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.03188447636854239,"rank":307,"remainingConfigurations":398},{"removed":"vibe-code","score":0.03171913939220007,"rank":307,"remainingConfigurations":398}]},"glm-4.5v--effort-reasoning":{"score":0.030438589344463963,"rank":308,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.036981661549307626,"rank":310,"remainingConfigurations":398},{"removed":"Datacurve","score":0.025812768936666407,"rank":309,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.03011869846320504,"rank":308,"remainingConfigurations":398},{"removed":"Scale","score":0.03396881308699685,"rank":308,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.030379351644620245,"rank":308,"remainingConfigurations":398},{"removed":"Cognition","score":0.03203483140300655,"rank":309,"remainingConfigurations":398},{"removed":"LiveBench","score":0.031215333435592532,"rank":307,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0312812656718438,"rank":308,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.030697216661867685,"rank":290,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02957375449226968,"rank":307,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.030440477014042355,"rank":308,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.030408834963008308,"rank":308,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.030385385816893873,"rank":308,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.030438589344463963,"rank":308,"remainingConfigurations":398},{"removed":"All provider reports","score":0.030352326741429347,"rank":308,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.030537562539843608,"rank":308,"remainingConfigurations":398},{"removed":"briefcase","score":0.030376984747307743,"rank":308,"remainingConfigurations":398},{"removed":"aime","score":0.027939818205448472,"rank":312,"remainingConfigurations":398},{"removed":"apex-agents","score":0.030786884565627153,"rank":308,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.033505105932155076,"rank":296,"remainingConfigurations":398},{"removed":"automationbench","score":0.030429889009344627,"rank":308,"remainingConfigurations":398},{"removed":"critpt","score":0.03041358414059593,"rank":309,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.030489456517440183,"rank":308,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.030841323936227433,"rank":308,"remainingConfigurations":398},{"removed":"gdpval","score":0.030610290936029783,"rank":309,"remainingConfigurations":398},{"removed":"gmmlu","score":0.030689306150394915,"rank":309,"remainingConfigurations":398},{"removed":"gpqa","score":0.029268073548339258,"rank":308,"remainingConfigurations":398},{"removed":"harvey","score":0.03009178325629903,"rank":308,"remainingConfigurations":398},{"removed":"hle","score":0.03193511462898659,"rank":310,"remainingConfigurations":398},{"removed":"ifbench","score":0.030984372343942346,"rank":303,"remainingConfigurations":398},{"removed":"itbench","score":0.030396107782573744,"rank":308,"remainingConfigurations":398},{"removed":"livecodebench","score":0.028904732598749826,"rank":312,"remainingConfigurations":398},{"removed":"math500","score":0.03067310668784098,"rank":308,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03046950146768444,"rank":309,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.034238625526992,"rank":307,"remainingConfigurations":398},{"removed":"omniscience","score":0.026148113267579043,"rank":315,"remainingConfigurations":398},{"removed":"scicode","score":0.031061893619997363,"rank":308,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03125287016565429,"rank":307,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03137414999349706,"rank":307,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03669375438528523,"rank":310,"remainingConfigurations":398},{"removed":"deepswe","score":0.02583241158617694,"rank":309,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03044754218309111,"rank":308,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.030225767504339262,"rank":308,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03203483140300655,"rank":309,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.030472268697985097,"rank":308,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.030153096482413048,"rank":308,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.030394238875596377,"rank":308,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.030323088939763963,"rank":308,"remainingConfigurations":398},{"removed":"livebench-math","score":0.030493519548045685,"rank":308,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.03018063576131594,"rank":308,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03080970267573391,"rank":308,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03050454811991025,"rank":308,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02993984645767107,"rank":308,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.030227832555048517,"rank":308,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.03092758648921283,"rank":308,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0312812656718438,"rank":308,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.028819881986124705,"rank":307,"remainingConfigurations":398},{"removed":"frontiermath","score":0.030748921375523455,"rank":308,"remainingConfigurations":398},{"removed":"simpleqa","score":0.03171522838548079,"rank":309,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.030282659323297063,"rank":308,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.030327792162194885,"rank":308,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0303077892275368,"rank":308,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.030383368292110025,"rank":308,"remainingConfigurations":398},{"removed":"vibe-code","score":0.030225707001881475,"rank":308,"remainingConfigurations":398}]},"gpt-oss-20b--effort-low":{"score":0.030380674525953374,"rank":309,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.029099424332332025,"rank":150,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03699025925013704,"rank":309,"remainingConfigurations":398},{"removed":"Datacurve","score":0.025826274446932473,"rank":308,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.030099948581384,"rank":309,"remainingConfigurations":398},{"removed":"Scale","score":0.03386761805005814,"rank":309,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.03034797591622231,"rank":309,"remainingConfigurations":398},{"removed":"Cognition","score":0.03217693109718102,"rank":308,"remainingConfigurations":398},{"removed":"LiveBench","score":0.031063475689509346,"rank":308,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03111691614922643,"rank":309,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.032036789750084595,"rank":289,"remainingConfigurations":381},{"removed":"Vals AI","score":0.029572244094944914,"rank":308,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.030382183875770852,"rank":309,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.030348819011436722,"rank":309,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0303317093175268,"rank":309,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.030380674525953374,"rank":309,"remainingConfigurations":398},{"removed":"All provider reports","score":0.03029632065693826,"rank":309,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.03047770748915728,"rank":309,"remainingConfigurations":398},{"removed":"briefcase","score":0.03032101300618323,"rank":310,"remainingConfigurations":398},{"removed":"aime","score":0.02849435045371329,"rank":310,"remainingConfigurations":398},{"removed":"apex-agents","score":0.03070868069311172,"rank":309,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03049534756627691,"rank":310,"remainingConfigurations":398},{"removed":"automationbench","score":0.030358805507499777,"rank":309,"remainingConfigurations":398},{"removed":"critpt","score":0.030318609831983978,"rank":310,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.030424940076786745,"rank":309,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.030733211623695897,"rank":309,"remainingConfigurations":398},{"removed":"gdpval","score":0.030496715578686658,"rank":310,"remainingConfigurations":398},{"removed":"gmmlu","score":0.031649132758832826,"rank":308,"remainingConfigurations":398},{"removed":"gpqa","score":0.03220925735412275,"rank":304,"remainingConfigurations":398},{"removed":"harvey","score":0.030024033347175696,"rank":309,"remainingConfigurations":398},{"removed":"hle","score":0.0325047580772399,"rank":308,"remainingConfigurations":398},{"removed":"ifbench","score":0.02739106164244336,"rank":313,"remainingConfigurations":398},{"removed":"itbench","score":0.030332794608269473,"rank":309,"remainingConfigurations":398},{"removed":"livecodebench","score":0.029037094922661346,"rank":310,"remainingConfigurations":398},{"removed":"math500","score":0.030523400314378193,"rank":309,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.03308735818122862,"rank":304,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03257887263785408,"rank":309,"remainingConfigurations":398},{"removed":"omniscience","score":0.029639788706021335,"rank":308,"remainingConfigurations":398},{"removed":"scicode","score":0.030929320180063533,"rank":309,"remainingConfigurations":398},{"removed":"tau-bench","score":0.028187650995661732,"rank":316,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03145074017801973,"rank":306,"remainingConfigurations":398},{"removed":"arc-agi","score":0.036716352602175435,"rank":309,"remainingConfigurations":398},{"removed":"deepswe","score":0.025846576260581566,"rank":308,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.03038946065423753,"rank":309,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.03017373049148316,"rank":309,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03217693109718102,"rank":308,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.03042565858416031,"rank":309,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.03008814842520169,"rank":309,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.030337636220431143,"rank":309,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.030265179316684862,"rank":309,"remainingConfigurations":398},{"removed":"livebench-math","score":0.030442647382137884,"rank":309,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.030103463835990243,"rank":309,"remainingConfigurations":398},{"removed":"livebench-language","score":0.03074997761477947,"rank":309,"remainingConfigurations":398},{"removed":"livebench-data","score":0.03045070805842812,"rank":309,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02989003909345587,"rank":309,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.030168416101911,"rank":309,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.030872280630292567,"rank":309,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03111691614922643,"rank":309,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02775045780466733,"rank":310,"remainingConfigurations":398},{"removed":"frontiermath","score":0.030641478127861596,"rank":309,"remainingConfigurations":398},{"removed":"simpleqa","score":0.031734361469863866,"rank":308,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.03022491089344372,"rank":309,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.030272831476434562,"rank":309,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.030245858047540593,"rank":309,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.030326557070282565,"rank":309,"remainingConfigurations":398},{"removed":"vibe-code","score":0.030172715718500363,"rank":309,"remainingConfigurations":398}]},"llama-4-maverick--effort-non-reasoning":{"score":0.029788714075503545,"rank":310,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03600891367762978,"rank":311,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02523171806570231,"rank":310,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.029479300504695483,"rank":310,"remainingConfigurations":398},{"removed":"Scale","score":0.033256297831759526,"rank":310,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.029740016225895522,"rank":310,"remainingConfigurations":398},{"removed":"Cognition","score":0.03128638589044325,"rank":310,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03057336192440997,"rank":309,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.030645050198755953,"rank":310,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.030276290256109912,"rank":291,"remainingConfigurations":381},{"removed":"Vals AI","score":0.028981802204844084,"rank":309,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.029790511732274125,"rank":310,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.029759680731916458,"rank":310,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.029736188804533648,"rank":310,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.029788714075503545,"rank":310,"remainingConfigurations":398},{"removed":"All provider reports","score":0.029703858708906284,"rank":310,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02989792089365308,"rank":310,"remainingConfigurations":398},{"removed":"briefcase","score":0.030344072797418933,"rank":309,"remainingConfigurations":398},{"removed":"aime","score":0.03258262645055369,"rank":303,"remainingConfigurations":398},{"removed":"apex-agents","score":0.030158199374151862,"rank":310,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.028563331791348397,"rank":313,"remainingConfigurations":398},{"removed":"automationbench","score":0.03028857192723058,"rank":310,"remainingConfigurations":398},{"removed":"critpt","score":0.02962001405909523,"rank":311,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02984632659159227,"rank":310,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.030598711386027197,"rank":310,"remainingConfigurations":398},{"removed":"gdpval","score":0.031207456465818646,"rank":308,"remainingConfigurations":398},{"removed":"gmmlu","score":0.028087874909982602,"rank":315,"remainingConfigurations":398},{"removed":"gpqa","score":0.029014300081756286,"rank":309,"remainingConfigurations":398},{"removed":"harvey","score":0.029460318308150255,"rank":310,"remainingConfigurations":398},{"removed":"hle","score":0.032095845813600865,"rank":309,"remainingConfigurations":398},{"removed":"ifbench","score":0.028068708262578675,"rank":311,"remainingConfigurations":398},{"removed":"itbench","score":0.029754537005073366,"rank":310,"remainingConfigurations":398},{"removed":"livecodebench","score":0.030744523701007814,"rank":307,"remainingConfigurations":398},{"removed":"math500","score":0.0310214174484439,"rank":307,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.029152146567197085,"rank":313,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.031012091625193448,"rank":310,"remainingConfigurations":398},{"removed":"omniscience","score":0.02580494739770516,"rank":317,"remainingConfigurations":398},{"removed":"scicode","score":0.030313923729626466,"rank":310,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03046007241517583,"rank":309,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.029699202479316924,"rank":312,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03573886062332036,"rank":311,"remainingConfigurations":398},{"removed":"deepswe","score":0.02525128096755241,"rank":310,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.029797658227977964,"rank":310,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02958241878040153,"rank":310,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03128638589044325,"rank":310,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.029821080045268806,"rank":310,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.02950663594505405,"rank":310,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.029745930819652117,"rank":310,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02967824551944777,"rank":310,"remainingConfigurations":398},{"removed":"livebench-math","score":0.029842091378581573,"rank":310,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02953836357959869,"rank":310,"remainingConfigurations":398},{"removed":"livebench-language","score":0.030154319617150028,"rank":310,"remainingConfigurations":398},{"removed":"livebench-data","score":0.029852487808339934,"rank":310,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02929880520391503,"rank":310,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.029582420604791826,"rank":310,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.030265736673038366,"rank":310,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.030645050198755953,"rank":310,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02828963758193769,"rank":308,"remainingConfigurations":398},{"removed":"frontiermath","score":0.03007480474031486,"rank":310,"remainingConfigurations":398},{"removed":"simpleqa","score":0.031039110007747037,"rank":310,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.029635650964075767,"rank":310,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.029680333334728026,"rank":310,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.029660198350148548,"rank":310,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.029735650946226294,"rank":310,"remainingConfigurations":398},{"removed":"vibe-code","score":0.029579821443733913,"rank":310,"remainingConfigurations":398}]},"qwen3-vl-30b-a3b-instruct--effort-non-reasoning":{"score":0.029407478788881555,"rank":311,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.035698804518142474,"rank":312,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02491765848612815,"rank":311,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.029090865357972822,"rank":311,"remainingConfigurations":398},{"removed":"Scale","score":0.03283030439546311,"rank":311,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0293528832858608,"rank":311,"remainingConfigurations":398},{"removed":"Cognition","score":0.03094368668672397,"rank":311,"remainingConfigurations":398},{"removed":"LiveBench","score":0.03016178200349069,"rank":310,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.03023738374182928,"rank":311,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.029636208662312914,"rank":292,"remainingConfigurations":381},{"removed":"Vals AI","score":0.028577204424928167,"rank":310,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02940931236593734,"rank":311,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.029378707232149335,"rank":311,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.029356029560495822,"rank":311,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.029407478788881555,"rank":311,"remainingConfigurations":398},{"removed":"All provider reports","score":0.029324066876945946,"rank":311,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.029506189931330726,"rank":311,"remainingConfigurations":398},{"removed":"briefcase","score":0.02935719261373392,"rank":311,"remainingConfigurations":398},{"removed":"aime","score":0.026838899288643234,"rank":314,"remainingConfigurations":398},{"removed":"apex-agents","score":0.029742932093981034,"rank":311,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02915965705847472,"rank":312,"remainingConfigurations":398},{"removed":"automationbench","score":0.029405337547409222,"rank":311,"remainingConfigurations":398},{"removed":"critpt","score":0.02933951889227654,"rank":312,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02945566964939732,"rank":311,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.029805989529855217,"rank":311,"remainingConfigurations":398},{"removed":"gdpval","score":0.029612758154660426,"rank":311,"remainingConfigurations":398},{"removed":"gmmlu","score":0.029668477681278088,"rank":310,"remainingConfigurations":398},{"removed":"gpqa","score":0.02786861176434824,"rank":314,"remainingConfigurations":398},{"removed":"harvey","score":0.029066463303614315,"rank":311,"remainingConfigurations":398},{"removed":"hle","score":0.0307460260904307,"rank":313,"remainingConfigurations":398},{"removed":"ifbench","score":0.03042592825057779,"rank":305,"remainingConfigurations":398},{"removed":"itbench","score":0.029365240293002862,"rank":311,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02941220166999355,"rank":309,"remainingConfigurations":398},{"removed":"math500","score":0.029608924686176374,"rank":312,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.030334937229744636,"rank":310,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.030163611444916163,"rank":313,"remainingConfigurations":398},{"removed":"omniscience","score":0.028011183014404726,"rank":310,"remainingConfigurations":398},{"removed":"scicode","score":0.030009509944170416,"rank":311,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03119656614077176,"rank":308,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.029998344830926896,"rank":310,"remainingConfigurations":398},{"removed":"arc-agi","score":0.035420511916018985,"rank":312,"remainingConfigurations":398},{"removed":"deepswe","score":0.024936677781393735,"rank":311,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.029416145640484805,"rank":311,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.029202022879340084,"rank":311,"remainingConfigurations":398},{"removed":"frontiercode","score":0.03094368668672397,"rank":311,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02943907648446863,"rank":311,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.029130471005689593,"rank":311,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.029364616662756877,"rank":311,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02929602798816522,"rank":311,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02946064907956739,"rank":311,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02915786338057216,"rank":311,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02976682941616227,"rank":311,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02947121162106149,"rank":311,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.028924707553292402,"rank":311,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02920347534308056,"rank":311,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.029880790920407338,"rank":311,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.03023738374182928,"rank":311,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.027847187149124833,"rank":309,"remainingConfigurations":398},{"removed":"frontiermath","score":0.029715141515745624,"rank":311,"remainingConfigurations":398},{"removed":"simpleqa","score":0.030644915912218035,"rank":311,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.029256525169109624,"rank":311,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.029300202930615433,"rank":311,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.029280822500940218,"rank":311,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.029354012677861835,"rank":311,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02920146573874365,"rank":311,"remainingConfigurations":398}]},"gpt-4o--effort-non-reasoning":{"score":0.02891004376404907,"rank":312,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03489563100738036,"rank":313,"remainingConfigurations":398},{"removed":"Datacurve","score":0.024517758080085855,"rank":312,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.028612153719586655,"rank":312,"remainingConfigurations":398},{"removed":"Scale","score":0.03228398641957877,"rank":312,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02885067500495184,"rank":312,"remainingConfigurations":398},{"removed":"Cognition","score":0.030433874459203595,"rank":312,"remainingConfigurations":398},{"removed":"LiveBench","score":0.029653521747838408,"rank":311,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.029712111137728897,"rank":312,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.029141944332441574,"rank":293,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0280819665506911,"rank":311,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.028911832541975244,"rank":312,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02888143650715569,"rank":312,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.028858939089750412,"rank":312,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02891004376404907,"rank":312,"remainingConfigurations":398},{"removed":"All provider reports","score":0.028827167507014726,"rank":312,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02900458740992078,"rank":312,"remainingConfigurations":398},{"removed":"briefcase","score":0.028853106894913536,"rank":312,"remainingConfigurations":398},{"removed":"aime","score":0.02896352632969289,"rank":308,"remainingConfigurations":398},{"removed":"apex-agents","score":0.029243283020037158,"rank":312,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02855602177686078,"rank":314,"remainingConfigurations":398},{"removed":"automationbench","score":0.02892321169438587,"rank":312,"remainingConfigurations":398},{"removed":"critpt","score":0.03139821015709492,"rank":307,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02895908968330919,"rank":312,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.029305300892592822,"rank":312,"remainingConfigurations":398},{"removed":"gdpval","score":0.02898543844953712,"rank":312,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02914625730030551,"rank":312,"remainingConfigurations":398},{"removed":"gpqa","score":0.028703376469859262,"rank":310,"remainingConfigurations":398},{"removed":"harvey","score":0.028553518746229762,"rank":312,"remainingConfigurations":398},{"removed":"hle","score":0.030799922289416488,"rank":312,"remainingConfigurations":398},{"removed":"ifbench","score":0.027981592959311793,"rank":312,"remainingConfigurations":398},{"removed":"itbench","score":0.028846071842773355,"rank":312,"remainingConfigurations":398},{"removed":"livecodebench","score":0.028991739857497183,"rank":311,"remainingConfigurations":398},{"removed":"math500","score":0.029157967780915714,"rank":313,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.02991604289115987,"rank":311,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.030932856236479053,"rank":311,"remainingConfigurations":398},{"removed":"omniscience","score":0.027726668303097946,"rank":311,"remainingConfigurations":398},{"removed":"scicode","score":0.029514080288770863,"rank":312,"remainingConfigurations":398},{"removed":"tau-bench","score":0.028209044078033374,"rank":315,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.025746093335073775,"rank":319,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0346198504344526,"rank":313,"remainingConfigurations":398},{"removed":"deepswe","score":0.024536355666828408,"rank":312,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.028918541008009366,"rank":312,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.028707212700751602,"rank":312,"remainingConfigurations":398},{"removed":"frontiercode","score":0.030433874459203595,"rank":312,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02894241003635388,"rank":312,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.028639293950521793,"rank":312,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02886782013175465,"rank":312,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.028799614604572917,"rank":312,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02896220401369635,"rank":312,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.028664609986862415,"rank":312,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02926352277722005,"rank":312,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02897291610843039,"rank":312,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.028435007254363667,"rank":312,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.028709310177982224,"rank":312,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.029375799952138928,"rank":312,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.029712111137728897,"rank":312,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02741279345844153,"rank":311,"remainingConfigurations":398},{"removed":"frontiermath","score":0.029246678248732436,"rank":312,"remainingConfigurations":398},{"removed":"simpleqa","score":0.030118671509720172,"rank":312,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02876152840753435,"rank":312,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.028804480089321367,"rank":312,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.028785487075997294,"rank":312,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.028857171905055917,"rank":312,"remainingConfigurations":398},{"removed":"vibe-code","score":0.028707306386928838,"rank":312,"remainingConfigurations":398}]},"step3-vl-10b--effort-reasoning":{"score":0.028646136685672518,"rank":313,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0348037608386785,"rank":314,"remainingConfigurations":398},{"removed":"Datacurve","score":0.024284563051528135,"rank":313,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02834897571080607,"rank":313,"remainingConfigurations":398},{"removed":"Scale","score":0.03199636811699503,"rank":313,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.028591319832851333,"rank":313,"remainingConfigurations":398},{"removed":"Cognition","score":0.030158924165472792,"rank":314,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02938479921804185,"rank":312,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02947575123206188,"rank":313,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.028820314957317683,"rank":295,"remainingConfigurations":381},{"removed":"Vals AI","score":0.027836325659101713,"rank":312,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02864793230051065,"rank":313,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.028618230119195478,"rank":313,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.02859584721605606,"rank":313,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.028646136685672518,"rank":313,"remainingConfigurations":398},{"removed":"All provider reports","score":0.028564827037986656,"rank":313,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.028749185011760353,"rank":313,"remainingConfigurations":398},{"removed":"briefcase","score":0.028597028944673916,"rank":313,"remainingConfigurations":398},{"removed":"aime","score":0.028603191862736785,"rank":309,"remainingConfigurations":398},{"removed":"apex-agents","score":0.028974565851036277,"rank":313,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03282526203097106,"rank":300,"remainingConfigurations":398},{"removed":"automationbench","score":0.028653885244781286,"rank":313,"remainingConfigurations":398},{"removed":"critpt","score":0.02882343173062299,"rank":313,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02869829113370027,"rank":313,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.029031994463688298,"rank":313,"remainingConfigurations":398},{"removed":"gdpval","score":0.02880596999186451,"rank":313,"remainingConfigurations":398},{"removed":"gmmlu","score":0.028900859837428506,"rank":313,"remainingConfigurations":398},{"removed":"gpqa","score":0.026765934403072802,"rank":317,"remainingConfigurations":398},{"removed":"harvey","score":0.028319162526901042,"rank":313,"remainingConfigurations":398},{"removed":"hle","score":0.026775369909220702,"rank":323,"remainingConfigurations":398},{"removed":"ifbench","score":0.02416275060609663,"rank":319,"remainingConfigurations":398},{"removed":"itbench","score":0.02860821918010625,"rank":313,"remainingConfigurations":398},{"removed":"livecodebench","score":0.028571152490324467,"rank":313,"remainingConfigurations":398},{"removed":"math500","score":0.028750276115950196,"rank":314,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.029501938735302546,"rank":312,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02807059151411423,"rank":319,"remainingConfigurations":398},{"removed":"omniscience","score":0.02931380442527041,"rank":309,"remainingConfigurations":398},{"removed":"scicode","score":0.0292327222902055,"rank":313,"remainingConfigurations":398},{"removed":"tau-bench","score":0.03180849148898824,"rank":303,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02975635698683092,"rank":311,"remainingConfigurations":398},{"removed":"arc-agi","score":0.034527993957055705,"rank":314,"remainingConfigurations":398},{"removed":"deepswe","score":0.02430309167920917,"rank":313,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.028654587800623868,"rank":313,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.028446727813745982,"rank":313,"remainingConfigurations":398},{"removed":"frontiercode","score":0.030158924165472792,"rank":314,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02867833168120015,"rank":313,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.028377565910739835,"rank":313,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0286043343287708,"rank":313,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.028537449829600187,"rank":313,"remainingConfigurations":398},{"removed":"livebench-math","score":0.028698014151149157,"rank":313,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.028402515780576176,"rank":313,"remainingConfigurations":398},{"removed":"livebench-language","score":0.028996763309203217,"rank":313,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02870857434864325,"rank":313,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.028175186712745787,"rank":313,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.028447052379137527,"rank":313,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.02910779214564167,"rank":313,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02947575123206188,"rank":313,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.027145601816079196,"rank":312,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02894331940859755,"rank":313,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02984912522110253,"rank":313,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.028498901833639206,"rank":313,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.028541546745517326,"rank":313,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02852245894712982,"rank":313,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02859401705898405,"rank":313,"remainingConfigurations":398},{"removed":"vibe-code","score":0.028445279383303088,"rank":313,"remainingConfigurations":398}]},"qwen3-30b-a3b--effort-reasoning":{"score":0.02849893221491914,"rank":314,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.034625366962224076,"rank":315,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02415810049590807,"rank":314,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.028195973028881077,"rank":314,"remainingConfigurations":398},{"removed":"Scale","score":0.03182235819498349,"rank":314,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02844237058501313,"rank":314,"remainingConfigurations":398},{"removed":"Cognition","score":0.030002924255858793,"rank":315,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02923191493286902,"rank":313,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02930898667674652,"rank":314,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02875417731726022,"rank":296,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02769121027369334,"rank":313,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.028500700123626762,"rank":314,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.028471049418541713,"rank":314,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.028449163130446754,"rank":314,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02849893221491914,"rank":314,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02841817008366293,"rank":314,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.028592676742302703,"rank":314,"remainingConfigurations":398},{"removed":"briefcase","score":0.02844397031784721,"rank":314,"remainingConfigurations":398},{"removed":"aime","score":0.026203232717540933,"rank":317,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0288304243601,"rank":314,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.03120083129407139,"rank":308,"remainingConfigurations":398},{"removed":"automationbench","score":0.02848762633400821,"rank":314,"remainingConfigurations":398},{"removed":"critpt","score":0.028145270899372885,"rank":315,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.028548388276588524,"rank":314,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.028867903418425284,"rank":314,"remainingConfigurations":398},{"removed":"gdpval","score":0.02863778905767639,"rank":314,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02873343778870994,"rank":314,"remainingConfigurations":398},{"removed":"gpqa","score":0.028479560543935776,"rank":311,"remainingConfigurations":398},{"removed":"harvey","score":0.02816988875614218,"rank":314,"remainingConfigurations":398},{"removed":"hle","score":0.02984907027609544,"rank":315,"remainingConfigurations":398},{"removed":"ifbench","score":0.027048236382448954,"rank":315,"remainingConfigurations":398},{"removed":"itbench","score":0.028457987300822277,"rank":314,"remainingConfigurations":398},{"removed":"livecodebench","score":0.028307562426552343,"rank":315,"remainingConfigurations":398},{"removed":"math500","score":0.027402757123579497,"rank":315,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.028848544066123763,"rank":314,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03057321234614722,"rank":312,"remainingConfigurations":398},{"removed":"omniscience","score":0.02650833641512002,"rank":313,"remainingConfigurations":398},{"removed":"scicode","score":0.02906929614698377,"rank":314,"remainingConfigurations":398},{"removed":"tau-bench","score":0.028462719487346525,"rank":314,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.03037378515940067,"rank":309,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03435413469911991,"rank":315,"remainingConfigurations":398},{"removed":"deepswe","score":0.02417654742136245,"rank":314,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.028507351369009882,"rank":314,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.028299332091314282,"rank":314,"remainingConfigurations":398},{"removed":"frontiercode","score":0.030002924255858793,"rank":315,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.028530676655491773,"rank":314,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.028230775752337785,"rank":314,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02845744714593575,"rank":314,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.028390787149183323,"rank":314,"remainingConfigurations":398},{"removed":"livebench-math","score":0.028550591797826305,"rank":314,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02825620505607251,"rank":314,"remainingConfigurations":398},{"removed":"livebench-language","score":0.028847688930079066,"rank":314,"remainingConfigurations":398},{"removed":"livebench-data","score":0.028561105170775026,"rank":314,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.028030251240226362,"rank":314,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.028300791749350473,"rank":314,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.028958787922879675,"rank":314,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02930898667674652,"rank":314,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02693659525580296,"rank":313,"remainingConfigurations":398},{"removed":"frontiermath","score":0.028792286489722787,"rank":314,"remainingConfigurations":398},{"removed":"simpleqa","score":0.029701592357778337,"rank":314,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.028352387802189905,"rank":314,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02839478944627329,"rank":314,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.028376014875992495,"rank":314,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.028446979895830265,"rank":314,"remainingConfigurations":398},{"removed":"vibe-code","score":0.028298871574598174,"rank":314,"remainingConfigurations":398}]},"gpt-5--effort-minimal":{"score":0.028120594971865295,"rank":315,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01106547083545901,"rank":161,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.044209462821228125,"rank":292,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02386891460694805,"rank":315,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.028132288462133625,"rank":315,"remainingConfigurations":398},{"removed":"Scale","score":0.031487921291238966,"rank":315,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.028023852177279485,"rank":315,"remainingConfigurations":398},{"removed":"Cognition","score":0.030314541857236615,"rank":313,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02871784619671094,"rank":314,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.028851862516266535,"rank":315,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0277310400995872,"rank":298,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02714847384091025,"rank":314,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.028122114081100602,"rank":315,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.028084042460604575,"rank":315,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.028079193301437096,"rank":315,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.028120594971865295,"rank":315,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02803955905581633,"rank":315,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.028208579147901914,"rank":315,"remainingConfigurations":398},{"removed":"briefcase","score":0.028160817746639703,"rank":315,"remainingConfigurations":398},{"removed":"aime","score":0.029560209249324093,"rank":306,"remainingConfigurations":398},{"removed":"apex-agents","score":0.028390518905484597,"rank":315,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.028161214264415268,"rank":315,"remainingConfigurations":398},{"removed":"automationbench","score":0.028186106982841536,"rank":315,"remainingConfigurations":398},{"removed":"critpt","score":0.028768758376128533,"rank":314,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.028169129491423694,"rank":315,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.028455748417259032,"rank":315,"remainingConfigurations":398},{"removed":"gdpval","score":0.028409823397052083,"rank":315,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02642898036249459,"rank":318,"remainingConfigurations":398},{"removed":"gpqa","score":0.028279282182787205,"rank":312,"remainingConfigurations":398},{"removed":"harvey","score":0.027806739186668216,"rank":315,"remainingConfigurations":398},{"removed":"hle","score":0.03028875129827917,"rank":314,"remainingConfigurations":398},{"removed":"ifbench","score":0.0272165033235065,"rank":314,"remainingConfigurations":398},{"removed":"itbench","score":0.028097739177288274,"rank":315,"remainingConfigurations":398},{"removed":"livecodebench","score":0.028408409451362613,"rank":314,"remainingConfigurations":398},{"removed":"math500","score":0.029779616090717272,"rank":311,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0286897231631467,"rank":315,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.03008530523244741,"rank":314,"remainingConfigurations":398},{"removed":"omniscience","score":0.024889676131398333,"rank":319,"remainingConfigurations":398},{"removed":"scicode","score":0.028626853217868214,"rank":315,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02736615047626773,"rank":318,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.027879689546585294,"rank":315,"remainingConfigurations":398},{"removed":"arc-agi","score":0.04389236510531617,"rank":291,"remainingConfigurations":398},{"removed":"deepswe","score":0.02388471704602498,"rank":315,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.02812833515438387,"rank":315,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.028103989674084395,"rank":315,"remainingConfigurations":398},{"removed":"frontiercode","score":0.030314541857236615,"rank":313,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.028160749953827918,"rank":315,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.027867855758794313,"rank":315,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.028079826500400012,"rank":315,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02801031640719333,"rank":315,"remainingConfigurations":398},{"removed":"livebench-math","score":0.028168206605142687,"rank":315,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.027881956889857378,"rank":315,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0284552362207679,"rank":315,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02816928265165901,"rank":315,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02765738573308212,"rank":315,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.027929409624735137,"rank":315,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.028594390261926558,"rank":315,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.028851862516266535,"rank":315,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.026137826339995496,"rank":315,"remainingConfigurations":398},{"removed":"frontiermath","score":0.028499554848370374,"rank":315,"remainingConfigurations":398},{"removed":"simpleqa","score":0.029274546263051742,"rank":315,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02797521415800687,"rank":315,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.028009432964441906,"rank":315,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.028016124923911107,"rank":315,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02805579358508827,"rank":315,"remainingConfigurations":398},{"removed":"vibe-code","score":0.027913240128495442,"rank":315,"remainingConfigurations":398}]},"qwen3-30b-a3b-instruct-2507--effort-non-reasoning":{"score":0.027860356875070488,"rank":316,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03378297394228989,"rank":316,"remainingConfigurations":398},{"removed":"Datacurve","score":0.023593343735623887,"rank":316,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.027557226462580856,"rank":316,"remainingConfigurations":398},{"removed":"Scale","score":0.031115517583366312,"rank":316,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02780723259067769,"rank":316,"remainingConfigurations":398},{"removed":"Cognition","score":0.02931276745157298,"rank":316,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02857968492456336,"rank":315,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02864298508455328,"rank":316,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.028072108160703182,"rank":297,"remainingConfigurations":381},{"removed":"Vals AI","score":0.027074595592830503,"rank":315,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.027862084514306832,"rank":316,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02783306293825727,"rank":316,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.027811648637332695,"rank":316,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.027860356875070488,"rank":316,"remainingConfigurations":398},{"removed":"All provider reports","score":0.027781311645579652,"rank":316,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.027954647801732926,"rank":316,"remainingConfigurations":398},{"removed":"briefcase","score":0.027784843257454662,"rank":316,"remainingConfigurations":398},{"removed":"aime","score":0.026336079578157427,"rank":316,"remainingConfigurations":398},{"removed":"apex-agents","score":0.028179404138842738,"rank":316,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.027901525214029485,"rank":316,"remainingConfigurations":398},{"removed":"automationbench","score":0.02782612609559906,"rank":316,"remainingConfigurations":398},{"removed":"critpt","score":0.027538901486564113,"rank":316,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02790480352171615,"rank":316,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02819694792300546,"rank":316,"remainingConfigurations":398},{"removed":"gdpval","score":0.028027549265039167,"rank":316,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02932551810890918,"rank":311,"remainingConfigurations":398},{"removed":"gpqa","score":0.027339427867744584,"rank":316,"remainingConfigurations":398},{"removed":"harvey","score":0.027538687769697246,"rank":316,"remainingConfigurations":398},{"removed":"hle","score":0.02873989135431446,"rank":318,"remainingConfigurations":398},{"removed":"ifbench","score":0.028528974534785312,"rank":309,"remainingConfigurations":398},{"removed":"itbench","score":0.027821073188191357,"rank":316,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02715665569957017,"rank":316,"remainingConfigurations":398},{"removed":"math500","score":0.025536062617194714,"rank":319,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.028025716840046466,"rank":317,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.029927986181963833,"rank":315,"remainingConfigurations":398},{"removed":"omniscience","score":0.026620359633519792,"rank":312,"remainingConfigurations":398},{"removed":"scicode","score":0.028388795495383073,"rank":316,"remainingConfigurations":398},{"removed":"tau-bench","score":0.029956301792730258,"rank":310,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.028273870637811522,"rank":314,"remainingConfigurations":398},{"removed":"arc-agi","score":0.033521046893782554,"rank":316,"remainingConfigurations":398},{"removed":"deepswe","score":0.023611423812243137,"rank":316,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.027868609377981274,"rank":316,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02766476543373658,"rank":316,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02931276745157298,"rank":316,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.027889529284868944,"rank":316,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.027597017836739304,"rank":316,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.027819672078141594,"rank":316,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.027754917097703405,"rank":316,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02791096156665525,"rank":316,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.027622909886764888,"rank":316,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02820183232471185,"rank":316,"remainingConfigurations":398},{"removed":"livebench-data","score":0.027921009540785895,"rank":316,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02740159401400979,"rank":316,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.027666470231298316,"rank":316,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.028310369514736502,"rank":316,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02864298508455328,"rank":316,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.026367562668804384,"rank":314,"remainingConfigurations":398},{"removed":"frontiermath","score":0.028152841690691866,"rank":316,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02903912014768668,"rank":316,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.027716887475075638,"rank":316,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02775841173739919,"rank":316,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.027739983272433936,"rank":316,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.027809551373955698,"rank":316,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02766459055006519,"rank":316,"remainingConfigurations":398}]},"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning":{"score":0.026969883122660035,"rank":317,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03277660030932756,"rank":317,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02285763870138356,"rank":317,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.026687588369743664,"rank":317,"remainingConfigurations":398},{"removed":"Scale","score":0.030131000879074468,"rank":317,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.026915343273885117,"rank":317,"remainingConfigurations":398},{"removed":"Cognition","score":0.028401963231977103,"rank":317,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02766751950058095,"rank":316,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02774267302382671,"rank":317,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.027257652873099756,"rank":299,"remainingConfigurations":381},{"removed":"Vals AI","score":0.026204194513063463,"rank":316,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.026971564885093363,"rank":317,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02694340359479211,"rank":317,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.026922575477354025,"rank":317,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.026969883122660035,"rank":317,"remainingConfigurations":398},{"removed":"All provider reports","score":0.026893145427169775,"rank":317,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.027057877105132938,"rank":317,"remainingConfigurations":398},{"removed":"briefcase","score":0.026901173405865567,"rank":317,"remainingConfigurations":398},{"removed":"aime","score":0.024170662161975522,"rank":322,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02728430989928388,"rank":317,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02590417259914675,"rank":319,"remainingConfigurations":398},{"removed":"automationbench","score":0.026945241751181414,"rank":317,"remainingConfigurations":398},{"removed":"critpt","score":0.02657083088304295,"rank":317,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.027016059588325498,"rank":317,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.027314894798170897,"rank":317,"remainingConfigurations":398},{"removed":"gdpval","score":0.02708117348113133,"rank":317,"remainingConfigurations":398},{"removed":"gmmlu","score":0.027186460627763028,"rank":316,"remainingConfigurations":398},{"removed":"gpqa","score":0.02753940127210396,"rank":315,"remainingConfigurations":398},{"removed":"harvey","score":0.026658255457646555,"rank":317,"remainingConfigurations":398},{"removed":"hle","score":0.028517831810508983,"rank":319,"remainingConfigurations":398},{"removed":"ifbench","score":0.028132029870011916,"rank":310,"remainingConfigurations":398},{"removed":"itbench","score":0.026931808403298712,"rank":317,"remainingConfigurations":398},{"removed":"livecodebench","score":0.024463021764887613,"rank":322,"remainingConfigurations":398},{"removed":"math500","score":0.02725596077110863,"rank":316,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.028082965021037784,"rank":316,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.029496973425886,"rank":316,"remainingConfigurations":398},{"removed":"omniscience","score":0.026004186199374252,"rank":316,"remainingConfigurations":398},{"removed":"scicode","score":0.027507451286170867,"rank":317,"remainingConfigurations":398},{"removed":"tau-bench","score":0.027766016000458926,"rank":317,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02779916850423329,"rank":316,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03251660843747415,"rank":317,"remainingConfigurations":398},{"removed":"deepswe","score":0.02287509861369944,"rank":317,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.02697786470646621,"rank":317,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02678118561933343,"rank":317,"remainingConfigurations":398},{"removed":"frontiercode","score":0.028401963231977103,"rank":317,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.027000476139919904,"rank":317,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.02671591758249295,"rank":317,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.026930631509410358,"rank":317,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.026867224476259832,"rank":317,"remainingConfigurations":398},{"removed":"livebench-math","score":0.027018887879903104,"rank":317,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02673948480947455,"rank":317,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02730090464765071,"rank":317,"remainingConfigurations":398},{"removed":"livebench-data","score":0.027028932035550055,"rank":317,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02652509051613383,"rank":317,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.026781801714695696,"rank":317,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.027406445137755604,"rank":317,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02774267302382671,"rank":317,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.025535380133044915,"rank":317,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0272486332689674,"rank":317,"remainingConfigurations":398},{"removed":"simpleqa","score":0.028109650782619188,"rank":317,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.026830790504147013,"rank":317,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.026871017751133087,"rank":317,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.026853231566317276,"rank":317,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.026920460271302047,"rank":317,"remainingConfigurations":398},{"removed":"vibe-code","score":0.026780046977585358,"rank":317,"remainingConfigurations":398}]},"ernie-4.5-300b-a47b-pt--effort-non-reasoning":{"score":0.026838472829378044,"rank":318,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03263503881217563,"rank":318,"remainingConfigurations":398},{"removed":"Datacurve","score":0.022731472953870496,"rank":318,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.026554696979319132,"rank":318,"remainingConfigurations":398},{"removed":"Scale","score":0.02998993124662031,"rank":318,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0267868324574693,"rank":318,"remainingConfigurations":398},{"removed":"Cognition","score":0.02825145233641735,"rank":318,"remainingConfigurations":398},{"removed":"LiveBench","score":0.027533642138215717,"rank":317,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02761272726471158,"rank":318,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.027043964137152477,"rank":300,"remainingConfigurations":381},{"removed":"Vals AI","score":0.026082658046273435,"rank":317,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02684014402641285,"rank":318,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.026812164425059005,"rank":318,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.026791574053777842,"rank":318,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.026838472829378044,"rank":318,"remainingConfigurations":398},{"removed":"All provider reports","score":0.026762330523533277,"rank":318,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02693690956388942,"rank":318,"remainingConfigurations":398},{"removed":"briefcase","score":0.02684656212484771,"rank":318,"remainingConfigurations":398},{"removed":"aime","score":0.027069083806755868,"rank":313,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02715759945959566,"rank":318,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02659612285864642,"rank":318,"remainingConfigurations":398},{"removed":"automationbench","score":0.02689049697856459,"rank":318,"remainingConfigurations":398},{"removed":"critpt","score":0.0264278133014143,"rank":318,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02690501696074311,"rank":318,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.027246672697276316,"rank":318,"remainingConfigurations":398},{"removed":"gdpval","score":0.02708056689101034,"rank":318,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02710045332709016,"rank":317,"remainingConfigurations":398},{"removed":"gpqa","score":0.022812773800036674,"rank":326,"remainingConfigurations":398},{"removed":"harvey","score":0.026537880563123298,"rank":318,"remainingConfigurations":398},{"removed":"hle","score":0.03185764466580112,"rank":311,"remainingConfigurations":398},{"removed":"ifbench","score":0.025956229242481674,"rank":316,"remainingConfigurations":398},{"removed":"itbench","score":0.026807751997171222,"rank":318,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02682957677592357,"rank":317,"remainingConfigurations":398},{"removed":"math500","score":0.02683534781525253,"rank":317,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.02682515489960363,"rank":318,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.028883562535961887,"rank":318,"remainingConfigurations":398},{"removed":"omniscience","score":0.02308193840568595,"rank":323,"remainingConfigurations":398},{"removed":"scicode","score":0.027437425075247282,"rank":318,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02984152651475513,"rank":311,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02718887059309587,"rank":317,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03237902988679102,"rank":318,"remainingConfigurations":398},{"removed":"deepswe","score":0.02274889803991989,"rank":318,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0268464280126218,"rank":318,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02665053598002581,"rank":318,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02825145233641735,"rank":318,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.026867943741955374,"rank":318,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.026584884822748855,"rank":318,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.026799409336111992,"rank":318,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.026736689460822288,"rank":318,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0268873117912234,"rank":318,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.026609065077215655,"rank":318,"remainingConfigurations":398},{"removed":"livebench-language","score":0.027168034322185303,"rank":318,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02689720596687979,"rank":318,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.026395746875314808,"rank":318,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.026651265626171802,"rank":318,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.02727297455899222,"rank":318,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02761272726471158,"rank":318,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02540098010453384,"rank":318,"remainingConfigurations":398},{"removed":"frontiermath","score":0.027121561503436448,"rank":318,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02797772841386596,"rank":318,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02670001732093566,"rank":318,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.026740076580204174,"rank":318,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.026722298119861928,"rank":318,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.026789367242680953,"rank":318,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02664954261614856,"rank":318,"remainingConfigurations":398}]},"qwen3-14b--effort-reasoning":{"score":0.025458495850663804,"rank":319,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03086072943300527,"rank":320,"remainingConfigurations":398},{"removed":"Datacurve","score":0.021563501255795325,"rank":319,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.025200147536044926,"rank":319,"remainingConfigurations":398},{"removed":"Scale","score":0.028453154877349295,"rank":319,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.025417267682060044,"rank":319,"remainingConfigurations":398},{"removed":"Cognition","score":0.026771264944365252,"rank":319,"remainingConfigurations":398},{"removed":"LiveBench","score":0.026147113066905647,"rank":318,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0261916904834697,"rank":319,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02583123631035032,"rank":301,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02477654902231763,"rank":318,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.025460039040361527,"rank":319,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.025433569291208685,"rank":319,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.025413347615562274,"rank":319,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.025458495850663804,"rank":319,"remainingConfigurations":398},{"removed":"All provider reports","score":0.025385564099756952,"rank":319,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.025555884274377872,"rank":319,"remainingConfigurations":398},{"removed":"briefcase","score":0.02592547845687986,"rank":319,"remainingConfigurations":398},{"removed":"aime","score":0.024841757655505472,"rank":320,"remainingConfigurations":398},{"removed":"apex-agents","score":0.025774234368034162,"rank":319,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.026932852476306984,"rank":317,"remainingConfigurations":398},{"removed":"automationbench","score":0.02623408405802891,"rank":319,"remainingConfigurations":398},{"removed":"critpt","score":0.024998168180086777,"rank":319,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.025517813964588187,"rank":319,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.025349775117835077,"rank":321,"remainingConfigurations":398},{"removed":"gdpval","score":0.02613696217828017,"rank":319,"remainingConfigurations":398},{"removed":"gmmlu","score":0.025628506711169525,"rank":320,"remainingConfigurations":398},{"removed":"gpqa","score":0.025290910238201052,"rank":321,"remainingConfigurations":398},{"removed":"harvey","score":0.025178783141153047,"rank":319,"remainingConfigurations":398},{"removed":"hle","score":0.027866475461973215,"rank":320,"remainingConfigurations":398},{"removed":"ifbench","score":0.02407459783387079,"rank":320,"remainingConfigurations":398},{"removed":"itbench","score":0.025426968801767657,"rank":319,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02475618448337215,"rank":321,"remainingConfigurations":398},{"removed":"math500","score":0.024353621138079123,"rank":322,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.025851785877124497,"rank":321,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.027359854307247734,"rank":321,"remainingConfigurations":398},{"removed":"omniscience","score":0.02432846687745051,"rank":321,"remainingConfigurations":398},{"removed":"scicode","score":0.025816884597080703,"rank":320,"remainingConfigurations":398},{"removed":"tau-bench","score":0.024360914523594682,"rank":321,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.025612242463487266,"rank":320,"remainingConfigurations":398},{"removed":"arc-agi","score":0.03062049330870061,"rank":320,"remainingConfigurations":398},{"removed":"deepswe","score":0.02158024967003191,"rank":319,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.025466204400609118,"rank":319,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02528277304711869,"rank":319,"remainingConfigurations":398},{"removed":"frontiercode","score":0.026771264944365252,"rank":319,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.025488841662780374,"rank":319,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.025217150417180728,"rank":319,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.025422080425211505,"rank":319,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.025364155226448287,"rank":319,"remainingConfigurations":398},{"removed":"livebench-math","score":0.025504565498459395,"rank":319,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.025241854189657607,"rank":319,"remainingConfigurations":398},{"removed":"livebench-language","score":0.025773412689021207,"rank":319,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02551431970849179,"rank":319,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.025036416596017613,"rank":319,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.025280420308026377,"rank":319,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.025870268347176595,"rank":319,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0261916904834697,"rank":319,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.024133155252776248,"rank":319,"remainingConfigurations":398},{"removed":"frontiermath","score":0.025706554920134034,"rank":319,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02653716410452604,"rank":319,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.025326616669824404,"rank":319,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.025365168396999826,"rank":319,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0253477144770599,"rank":319,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02541264154968023,"rank":319,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02527854561212811,"rank":319,"remainingConfigurations":398}]},"qwen3-vl-8b-thinking--effort-reasoning":{"score":0.025392652804937476,"rank":320,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.030873950603260758,"rank":319,"remainingConfigurations":398},{"removed":"Datacurve","score":0.021496922260752716,"rank":320,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02512081664674594,"rank":320,"remainingConfigurations":398},{"removed":"Scale","score":0.028382963035926367,"rank":320,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02534439653509717,"rank":320,"remainingConfigurations":398},{"removed":"Cognition","score":0.02672882266362557,"rank":320,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02605641281900665,"rank":319,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02612692778281873,"rank":320,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02560668238370051,"rank":303,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02467839618954852,"rank":319,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02539424321060794,"rank":320,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02536769563131429,"rank":320,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.025347993864734044,"rank":320,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.025392652804937476,"rank":320,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02532025391471565,"rank":320,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.025485795943105672,"rank":320,"remainingConfigurations":398},{"removed":"briefcase","score":0.02535942836448209,"rank":320,"remainingConfigurations":398},{"removed":"aime","score":0.026792631055291772,"rank":315,"remainingConfigurations":398},{"removed":"apex-agents","score":0.025688852163900763,"rank":320,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02466731477588524,"rank":322,"remainingConfigurations":398},{"removed":"automationbench","score":0.025405580990621308,"rank":320,"remainingConfigurations":398},{"removed":"critpt","score":0.022041274743747414,"rank":323,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02544879286154166,"rank":320,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.025753965036317952,"rank":319,"remainingConfigurations":398},{"removed":"gdpval","score":0.02557493745447392,"rank":320,"remainingConfigurations":398},{"removed":"gmmlu","score":0.025651061262520338,"rank":319,"remainingConfigurations":398},{"removed":"gpqa","score":0.02549990038935628,"rank":320,"remainingConfigurations":398},{"removed":"harvey","score":0.025105117345393706,"rank":320,"remainingConfigurations":398},{"removed":"hle","score":0.029249911544710256,"rank":316,"remainingConfigurations":398},{"removed":"ifbench","score":0.0239839903744077,"rank":321,"remainingConfigurations":398},{"removed":"itbench","score":0.025358937870138043,"rank":320,"remainingConfigurations":398},{"removed":"livecodebench","score":0.026619077654502925,"rank":318,"remainingConfigurations":398},{"removed":"math500","score":0.02555755937184601,"rank":318,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.02639866746725121,"rank":319,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02679418192557241,"rank":322,"remainingConfigurations":398},{"removed":"omniscience","score":0.021585301252535046,"rank":326,"remainingConfigurations":398},{"removed":"scicode","score":0.02593374184194938,"rank":319,"remainingConfigurations":398},{"removed":"tau-bench","score":0.025728960244865744,"rank":319,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02642944828239201,"rank":318,"remainingConfigurations":398},{"removed":"arc-agi","score":0.030630537373590574,"rank":319,"remainingConfigurations":398},{"removed":"deepswe","score":0.021513408021725407,"rank":320,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.025400196387170244,"rank":320,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.025214967670196525,"rank":320,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02672882266362557,"rank":320,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.025420475564197655,"rank":320,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.025151947945012507,"rank":320,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.025355706907197007,"rank":320,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.025296235958631053,"rank":320,"remainingConfigurations":398},{"removed":"livebench-math","score":0.025438940609963292,"rank":320,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02517508964362106,"rank":320,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02570538095683969,"rank":320,"remainingConfigurations":398},{"removed":"livebench-data","score":0.025448400850761523,"rank":320,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.024972611424648284,"rank":320,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.025215008882823613,"rank":320,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.025804913928222744,"rank":320,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02612692778281873,"rank":320,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.024033608821039318,"rank":320,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02566006203416084,"rank":320,"remainingConfigurations":398},{"removed":"simpleqa","score":0.026470803750885494,"rank":320,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02526127711760122,"rank":320,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.025299291806275947,"rank":320,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02528243741678832,"rank":320,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.025345992259138143,"rank":320,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02521344750180006,"rank":320,"remainingConfigurations":398}]},"gpt-5.4-nano--effort-non-reasoning":{"score":0.02518070973826897,"rank":321,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.03065962370833282,"rank":321,"remainingConfigurations":398},{"removed":"Datacurve","score":0.021350565455609993,"rank":321,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.024935918739696233,"rank":321,"remainingConfigurations":398},{"removed":"Scale","score":0.028165730220304108,"rank":321,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.025132250520456534,"rank":321,"remainingConfigurations":398},{"removed":"Cognition","score":0.026528078770448413,"rank":321,"remainingConfigurations":398},{"removed":"LiveBench","score":0.025849370083704012,"rank":320,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.025961365626251495,"rank":321,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02544669706639725,"rank":304,"remainingConfigurations":381},{"removed":"Vals AI","score":0.024473900674784523,"rank":320,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.025182280446789034,"rank":321,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.025156407195728397,"rank":321,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.025136148261964152,"rank":321,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02518070973826897,"rank":321,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02510905082347317,"rank":321,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.025275627852765065,"rank":321,"remainingConfigurations":398},{"removed":"briefcase","score":0.025202009045951063,"rank":321,"remainingConfigurations":398},{"removed":"aime","score":0.025111523685082612,"rank":319,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02553101504868888,"rank":321,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02484362467036118,"rank":321,"remainingConfigurations":398},{"removed":"automationbench","score":0.025248026174267888,"rank":321,"remainingConfigurations":398},{"removed":"critpt","score":0.02481335992448083,"rank":320,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02526870249557997,"rank":321,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.025585717346331683,"rank":320,"remainingConfigurations":398},{"removed":"gdpval","score":0.02243909062595886,"rank":325,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02533017521679014,"rank":321,"remainingConfigurations":398},{"removed":"gpqa","score":0.025960824267388077,"rank":318,"remainingConfigurations":398},{"removed":"harvey","score":0.02491000951041958,"rank":321,"remainingConfigurations":398},{"removed":"hle","score":0.029246406022917778,"rank":317,"remainingConfigurations":398},{"removed":"ifbench","score":0.025848202844614556,"rank":317,"remainingConfigurations":398},{"removed":"itbench","score":0.02497093954895675,"rank":321,"remainingConfigurations":398},{"removed":"livecodebench","score":0.025114493427262272,"rank":319,"remainingConfigurations":398},{"removed":"math500","score":0.02532573244818857,"rank":320,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.025945020994597157,"rank":320,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.029313679825438515,"rank":317,"remainingConfigurations":398},{"removed":"omniscience","score":0.024370210014158896,"rank":320,"remainingConfigurations":398},{"removed":"scicode","score":0.02576242780154146,"rank":321,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02343255477686303,"rank":324,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02214472808659185,"rank":326,"remainingConfigurations":398},{"removed":"arc-agi","score":0.030410589123842396,"rank":321,"remainingConfigurations":398},{"removed":"deepswe","score":0.02136703930364273,"rank":321,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.02518817402237729,"rank":321,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.025005989591303724,"rank":321,"remainingConfigurations":398},{"removed":"frontiercode","score":0.026528078770448413,"rank":321,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.025211445054448608,"rank":321,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.02494352528674887,"rank":321,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02514422944514387,"rank":321,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.025084566674310606,"rank":321,"remainingConfigurations":398},{"removed":"livebench-math","score":0.025226905366498586,"rank":321,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.024964628013756596,"rank":321,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02549051979298381,"rank":321,"remainingConfigurations":398},{"removed":"livebench-data","score":0.025236437249869792,"rank":321,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.024764093685077124,"rank":321,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02500455306259786,"rank":321,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.025589631574980867,"rank":321,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.025961365626251495,"rank":321,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.023917177589681204,"rank":321,"remainingConfigurations":398},{"removed":"frontiermath","score":0.025429202528642683,"rank":321,"remainingConfigurations":398},{"removed":"simpleqa","score":0.026243653924250685,"rank":321,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.025050660476057644,"rank":321,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.025087934407889086,"rank":321,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02507118339580354,"rank":321,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.025134556505259992,"rank":321,"remainingConfigurations":398},{"removed":"vibe-code","score":0.025003320171191844,"rank":321,"remainingConfigurations":398}]},"gemma-4-e4b-it--effort-non-reasoning":{"score":0.024763792649207528,"rank":322,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.030079599572525362,"rank":322,"remainingConfigurations":398},{"removed":"Datacurve","score":0.02098824607453131,"rank":322,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.024510843978963054,"rank":322,"remainingConfigurations":398},{"removed":"Scale","score":0.027692229349493794,"rank":322,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02471207192230365,"rank":322,"remainingConfigurations":398},{"removed":"Cognition","score":0.02609431514075269,"rank":322,"remainingConfigurations":398},{"removed":"LiveBench","score":0.025411950652472978,"rank":321,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.025483931053835146,"rank":322,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.024971590311372915,"rank":305,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02406001055489602,"rank":321,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.024765349711604847,"rank":322,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.024739528228736624,"rank":322,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.024720129424180504,"rank":322,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.024763792649207528,"rank":322,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02469314554701342,"rank":322,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.024850879456836356,"rank":322,"remainingConfigurations":398},{"removed":"briefcase","score":0.024703869446692093,"rank":322,"remainingConfigurations":398},{"removed":"aime","score":0.02480077711364279,"rank":321,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02505857490412139,"rank":322,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.024860741543491983,"rank":320,"remainingConfigurations":398},{"removed":"automationbench","score":0.024752194489917778,"rank":322,"remainingConfigurations":398},{"removed":"critpt","score":0.020201469296595314,"rank":328,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.024812349978655373,"rank":322,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02508946636659987,"rank":322,"remainingConfigurations":398},{"removed":"gdpval","score":0.024864326984439963,"rank":322,"remainingConfigurations":398},{"removed":"gmmlu","score":0.024948896166917558,"rank":322,"remainingConfigurations":398},{"removed":"gpqa","score":0.02576241775551645,"rank":319,"remainingConfigurations":398},{"removed":"harvey","score":0.02448030299120418,"rank":322,"remainingConfigurations":398},{"removed":"hle","score":0.027083122908477492,"rank":322,"remainingConfigurations":398},{"removed":"ifbench","score":0.022807487944240274,"rank":325,"remainingConfigurations":398},{"removed":"itbench","score":0.024730604030890977,"rank":322,"remainingConfigurations":398},{"removed":"livecodebench","score":0.024789054952621375,"rank":320,"remainingConfigurations":398},{"removed":"math500","score":0.024994650864896162,"rank":321,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.025619965611817536,"rank":322,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02736133210613152,"rank":320,"remainingConfigurations":398},{"removed":"omniscience","score":0.02649578996414805,"rank":314,"remainingConfigurations":398},{"removed":"scicode","score":0.02526424265462368,"rank":322,"remainingConfigurations":398},{"removed":"tau-bench","score":0.024470103384625925,"rank":320,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.023926689049996012,"rank":321,"remainingConfigurations":398},{"removed":"arc-agi","score":0.029836745018809452,"rank":322,"remainingConfigurations":398},{"removed":"deepswe","score":0.021004312878279866,"rank":322,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.024771148772647123,"rank":322,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.024590666241051138,"rank":322,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02609431514075269,"rank":322,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02479260441808519,"rank":322,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.02453033112474083,"rank":322,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.024727753339445647,"rank":322,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.024669275440811742,"rank":322,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02480894893852593,"rank":322,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02455124960278485,"rank":322,"remainingConfigurations":398},{"removed":"livebench-language","score":0.025069106354673607,"rank":322,"remainingConfigurations":398},{"removed":"livebench-data","score":0.024818482013456558,"rank":322,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.024353674346699713,"rank":322,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02459027430624482,"rank":322,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.025166400410969268,"rank":322,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.025483931053835146,"rank":322,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.023468874941263002,"rank":322,"remainingConfigurations":398},{"removed":"frontiermath","score":0.025032434672753966,"rank":322,"remainingConfigurations":398},{"removed":"simpleqa","score":0.025811869584891994,"rank":322,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.024635559101256883,"rank":322,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02467264774234329,"rank":322,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.024656133681390798,"rank":322,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02471818705783373,"rank":322,"remainingConfigurations":398},{"removed":"vibe-code","score":0.024588840637753077,"rank":322,"remainingConfigurations":398}]},"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning":{"score":0.02373281554642104,"rank":323,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.028895244655930158,"rank":323,"remainingConfigurations":398},{"removed":"Datacurve","score":0.020113482801548878,"rank":323,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02349124552982026,"rank":323,"remainingConfigurations":398},{"removed":"Scale","score":0.026556551646738872,"rank":323,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.023688069644049833,"rank":323,"remainingConfigurations":398},{"removed":"Cognition","score":0.025007868576439718,"rank":323,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02436384786293137,"rank":322,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.024443656722367924,"rank":323,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.023969140442413706,"rank":306,"remainingConfigurations":381},{"removed":"Vals AI","score":0.023074522312757816,"rank":322,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.023734299476033224,"rank":323,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.023709725564062745,"rank":323,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.02369099235202074,"rank":323,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02373281554642104,"rank":323,"remainingConfigurations":398},{"removed":"All provider reports","score":0.023665277068155983,"rank":323,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.023820466389356688,"rank":323,"remainingConfigurations":398},{"removed":"briefcase","score":0.023646481266217777,"rank":323,"remainingConfigurations":398},{"removed":"aime","score":0.023663619937084143,"rank":323,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02401625982147303,"rank":323,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.023860251354341475,"rank":323,"remainingConfigurations":398},{"removed":"automationbench","score":0.023696104278573226,"rank":323,"remainingConfigurations":398},{"removed":"critpt","score":0.023277436345072233,"rank":321,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.023780497093952815,"rank":323,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.024015756289782548,"rank":323,"remainingConfigurations":398},{"removed":"gdpval","score":0.024902649525182206,"rank":321,"remainingConfigurations":398},{"removed":"gmmlu","score":0.023937918096306535,"rank":324,"remainingConfigurations":398},{"removed":"gpqa","score":0.025000039921799513,"rank":322,"remainingConfigurations":398},{"removed":"harvey","score":0.023466359191705245,"rank":323,"remainingConfigurations":398},{"removed":"hle","score":0.02562660474060555,"rank":326,"remainingConfigurations":398},{"removed":"ifbench","score":0.018020888043072277,"rank":340,"remainingConfigurations":398},{"removed":"itbench","score":0.023700938399141225,"rank":323,"remainingConfigurations":398},{"removed":"livecodebench","score":0.023651942940769097,"rank":324,"remainingConfigurations":398},{"removed":"math500","score":0.02384725588473638,"rank":323,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.024462967738008226,"rank":324,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02546525909074789,"rank":325,"remainingConfigurations":398},{"removed":"omniscience","score":0.025285503655183075,"rank":318,"remainingConfigurations":398},{"removed":"scicode","score":0.024189135057303468,"rank":323,"remainingConfigurations":398},{"removed":"tau-bench","score":0.022987875069067465,"rank":325,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.023740420438123497,"rank":322,"remainingConfigurations":398},{"removed":"arc-agi","score":0.028657201853070333,"rank":323,"remainingConfigurations":398},{"removed":"deepswe","score":0.020128961481268665,"rank":323,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.023739906550081197,"rank":323,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.023567756962557817,"rank":323,"remainingConfigurations":398},{"removed":"frontiercode","score":0.025007868576439718,"rank":323,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02376170158614702,"rank":323,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.023509005471506608,"rank":323,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.023698437735244497,"rank":323,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02364293356830788,"rank":323,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0237762261762739,"rank":323,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02352869452318335,"rank":323,"remainingConfigurations":398},{"removed":"livebench-language","score":0.024026276634835378,"rank":323,"remainingConfigurations":398},{"removed":"livebench-data","score":0.023785518896559676,"rank":323,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.023338860507170305,"rank":323,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.023566102964693945,"rank":323,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.02411922304574332,"rank":323,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.024443656722367924,"rank":323,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02249443102333037,"rank":323,"remainingConfigurations":398},{"removed":"frontiermath","score":0.023975139608530326,"rank":323,"remainingConfigurations":398},{"removed":"simpleqa","score":0.024740718877170127,"rank":323,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.023609652751422208,"rank":323,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02364538074221614,"rank":323,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.023629247858939734,"rank":323,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02368926207722487,"rank":323,"remainingConfigurations":398},{"removed":"vibe-code","score":0.023564870247768228,"rank":323,"remainingConfigurations":398}]},"gemma-4-e4b-it--effort-reasoning":{"score":0.023074250162811036,"rank":324,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02805916885686782,"rank":324,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01956036332438732,"rank":324,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.022845752419307853,"rank":324,"remainingConfigurations":398},{"removed":"Scale","score":0.025818083955625154,"rank":324,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.023030793829091494,"rank":324,"remainingConfigurations":398},{"removed":"Cognition","score":0.024322533110812655,"rank":324,"remainingConfigurations":398},{"removed":"LiveBench","score":0.023691523568765863,"rank":323,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02375984872913743,"rank":324,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02321830095770067,"rank":308,"remainingConfigurations":381},{"removed":"Vals AI","score":0.02243068953229362,"rank":324,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02307569093443347,"rank":324,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.023051696267062008,"rank":324,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.023033413898518235,"rank":324,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.023074250162811036,"rank":324,"remainingConfigurations":398},{"removed":"All provider reports","score":0.023008298967519717,"rank":324,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.023158964508820698,"rank":324,"remainingConfigurations":398},{"removed":"briefcase","score":0.022994302831111684,"rank":324,"remainingConfigurations":398},{"removed":"aime","score":0.02305174480257984,"rank":326,"remainingConfigurations":398},{"removed":"apex-agents","score":0.023353527765905057,"rank":324,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.022406998168982575,"rank":325,"remainingConfigurations":398},{"removed":"automationbench","score":0.023043683448883138,"rank":324,"remainingConfigurations":398},{"removed":"critpt","score":0.018473100646601494,"rank":335,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.023123324325162228,"rank":324,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.023362063869906757,"rank":324,"remainingConfigurations":398},{"removed":"gdpval","score":0.024044699130721017,"rank":323,"remainingConfigurations":398},{"removed":"gmmlu","score":0.023256542625995066,"rank":325,"remainingConfigurations":398},{"removed":"gpqa","score":0.023237678171385806,"rank":323,"remainingConfigurations":398},{"removed":"harvey","score":0.02281622294433271,"rank":324,"remainingConfigurations":398},{"removed":"hle","score":0.027134677463552765,"rank":321,"remainingConfigurations":398},{"removed":"ifbench","score":0.020223027588359307,"rank":333,"remainingConfigurations":398},{"removed":"itbench","score":0.02304559785151235,"rank":324,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02305020352847828,"rank":325,"remainingConfigurations":398},{"removed":"math500","score":0.023235259726873573,"rank":324,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.023838473836928387,"rank":325,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.025289206018282814,"rank":326,"remainingConfigurations":398},{"removed":"omniscience","score":0.024282046122769563,"rank":322,"remainingConfigurations":398},{"removed":"scicode","score":0.023530173415492767,"rank":324,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02370896279000539,"rank":323,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.022712935475588347,"rank":324,"remainingConfigurations":398},{"removed":"arc-agi","score":0.027825680233348544,"rank":324,"remainingConfigurations":398},{"removed":"deepswe","score":0.019575396623615363,"rank":324,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.023081149387829316,"rank":324,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.022913506410424844,"rank":324,"remainingConfigurations":398},{"removed":"frontiercode","score":0.024322533110812655,"rank":324,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.023102666323203135,"rank":324,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.022856338802585058,"rank":324,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02304090724138405,"rank":324,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.022986601923173377,"rank":324,"remainingConfigurations":398},{"removed":"livebench-math","score":0.023116449303621157,"rank":324,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.022875640550950798,"rank":324,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02335992407749656,"rank":324,"remainingConfigurations":398},{"removed":"livebench-data","score":0.023125557411870428,"rank":324,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02269072671381854,"rank":324,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.022911960381589883,"rank":324,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.023450447750040623,"rank":324,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02375984872913743,"rank":324,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.021883615550050958,"rank":324,"remainingConfigurations":398},{"removed":"frontiermath","score":0.023320132656719474,"rank":324,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02405369955148959,"rank":324,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.022954344573825544,"rank":324,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.022989116173525864,"rank":324,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.022973481282244867,"rank":324,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02303177229148702,"rank":324,"remainingConfigurations":398},{"removed":"vibe-code","score":0.022910717992921537,"rank":324,"remainingConfigurations":398}]},"labs-devstral-small-2512--effort-non-reasoning":{"score":0.023042355039177436,"rank":325,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.027977406248770143,"rank":325,"remainingConfigurations":398},{"removed":"Datacurve","score":0.019492452546219154,"rank":325,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02280312210165106,"rank":325,"remainingConfigurations":398},{"removed":"Scale","score":0.02581543688792823,"rank":325,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.023002752789707582,"rank":325,"remainingConfigurations":398},{"removed":"Cognition","score":0.02422483730318836,"rank":325,"remainingConfigurations":398},{"removed":"LiveBench","score":0.023671167950220173,"rank":324,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02373205826843004,"rank":325,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02352666334437672,"rank":307,"remainingConfigurations":381},{"removed":"Vals AI","score":0.022436460207877863,"rank":323,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02304377286022012,"rank":325,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.023019726174117103,"rank":325,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.023001315611092827,"rank":325,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.023042355039177436,"rank":325,"remainingConfigurations":398},{"removed":"All provider reports","score":0.022976108052707264,"rank":325,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.023137857760270258,"rank":325,"remainingConfigurations":398},{"removed":"briefcase","score":0.021518079339973874,"rank":329,"remainingConfigurations":398},{"removed":"aime","score":0.023607975846202712,"rank":324,"remainingConfigurations":398},{"removed":"apex-agents","score":0.023342610971836247,"rank":325,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.022647438786949664,"rank":324,"remainingConfigurations":398},{"removed":"automationbench","score":0.021677391235142646,"rank":329,"remainingConfigurations":398},{"removed":"critpt","score":0.022503202442873325,"rank":322,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.023099100916886883,"rank":325,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.023225920890716473,"rank":325,"remainingConfigurations":398},{"removed":"gdpval","score":0.021655127920411993,"rank":329,"remainingConfigurations":398},{"removed":"gmmlu","score":0.024084903273697823,"rank":323,"remainingConfigurations":398},{"removed":"gpqa","score":0.023221393771844383,"rank":324,"remainingConfigurations":398},{"removed":"harvey","score":0.022796482960150983,"rank":325,"remainingConfigurations":398},{"removed":"hle","score":0.02621323073548812,"rank":325,"remainingConfigurations":398},{"removed":"ifbench","score":0.023467715132337558,"rank":323,"remainingConfigurations":398},{"removed":"itbench","score":0.023024222396560615,"rank":325,"remainingConfigurations":398},{"removed":"livecodebench","score":0.023828138376796735,"rank":323,"remainingConfigurations":398},{"removed":"math500","score":0.023191393078991873,"rank":325,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.025334713979193818,"rank":323,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.025590401520712597,"rank":323,"remainingConfigurations":398},{"removed":"omniscience","score":0.0216833963797414,"rank":325,"remainingConfigurations":398},{"removed":"scicode","score":0.023013466508168535,"rank":326,"remainingConfigurations":398},{"removed":"tau-bench","score":0.021830240684296398,"rank":327,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.021787107636717446,"rank":327,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02776356268327153,"rank":325,"remainingConfigurations":398},{"removed":"deepswe","score":0.019507620412075672,"rank":325,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.023049337663832496,"rank":325,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.022882182311256886,"rank":325,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02422483730318836,"rank":325,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.023068606162754936,"rank":325,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.022822493346403596,"rank":325,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.023009243270033456,"rank":325,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.022957113757119774,"rank":325,"remainingConfigurations":398},{"removed":"livebench-math","score":0.023084241852168206,"rank":325,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02284536322138721,"rank":325,"remainingConfigurations":398},{"removed":"livebench-language","score":0.023328606178853236,"rank":325,"remainingConfigurations":398},{"removed":"livebench-data","score":0.023092850639227086,"rank":325,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02265871876326687,"rank":325,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.022880481014504562,"rank":325,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.023417080076994584,"rank":325,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02373205826843004,"rank":325,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.021864539574279047,"rank":325,"remainingConfigurations":398},{"removed":"frontiermath","score":0.023266735523772963,"rank":325,"remainingConfigurations":398},{"removed":"simpleqa","score":0.024023269651649286,"rank":325,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02292242995511121,"rank":325,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02295736945981033,"rank":325,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0229417203670397,"rank":325,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.023000382848286805,"rank":325,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02287880976017269,"rank":325,"remainingConfigurations":398}]},"mistral-small-4--effort-non-reasoning":{"score":0.022531014373709652,"rank":326,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.027411867178690628,"rank":326,"remainingConfigurations":398},{"removed":"Datacurve","score":0.019091141770909762,"rank":326,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.022301240310311363,"rank":326,"remainingConfigurations":398},{"removed":"Scale","score":0.02521613528471856,"rank":326,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.022483413237140943,"rank":326,"remainingConfigurations":398},{"removed":"Cognition","score":0.023755483026662378,"rank":326,"remainingConfigurations":398},{"removed":"LiveBench","score":0.023126586180826848,"rank":325,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.023199561256735446,"rank":326,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.022801445246695026,"rank":309,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0218924267549476,"rank":325,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02253243595258847,"rank":326,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.022508874238473586,"rank":326,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0224912073268788,"rank":326,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.022531014373709652,"rank":326,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02246658094974353,"rank":326,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.022616373237160935,"rank":326,"remainingConfigurations":398},{"removed":"briefcase","score":0.022496866283090406,"rank":325,"remainingConfigurations":398},{"removed":"aime","score":0.022451157109280546,"rank":329,"remainingConfigurations":398},{"removed":"apex-agents","score":0.022804325695891428,"rank":326,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.022025741456242667,"rank":327,"remainingConfigurations":398},{"removed":"automationbench","score":0.022537967767401402,"rank":325,"remainingConfigurations":398},{"removed":"critpt","score":0.018129396954566224,"rank":337,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02258446535645341,"rank":326,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.022836640408599684,"rank":326,"remainingConfigurations":398},{"removed":"gdpval","score":0.022661938412928382,"rank":324,"remainingConfigurations":398},{"removed":"gmmlu","score":0.022729815447156344,"rank":326,"remainingConfigurations":398},{"removed":"gpqa","score":0.022894178537477234,"rank":325,"remainingConfigurations":398},{"removed":"harvey","score":0.022276641502837563,"rank":326,"remainingConfigurations":398},{"removed":"hle","score":0.026748867108124394,"rank":324,"remainingConfigurations":398},{"removed":"ifbench","score":0.023076771890556107,"rank":324,"remainingConfigurations":398},{"removed":"itbench","score":0.022505655233217656,"rank":326,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02244998330971597,"rank":327,"remainingConfigurations":398},{"removed":"math500","score":0.022629281547398947,"rank":327,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.02319251486749352,"rank":326,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.025579194994417215,"rank":324,"remainingConfigurations":398},{"removed":"omniscience","score":0.02013328797336977,"rank":329,"remainingConfigurations":398},{"removed":"scicode","score":0.02301671547160111,"rank":325,"remainingConfigurations":398},{"removed":"tau-bench","score":0.024025234194287346,"rank":322,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02101378464426532,"rank":333,"remainingConfigurations":398},{"removed":"arc-agi","score":0.027186871929448315,"rank":326,"remainingConfigurations":398},{"removed":"deepswe","score":0.019105790584594218,"rank":326,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.022537732989940867,"rank":326,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.022373401964530023,"rank":326,"remainingConfigurations":398},{"removed":"frontiercode","score":0.023755483026662378,"rank":326,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02255771533289137,"rank":326,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.022318116084974315,"rank":326,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.022498248675027904,"rank":326,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.022444897410615488,"rank":326,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02257228428916031,"rank":326,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.022336624055964645,"rank":326,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02280997969760544,"rank":326,"remainingConfigurations":398},{"removed":"livebench-data","score":0.022581098408172465,"rank":326,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.022156321160441056,"rank":326,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.022372414784303102,"rank":326,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.022899118472354502,"rank":326,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.023199561256735446,"rank":326,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02136196521366804,"rank":326,"remainingConfigurations":398},{"removed":"frontiermath","score":0.022780743066003844,"rank":326,"remainingConfigurations":398},{"removed":"simpleqa","score":0.023489447583062133,"rank":326,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02241383728684269,"rank":326,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.022447710096449167,"rank":326,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02243265770768006,"rank":326,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02248924663262559,"rank":326,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02237117977255877,"rank":326,"remainingConfigurations":398}]},"amazon-nova-2-lite--effort-non-reasoning":{"score":0.022081728509690382,"rank":327,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02683477233467316,"rank":328,"remainingConfigurations":398},{"removed":"Datacurve","score":0.018691422309303235,"rank":327,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.021860575575238118,"rank":327,"remainingConfigurations":398},{"removed":"Scale","score":0.024715076297325205,"rank":327,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02203159681798052,"rank":327,"remainingConfigurations":398},{"removed":"Cognition","score":0.02327476086143171,"rank":327,"remainingConfigurations":398},{"removed":"LiveBench","score":0.022660819510718747,"rank":326,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.022712491022802997,"rank":327,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.022459667263766678,"rank":310,"remainingConfigurations":381},{"removed":"Vals AI","score":0.021449805875439588,"rank":326,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02208310974743764,"rank":327,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02205982887478634,"rank":327,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.022042794949059946,"rank":327,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.022081728509690382,"rank":327,"remainingConfigurations":398},{"removed":"All provider reports","score":0.022018448996154575,"rank":327,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.022157576632871448,"rank":327,"remainingConfigurations":398},{"removed":"briefcase","score":0.022039277606956068,"rank":326,"remainingConfigurations":398},{"removed":"aime","score":0.022787003526313823,"rank":327,"remainingConfigurations":398},{"removed":"apex-agents","score":0.022352269141552458,"rank":327,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.022289299605562047,"rank":326,"remainingConfigurations":398},{"removed":"automationbench","score":0.02210074499733745,"rank":326,"remainingConfigurations":398},{"removed":"critpt","score":0.021368836558897486,"rank":324,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.022122225117819583,"rank":327,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02238733881008428,"rank":327,"remainingConfigurations":398},{"removed":"gdpval","score":0.022212144588497445,"rank":326,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02074632620596641,"rank":330,"remainingConfigurations":398},{"removed":"gpqa","score":0.02182176790073694,"rank":329,"remainingConfigurations":398},{"removed":"harvey","score":0.02182932974619066,"rank":327,"remainingConfigurations":398},{"removed":"hle","score":0.02556697928181777,"rank":327,"remainingConfigurations":398},{"removed":"ifbench","score":0.0207037241051494,"rank":329,"remainingConfigurations":398},{"removed":"itbench","score":0.02205643476472875,"rank":327,"remainingConfigurations":398},{"removed":"livecodebench","score":0.022903339573230996,"rank":326,"remainingConfigurations":398},{"removed":"math500","score":0.02225781775073064,"rank":329,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.022833238906109766,"rank":328,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.024262849747877638,"rank":327,"remainingConfigurations":398},{"removed":"omniscience","score":0.021055984926233673,"rank":327,"remainingConfigurations":398},{"removed":"scicode","score":0.022551196746063318,"rank":327,"remainingConfigurations":398},{"removed":"tau-bench","score":0.019720155722791715,"rank":333,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.021762391413179843,"rank":328,"remainingConfigurations":398},{"removed":"arc-agi","score":0.026619567292779697,"rank":328,"remainingConfigurations":398},{"removed":"deepswe","score":0.01870578785269948,"rank":327,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.022088324552438098,"rank":327,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.021926363138502426,"rank":327,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02327476086143171,"rank":327,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02210604254133285,"rank":327,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.021872407794633817,"rank":327,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02204941291096754,"rank":327,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.021997189347285184,"rank":327,"remainingConfigurations":398},{"removed":"livebench-math","score":0.022122266082844455,"rank":327,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02189105076509935,"rank":327,"remainingConfigurations":398},{"removed":"livebench-language","score":0.022355264337297783,"rank":327,"remainingConfigurations":398},{"removed":"livebench-data","score":0.022130575171554256,"rank":327,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.021714189972658452,"rank":327,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.021926263279584347,"rank":327,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.022443037371560184,"rank":327,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.022712491022802997,"rank":327,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.02089448324352099,"rank":327,"remainingConfigurations":398},{"removed":"frontiermath","score":0.022314386422842617,"rank":327,"remainingConfigurations":398},{"removed":"simpleqa","score":0.023023609191963706,"rank":327,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.021966748202609594,"rank":327,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.021999928669696273,"rank":327,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.021985355034934793,"rank":327,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02204064002971876,"rank":327,"remainingConfigurations":398},{"removed":"vibe-code","score":0.021924863139342287,"rank":327,"remainingConfigurations":398}]},"nvidia-nemotron-nano-9b-v2--effort-reasoning":{"score":0.022039063931251147,"rank":328,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.026869462372916274,"rank":327,"remainingConfigurations":398},{"removed":"Datacurve","score":0.018661185666227653,"rank":328,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02181005079664376,"rank":328,"remainingConfigurations":398},{"removed":"Scale","score":0.02466078882697523,"rank":328,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.021991609863649772,"rank":328,"remainingConfigurations":398},{"removed":"Cognition","score":0.023228734931115977,"rank":328,"remainingConfigurations":398},{"removed":"LiveBench","score":0.022619753428850153,"rank":327,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.022711983434476585,"rank":328,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.022138779430379674,"rank":311,"remainingConfigurations":381},{"removed":"Vals AI","score":0.021413965410149505,"rank":327,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.022040446706704565,"rank":328,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.022017340251037475,"rank":328,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.02200028432246555,"rank":328,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.022039063931251147,"rank":328,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02197612171330812,"rank":328,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.022117912692385416,"rank":328,"remainingConfigurations":398},{"removed":"briefcase","score":0.021990759749381108,"rank":327,"remainingConfigurations":398},{"removed":"aime","score":0.019606650153829605,"rank":334,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02230323789345129,"rank":328,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02191355193654768,"rank":328,"remainingConfigurations":398},{"removed":"automationbench","score":0.02202847999575939,"rank":327,"remainingConfigurations":398},{"removed":"critpt","score":0.02122901800251564,"rank":325,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.022084424696992316,"rank":328,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.022327556585613705,"rank":328,"remainingConfigurations":398},{"removed":"gdpval","score":0.02214832258286314,"rank":327,"remainingConfigurations":398},{"removed":"gmmlu","score":0.022236761843585695,"rank":327,"remainingConfigurations":398},{"removed":"gpqa","score":0.02225793858736962,"rank":327,"remainingConfigurations":398},{"removed":"harvey","score":0.02178956064505651,"rank":328,"remainingConfigurations":398},{"removed":"hle","score":0.023615833216537024,"rank":330,"remainingConfigurations":398},{"removed":"ifbench","score":0.02361647662776944,"rank":322,"remainingConfigurations":398},{"removed":"itbench","score":0.02201325679066143,"rank":328,"remainingConfigurations":398},{"removed":"livecodebench","score":0.018549568362445232,"rank":337,"remainingConfigurations":398},{"removed":"math500","score":0.022276096581279787,"rank":328,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.023142813149359787,"rank":327,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.023624353172358614,"rank":328,"remainingConfigurations":398},{"removed":"omniscience","score":0.02174308645554987,"rank":324,"remainingConfigurations":398},{"removed":"scicode","score":0.022484433542398385,"rank":328,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0221844454067644,"rank":326,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02362059543660446,"rank":323,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02665244305528971,"rank":327,"remainingConfigurations":398},{"removed":"deepswe","score":0.01867553355895946,"rank":328,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.022045648156797895,"rank":328,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02188469515683993,"rank":328,"remainingConfigurations":398},{"removed":"frontiercode","score":0.023228734931115977,"rank":328,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.02206488275932716,"rank":328,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.021830168110557376,"rank":328,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02200704758655851,"rank":328,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.021954890375560657,"rank":328,"remainingConfigurations":398},{"removed":"livebench-math","score":0.022079523913752643,"rank":328,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.021848540940072738,"rank":328,"remainingConfigurations":398},{"removed":"livebench-language","score":0.022312134356378643,"rank":328,"remainingConfigurations":398},{"removed":"livebench-data","score":0.022088102272086418,"rank":328,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.021672218104623147,"rank":328,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02188377109285007,"rank":328,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.02239969365070411,"rank":328,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.022711983434476585,"rank":328,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.020814774494664755,"rank":328,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02227135714397671,"rank":328,"remainingConfigurations":398},{"removed":"simpleqa","score":0.022981620894393318,"rank":328,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02192431676093093,"rank":328,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.021957473950263127,"rank":328,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02194282815590445,"rank":328,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.021998137021164595,"rank":328,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02188251633423043,"rank":328,"remainingConfigurations":398}]},"mistral-medium-2505--effort-non-reasoning":{"score":0.02181123750802792,"rank":329,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.026552417945888473,"rank":329,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01845245221216461,"rank":329,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.021576326279779356,"rank":329,"remainingConfigurations":398},{"removed":"Scale","score":0.0244022981654478,"rank":329,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.021769543265760943,"rank":329,"remainingConfigurations":398},{"removed":"Cognition","score":0.022970085250078418,"rank":329,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02239127418253564,"rank":328,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.022447064435046366,"rank":329,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02199489278079135,"rank":312,"remainingConfigurations":381},{"removed":"Vals AI","score":0.021201662534147195,"rank":328,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.021812608366303447,"rank":329,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02178968035436191,"rank":329,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.021772758037435797,"rank":329,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02181123750802792,"rank":329,"remainingConfigurations":398},{"removed":"All provider reports","score":0.021748789905673072,"rank":329,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.021894431592661443,"rank":329,"remainingConfigurations":398},{"removed":"briefcase","score":0.021776249422286217,"rank":328,"remainingConfigurations":398},{"removed":"aime","score":0.02268077516827768,"rank":328,"remainingConfigurations":398},{"removed":"apex-agents","score":0.022071616383100696,"rank":329,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.021215733320732334,"rank":329,"remainingConfigurations":398},{"removed":"automationbench","score":0.021812930008744878,"rank":328,"remainingConfigurations":398},{"removed":"critpt","score":0.02104429640873742,"rank":326,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.021858468990577456,"rank":329,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02211449650337753,"rank":329,"remainingConfigurations":398},{"removed":"gdpval","score":0.021961744579182235,"rank":328,"remainingConfigurations":398},{"removed":"gmmlu","score":0.022049788528498235,"rank":328,"remainingConfigurations":398},{"removed":"gpqa","score":0.021659177019381515,"rank":330,"remainingConfigurations":398},{"removed":"harvey","score":0.021567293450462554,"rank":329,"remainingConfigurations":398},{"removed":"hle","score":0.024528205177683015,"rank":328,"remainingConfigurations":398},{"removed":"ifbench","score":0.02062366657592656,"rank":330,"remainingConfigurations":398},{"removed":"itbench","score":0.021785440799973483,"rank":329,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02203907559977684,"rank":329,"remainingConfigurations":398},{"removed":"math500","score":0.021929646761581798,"rank":330,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.022052388603902823,"rank":330,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.023390254277154077,"rank":329,"remainingConfigurations":398},{"removed":"omniscience","score":0.019061744627818077,"rank":332,"remainingConfigurations":398},{"removed":"scicode","score":0.022269868586285185,"rank":329,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02158687691506381,"rank":328,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02241006701629578,"rank":325,"remainingConfigurations":398},{"removed":"arc-agi","score":0.026339751259098747,"rank":329,"remainingConfigurations":398},{"removed":"deepswe","score":0.018466664220266927,"rank":329,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.021817759610601836,"rank":329,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02165829328631597,"rank":329,"remainingConfigurations":398},{"removed":"frontiercode","score":0.022970085250078418,"rank":329,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.021835758818309986,"rank":329,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.02160357212693342,"rank":329,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.021779564993256003,"rank":329,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.021728285972716452,"rank":329,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0218512961655651,"rank":329,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.021622771467318697,"rank":329,"remainingConfigurations":398},{"removed":"livebench-language","score":0.022081715237690078,"rank":329,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02185962762355902,"rank":329,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.02144802553791836,"rank":329,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.021657528370029013,"rank":329,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.022168116973689672,"rank":329,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.022447064435046366,"rank":329,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.020630520470008306,"rank":329,"remainingConfigurations":398},{"removed":"frontiermath","score":0.022043969955505213,"rank":329,"remainingConfigurations":398},{"removed":"simpleqa","score":0.022746486262139168,"rank":329,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.021697603808005565,"rank":329,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.02173046881152847,"rank":329,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.021715929348133822,"rank":329,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02177075048139877,"rank":329,"remainingConfigurations":398},{"removed":"vibe-code","score":0.021656290977600846,"rank":329,"remainingConfigurations":398}]},"amazon-nova-premier--effort-non-reasoning":{"score":0.02099400791350294,"rank":330,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02555432116032742,"rank":330,"remainingConfigurations":398},{"removed":"Datacurve","score":0.017755458385510292,"rank":330,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02076996086055737,"rank":330,"remainingConfigurations":398},{"removed":"Scale","score":0.02350054931595541,"rank":330,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.02095120801378582,"rank":330,"remainingConfigurations":398},{"removed":"Cognition","score":0.022108581388156176,"rank":330,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02155148457767761,"rank":329,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.021603271304460877,"rank":330,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02119374887079575,"rank":313,"remainingConfigurations":381},{"removed":"Vals AI","score":0.020404078277724585,"rank":329,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02099532429327561,"rank":330,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.020973254065938713,"rank":330,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.02095703166533482,"rank":330,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.02099400791350294,"rank":330,"remainingConfigurations":398},{"removed":"All provider reports","score":0.020933949731054932,"rank":330,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02107407138259351,"rank":330,"remainingConfigurations":398},{"removed":"briefcase","score":0.020959594627138225,"rank":330,"remainingConfigurations":398},{"removed":"aime","score":0.02318981182885212,"rank":325,"remainingConfigurations":398},{"removed":"apex-agents","score":0.021246825433701027,"rank":330,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.02006726069625063,"rank":333,"remainingConfigurations":398},{"removed":"automationbench","score":0.02098879882763305,"rank":330,"remainingConfigurations":398},{"removed":"critpt","score":0.020203381562466212,"rank":327,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02104017769692032,"rank":330,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.021266481855879496,"rank":330,"remainingConfigurations":398},{"removed":"gdpval","score":0.021122651822381124,"rank":330,"remainingConfigurations":398},{"removed":"gmmlu","score":0.020188998948540166,"rank":335,"remainingConfigurations":398},{"removed":"gpqa","score":0.021015509699223528,"rank":333,"remainingConfigurations":398},{"removed":"harvey","score":0.02075918811574152,"rank":330,"remainingConfigurations":398},{"removed":"hle","score":0.02336271087678955,"rank":331,"remainingConfigurations":398},{"removed":"ifbench","score":0.020504161453930487,"rank":331,"remainingConfigurations":398},{"removed":"itbench","score":0.02096874438414577,"rank":330,"remainingConfigurations":398},{"removed":"livecodebench","score":0.022159726239553906,"rank":328,"remainingConfigurations":398},{"removed":"math500","score":0.022654570696439422,"rank":326,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.022030831839281475,"rank":331,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02255113166902681,"rank":330,"remainingConfigurations":398},{"removed":"omniscience","score":0.0173670731318751,"rank":336,"remainingConfigurations":398},{"removed":"scicode","score":0.021416625521583355,"rank":330,"remainingConfigurations":398},{"removed":"tau-bench","score":0.019393347856287966,"rank":335,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.020589189899167734,"rank":334,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02535106309663833,"rank":330,"remainingConfigurations":398},{"removed":"deepswe","score":0.017769160986137147,"rank":330,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.021000300601216618,"rank":330,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.020846488395811467,"rank":330,"remainingConfigurations":398},{"removed":"frontiercode","score":0.022108581388156176,"rank":330,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.021017280765026024,"rank":330,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.020793948466535667,"rank":330,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.020963445810516696,"rank":330,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.020914134488583955,"rank":330,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02103266396605605,"rank":330,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.020812192835339204,"rank":330,"remainingConfigurations":398},{"removed":"livebench-language","score":0.021254728286073537,"rank":330,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02104068777497563,"rank":330,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.020643859229523533,"rank":330,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0208458166776959,"rank":330,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0213382069898929,"rank":330,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.021603271304460877,"rank":330,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.019856405556548842,"rank":330,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02121762386845272,"rank":330,"remainingConfigurations":398},{"removed":"simpleqa","score":0.021896163779757324,"rank":330,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.020884456523690444,"rank":330,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.020916124204494235,"rank":330,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.020902120520720168,"rank":330,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02095495580678665,"rank":330,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02084462191871914,"rank":330,"remainingConfigurations":398}]},"qwen3-coder-30b-a3b-instruct--effort-non-reasoning":{"score":0.020855055868054445,"rank":331,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0254158401983639,"rank":331,"remainingConfigurations":398},{"removed":"Datacurve","score":0.017642390114784853,"rank":331,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.02063585958540266,"rank":331,"remainingConfigurations":398},{"removed":"Scale","score":0.023344930734260014,"rank":331,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.020813194387724387,"rank":331,"remainingConfigurations":398},{"removed":"Cognition","score":0.021967823848532204,"rank":331,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02140980647237564,"rank":330,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.021468207910217852,"rank":331,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02104480002166033,"rank":314,"remainingConfigurations":381},{"removed":"Vals AI","score":0.020270540347773817,"rank":330,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.020856365159617526,"rank":331,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.02083445605155604,"rank":331,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.020818330005421385,"rank":331,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.020855055868054445,"rank":331,"remainingConfigurations":398},{"removed":"All provider reports","score":0.020795417456905316,"rank":331,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.020934056869076515,"rank":331,"remainingConfigurations":398},{"removed":"briefcase","score":0.020829058250291084,"rank":331,"remainingConfigurations":398},{"removed":"aime","score":0.021802900448707373,"rank":330,"remainingConfigurations":398},{"removed":"apex-agents","score":0.021104990204419662,"rank":331,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.020023135175316925,"rank":334,"remainingConfigurations":398},{"removed":"automationbench","score":0.02086724000990138,"rank":331,"remainingConfigurations":398},{"removed":"critpt","score":0.02000656749339645,"rank":330,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.020905277750820822,"rank":331,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.021148498851292944,"rank":331,"remainingConfigurations":398},{"removed":"gdpval","score":0.02102284733975812,"rank":331,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02107889317269673,"rank":329,"remainingConfigurations":398},{"removed":"gpqa","score":0.02110540460566866,"rank":332,"remainingConfigurations":398},{"removed":"harvey","score":0.020620247272032603,"rank":331,"remainingConfigurations":398},{"removed":"hle","score":0.023627583333856964,"rank":329,"remainingConfigurations":398},{"removed":"ifbench","score":0.02098060631269769,"rank":328,"remainingConfigurations":398},{"removed":"itbench","score":0.02082998035709491,"rank":331,"remainingConfigurations":398},{"removed":"livecodebench","score":0.020844638149216502,"rank":331,"remainingConfigurations":398},{"removed":"math500","score":0.02125193767665198,"rank":331,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.022328506941205372,"rank":329,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.022445884910974698,"rank":331,"remainingConfigurations":398},{"removed":"omniscience","score":0.018712615615085002,"rank":334,"remainingConfigurations":398},{"removed":"scicode","score":0.021299261950372027,"rank":331,"remainingConfigurations":398},{"removed":"tau-bench","score":0.019449983494054777,"rank":334,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01926856959403182,"rank":336,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02521243144948038,"rank":331,"remainingConfigurations":398},{"removed":"deepswe","score":0.017656002135664605,"rank":331,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.020861306483817687,"rank":331,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.02070879727020342,"rank":331,"remainingConfigurations":398},{"removed":"frontiercode","score":0.021967823848532204,"rank":331,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.020878814384609284,"rank":331,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.020656382363239478,"rank":331,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.02082477700877294,"rank":331,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02077570767634689,"rank":331,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02089346856147037,"rank":331,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.0206743001686741,"rank":331,"remainingConfigurations":398},{"removed":"livebench-language","score":0.021114119629801333,"rank":331,"remainingConfigurations":398},{"removed":"livebench-data","score":0.020901555686696365,"rank":331,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.020507152835890843,"rank":331,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02070776441134255,"rank":331,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.021197078110169156,"rank":331,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.021468207910217852,"rank":331,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01972549844613718,"rank":331,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02107765624907673,"rank":331,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0217522866889302,"rank":331,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.020746207830089524,"rank":331,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.020777689577479237,"rank":331,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.020763741487120357,"rank":331,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.020816262500285954,"rank":331,"remainingConfigurations":398},{"removed":"vibe-code","score":0.02070663472174388,"rank":331,"remainingConfigurations":398}]},"glm-4.7-flash--effort-non-reasoning":{"score":0.020466300118679434,"rank":332,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.012145614676548845,"rank":159,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.025234765266129874,"rank":332,"remainingConfigurations":398},{"removed":"Datacurve","score":0.017489149062702925,"rank":332,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.020305802548475912,"rank":332,"remainingConfigurations":398},{"removed":"Scale","score":0.022894127162869638,"rank":332,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.020498282579356077,"rank":332,"remainingConfigurations":398},{"removed":"Cognition","score":0.021834576323449494,"rank":332,"remainingConfigurations":398},{"removed":"LiveBench","score":0.020997186805234103,"rank":331,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02101804334957266,"rank":332,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.02882712560932121,"rank":294,"remainingConfigurations":381},{"removed":"Vals AI","score":0.020059505599256563,"rank":331,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.020467171279586402,"rank":332,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.020444135967423855,"rank":332,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.02043461961125594,"rank":332,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.020466300118679434,"rank":332,"remainingConfigurations":398},{"removed":"All provider reports","score":0.02040991098560763,"rank":332,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.020542013931223013,"rank":332,"remainingConfigurations":398},{"removed":"briefcase","score":0.02046465687312185,"rank":332,"remainingConfigurations":398},{"removed":"aime","score":0.019353838069670014,"rank":335,"remainingConfigurations":398},{"removed":"apex-agents","score":0.020696433853662963,"rank":332,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.021001934543441347,"rank":330,"remainingConfigurations":398},{"removed":"automationbench","score":0.020496453046274312,"rank":332,"remainingConfigurations":398},{"removed":"critpt","score":0.02008782809767291,"rank":329,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.020512338205320117,"rank":332,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.020722287471977997,"rank":332,"remainingConfigurations":398},{"removed":"gdpval","score":0.02057676199501479,"rank":332,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0207108667523109,"rank":331,"remainingConfigurations":398},{"removed":"gpqa","score":0.02206509122786443,"rank":328,"remainingConfigurations":398},{"removed":"harvey","score":0.02023309056251051,"rank":332,"remainingConfigurations":398},{"removed":"hle","score":0.021959052392435896,"rank":332,"remainingConfigurations":398},{"removed":"ifbench","score":0.018457895384453082,"rank":339,"remainingConfigurations":398},{"removed":"itbench","score":0.02044320685217473,"rank":332,"remainingConfigurations":398},{"removed":"livecodebench","score":0.020692743445938102,"rank":332,"remainingConfigurations":398},{"removed":"math500","score":0.020637946146011592,"rank":332,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.021352478645279494,"rank":332,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.022061433046170018,"rank":332,"remainingConfigurations":398},{"removed":"omniscience","score":0.020664586752767517,"rank":328,"remainingConfigurations":398},{"removed":"scicode","score":0.020853482753423667,"rank":332,"remainingConfigurations":398},{"removed":"tau-bench","score":0.016524861755892486,"rank":343,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02136143216215877,"rank":330,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02500134415569096,"rank":332,"remainingConfigurations":398},{"removed":"deepswe","score":0.01750330717671404,"rank":332,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.020472260940064217,"rank":332,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.020328568769421202,"rank":332,"remainingConfigurations":398},{"removed":"frontiercode","score":0.021834576323449494,"rank":332,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.020509737575413706,"rank":332,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.020266598372031045,"rank":332,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.020437924029796214,"rank":332,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.020387284331128627,"rank":332,"remainingConfigurations":398},{"removed":"livebench-math","score":0.020511364156351502,"rank":332,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.02026930280118433,"rank":332,"remainingConfigurations":398},{"removed":"livebench-language","score":0.020719660771499428,"rank":332,"remainingConfigurations":398},{"removed":"livebench-data","score":0.02051754528886281,"rank":332,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.020130905494275025,"rank":332,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.02032041860476912,"rank":332,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.020804080233388603,"rank":332,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02101804334957266,"rank":332,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.019283891665332297,"rank":332,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02080359644266739,"rank":332,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02156890959224651,"rank":332,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.02035942124610092,"rank":332,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.020393434913987544,"rank":332,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.020371614335905824,"rank":332,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.02042966865211561,"rank":332,"remainingConfigurations":398},{"removed":"vibe-code","score":0.020325990788477282,"rank":332,"remainingConfigurations":398}]},"nvidia-nemotron-nano-9b-v2--effort-non-reasoning":{"score":0.020098403865662806,"rank":333,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.024538191268219784,"rank":333,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01701297915549436,"rank":333,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.019890188908354114,"rank":333,"remainingConfigurations":398},{"removed":"Scale","score":0.02250403746242287,"rank":333,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.020054491778161012,"rank":333,"remainingConfigurations":398},{"removed":"Cognition","score":0.02119175219904068,"rank":333,"remainingConfigurations":398},{"removed":"LiveBench","score":0.020632202087614602,"rank":332,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02071406892120986,"rank":333,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.020210041965368707,"rank":316,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01952916906524711,"rank":332,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.020099668762580007,"rank":333,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.020078540439735226,"rank":333,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.020062965368314464,"rank":333,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.020098403865662806,"rank":333,"remainingConfigurations":398},{"removed":"All provider reports","score":0.020040868387344524,"rank":333,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.020172405823990006,"rank":333,"remainingConfigurations":398},{"removed":"briefcase","score":0.020060906846010324,"rank":333,"remainingConfigurations":398},{"removed":"aime","score":0.01823017285961728,"rank":338,"remainingConfigurations":398},{"removed":"apex-agents","score":0.0203422621630737,"rank":333,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.019796731718563474,"rank":336,"remainingConfigurations":398},{"removed":"automationbench","score":0.02009174534142734,"rank":333,"remainingConfigurations":398},{"removed":"critpt","score":0.019165513602871925,"rank":331,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.020143174647277245,"rank":333,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02036822643693427,"rank":333,"remainingConfigurations":398},{"removed":"gdpval","score":0.020192787912766862,"rank":333,"remainingConfigurations":398},{"removed":"gmmlu","score":0.020266496509183538,"rank":333,"remainingConfigurations":398},{"removed":"gpqa","score":0.020220179195283527,"rank":334,"remainingConfigurations":398},{"removed":"harvey","score":0.019872864048208642,"rank":333,"remainingConfigurations":398},{"removed":"hle","score":0.021815094072638166,"rank":333,"remainingConfigurations":398},{"removed":"ifbench","score":0.021401008627847287,"rank":326,"remainingConfigurations":398},{"removed":"itbench","score":0.020076689621948963,"rank":333,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01701457916725314,"rank":342,"remainingConfigurations":398},{"removed":"math500","score":0.020302975891261635,"rank":333,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.021038925816658654,"rank":333,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02157746394721577,"rank":333,"remainingConfigurations":398},{"removed":"omniscience","score":0.019934786336559897,"rank":330,"remainingConfigurations":398},{"removed":"scicode","score":0.020513426354354186,"rank":333,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01984883329253322,"rank":332,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02165428115763293,"rank":329,"remainingConfigurations":398},{"removed":"arc-agi","score":0.024337766594984708,"rank":333,"remainingConfigurations":398},{"removed":"deepswe","score":0.017026086949195073,"rank":333,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.020104428662187975,"rank":333,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01995759620412037,"rank":333,"remainingConfigurations":398},{"removed":"frontiercode","score":0.02119175219904068,"rank":333,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.020122294972117923,"rank":333,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.019907495654604857,"rank":333,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.020069227720497258,"rank":333,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.02002153101127657,"rank":333,"remainingConfigurations":398},{"removed":"livebench-math","score":0.02013544413473016,"rank":333,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01992387858643315,"rank":333,"remainingConfigurations":398},{"removed":"livebench-language","score":0.020348354294280113,"rank":333,"remainingConfigurations":398},{"removed":"livebench-data","score":0.020143379838270213,"rank":333,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.019762651159832653,"rank":333,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.019956221314455996,"rank":333,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.020428661836789513,"rank":333,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02071406892120986,"rank":333,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.018983760282265873,"rank":333,"remainingConfigurations":398},{"removed":"frontiermath","score":0.020312662426110347,"rank":333,"remainingConfigurations":398},{"removed":"simpleqa","score":0.020961762636227368,"rank":333,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.019993368421105395,"rank":333,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.020023707164665238,"rank":333,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.02001032272276007,"rank":333,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0200608714045966,"rank":333,"remainingConfigurations":398},{"removed":"vibe-code","score":0.019955133536410333,"rank":333,"remainingConfigurations":398}]},"deepseek-r1-distill-llama-70b--effort-reasoning":{"score":0.020030749441678396,"rank":334,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.024411058560172172,"rank":335,"remainingConfigurations":398},{"removed":"Datacurve","score":0.016942608509646663,"rank":334,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.019817090266776503,"rank":334,"remainingConfigurations":398},{"removed":"Scale","score":0.022422325300770946,"rank":334,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01999028271326136,"rank":334,"remainingConfigurations":398},{"removed":"Cognition","score":0.021102085558424813,"rank":335,"remainingConfigurations":398},{"removed":"LiveBench","score":0.02056544352642661,"rank":333,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.02062200861889841,"rank":334,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.020193387404455712,"rank":317,"remainingConfigurations":381},{"removed":"Vals AI","score":0.019469716828235815,"rank":333,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.020032008565040036,"rank":334,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.020010941496827934,"rank":334,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.019995444209814608,"rank":334,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.020030749441678396,"rank":334,"remainingConfigurations":398},{"removed":"All provider reports","score":0.019973410865333465,"rank":334,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02010826836613395,"rank":334,"remainingConfigurations":398},{"removed":"briefcase","score":0.019997581559025725,"rank":335,"remainingConfigurations":398},{"removed":"aime","score":0.018878119029648092,"rank":336,"remainingConfigurations":398},{"removed":"apex-agents","score":0.020272064719009043,"rank":334,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.020602716502826395,"rank":332,"remainingConfigurations":398},{"removed":"automationbench","score":0.02003332655178129,"rank":334,"remainingConfigurations":398},{"removed":"critpt","score":0.019142799667912803,"rank":332,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.020081301411734028,"rank":334,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.02030442152399366,"rank":334,"remainingConfigurations":398},{"removed":"gdpval","score":0.02017797500738833,"rank":334,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02022763602394997,"rank":334,"remainingConfigurations":398},{"removed":"gpqa","score":0.02112408593597886,"rank":331,"remainingConfigurations":398},{"removed":"harvey","score":0.01980674016467936,"rank":334,"remainingConfigurations":398},{"removed":"hle","score":0.020855491376134395,"rank":337,"remainingConfigurations":398},{"removed":"ifbench","score":0.02113090707735397,"rank":327,"remainingConfigurations":398},{"removed":"itbench","score":0.02000720034863955,"rank":334,"remainingConfigurations":398},{"removed":"livecodebench","score":0.021926388094897973,"rank":330,"remainingConfigurations":398},{"removed":"math500","score":0.018964804742947608,"rank":336,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01881763823945281,"rank":339,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.02156844773807984,"rank":334,"remainingConfigurations":398},{"removed":"omniscience","score":0.016772498457604052,"rank":338,"remainingConfigurations":398},{"removed":"scicode","score":0.020449851447965975,"rank":334,"remainingConfigurations":398},{"removed":"tau-bench","score":0.020039493486219608,"rank":331,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.021292420595205776,"rank":331,"remainingConfigurations":398},{"removed":"arc-agi","score":0.024214998835395893,"rank":335,"remainingConfigurations":398},{"removed":"deepswe","score":0.016955691783613037,"rank":334,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.020036761511369305,"rank":334,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01989025638916609,"rank":334,"remainingConfigurations":398},{"removed":"frontiercode","score":0.021102085558424813,"rank":335,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.020053716886898828,"rank":334,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.019839746669407063,"rank":334,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.020001676819093848,"rank":334,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.019954494405662927,"rank":334,"remainingConfigurations":398},{"removed":"livebench-math","score":0.020067705075086966,"rank":334,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01985680455420191,"rank":334,"remainingConfigurations":398},{"removed":"livebench-language","score":0.020279964789723395,"rank":334,"remainingConfigurations":398},{"removed":"livebench-data","score":0.020075522181761136,"rank":334,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01969608607089139,"rank":334,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.019889040032301523,"rank":334,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.020359840584370105,"rank":334,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.02062200861889841,"rank":334,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.018934948009177156,"rank":334,"remainingConfigurations":398},{"removed":"frontiermath","score":0.020244983933909357,"rank":334,"remainingConfigurations":398},{"removed":"simpleqa","score":0.020894157282297394,"rank":334,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01992603778431889,"rank":334,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01995631833566436,"rank":334,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01994290824638102,"rank":334,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01999340043704467,"rank":334,"remainingConfigurations":398},{"removed":"vibe-code","score":0.019887980236477015,"rank":334,"remainingConfigurations":398}]},"exaone-4.0-32b--effort-non-reasoning":{"score":0.020013507849383657,"rank":335,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02441608548682542,"rank":334,"remainingConfigurations":398},{"removed":"Datacurve","score":0.016940085926081535,"rank":335,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.019804014950771123,"rank":335,"remainingConfigurations":398},{"removed":"Scale","score":0.022408653573914625,"rank":335,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.019970293803646955,"rank":335,"remainingConfigurations":398},{"removed":"Cognition","score":0.021102582699278435,"rank":334,"remainingConfigurations":398},{"removed":"LiveBench","score":0.020544975387959612,"rank":334,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.020617596608454747,"rank":335,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.020210548142073428,"rank":315,"remainingConfigurations":381},{"removed":"Vals AI","score":0.019448261093219763,"rank":334,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.02001476573992467,"rank":335,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0199936903541516,"rank":335,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.019978265003727794,"rank":335,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.020013507849383657,"rank":335,"remainingConfigurations":398},{"removed":"All provider reports","score":0.019956222649146618,"rank":335,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.02008787671893424,"rank":335,"remainingConfigurations":398},{"removed":"briefcase","score":0.019999888455119696,"rank":334,"remainingConfigurations":398},{"removed":"aime","score":0.019780007451537452,"rank":333,"remainingConfigurations":398},{"removed":"apex-agents","score":0.02025762263259389,"rank":335,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.019881161323067026,"rank":335,"remainingConfigurations":398},{"removed":"automationbench","score":0.020030017751488615,"rank":335,"remainingConfigurations":398},{"removed":"critpt","score":0.019003637597291054,"rank":333,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.02005896794926247,"rank":335,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.020302771948687227,"rank":335,"remainingConfigurations":398},{"removed":"gdpval","score":0.020162859275923897,"rank":335,"remainingConfigurations":398},{"removed":"gmmlu","score":0.020180430068289193,"rank":336,"remainingConfigurations":398},{"removed":"gpqa","score":0.01922742388801734,"rank":336,"remainingConfigurations":398},{"removed":"harvey","score":0.0197891898386935,"rank":335,"remainingConfigurations":398},{"removed":"hle","score":0.020931735569229264,"rank":335,"remainingConfigurations":398},{"removed":"ifbench","score":0.01980131517768507,"rank":335,"remainingConfigurations":398},{"removed":"itbench","score":0.019992111515350585,"rank":335,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01938221855301989,"rank":336,"remainingConfigurations":398},{"removed":"math500","score":0.01889993460300292,"rank":337,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.019751674918376715,"rank":335,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.021520063354034627,"rank":335,"remainingConfigurations":398},{"removed":"omniscience","score":0.019592731892386327,"rank":331,"remainingConfigurations":398},{"removed":"scicode","score":0.020447638318074918,"rank":335,"remainingConfigurations":398},{"removed":"tau-bench","score":0.02147476138209291,"rank":329,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.02123105222332851,"rank":332,"remainingConfigurations":398},{"removed":"arc-agi","score":0.024216494063604488,"rank":334,"remainingConfigurations":398},{"removed":"deepswe","score":0.0169531426870719,"rank":335,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.020019506361407157,"rank":335,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01987317623973864,"rank":335,"remainingConfigurations":398},{"removed":"frontiercode","score":0.021102582699278435,"rank":334,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.020037304731956505,"rank":335,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.019823367956067317,"rank":335,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.019984468572165612,"rank":335,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01993694014208886,"rank":335,"remainingConfigurations":398},{"removed":"livebench-math","score":0.020050418443141867,"rank":335,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.019839642972512908,"rank":335,"remainingConfigurations":398},{"removed":"livebench-language","score":0.02026243205609028,"rank":335,"remainingConfigurations":398},{"removed":"livebench-data","score":0.020058265306201147,"rank":335,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.019679148826076496,"rank":335,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.019871923210096853,"rank":335,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.020342444841091694,"rank":335,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.020617596608454747,"rank":335,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.018917578937241882,"rank":335,"remainingConfigurations":398},{"removed":"frontiermath","score":0.02022938271553856,"rank":335,"remainingConfigurations":398},{"removed":"simpleqa","score":0.020875455974460156,"rank":335,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01990889817555803,"rank":335,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.019939107956926373,"rank":335,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01992579481723756,"rank":335,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01997610895125901,"rank":335,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01987082223112194,"rank":335,"remainingConfigurations":398}]},"ministral-3-14b--effort-non-reasoning":{"score":0.01960721484550848,"rank":336,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02383232321170574,"rank":336,"remainingConfigurations":398},{"removed":"Datacurve","score":0.016579606039154985,"rank":336,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.019404873353741782,"rank":336,"remainingConfigurations":398},{"removed":"Scale","score":0.021979030509817355,"rank":336,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.019573995457678486,"rank":336,"remainingConfigurations":398},{"removed":"Cognition","score":0.020627451878925694,"rank":336,"remainingConfigurations":398},{"removed":"LiveBench","score":0.020152715304402075,"rank":335,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.020192832154168214,"rank":336,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.019984606386471922,"rank":318,"remainingConfigurations":381},{"removed":"Vals AI","score":0.019088694744323106,"rank":335,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.019608430656173025,"rank":336,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01958787445641192,"rank":336,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.019572203262293104,"rank":336,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01960721484550848,"rank":336,"remainingConfigurations":398},{"removed":"All provider reports","score":0.019550655380708288,"rank":336,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.019686234955633382,"rank":336,"remainingConfigurations":398},{"removed":"briefcase","score":0.018987162430675608,"rank":337,"remainingConfigurations":398},{"removed":"aime","score":0.020139381347071484,"rank":332,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01986001943251647,"rank":336,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.019182515977384514,"rank":337,"remainingConfigurations":398},{"removed":"automationbench","score":0.019271739287990388,"rank":337,"remainingConfigurations":398},{"removed":"critpt","score":0.01890048135286078,"rank":334,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.019654974795569494,"rank":336,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.019354949175470176,"rank":337,"remainingConfigurations":398},{"removed":"gdpval","score":0.01920665196886934,"rank":337,"remainingConfigurations":398},{"removed":"gmmlu","score":0.02041836503339565,"rank":332,"remainingConfigurations":398},{"removed":"gpqa","score":0.019423263194204673,"rank":335,"remainingConfigurations":398},{"removed":"harvey","score":0.01939529087555256,"rank":336,"remainingConfigurations":398},{"removed":"hle","score":0.020920940107729078,"rank":336,"remainingConfigurations":398},{"removed":"ifbench","score":0.0195171022147851,"rank":337,"remainingConfigurations":398},{"removed":"itbench","score":0.019589379095319343,"rank":336,"remainingConfigurations":398},{"removed":"livecodebench","score":0.02000357280537174,"rank":335,"remainingConfigurations":398},{"removed":"math500","score":0.019736543421749794,"rank":334,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.021004800008348336,"rank":334,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.021251627846158926,"rank":336,"remainingConfigurations":398},{"removed":"omniscience","score":0.018864395052360178,"rank":333,"remainingConfigurations":398},{"removed":"scicode","score":0.02008852590579551,"rank":336,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01861072822408018,"rank":336,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.019239763195830335,"rank":337,"remainingConfigurations":398},{"removed":"arc-agi","score":0.023647265183387615,"rank":336,"remainingConfigurations":398},{"removed":"deepswe","score":0.016592541494747145,"rank":336,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.019613184290461574,"rank":336,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.019470699132450604,"rank":336,"remainingConfigurations":398},{"removed":"frontiercode","score":0.020627451878925694,"rank":336,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.019630150527722368,"rank":336,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.019419387325365738,"rank":336,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.019579051201894366,"rank":336,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.019534897560201287,"rank":336,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01964311569406407,"rank":336,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.019438157107280463,"rank":336,"remainingConfigurations":398},{"removed":"livebench-language","score":0.019852314350576467,"rank":336,"remainingConfigurations":398},{"removed":"livebench-data","score":0.019650649628046076,"rank":336,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.019278731652817807,"rank":336,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01946848937099796,"rank":336,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.019928553871820166,"rank":336,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.020192832154168214,"rank":336,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.018597512173560107,"rank":336,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01980015924966869,"rank":336,"remainingConfigurations":398},{"removed":"simpleqa","score":0.02044883840587011,"rank":336,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01950450735467837,"rank":336,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.019534385904061247,"rank":336,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.019521042099562316,"rank":336,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.019571095744967505,"rank":336,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01946718785102074,"rank":336,"remainingConfigurations":398}]},"qwen3-235b-a22b--effort-non-reasoning":{"score":0.01934836166964192,"rank":337,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.023616319293237126,"rank":337,"remainingConfigurations":398},{"removed":"Datacurve","score":0.016376723747420472,"rank":337,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.019146447005702272,"rank":337,"remainingConfigurations":398},{"removed":"Scale","score":0.02166974917736374,"rank":337,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.019306719053970623,"rank":337,"remainingConfigurations":398},{"removed":"Cognition","score":0.020404187315432237,"rank":337,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01986427009519644,"rank":336,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.019933880444847465,"rank":337,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.019737142774897656,"rank":319,"remainingConfigurations":381},{"removed":"Vals AI","score":0.018802754519303713,"rank":336,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01934957863768832,"rank":337,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0193291935230523,"rank":337,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01931424729993068,"rank":337,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01934836166964192,"rank":337,"remainingConfigurations":398},{"removed":"All provider reports","score":0.019292924456205413,"rank":337,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.019422236826491857,"rank":337,"remainingConfigurations":398},{"removed":"briefcase","score":0.019326999170897585,"rank":336,"remainingConfigurations":398},{"removed":"aime","score":0.02066634039230857,"rank":331,"remainingConfigurations":398},{"removed":"apex-agents","score":0.019585380520053982,"rank":337,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.020643122366053514,"rank":331,"remainingConfigurations":398},{"removed":"automationbench","score":0.01935845384208826,"rank":336,"remainingConfigurations":398},{"removed":"critpt","score":0.01840070511837338,"rank":336,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.019397310939508184,"rank":337,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.01961971453671281,"rank":336,"remainingConfigurations":398},{"removed":"gdpval","score":0.019481120703811174,"rank":336,"remainingConfigurations":398},{"removed":"gmmlu","score":0.019551560997182436,"rank":337,"remainingConfigurations":398},{"removed":"gpqa","score":0.01877644237164047,"rank":337,"remainingConfigurations":398},{"removed":"harvey","score":0.0191341566414949,"rank":337,"remainingConfigurations":398},{"removed":"hle","score":0.02141638725580164,"rank":334,"remainingConfigurations":398},{"removed":"ifbench","score":0.018614436679891613,"rank":338,"remainingConfigurations":398},{"removed":"itbench","score":0.01932821824468557,"rank":337,"remainingConfigurations":398},{"removed":"livecodebench","score":0.020074734884815818,"rank":334,"remainingConfigurations":398},{"removed":"math500","score":0.019480852775217408,"rank":335,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.019139910769870025,"rank":337,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.020824216005657984,"rank":337,"remainingConfigurations":398},{"removed":"omniscience","score":0.016404548060910067,"rank":340,"remainingConfigurations":398},{"removed":"scicode","score":0.019765656666675038,"rank":337,"remainingConfigurations":398},{"removed":"tau-bench","score":0.018600852471256948,"rank":337,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01910724446715834,"rank":338,"remainingConfigurations":398},{"removed":"arc-agi","score":0.023422196107609036,"rank":337,"remainingConfigurations":398},{"removed":"deepswe","score":0.016389354086297877,"rank":337,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.019354169193922913,"rank":337,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.019212702729959147,"rank":337,"remainingConfigurations":398},{"removed":"frontiercode","score":0.020404187315432237,"rank":337,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.019371451734944856,"rank":337,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.019164382901759234,"rank":337,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.019320292442015163,"rank":337,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01927437706937965,"rank":337,"remainingConfigurations":398},{"removed":"livebench-math","score":0.019384099663704465,"rank":337,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01917999855365284,"rank":337,"remainingConfigurations":398},{"removed":"livebench-language","score":0.019589323045688195,"rank":337,"remainingConfigurations":398},{"removed":"livebench-data","score":0.019391746350092404,"rank":337,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01902470912791318,"rank":337,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.019211283569549462,"rank":337,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.019666822329209226,"rank":337,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.019933880444847465,"rank":337,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.018282559871805947,"rank":337,"remainingConfigurations":398},{"removed":"frontiermath","score":0.019556357832613645,"rank":337,"remainingConfigurations":398},{"removed":"simpleqa","score":0.020182660462078117,"rank":337,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0192470955197724,"rank":337,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01927635037229136,"rank":337,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.019263448348254306,"rank":337,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01931215059376865,"rank":337,"remainingConfigurations":398},{"removed":"vibe-code","score":0.019210257015269506,"rank":337,"remainingConfigurations":398}]},"deepseek-r1-0528-qwen3-8b--effort-reasoning":{"score":0.018779921667382894,"rank":338,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02290180209710721,"rank":338,"remainingConfigurations":398},{"removed":"Datacurve","score":0.015881206341034456,"rank":338,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.018580476193497928,"rank":338,"remainingConfigurations":398},{"removed":"Scale","score":0.02103037877713082,"rank":338,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.018741643736952612,"rank":338,"remainingConfigurations":398},{"removed":"Cognition","score":0.019788083696662007,"rank":338,"remainingConfigurations":398},{"removed":"LiveBench","score":0.019283938427932284,"rank":337,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.019337693644955273,"rank":338,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01891627352819442,"rank":320,"remainingConfigurations":381},{"removed":"Vals AI","score":0.018254542027286467,"rank":337,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.018781104405858975,"rank":338,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.018761318738672383,"rank":338,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.018746777067139203,"rank":338,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.018779921667382894,"rank":338,"remainingConfigurations":398},{"removed":"All provider reports","score":0.018726081886454495,"rank":338,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.018851936776186306,"rank":338,"remainingConfigurations":398},{"removed":"briefcase","score":0.018762173843112944,"rank":338,"remainingConfigurations":398},{"removed":"aime","score":0.016868683325365643,"rank":341,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01900562213023661,"rank":338,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.018950978867724635,"rank":338,"remainingConfigurations":398},{"removed":"automationbench","score":0.018789074075251697,"rank":338,"remainingConfigurations":398},{"removed":"critpt","score":0.017815539009839666,"rank":338,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01882459613870124,"rank":338,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.01904963665143543,"rank":338,"remainingConfigurations":398},{"removed":"gdpval","score":0.01892195400869508,"rank":338,"remainingConfigurations":398},{"removed":"gmmlu","score":0.018968813362706633,"rank":338,"remainingConfigurations":398},{"removed":"gpqa","score":0.018168881647017767,"rank":338,"remainingConfigurations":398},{"removed":"harvey","score":0.018569123641610143,"rank":338,"remainingConfigurations":398},{"removed":"hle","score":0.019026074246612915,"rank":342,"remainingConfigurations":398},{"removed":"ifbench","score":0.0204179734322374,"rank":332,"remainingConfigurations":398},{"removed":"itbench","score":0.0187586380492898,"rank":338,"remainingConfigurations":398},{"removed":"livecodebench","score":0.017603374022728772,"rank":339,"remainingConfigurations":398},{"removed":"math500","score":0.01782998316882214,"rank":338,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.019442472696603465,"rank":336,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.020255053404633374,"rank":338,"remainingConfigurations":398},{"removed":"omniscience","score":0.018078634231642358,"rank":335,"remainingConfigurations":398},{"removed":"scicode","score":0.01918706350063407,"rank":338,"remainingConfigurations":398},{"removed":"tau-bench","score":0.020145693457395857,"rank":330,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.019868756663578378,"rank":335,"remainingConfigurations":398},{"removed":"arc-agi","score":0.022716857066970936,"rank":338,"remainingConfigurations":398},{"removed":"deepswe","score":0.01589348591167921,"rank":338,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01878557043505607,"rank":338,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01864818152469368,"rank":338,"remainingConfigurations":398},{"removed":"frontiercode","score":0.019788083696662007,"rank":338,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.018801669889710007,"rank":338,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.018600588427388532,"rank":338,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.018752678111304925,"rank":338,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.018708369836582233,"rank":338,"remainingConfigurations":398},{"removed":"livebench-math","score":0.018814657061031855,"rank":338,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.018616362829763103,"rank":338,"remainingConfigurations":398},{"removed":"livebench-language","score":0.019014131922301516,"rank":338,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01882205678643235,"rank":338,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.018465428338527105,"rank":338,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01864671980744591,"rank":338,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.019089299628191305,"rank":338,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.019337693644955273,"rank":338,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.017750191919921814,"rank":338,"remainingConfigurations":398},{"removed":"frontiermath","score":0.018981417686986437,"rank":338,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01959176966482978,"rank":338,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.018681512477047982,"rank":338,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.018709963680977566,"rank":338,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01869737176923265,"rank":338,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.018744778255747885,"rank":338,"remainingConfigurations":398},{"removed":"vibe-code","score":0.018645762426635324,"rank":338,"remainingConfigurations":398}]},"deepseek-r1-distill-qwen-32b--effort-reasoning":{"score":0.018205611744636325,"rank":339,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.022264542176725327,"rank":339,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01540426181184359,"rank":339,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01801377605310972,"rank":339,"remainingConfigurations":398},{"removed":"Scale","score":0.020394211891808515,"rank":339,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01816693669917999,"rank":339,"remainingConfigurations":398},{"removed":"Cognition","score":0.01920034999577858,"rank":339,"remainingConfigurations":398},{"removed":"LiveBench","score":0.018693381189340153,"rank":338,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.018757185966536253,"rank":339,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.018403027243454145,"rank":321,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01769540783401127,"rank":338,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.018206756140708782,"rank":339,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.018187487196499052,"rank":339,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01817349505811469,"rank":339,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.018205611744636325,"rank":339,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01815333706853237,"rank":339,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.018273353827243786,"rank":339,"remainingConfigurations":398},{"removed":"briefcase","score":0.018173107558558766,"rank":339,"remainingConfigurations":398},{"removed":"aime","score":0.01558203159523692,"rank":350,"remainingConfigurations":398},{"removed":"apex-agents","score":0.018425017148208978,"rank":339,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.018939165532752822,"rank":339,"remainingConfigurations":398},{"removed":"automationbench","score":0.018203289198908353,"rank":339,"remainingConfigurations":398},{"removed":"critpt","score":0.017523872362224104,"rank":339,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01824483603155341,"rank":339,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.018450828191831744,"rank":339,"remainingConfigurations":398},{"removed":"gdpval","score":0.018327821109711952,"rank":339,"remainingConfigurations":398},{"removed":"gmmlu","score":0.018380860579404586,"rank":339,"remainingConfigurations":398},{"removed":"gpqa","score":0.017273737749883996,"rank":340,"remainingConfigurations":398},{"removed":"harvey","score":0.018001179027979316,"rank":339,"remainingConfigurations":398},{"removed":"hle","score":0.01968469289419176,"rank":339,"remainingConfigurations":398},{"removed":"ifbench","score":0.020209707951620304,"rank":334,"remainingConfigurations":398},{"removed":"itbench","score":0.018183661287873704,"rank":339,"remainingConfigurations":398},{"removed":"livecodebench","score":0.020413623618654796,"rank":333,"remainingConfigurations":398},{"removed":"math500","score":0.016322837837982787,"rank":347,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01881931576378272,"rank":338,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0195775908920254,"rank":339,"remainingConfigurations":398},{"removed":"omniscience","score":0.017016988121777606,"rank":337,"remainingConfigurations":398},{"removed":"scicode","score":0.01858410864416232,"rank":339,"remainingConfigurations":398},{"removed":"tau-bench","score":0.017844494038665688,"rank":338,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.018305318479997782,"rank":339,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02208089806190804,"rank":339,"remainingConfigurations":398},{"removed":"deepswe","score":0.015416165804427206,"rank":339,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01821109067159759,"rank":339,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.018078088458517588,"rank":339,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01920034999577858,"rank":339,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0182274919011112,"rank":339,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.018032187518226613,"rank":339,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01817923830219838,"rank":339,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.018136044153122196,"rank":339,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0182393500266072,"rank":339,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.018046729652460274,"rank":339,"remainingConfigurations":398},{"removed":"livebench-language","score":0.01843284596602642,"rank":339,"remainingConfigurations":398},{"removed":"livebench-data","score":0.018246534096859224,"rank":339,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.017900438922527847,"rank":339,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.018076344789418615,"rank":339,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.018506003126097462,"rank":339,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.018757185966536253,"rank":339,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01718418952774813,"rank":339,"remainingConfigurations":398},{"removed":"frontiermath","score":0.018401600383132308,"rank":339,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01899498291839758,"rank":339,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01811009592647124,"rank":339,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.018137703055520087,"rank":339,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01812555564707974,"rank":339,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.018171433943585908,"rank":339,"remainingConfigurations":398},{"removed":"vibe-code","score":0.018075389522351652,"rank":339,"remainingConfigurations":398}]},"deepseek-r1-distill-qwen-14b--effort-reasoning":{"score":0.01755933212976044,"rank":340,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0214828131193998,"rank":340,"remainingConfigurations":398},{"removed":"Datacurve","score":0.014855902420736216,"rank":340,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.017374700508341688,"rank":340,"remainingConfigurations":398},{"removed":"Scale","score":0.019674306459327762,"rank":340,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01752182750876932,"rank":340,"remainingConfigurations":398},{"removed":"Cognition","score":0.018520785074678223,"rank":340,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0180310233159595,"rank":339,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.018093967138986228,"rank":340,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.017738017131863144,"rank":324,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01706747828837812,"rank":339,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01756043702809554,"rank":340,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.017541836760777967,"rank":340,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.017528334107982452,"rank":340,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01755933212976044,"rank":340,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01750887471697397,"rank":340,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01762516137257247,"rank":340,"remainingConfigurations":398},{"removed":"briefcase","score":0.017521667752850644,"rank":341,"remainingConfigurations":398},{"removed":"aime","score":0.015613415673695256,"rank":349,"remainingConfigurations":398},{"removed":"apex-agents","score":0.017771664465074635,"rank":340,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.018046789176426964,"rank":342,"remainingConfigurations":398},{"removed":"automationbench","score":0.017548256656576985,"rank":340,"remainingConfigurations":398},{"removed":"critpt","score":0.016881978270164567,"rank":340,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.017598059689397195,"rank":340,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.01778691621380354,"rank":340,"remainingConfigurations":398},{"removed":"gdpval","score":0.01766064866815299,"rank":341,"remainingConfigurations":398},{"removed":"gmmlu","score":0.017722587213843077,"rank":340,"remainingConfigurations":398},{"removed":"gpqa","score":0.018025038047269234,"rank":339,"remainingConfigurations":398},{"removed":"harvey","score":0.01736259264079473,"rank":340,"remainingConfigurations":398},{"removed":"hle","score":0.019812480619472078,"rank":338,"remainingConfigurations":398},{"removed":"ifbench","score":0.01951761971718793,"rank":336,"remainingConfigurations":398},{"removed":"itbench","score":0.017538611438819518,"rank":340,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01782332471206998,"rank":338,"remainingConfigurations":398},{"removed":"math500","score":0.015225841956923537,"rank":352,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017887756067108632,"rank":342,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01889647403673901,"rank":341,"remainingConfigurations":398},{"removed":"omniscience","score":0.016400485209086612,"rank":341,"remainingConfigurations":398},{"removed":"scicode","score":0.01791609833706351,"rank":340,"remainingConfigurations":398},{"removed":"tau-bench","score":0.017193079196399064,"rank":340,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.017644920766823776,"rank":341,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02130502030042293,"rank":340,"remainingConfigurations":398},{"removed":"deepswe","score":0.014867390629890329,"rank":340,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.017564622449167844,"rank":340,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.017436331056472566,"rank":340,"remainingConfigurations":398},{"removed":"frontiercode","score":0.018520785074678223,"rank":340,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.017580538012346155,"rank":340,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.01739194228885756,"rank":340,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.017533900971151078,"rank":340,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01749220108664997,"rank":340,"remainingConfigurations":398},{"removed":"livebench-math","score":0.017591915013715095,"rank":340,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.017405860512616514,"rank":340,"remainingConfigurations":398},{"removed":"livebench-language","score":0.01777877028590915,"rank":340,"remainingConfigurations":398},{"removed":"livebench-data","score":0.017598878545124222,"rank":340,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.017264640117970007,"rank":340,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.017434488460734147,"rank":340,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.017849463936495683,"rank":340,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.018093967138986228,"rank":340,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.016573112637362334,"rank":341,"remainingConfigurations":398},{"removed":"frontiermath","score":0.017748688548359943,"rank":340,"remainingConfigurations":398},{"removed":"simpleqa","score":0.018321822785373237,"rank":340,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.017467092848801737,"rank":340,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01749374964462623,"rank":340,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.017482023177535073,"rank":340,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01752630695878996,"rank":340,"remainingConfigurations":398},{"removed":"vibe-code","score":0.017433585499843085,"rank":340,"remainingConfigurations":398}]},"qwen3-8b--effort-reasoning":{"score":0.017520699653287834,"rank":341,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0213492362203719,"rank":341,"remainingConfigurations":398},{"removed":"Datacurve","score":0.014828976424851627,"rank":341,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.017343858634645274,"rank":341,"remainingConfigurations":398},{"removed":"Scale","score":0.01962651016110612,"rank":341,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01749341070609811,"rank":341,"remainingConfigurations":398},{"removed":"Cognition","score":0.01845813098421788,"rank":341,"remainingConfigurations":398},{"removed":"LiveBench","score":0.018016632544066487,"rank":340,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.018066192540573133,"rank":341,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.017847027844603174,"rank":323,"remainingConfigurations":381},{"removed":"Vals AI","score":0.017065940605240318,"rank":340,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.017521783387848273,"rank":341,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01750336876195786,"rank":341,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01748942874997001,"rank":341,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.017520699653287834,"rank":341,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0174701076660439,"rank":341,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.017595723239262215,"rank":341,"remainingConfigurations":398},{"removed":"briefcase","score":0.01758251441218378,"rank":340,"remainingConfigurations":398},{"removed":"aime","score":0.01858214356046724,"rank":337,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01775167744999818,"rank":341,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.018242775607678226,"rank":341,"remainingConfigurations":398},{"removed":"automationbench","score":0.01737113842128928,"rank":342,"remainingConfigurations":398},{"removed":"critpt","score":0.016675992303953637,"rank":341,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.017576089528359328,"rank":341,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.016887709278554625,"rank":344,"remainingConfigurations":398},{"removed":"gdpval","score":0.017796665625822352,"rank":340,"remainingConfigurations":398},{"removed":"gmmlu","score":0.017688400683840828,"rank":341,"remainingConfigurations":398},{"removed":"gpqa","score":0.01704291980143375,"rank":343,"remainingConfigurations":398},{"removed":"harvey","score":0.017338437306080975,"rank":341,"remainingConfigurations":398},{"removed":"hle","score":0.01929202153863209,"rank":341,"remainingConfigurations":398},{"removed":"ifbench","score":0.016984020597276106,"rank":343,"remainingConfigurations":398},{"removed":"itbench","score":0.017508717975053028,"rank":341,"remainingConfigurations":398},{"removed":"livecodebench","score":0.017243771582701715,"rank":340,"remainingConfigurations":398},{"removed":"math500","score":0.017435021637697324,"rank":340,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017856758567506206,"rank":343,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.018854015454524312,"rank":342,"remainingConfigurations":398},{"removed":"omniscience","score":0.016640863882819195,"rank":339,"remainingConfigurations":398},{"removed":"scicode","score":0.017703814722060937,"rank":342,"remainingConfigurations":398},{"removed":"tau-bench","score":0.016814615927417512,"rank":342,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01747801493507111,"rank":343,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02117481741145727,"rank":341,"remainingConfigurations":398},{"removed":"deepswe","score":0.014840563427042,"rank":341,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.017526058177916234,"rank":341,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.017399195016905667,"rank":341,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01845813098421788,"rank":341,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.017542746687122312,"rank":341,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.017353172841653185,"rank":341,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.017495636479430525,"rank":341,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.017456253794194753,"rank":341,"remainingConfigurations":398},{"removed":"livebench-math","score":0.017552942166434056,"rank":341,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.017368664765892546,"rank":341,"remainingConfigurations":398},{"removed":"livebench-language","score":0.017740553485033516,"rank":341,"remainingConfigurations":398},{"removed":"livebench-data","score":0.017560025989513086,"rank":341,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.017226032651184848,"rank":341,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.017396133245589623,"rank":341,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.017809209350474545,"rank":341,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.018066192540573133,"rank":341,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.016610062602796943,"rank":340,"remainingConfigurations":398},{"removed":"frontiermath","score":0.017695918420133554,"rank":341,"remainingConfigurations":398},{"removed":"simpleqa","score":0.018277282710485458,"rank":341,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01742857395772966,"rank":341,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.017455396602595888,"rank":341,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.017443356102566403,"rank":341,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.017488280555586513,"rank":341,"remainingConfigurations":398},{"removed":"vibe-code","score":0.017395085629355832,"rank":341,"remainingConfigurations":398}]},"qwen3-omni-30b-a3b-instruct--effort-non-reasoning":{"score":0.017369442554752663,"rank":342,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.021202282115610465,"rank":342,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01468463045613423,"rank":342,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.017187518209593123,"rank":342,"remainingConfigurations":398},{"removed":"Scale","score":0.01946014393560051,"rank":342,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.017334615281072996,"rank":342,"remainingConfigurations":398},{"removed":"Cognition","score":0.01830595799974497,"rank":342,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01784005327098923,"rank":341,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0178909520331326,"rank":342,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.017519510759016817,"rank":326,"remainingConfigurations":381},{"removed":"Vals AI","score":0.016884800212411302,"rank":341,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.017370542961100476,"rank":342,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0173521901748685,"rank":342,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.017338655563237507,"rank":342,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.017369442554752663,"rank":342,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01731946465135647,"rank":342,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01743752561544438,"rank":342,"remainingConfigurations":398},{"removed":"briefcase","score":0.017356059903182244,"rank":342,"remainingConfigurations":398},{"removed":"aime","score":0.016156144691742078,"rank":346,"remainingConfigurations":398},{"removed":"apex-agents","score":0.017580101693005102,"rank":342,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.018378896666351018,"rank":340,"remainingConfigurations":398},{"removed":"automationbench","score":0.01738557328055358,"rank":341,"remainingConfigurations":398},{"removed":"critpt","score":0.016364686659584366,"rank":342,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.017413082392566344,"rank":342,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.017629296431243318,"rank":341,"remainingConfigurations":398},{"removed":"gdpval","score":0.017505567900144688,"rank":342,"remainingConfigurations":398},{"removed":"gmmlu","score":0.01755216929772536,"rank":342,"remainingConfigurations":398},{"removed":"gpqa","score":0.016530527071880487,"rank":344,"remainingConfigurations":398},{"removed":"harvey","score":0.01717649958746242,"rank":342,"remainingConfigurations":398},{"removed":"hle","score":0.018379912299129917,"rank":344,"remainingConfigurations":398},{"removed":"ifbench","score":0.017648741632182115,"rank":342,"remainingConfigurations":398},{"removed":"itbench","score":0.017351232297721834,"rank":342,"remainingConfigurations":398},{"removed":"livecodebench","score":0.016779423688573575,"rank":344,"remainingConfigurations":398},{"removed":"math500","score":0.0175076959272744,"rank":339,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.018015238110720585,"rank":341,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01797425995175117,"rank":343,"remainingConfigurations":398},{"removed":"omniscience","score":0.01617430279675934,"rank":342,"remainingConfigurations":398},{"removed":"scicode","score":0.017757919328269707,"rank":341,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01779268984594894,"rank":339,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.018297215357312203,"rank":340,"remainingConfigurations":398},{"removed":"arc-agi","score":0.021029081329016566,"rank":342,"remainingConfigurations":398},{"removed":"deepswe","score":0.01469598857420948,"rank":342,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.017374675775278396,"rank":342,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.017247747021945974,"rank":342,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01830595799974497,"rank":342,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01738974475771089,"rank":342,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.017203271935874336,"rank":342,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.017344248789567186,"rank":342,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.017303134339100797,"rank":342,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01740161947192986,"rank":342,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.017217803684885777,"rank":342,"remainingConfigurations":398},{"removed":"livebench-language","score":0.017586657003596285,"rank":342,"remainingConfigurations":398},{"removed":"livebench-data","score":0.017408515466794578,"rank":342,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01707779918274041,"rank":342,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.017245904924794466,"rank":342,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.017656409726263204,"rank":342,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0178909520331326,"rank":342,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01642344410694238,"rank":342,"remainingConfigurations":398},{"removed":"frontiermath","score":0.017555887473828014,"rank":342,"remainingConfigurations":398},{"removed":"simpleqa","score":0.018120611569697378,"rank":342,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.017278178997468745,"rank":342,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0173045427798693,"rank":342,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01729290807514144,"rank":342,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0173367793986059,"rank":342,"remainingConfigurations":398},{"removed":"vibe-code","score":0.017245041954142636,"rank":342,"remainingConfigurations":398}]},"glm-4.6v--effort-non-reasoning":{"score":0.017262836172222278,"rank":343,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.021086390870108242,"rank":343,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0146068769914434,"rank":343,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01708542176324371,"rank":343,"remainingConfigurations":398},{"removed":"Scale","score":0.01934960627594563,"rank":343,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.017224688939545648,"rank":343,"remainingConfigurations":398},{"removed":"Cognition","score":0.01821296022314192,"rank":343,"remainingConfigurations":398},{"removed":"LiveBench","score":0.017727161665696056,"rank":342,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.017779856988488565,"rank":343,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01753456400667914,"rank":325,"remainingConfigurations":381},{"removed":"Vals AI","score":0.016775444196143654,"rank":342,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01726392790929011,"rank":343,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01724565574285868,"rank":343,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.017232259012109796,"rank":343,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.017262836172222278,"rank":343,"remainingConfigurations":398},{"removed":"All provider reports","score":0.017213148869597378,"rank":343,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.017327277231498597,"rank":343,"remainingConfigurations":398},{"removed":"briefcase","score":0.01723568099251745,"rank":343,"remainingConfigurations":398},{"removed":"aime","score":0.017981235065910123,"rank":339,"remainingConfigurations":398},{"removed":"apex-agents","score":0.017477149066959942,"rank":343,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.017197527091747798,"rank":343,"remainingConfigurations":398},{"removed":"automationbench","score":0.017261593817426812,"rank":343,"remainingConfigurations":398},{"removed":"critpt","score":0.01629597065293436,"rank":343,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01730627544432486,"rank":343,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.017501275130595604,"rank":342,"remainingConfigurations":398},{"removed":"gdpval","score":0.017384011761293356,"rank":343,"remainingConfigurations":398},{"removed":"gmmlu","score":0.017155713882082303,"rank":344,"remainingConfigurations":398},{"removed":"gpqa","score":0.017103752978236218,"rank":341,"remainingConfigurations":398},{"removed":"harvey","score":0.017071789450915295,"rank":343,"remainingConfigurations":398},{"removed":"hle","score":0.01951379617213764,"rank":340,"remainingConfigurations":398},{"removed":"ifbench","score":0.017822548601455896,"rank":341,"remainingConfigurations":398},{"removed":"itbench","score":0.0172448160715728,"rank":343,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01683753035254714,"rank":343,"remainingConfigurations":398},{"removed":"math500","score":0.01741554619802484,"rank":341,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017195664271900276,"rank":346,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.019367877720173107,"rank":340,"remainingConfigurations":398},{"removed":"omniscience","score":0.014914639732515673,"rank":350,"remainingConfigurations":398},{"removed":"scicode","score":0.017633056669727306,"rank":343,"remainingConfigurations":398},{"removed":"tau-bench","score":0.016119595563562517,"rank":344,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01758478255310884,"rank":342,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0209096450874503,"rank":343,"remainingConfigurations":398},{"removed":"deepswe","score":0.014618158044581187,"rank":343,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01726803448284728,"rank":343,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.017141828597876257,"rank":343,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01821296022314192,"rank":343,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.017283488206986965,"rank":343,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0170985050336106,"rank":343,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.017237738489589195,"rank":343,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.017196611942187218,"rank":343,"remainingConfigurations":398},{"removed":"livebench-math","score":0.017294823724569745,"rank":343,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.017112041917936357,"rank":343,"remainingConfigurations":398},{"removed":"livebench-language","score":0.017478681738014642,"rank":343,"remainingConfigurations":398},{"removed":"livebench-data","score":0.017301687153007304,"rank":343,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.016972934969562613,"rank":343,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.017140045908165764,"rank":343,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01754821499407896,"rank":343,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.017779856988488565,"rank":343,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.016305247374796498,"rank":343,"remainingConfigurations":398},{"removed":"frontiermath","score":0.017448577761174575,"rank":343,"remainingConfigurations":398},{"removed":"simpleqa","score":0.018008240552389313,"rank":343,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01717211891607551,"rank":343,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.017198295478290822,"rank":343,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.017186799422649307,"rank":343,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.017230303257059508,"rank":343,"remainingConfigurations":398},{"removed":"vibe-code","score":0.017139140987206498,"rank":343,"remainingConfigurations":398}]},"gemini-2.5-flash-lite--effort-non-reasoning":{"score":0.016828564890230945,"rank":344,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02059904871992749,"rank":344,"remainingConfigurations":398},{"removed":"Datacurve","score":0.014241850218489123,"rank":344,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01665409338578872,"rank":344,"remainingConfigurations":398},{"removed":"Scale","score":0.018863811226158864,"rank":344,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.016792545098714355,"rank":344,"remainingConfigurations":398},{"removed":"Cognition","score":0.017760118311478213,"rank":344,"remainingConfigurations":398},{"removed":"LiveBench","score":0.017283093402307954,"rank":343,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.017353831625007483,"rank":344,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.017065875966111924,"rank":327,"remainingConfigurations":381},{"removed":"Vals AI","score":0.016356370160487108,"rank":343,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.016829628944336806,"rank":344,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.016811803704998695,"rank":344,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.016798767223808943,"rank":344,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.016828564890230945,"rank":344,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01678012267645068,"rank":344,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.016891763233539744,"rank":344,"remainingConfigurations":398},{"removed":"briefcase","score":0.016809385140873313,"rank":344,"remainingConfigurations":398},{"removed":"aime","score":0.01680454994744861,"rank":343,"remainingConfigurations":398},{"removed":"apex-agents","score":0.017036680343258,"rank":344,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.016044469915607082,"rank":348,"remainingConfigurations":398},{"removed":"automationbench","score":0.01684061975599352,"rank":344,"remainingConfigurations":398},{"removed":"critpt","score":0.015809729177701428,"rank":344,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01687181174344247,"rank":344,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.01706948322683607,"rank":343,"remainingConfigurations":398},{"removed":"gdpval","score":0.01696934898322933,"rank":344,"remainingConfigurations":398},{"removed":"gmmlu","score":0.017016495102762916,"rank":345,"remainingConfigurations":398},{"removed":"gpqa","score":0.017053188604615292,"rank":342,"remainingConfigurations":398},{"removed":"harvey","score":0.016642195187776394,"rank":344,"remainingConfigurations":398},{"removed":"hle","score":0.018904490118036184,"rank":343,"remainingConfigurations":398},{"removed":"ifbench","score":0.016941578393163653,"rank":344,"remainingConfigurations":398},{"removed":"itbench","score":0.01681135135529861,"rank":344,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01660993601885071,"rank":347,"remainingConfigurations":398},{"removed":"math500","score":0.016278087966283553,"rank":348,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017497029518060994,"rank":345,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.017605502306549507,"rank":346,"remainingConfigurations":398},{"removed":"omniscience","score":0.015259237267387482,"rank":347,"remainingConfigurations":398},{"removed":"scicode","score":0.01719860214379489,"rank":344,"remainingConfigurations":398},{"removed":"tau-bench","score":0.016969021342718837,"rank":341,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.017297806380644005,"rank":344,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02042498830268739,"rank":344,"remainingConfigurations":398},{"removed":"deepswe","score":0.014252855161706773,"rank":344,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01683363589856454,"rank":344,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01671064135733514,"rank":344,"remainingConfigurations":398},{"removed":"frontiercode","score":0.017760118311478213,"rank":344,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.016849165131057362,"rank":344,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.016668292946914624,"rank":344,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01680416957128734,"rank":344,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01676405406636229,"rank":344,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01685979194462327,"rank":344,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.016681333016671063,"rank":344,"remainingConfigurations":398},{"removed":"livebench-language","score":0.017039159990714165,"rank":344,"remainingConfigurations":398},{"removed":"livebench-data","score":0.016866537593109215,"rank":344,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.016545747132532863,"rank":344,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.016708740215847773,"rank":344,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.017107031977291562,"rank":344,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.017353831625007483,"rank":344,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.015911563696523984,"rank":345,"remainingConfigurations":398},{"removed":"frontiermath","score":0.017011273494582736,"rank":344,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01755778135345307,"rank":344,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.016740055993245875,"rank":344,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01676560918962142,"rank":344,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0167543742523352,"rank":344,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01679682180721993,"rank":344,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0167078965745607,"rank":344,"remainingConfigurations":398}]},"qwen3-4b-instruct-2507--effort-non-reasoning":{"score":0.01655304171226964,"rank":345,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.020200066763825894,"rank":345,"remainingConfigurations":398},{"removed":"Datacurve","score":0.013989263630725354,"rank":345,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.016380860827630253,"rank":345,"remainingConfigurations":398},{"removed":"Scale","score":0.01855086853234225,"rank":345,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.016517602640802518,"rank":345,"remainingConfigurations":398},{"removed":"Cognition","score":0.017443906528936674,"rank":346,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01700067719738885,"rank":344,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.017047663120739753,"rank":345,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.016720848303267425,"rank":328,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01608857973866706,"rank":344,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.016554088415421043,"rank":345,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01653659560430208,"rank":345,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01652373960710916,"rank":345,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01655304171226964,"rank":345,"remainingConfigurations":398},{"removed":"All provider reports","score":0.016505440556535852,"rank":345,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01661717157892566,"rank":345,"remainingConfigurations":398},{"removed":"briefcase","score":0.016507566443033427,"rank":345,"remainingConfigurations":398},{"removed":"aime","score":0.0153119563820035,"rank":351,"remainingConfigurations":398},{"removed":"apex-agents","score":0.016753797122122764,"rank":345,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01672577029198857,"rank":345,"remainingConfigurations":398},{"removed":"automationbench","score":0.016529177194830876,"rank":345,"remainingConfigurations":398},{"removed":"critpt","score":0.015538075290476322,"rank":346,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.016594350683519853,"rank":345,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.016762761082850505,"rank":346,"remainingConfigurations":398},{"removed":"gdpval","score":0.016654426478929583,"rank":346,"remainingConfigurations":398},{"removed":"gmmlu","score":0.01722795336869418,"rank":343,"remainingConfigurations":398},{"removed":"gpqa","score":0.016448015714519707,"rank":345,"remainingConfigurations":398},{"removed":"harvey","score":0.016368237884863458,"rank":345,"remainingConfigurations":398},{"removed":"hle","score":0.017745801164735262,"rank":347,"remainingConfigurations":398},{"removed":"ifbench","score":0.016012706692986472,"rank":347,"remainingConfigurations":398},{"removed":"itbench","score":0.01653546277764921,"rank":345,"remainingConfigurations":398},{"removed":"livecodebench","score":0.016439569103803738,"rank":348,"remainingConfigurations":398},{"removed":"math500","score":0.01667520906506226,"rank":343,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01818229901956483,"rank":340,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01782601066711376,"rank":344,"remainingConfigurations":398},{"removed":"omniscience","score":0.01603797837425559,"rank":343,"remainingConfigurations":398},{"removed":"scicode","score":0.016885636616822804,"rank":345,"remainingConfigurations":398},{"removed":"tau-bench","score":0.015725577985102213,"rank":346,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.016475715096124086,"rank":345,"remainingConfigurations":398},{"removed":"arc-agi","score":0.02003636508954199,"rank":345,"remainingConfigurations":398},{"removed":"deepswe","score":0.014000105387117863,"rank":345,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.016558040392133724,"rank":345,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.016436821563261282,"rank":345,"remainingConfigurations":398},{"removed":"frontiercode","score":0.017443906528936674,"rank":346,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.016572136215972404,"rank":345,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.016394543867479235,"rank":345,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.016528976183306104,"rank":345,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.016489839093138874,"rank":345,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01658378255433685,"rank":345,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01640821048606163,"rank":345,"remainingConfigurations":398},{"removed":"livebench-language","score":0.016760348810303898,"rank":345,"remainingConfigurations":398},{"removed":"livebench-data","score":0.016590362513331673,"rank":345,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.016274676494175192,"rank":345,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01643511848407616,"rank":345,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.016827056755910154,"rank":345,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.017047663120739753,"rank":345,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.015655982117380285,"rank":346,"remainingConfigurations":398},{"removed":"frontiermath","score":0.016730368453472744,"rank":345,"remainingConfigurations":398},{"removed":"simpleqa","score":0.017270530473978973,"rank":346,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01646592872791919,"rank":345,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01649108382231786,"rank":345,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.016479983898710904,"rank":345,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.016521851139749175,"rank":345,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01643429809157101,"rank":345,"remainingConfigurations":398}]},"mistral-small-2506--effort-non-reasoning":{"score":0.01641150308725937,"rank":346,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01997590632516498,"rank":347,"remainingConfigurations":398},{"removed":"Datacurve","score":0.013874143473591734,"rank":347,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.016241264954196158,"rank":347,"remainingConfigurations":398},{"removed":"Scale","score":0.018399339353792277,"rank":346,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01638409465301892,"rank":347,"remainingConfigurations":398},{"removed":"Cognition","score":0.01728032814349936,"rank":347,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01687473774053984,"rank":345,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01690682531249432,"rank":346,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.016701844980062962,"rank":329,"remainingConfigurations":381},{"removed":"Vals AI","score":0.015982578413524764,"rank":346,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.016412527575738804,"rank":346,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.016395231357179133,"rank":346,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.016382165263444083,"rank":346,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01641150308725937,"rank":346,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0163640367731652,"rank":346,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.016479744334819142,"rank":346,"remainingConfigurations":398},{"removed":"briefcase","score":0.01638137013650866,"rank":346,"remainingConfigurations":398},{"removed":"aime","score":0.016781567001629843,"rank":344,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01662370004867921,"rank":346,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.016131823581506163,"rank":347,"remainingConfigurations":398},{"removed":"automationbench","score":0.01627387135986359,"rank":347,"remainingConfigurations":398},{"removed":"critpt","score":0.015585022088866397,"rank":345,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.016454361342467645,"rank":346,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.016790382025825962,"rank":345,"remainingConfigurations":398},{"removed":"gdpval","score":0.016715781345249835,"rank":345,"remainingConfigurations":398},{"removed":"gmmlu","score":0.016519223945794814,"rank":347,"remainingConfigurations":398},{"removed":"gpqa","score":0.016393337692329844,"rank":346,"remainingConfigurations":398},{"removed":"harvey","score":0.01623468862164004,"rank":346,"remainingConfigurations":398},{"removed":"hle","score":0.01760489023583373,"rank":348,"remainingConfigurations":398},{"removed":"ifbench","score":0.015878756027775952,"rank":348,"remainingConfigurations":398},{"removed":"itbench","score":0.01639773305759409,"rank":346,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01718257754748567,"rank":341,"remainingConfigurations":398},{"removed":"math500","score":0.016489227072367645,"rank":345,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017570975729402565,"rank":344,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.017745218208988268,"rank":345,"remainingConfigurations":398},{"removed":"omniscience","score":0.015299157775056511,"rank":346,"remainingConfigurations":398},{"removed":"scicode","score":0.01648638917254152,"rank":347,"remainingConfigurations":398},{"removed":"tau-bench","score":0.015371699416906458,"rank":348,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.015902983741378895,"rank":347,"remainingConfigurations":398},{"removed":"arc-agi","score":0.019817662428434545,"rank":347,"remainingConfigurations":398},{"removed":"deepswe","score":0.013884992368312287,"rank":347,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.016416518477379845,"rank":346,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.016296906724091387,"rank":346,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01728032814349936,"rank":347,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.016431148128584924,"rank":346,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.016253768791180265,"rank":346,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.016387932956183845,"rank":346,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.016351203377052596,"rank":346,"remainingConfigurations":398},{"removed":"livebench-math","score":0.016441785814562886,"rank":346,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01626878982941585,"rank":346,"remainingConfigurations":398},{"removed":"livebench-language","score":0.016617794758169904,"rank":346,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01644823028497153,"rank":346,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.016135003343502676,"rank":346,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01629462446642899,"rank":346,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01668246103156282,"rank":346,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01690682531249432,"rank":346,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.015551201010775487,"rank":348,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01657621103771541,"rank":347,"remainingConfigurations":398},{"removed":"simpleqa","score":0.017122744508213987,"rank":347,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01632501828611554,"rank":346,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.016350140131678115,"rank":346,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01633896493048893,"rank":346,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01638093192714266,"rank":346,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01629363309167301,"rank":346,"remainingConfigurations":398}]},"qwen3-30b-a3b--effort-non-reasoning":{"score":0.016387532953628273,"rank":347,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.020358814120136404,"rank":153,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.02016696521919443,"rank":346,"remainingConfigurations":398},{"removed":"Datacurve","score":0.013974285725483428,"rank":346,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.016242975923610087,"rank":346,"remainingConfigurations":398},{"removed":"Scale","score":0.018348669303339532,"rank":347,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01640803690494924,"rank":346,"remainingConfigurations":398},{"removed":"Cognition","score":0.017444863165469532,"rank":345,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01682615580808902,"rank":346,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.016809873220439402,"rank":347,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.014257435396917493,"rank":339,"remainingConfigurations":381},{"removed":"Vals AI","score":0.016055730431026313,"rank":345,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.016388316455370425,"rank":347,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01637001921976218,"rank":347,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01636123232528779,"rank":347,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.016387532953628273,"rank":347,"remainingConfigurations":398},{"removed":"All provider reports","score":0.016341719187758473,"rank":347,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01644658788711698,"rank":347,"remainingConfigurations":398},{"removed":"briefcase","score":0.01634701750031385,"rank":347,"remainingConfigurations":398},{"removed":"aime","score":0.01685185823951235,"rank":342,"remainingConfigurations":398},{"removed":"apex-agents","score":0.016573287608932303,"rank":347,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01688193122062673,"rank":344,"remainingConfigurations":398},{"removed":"automationbench","score":0.016368454976386716,"rank":346,"remainingConfigurations":398},{"removed":"critpt","score":0.015396001142338129,"rank":347,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.016423617247028222,"rank":347,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.016562431949655777,"rank":347,"remainingConfigurations":398},{"removed":"gdpval","score":0.01643035639023777,"rank":347,"remainingConfigurations":398},{"removed":"gmmlu","score":0.016536276496788117,"rank":346,"remainingConfigurations":398},{"removed":"gpqa","score":0.016359357007311483,"rank":347,"remainingConfigurations":398},{"removed":"harvey","score":0.016198685979274565,"rank":347,"remainingConfigurations":398},{"removed":"hle","score":0.017163535100279168,"rank":351,"remainingConfigurations":398},{"removed":"ifbench","score":0.0162126331643069,"rank":346,"remainingConfigurations":398},{"removed":"itbench","score":0.016366270817804503,"rank":347,"remainingConfigurations":398},{"removed":"livecodebench","score":0.016633246807743387,"rank":345,"remainingConfigurations":398},{"removed":"math500","score":0.01653715849174593,"rank":344,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.016954828452154076,"rank":348,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.017594076593287534,"rank":347,"remainingConfigurations":398},{"removed":"omniscience","score":0.01570410602063518,"rank":344,"remainingConfigurations":398},{"removed":"scicode","score":0.016671649823742012,"rank":346,"remainingConfigurations":398},{"removed":"tau-bench","score":0.015722928763149468,"rank":347,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01588358085240452,"rank":348,"remainingConfigurations":398},{"removed":"arc-agi","score":0.019983292587897983,"rank":346,"remainingConfigurations":398},{"removed":"deepswe","score":0.013985519999545044,"rank":346,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01639237524310239,"rank":347,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01627577896989901,"rank":347,"remainingConfigurations":398},{"removed":"frontiercode","score":0.017444863165469532,"rank":345,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.016419354839461667,"rank":347,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.016226823273298812,"rank":347,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.016364617349202693,"rank":347,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.016324279631242267,"rank":347,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01642247831592364,"rank":347,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01623211246994592,"rank":347,"remainingConfigurations":398},{"removed":"livebench-language","score":0.016592178202131255,"rank":347,"remainingConfigurations":398},{"removed":"livebench-data","score":0.016427882110757044,"rank":347,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.016115736751434392,"rank":347,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.016269994899641507,"rank":347,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01666008522169224,"rank":347,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.016809873220439402,"rank":347,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.014635646595446299,"rank":351,"remainingConfigurations":398},{"removed":"frontiermath","score":0.016690380181039473,"rank":346,"remainingConfigurations":398},{"removed":"simpleqa","score":0.017275324480637025,"rank":345,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.016301254693834658,"rank":347,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.016328086679999448,"rank":347,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.016312170342131786,"rank":347,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01635752900126926,"rank":347,"remainingConfigurations":398},{"removed":"vibe-code","score":0.016273233072927037,"rank":347,"remainingConfigurations":398}]},"qwen3-14b--effort-non-reasoning":{"score":0.016043162693983887,"rank":348,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.01830147914251385,"rank":155,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.019749767588263585,"rank":348,"remainingConfigurations":398},{"removed":"Datacurve","score":0.013681520244174461,"rank":348,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.015901560214436488,"rank":348,"remainingConfigurations":398},{"removed":"Scale","score":0.017966153127225864,"rank":348,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.016063745542251127,"rank":348,"remainingConfigurations":398},{"removed":"Cognition","score":0.0170799068170023,"rank":348,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01647382027886807,"rank":347,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.016457960700625978,"rank":348,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.014775907471019359,"rank":336,"remainingConfigurations":381},{"removed":"Vals AI","score":0.015720080264823046,"rank":347,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.016043932535203673,"rank":348,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.016026018449925943,"rank":348,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.016017386188670303,"rank":348,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.016043162693983887,"rank":348,"remainingConfigurations":398},{"removed":"All provider reports","score":0.015998284833025882,"rank":348,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.016101705373111574,"rank":348,"remainingConfigurations":398},{"removed":"briefcase","score":0.016008947417434582,"rank":348,"remainingConfigurations":398},{"removed":"aime","score":0.014076645485550788,"rank":360,"remainingConfigurations":398},{"removed":"apex-agents","score":0.016225916564987054,"rank":348,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01655842679786686,"rank":346,"remainingConfigurations":398},{"removed":"automationbench","score":0.016028593906958523,"rank":348,"remainingConfigurations":398},{"removed":"critpt","score":0.015093182066340423,"rank":348,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.016079386338147497,"rank":348,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.016220672419765252,"rank":349,"remainingConfigurations":398},{"removed":"gdpval","score":0.016091602018981094,"rank":348,"remainingConfigurations":398},{"removed":"gmmlu","score":0.016181663963403727,"rank":348,"remainingConfigurations":398},{"removed":"gpqa","score":0.01518981406221933,"rank":352,"remainingConfigurations":398},{"removed":"harvey","score":0.0158589518210678,"rank":348,"remainingConfigurations":398},{"removed":"hle","score":0.01730734452568722,"rank":350,"remainingConfigurations":398},{"removed":"ifbench","score":0.016409797003412042,"rank":345,"remainingConfigurations":398},{"removed":"itbench","score":0.016022506026258595,"rank":348,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01663070459985305,"rank":346,"remainingConfigurations":398},{"removed":"math500","score":0.016109017102902076,"rank":349,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.017099803504501767,"rank":347,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.017224138813568032,"rank":348,"remainingConfigurations":398},{"removed":"omniscience","score":0.015216448948428414,"rank":348,"remainingConfigurations":398},{"removed":"scicode","score":0.01632726786230578,"rank":348,"remainingConfigurations":398},{"removed":"tau-bench","score":0.014813259175687724,"rank":350,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.015855986289682402,"rank":350,"remainingConfigurations":398},{"removed":"arc-agi","score":0.019569107258951193,"rank":348,"remainingConfigurations":398},{"removed":"deepswe","score":0.0136925189435304,"rank":348,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01604790648544244,"rank":348,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01593371850090988,"rank":348,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0170799068170023,"rank":348,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01607438673503082,"rank":348,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.015885795087457917,"rank":348,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01602072480376922,"rank":348,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.015981219912322608,"rank":348,"remainingConfigurations":398},{"removed":"livebench-math","score":0.016077361479867432,"rank":348,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.015890979068057882,"rank":348,"remainingConfigurations":398},{"removed":"livebench-language","score":0.016243639831776884,"rank":348,"remainingConfigurations":398},{"removed":"livebench-data","score":0.016082674542139463,"rank":348,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.015776881533101292,"rank":348,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01592801927693896,"rank":348,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.016310183241868722,"rank":348,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.016457960700625978,"rank":348,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.016155459073288237,"rank":344,"remainingConfigurations":398},{"removed":"frontiermath","score":0.016344068605154683,"rank":348,"remainingConfigurations":398},{"removed":"simpleqa","score":0.016915406544733037,"rank":348,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.015958641434280423,"rank":348,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.015984909140985895,"rank":348,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01596936377468741,"rank":348,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.016013748697222673,"rank":348,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01593116619519256,"rank":348,"remainingConfigurations":398}]},"llama-4-scout--effort-non-reasoning":{"score":0.015887257144236357,"rank":349,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01933498520183605,"rank":349,"remainingConfigurations":398},{"removed":"Datacurve","score":0.013430337200812048,"rank":349,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01572276725908035,"rank":349,"remainingConfigurations":398},{"removed":"Scale","score":0.017806587262799507,"rank":349,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01586088905890053,"rank":349,"remainingConfigurations":398},{"removed":"Cognition","score":0.01673031493416371,"rank":349,"remainingConfigurations":398},{"removed":"LiveBench","score":0.016337174483286095,"rank":348,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.016359167281788458,"rank":349,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01614749467949025,"rank":331,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01547320825379119,"rank":348,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.015888250029156396,"rank":349,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01587149430285042,"rank":349,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.015858845250998555,"rank":349,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.015887257144236357,"rank":349,"remainingConfigurations":398},{"removed":"All provider reports","score":0.015841283273873945,"rank":349,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.015953785796922828,"rank":349,"remainingConfigurations":398},{"removed":"briefcase","score":0.015842062400964,"rank":349,"remainingConfigurations":398},{"removed":"aime","score":0.017083591713512765,"rank":340,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01609164076359722,"rank":349,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.015322712458087568,"rank":351,"remainingConfigurations":398},{"removed":"automationbench","score":0.015985003290088017,"rank":349,"remainingConfigurations":398},{"removed":"critpt","score":0.015046643684851382,"rank":349,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.015928661046751214,"rank":349,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.01623850691004232,"rank":348,"remainingConfigurations":398},{"removed":"gdpval","score":0.0160796494258871,"rank":349,"remainingConfigurations":398},{"removed":"gmmlu","score":0.015761743448810765,"rank":351,"remainingConfigurations":398},{"removed":"gpqa","score":0.015420099159760572,"rank":350,"remainingConfigurations":398},{"removed":"harvey","score":0.01571571461228716,"rank":349,"remainingConfigurations":398},{"removed":"hle","score":0.017460080398176855,"rank":349,"remainingConfigurations":398},{"removed":"ifbench","score":0.01469963839238908,"rank":354,"remainingConfigurations":398},{"removed":"itbench","score":0.015873555467811166,"rank":349,"remainingConfigurations":398},{"removed":"livecodebench","score":0.016394466928071994,"rank":349,"remainingConfigurations":398},{"removed":"math500","score":0.01646039061615078,"rank":346,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.015867129199913496,"rank":351,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01676875311169174,"rank":351,"remainingConfigurations":398},{"removed":"omniscience","score":0.014684166433878681,"rank":351,"remainingConfigurations":398},{"removed":"scicode","score":0.016266234331814938,"rank":349,"remainingConfigurations":398},{"removed":"tau-bench","score":0.015858240585483258,"rank":345,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.015863043711975073,"rank":349,"remainingConfigurations":398},{"removed":"arc-agi","score":0.019181395248666862,"rank":349,"remainingConfigurations":398},{"removed":"deepswe","score":0.013440843252700447,"rank":349,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.015892115742559776,"rank":349,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.015776298518756168,"rank":349,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01673031493416371,"rank":349,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0159063623556176,"rank":349,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.015734470617066645,"rank":349,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.015864441520239154,"rank":349,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.015828928681288695,"rank":349,"remainingConfigurations":398},{"removed":"livebench-math","score":0.015916605554235047,"rank":349,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01574892145336388,"rank":349,"remainingConfigurations":398},{"removed":"livebench-language","score":0.016087147808545234,"rank":349,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01592287129325427,"rank":349,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.015619337056446135,"rank":349,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.015773989187702973,"rank":349,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.016149868848174504,"rank":349,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.016359167281788458,"rank":349,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.015046118420292645,"rank":349,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01604700423254093,"rank":349,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01657669932984689,"rank":349,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0158034527891623,"rank":349,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01582779090325011,"rank":349,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.015816968335481945,"rank":349,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.015857612255275665,"rank":349,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01577304545640928,"rank":349,"remainingConfigurations":398}]},"qwen3-vl-8b-instruct--effort-non-reasoning":{"score":0.015642810131225305,"rank":350,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.019113602548072598,"rank":350,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01322155798032327,"rank":350,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.015479935612891163,"rank":350,"remainingConfigurations":398},{"removed":"Scale","score":0.017535310518778994,"rank":350,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.015611318043842295,"rank":350,"remainingConfigurations":398},{"removed":"Cognition","score":0.016491248371759935,"rank":350,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01607021770387396,"rank":349,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0161173186234308,"rank":350,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.015792091749320895,"rank":332,"remainingConfigurations":381},{"removed":"Vals AI","score":0.015207648950730327,"rank":349,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.015643803528168562,"rank":350,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01562723708877588,"rank":350,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.015615037445086863,"rank":350,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.015642810131225305,"rank":350,"remainingConfigurations":398},{"removed":"All provider reports","score":0.015597711712333734,"rank":350,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.015707296725316733,"rank":350,"remainingConfigurations":398},{"removed":"briefcase","score":0.015616207310988202,"rank":350,"remainingConfigurations":398},{"removed":"aime","score":0.01594127114757118,"rank":348,"remainingConfigurations":398},{"removed":"apex-agents","score":0.015835482252070397,"rank":350,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.015479814973299366,"rank":350,"remainingConfigurations":398},{"removed":"automationbench","score":0.015642161258844062,"rank":350,"remainingConfigurations":398},{"removed":"critpt","score":0.014583378509948905,"rank":350,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.015689523903038925,"rank":350,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.015861984872848418,"rank":350,"remainingConfigurations":398},{"removed":"gdpval","score":0.015756182855988975,"rank":350,"remainingConfigurations":398},{"removed":"gmmlu","score":0.015799091670286817,"rank":350,"remainingConfigurations":398},{"removed":"gpqa","score":0.01611965892936525,"rank":348,"remainingConfigurations":398},{"removed":"harvey","score":0.01547217183912338,"rank":350,"remainingConfigurations":398},{"removed":"hle","score":0.018091221453518276,"rank":345,"remainingConfigurations":398},{"removed":"ifbench","score":0.0154162047666008,"rank":349,"remainingConfigurations":398},{"removed":"itbench","score":0.015627583925362416,"rank":350,"remainingConfigurations":398},{"removed":"livecodebench","score":0.015884390732544783,"rank":350,"remainingConfigurations":398},{"removed":"math500","score":0.015760558978340476,"rank":350,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01673150550136274,"rank":350,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.016962522979046744,"rank":350,"remainingConfigurations":398},{"removed":"omniscience","score":0.01249101246756417,"rank":361,"remainingConfigurations":398},{"removed":"scicode","score":0.015978999900168576,"rank":350,"remainingConfigurations":398},{"removed":"tau-bench","score":0.014558822659874,"rank":353,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.016076723836997635,"rank":346,"remainingConfigurations":398},{"removed":"arc-agi","score":0.018956071685983195,"rank":350,"remainingConfigurations":398},{"removed":"deepswe","score":0.013231803367229863,"rank":350,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01564753739144879,"rank":350,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.015533192669533112,"rank":350,"remainingConfigurations":398},{"removed":"frontiercode","score":0.016491248371759935,"rank":350,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.015661367740480967,"rank":350,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.015492870779446652,"rank":350,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.015620137005679413,"rank":350,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.015583042798204402,"rank":350,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01567189018301624,"rank":350,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.015505691719975331,"rank":350,"remainingConfigurations":398},{"removed":"livebench-language","score":0.01583907484414176,"rank":350,"remainingConfigurations":398},{"removed":"livebench-data","score":0.015678183986066758,"rank":350,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.015379317201841004,"rank":350,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.015531158096506044,"rank":350,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.015902220126154516,"rank":350,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0161173186234308,"rank":350,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.014788316169041799,"rank":350,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01581155008149215,"rank":350,"remainingConfigurations":398},{"removed":"simpleqa","score":0.016322081205371534,"rank":350,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.015560346208175006,"rank":350,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.015584160041052113,"rank":350,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.015573659963830732,"rank":350,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01561324872350225,"rank":350,"remainingConfigurations":398},{"removed":"vibe-code","score":0.015530422298675456,"rank":350,"remainingConfigurations":398}]},"ministral-3-8b--effort-non-reasoning":{"score":0.015319057112822353,"rank":351,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01865055505832265,"rank":351,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012948489191002702,"rank":351,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.015162508933454699,"rank":351,"remainingConfigurations":398},{"removed":"Scale","score":0.01717301958024698,"rank":351,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.015294342489409586,"rank":351,"remainingConfigurations":398},{"removed":"Cognition","score":0.016131610470482154,"rank":351,"remainingConfigurations":398},{"removed":"LiveBench","score":0.015756848731662908,"rank":350,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01579033201605736,"rank":351,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.015635768933014705,"rank":333,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014922953293396475,"rank":350,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.015320015994543574,"rank":351,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.015303860901134017,"rank":351,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.015291615353779061,"rank":351,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.015319057112822353,"rank":351,"remainingConfigurations":398},{"removed":"All provider reports","score":0.015274681377996964,"rank":351,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01538436357630417,"rank":351,"remainingConfigurations":398},{"removed":"briefcase","score":0.014848154112017392,"rank":352,"remainingConfigurations":398},{"removed":"aime","score":0.015253394182734624,"rank":352,"remainingConfigurations":398},{"removed":"apex-agents","score":0.015521614447621075,"rank":351,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.014794561470706956,"rank":354,"remainingConfigurations":398},{"removed":"automationbench","score":0.014970954622435065,"rank":352,"remainingConfigurations":398},{"removed":"critpt","score":0.014458213246749297,"rank":351,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.015362200033264906,"rank":351,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.015358599897781678,"rank":351,"remainingConfigurations":398},{"removed":"gdpval","score":0.014894924585236507,"rank":354,"remainingConfigurations":398},{"removed":"gmmlu","score":0.015899081790121592,"rank":349,"remainingConfigurations":398},{"removed":"gpqa","score":0.015406991051779576,"rank":351,"remainingConfigurations":398},{"removed":"harvey","score":0.015157005946580116,"rank":351,"remainingConfigurations":398},{"removed":"hle","score":0.0164366969993058,"rank":353,"remainingConfigurations":398},{"removed":"ifbench","score":0.015354925308725379,"rank":350,"remainingConfigurations":398},{"removed":"itbench","score":0.01530875276343511,"rank":351,"remainingConfigurations":398},{"removed":"livecodebench","score":0.015736611003805787,"rank":351,"remainingConfigurations":398},{"removed":"math500","score":0.01542837797747202,"rank":351,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.016752310076681036,"rank":349,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01663128216788722,"rank":352,"remainingConfigurations":398},{"removed":"omniscience","score":0.014613878075835028,"rank":352,"remainingConfigurations":398},{"removed":"scicode","score":0.01572604394899576,"rank":351,"remainingConfigurations":398},{"removed":"tau-bench","score":0.014728069615405015,"rank":351,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.014977641821675927,"rank":354,"remainingConfigurations":398},{"removed":"arc-agi","score":0.018502507558436073,"rank":351,"remainingConfigurations":398},{"removed":"deepswe","score":0.012958624778465795,"rank":351,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.015323748059177073,"rank":351,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.015212196281589008,"rank":351,"remainingConfigurations":398},{"removed":"frontiercode","score":0.016131610470482154,"rank":351,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.015337634756106703,"rank":351,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.015171593140369427,"rank":351,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0152970650111518,"rank":351,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.015262892819700108,"rank":351,"remainingConfigurations":398},{"removed":"livebench-math","score":0.015347364066829931,"rank":351,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.015185554362792583,"rank":351,"remainingConfigurations":398},{"removed":"livebench-language","score":0.015512039326851407,"rank":351,"remainingConfigurations":398},{"removed":"livebench-data","score":0.015353458695108796,"rank":351,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.015060420935497233,"rank":351,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.015209706032820224,"rank":351,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.015572552408716368,"rank":351,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01579033201605736,"rank":351,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.014525052744157857,"rank":352,"remainingConfigurations":398},{"removed":"frontiermath","score":0.015472029588158484,"rank":351,"remainingConfigurations":398},{"removed":"simpleqa","score":0.015983716060669107,"rank":351,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01523816429528968,"rank":351,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.015261654469121097,"rank":351,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.015251200144574489,"rank":351,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.015290440261042891,"rank":351,"remainingConfigurations":398},{"removed":"vibe-code","score":0.015208810326875093,"rank":351,"remainingConfigurations":398}]},"qwen3.5-2b--effort-reasoning":{"score":0.015111113853890497,"rank":352,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.018607944362782965,"rank":352,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012807740165070474,"rank":352,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.014965190525275092,"rank":352,"remainingConfigurations":398},{"removed":"Scale","score":0.0169597829825271,"rank":352,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.015081389670297055,"rank":352,"remainingConfigurations":398},{"removed":"Cognition","score":0.01598929754655778,"rank":352,"remainingConfigurations":398},{"removed":"LiveBench","score":0.015529455599060908,"rank":351,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.015602360900365509,"rank":352,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.015238486245784997,"rank":334,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014694532745135998,"rank":351,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.015112074986642023,"rank":352,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.015096146934702771,"rank":352,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.015084188902119926,"rank":352,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.015111113853890497,"rank":352,"remainingConfigurations":398},{"removed":"All provider reports","score":0.015067522869663395,"rank":352,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.015176539512711867,"rank":352,"remainingConfigurations":398},{"removed":"briefcase","score":0.015084252236700608,"rank":351,"remainingConfigurations":398},{"removed":"aime","score":0.015034426389230318,"rank":353,"remainingConfigurations":398},{"removed":"apex-agents","score":0.015307760478611952,"rank":352,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01458314955948172,"rank":356,"remainingConfigurations":398},{"removed":"automationbench","score":0.015113340062211785,"rank":351,"remainingConfigurations":398},{"removed":"critpt","score":0.01389276197687401,"rank":353,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.015161693946222929,"rank":352,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.015322505812146864,"rank":352,"remainingConfigurations":398},{"removed":"gdpval","score":0.01516444132219459,"rank":352,"remainingConfigurations":398},{"removed":"gmmlu","score":0.015257262394672594,"rank":352,"remainingConfigurations":398},{"removed":"gpqa","score":0.015548326873659868,"rank":349,"remainingConfigurations":398},{"removed":"harvey","score":0.014955112986685032,"rank":352,"remainingConfigurations":398},{"removed":"hle","score":0.018064390022711443,"rank":346,"remainingConfigurations":398},{"removed":"ifbench","score":0.015148779164325046,"rank":351,"remainingConfigurations":398},{"removed":"itbench","score":0.015106452664617008,"rank":352,"remainingConfigurations":398},{"removed":"livecodebench","score":0.015085441501527243,"rank":353,"remainingConfigurations":398},{"removed":"math500","score":0.015197651011361038,"rank":353,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01559662914261152,"rank":353,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.016980980726538114,"rank":349,"remainingConfigurations":398},{"removed":"omniscience","score":0.0154723905335511,"rank":345,"remainingConfigurations":398},{"removed":"scicode","score":0.015439753208879676,"rank":352,"remainingConfigurations":398},{"removed":"tau-bench","score":0.011607476052121852,"rank":365,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01513267845340209,"rank":353,"remainingConfigurations":398},{"removed":"arc-agi","score":0.018440540538127815,"rank":352,"remainingConfigurations":398},{"removed":"deepswe","score":0.01281765646546588,"rank":352,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.015115687893911054,"rank":352,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01500545294623711,"rank":352,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01598929754655778,"rank":352,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.015130743096717074,"rank":352,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.014967444376532182,"rank":352,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.015089269402914345,"rank":352,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.015053417145935116,"rank":352,"remainingConfigurations":398},{"removed":"livebench-math","score":0.015139184359730414,"rank":352,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014978584945158213,"rank":352,"remainingConfigurations":398},{"removed":"livebench-language","score":0.015300962330660728,"rank":352,"remainingConfigurations":398},{"removed":"livebench-data","score":0.015145469841822393,"rank":352,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.014856255042581932,"rank":352,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.015003100698375167,"rank":352,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.015361895581352987,"rank":352,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.015602360900365509,"rank":352,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.014296337043939148,"rank":353,"remainingConfigurations":398},{"removed":"frontiermath","score":0.015277148066766527,"rank":352,"remainingConfigurations":398},{"removed":"simpleqa","score":0.015764499797755863,"rank":352,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.015031386405665011,"rank":352,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.015054424231284369,"rank":352,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.015044193011154472,"rank":352,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.015082567901280902,"rank":352,"remainingConfigurations":398},{"removed":"vibe-code","score":0.015002435787765044,"rank":352,"remainingConfigurations":398}]},"glm-4.5v--effort-non-reasoning":{"score":0.014797907857916029,"rank":353,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.018119215217611794,"rank":355,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012521055349333942,"rank":355,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0146463029451159,"rank":354,"remainingConfigurations":398},{"removed":"Scale","score":0.016602181103530515,"rank":353,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.014765532685439613,"rank":354,"remainingConfigurations":398},{"removed":"Cognition","score":0.015625987953340713,"rank":355,"remainingConfigurations":398},{"removed":"LiveBench","score":0.015201221929973382,"rank":352,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.015257195742320616,"rank":353,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.015043633676099018,"rank":335,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014382810981630911,"rank":354,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01479884787643936,"rank":353,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.014783148706952428,"rank":353,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01477163157482102,"rank":353,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014797907857916029,"rank":353,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014755209608225496,"rank":353,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.014857086153884242,"rank":353,"remainingConfigurations":398},{"removed":"briefcase","score":0.014774822140800822,"rank":353,"remainingConfigurations":398},{"removed":"aime","score":0.016030011534313496,"rank":347,"remainingConfigurations":398},{"removed":"apex-agents","score":0.014985300346013511,"rank":353,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.015553473197093506,"rank":349,"remainingConfigurations":398},{"removed":"automationbench","score":0.014796038804120013,"rank":353,"remainingConfigurations":398},{"removed":"critpt","score":0.013722717846324756,"rank":355,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.014840976437275749,"rank":353,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.015000685910547956,"rank":353,"remainingConfigurations":398},{"removed":"gdpval","score":0.014909184916883257,"rank":353,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0149502860838822,"rank":353,"remainingConfigurations":398},{"removed":"gpqa","score":0.01431750640729832,"rank":357,"remainingConfigurations":398},{"removed":"harvey","score":0.014637618885610599,"rank":353,"remainingConfigurations":398},{"removed":"hle","score":0.01675542817515766,"rank":352,"remainingConfigurations":398},{"removed":"ifbench","score":0.015005987071087941,"rank":353,"remainingConfigurations":398},{"removed":"itbench","score":0.014785225565813352,"rank":353,"remainingConfigurations":398},{"removed":"livecodebench","score":0.014723325120842262,"rank":356,"remainingConfigurations":398},{"removed":"math500","score":0.014894333681748917,"rank":354,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.014422469216110604,"rank":360,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.016458176201422585,"rank":354,"remainingConfigurations":398},{"removed":"omniscience","score":0.012303361471509488,"rank":362,"remainingConfigurations":398},{"removed":"scicode","score":0.015116547239652651,"rank":353,"remainingConfigurations":398},{"removed":"tau-bench","score":0.014698638716435598,"rank":352,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.014079466691232485,"rank":358,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01796373444078339,"rank":355,"remainingConfigurations":398},{"removed":"deepswe","score":0.012530748781506272,"rank":355,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.014802382535914824,"rank":353,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01469424502117604,"rank":353,"remainingConfigurations":398},{"removed":"frontiercode","score":0.015625987953340713,"rank":355,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014816397810268401,"rank":353,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.01465673424857493,"rank":353,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.014776468050590241,"rank":353,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01474107468786503,"rank":353,"remainingConfigurations":398},{"removed":"livebench-math","score":0.014825457947481151,"rank":353,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014667880513136352,"rank":353,"remainingConfigurations":398},{"removed":"livebench-language","score":0.014983809798868765,"rank":353,"remainingConfigurations":398},{"removed":"livebench-data","score":0.014831500807433009,"rank":353,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01454826449931975,"rank":353,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014692099213856861,"rank":353,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.015043844332256416,"rank":353,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.015257195742320616,"rank":353,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01399287029901365,"rank":354,"remainingConfigurations":398},{"removed":"frontiermath","score":0.014960200415415422,"rank":355,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01544088159241186,"rank":355,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014719779022437674,"rank":353,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.014742317208269738,"rank":353,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.014732424646182738,"rank":353,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.014769831225659558,"rank":353,"remainingConfigurations":398},{"removed":"vibe-code","score":0.014691398990689839,"rank":353,"remainingConfigurations":398}]},"qwen3.5-2b--effort-non-reasoning":{"score":0.014778550895213833,"rank":354,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.009790913329792256,"rank":163,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.018129694743670554,"rank":354,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012585461498585743,"rank":353,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.014652028553756857,"rank":353,"remainingConfigurations":398},{"removed":"Scale","score":0.016559868441186638,"rank":354,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.014767309191893544,"rank":353,"remainingConfigurations":398},{"removed":"Cognition","score":0.015742770555450935,"rank":353,"remainingConfigurations":398},{"removed":"LiveBench","score":0.015170264134482171,"rank":353,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.015205345650621883,"rank":354,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.016568448806845108,"rank":330,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014422232384123485,"rank":353,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.014779271114923227,"rank":354,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.01476320673927073,"rank":354,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01475398054587388,"rank":354,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014778550895213833,"rank":354,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014736809308830782,"rank":354,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.014840042396298048,"rank":354,"remainingConfigurations":398},{"removed":"briefcase","score":0.014756809531459789,"rank":354,"remainingConfigurations":398},{"removed":"aime","score":0.014265831746699584,"rank":358,"remainingConfigurations":398},{"removed":"apex-agents","score":0.014960739637326761,"rank":354,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01488674760248281,"rank":353,"remainingConfigurations":398},{"removed":"automationbench","score":0.014780731804183959,"rank":354,"remainingConfigurations":398},{"removed":"critpt","score":0.013834689090287492,"rank":354,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.014823982066487515,"rank":354,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.014965000395596303,"rank":354,"remainingConfigurations":398},{"removed":"gdpval","score":0.01526805268325977,"rank":351,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014919511862971887,"rank":354,"remainingConfigurations":398},{"removed":"gpqa","score":0.014636333993969861,"rank":353,"remainingConfigurations":398},{"removed":"harvey","score":0.014619321031522726,"rank":354,"remainingConfigurations":398},{"removed":"hle","score":0.015152799384194511,"rank":357,"remainingConfigurations":398},{"removed":"ifbench","score":0.015087425232522133,"rank":352,"remainingConfigurations":398},{"removed":"itbench","score":0.014769034902146544,"rank":354,"remainingConfigurations":398},{"removed":"livecodebench","score":0.014842394360266601,"rank":354,"remainingConfigurations":398},{"removed":"math500","score":0.014888425165758867,"rank":355,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.015348347278081148,"rank":354,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01653355808438962,"rank":353,"remainingConfigurations":398},{"removed":"omniscience","score":0.015188717840154582,"rank":349,"remainingConfigurations":398},{"removed":"scicode","score":0.015069381435090482,"rank":354,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01155171853784686,"rank":366,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.015133342247847832,"rank":352,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01796395715734374,"rank":354,"remainingConfigurations":398},{"removed":"deepswe","score":0.012595487162254166,"rank":353,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.014782959904953675,"rank":354,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01467713406856705,"rank":354,"remainingConfigurations":398},{"removed":"frontiercode","score":0.015742770555450935,"rank":353,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014804602166725815,"rank":354,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.014634865406498061,"rank":354,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.014757764934309059,"rank":354,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.014721856131647644,"rank":354,"remainingConfigurations":398},{"removed":"livebench-math","score":0.014808986803542866,"rank":354,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014640316763521994,"rank":354,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0149640528432018,"rank":354,"remainingConfigurations":398},{"removed":"livebench-data","score":0.014813837939619962,"rank":354,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01453218508567109,"rank":354,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014671984573433156,"rank":354,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.015025672986626007,"rank":354,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.015205345650621883,"rank":354,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.015588854732743927,"rank":347,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01496035113465056,"rank":354,"remainingConfigurations":398},{"removed":"simpleqa","score":0.015484649462798398,"rank":354,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014700519589248793,"rank":354,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01472410336129081,"rank":354,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.014711420448785631,"rank":354,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.014750925449080299,"rank":354,"remainingConfigurations":398},{"removed":"vibe-code","score":0.014673967087880288,"rank":354,"remainingConfigurations":398}]},"qwen3-32b--effort-non-reasoning":{"score":0.014714568687908186,"rank":355,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.020861017446462387,"rank":152,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.018179782667239786,"rank":353,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012569236764361306,"rank":354,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.014587305488538524,"rank":355,"remainingConfigurations":398},{"removed":"Scale","score":0.016485915640768237,"rank":355,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.014739848554000066,"rank":355,"remainingConfigurations":398},{"removed":"Cognition","score":0.015695509907786565,"rank":354,"remainingConfigurations":398},{"removed":"LiveBench","score":0.015112836831993763,"rank":354,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.015101094008596744,"rank":355,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.011518358432855131,"rank":354,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014436445284676898,"rank":352,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.014715261244767004,"rank":355,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.014698709379226295,"rank":355,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.014691071307500171,"rank":355,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014714568687908186,"rank":355,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014673402245202955,"rank":355,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01476669984270495,"rank":355,"remainingConfigurations":398},{"removed":"briefcase","score":0.014672459698487099,"rank":355,"remainingConfigurations":398},{"removed":"aime","score":0.01651866443878737,"rank":345,"remainingConfigurations":398},{"removed":"apex-agents","score":0.014881678567062018,"rank":355,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01518396383065825,"rank":352,"remainingConfigurations":398},{"removed":"automationbench","score":0.014689327239284835,"rank":355,"remainingConfigurations":398},{"removed":"critpt","score":0.014060385336900565,"rank":352,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.014745260753478947,"rank":355,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.014860364601462216,"rank":355,"remainingConfigurations":398},{"removed":"gdpval","score":0.014742429690804136,"rank":355,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014834589608033954,"rank":355,"remainingConfigurations":398},{"removed":"gpqa","score":0.013079746839470476,"rank":362,"remainingConfigurations":398},{"removed":"harvey","score":0.014544827364599893,"rank":355,"remainingConfigurations":398},{"removed":"hle","score":0.015695911488303294,"rank":354,"remainingConfigurations":398},{"removed":"ifbench","score":0.014534393154138283,"rank":355,"remainingConfigurations":398},{"removed":"itbench","score":0.01469515337755717,"rank":355,"remainingConfigurations":398},{"removed":"livecodebench","score":0.015189725269401431,"rank":352,"remainingConfigurations":398},{"removed":"math500","score":0.01463009384143475,"rank":357,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.014845481998723632,"rank":358,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01577151179620454,"rank":356,"remainingConfigurations":398},{"removed":"omniscience","score":0.013935298221559212,"rank":354,"remainingConfigurations":398},{"removed":"scicode","score":0.014958783521957284,"rank":355,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0141051549330549,"rank":354,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.014725319724079025,"rank":355,"remainingConfigurations":398},{"removed":"arc-agi","score":0.018006706340112078,"rank":353,"remainingConfigurations":398},{"removed":"deepswe","score":0.012579370717147117,"rank":354,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.014718921751075642,"rank":355,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.014614459363353741,"rank":355,"remainingConfigurations":398},{"removed":"frontiercode","score":0.015695509907786565,"rank":354,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014744958872283836,"rank":355,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.01457004829853821,"rank":355,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.014694065449114183,"rank":355,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01465754029334503,"rank":355,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01474628926340796,"rank":355,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014573817066236774,"rank":355,"remainingConfigurations":398},{"removed":"livebench-language","score":0.014898837555658137,"rank":355,"remainingConfigurations":398},{"removed":"livebench-data","score":0.014751132225877983,"rank":355,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.014469982088597436,"rank":355,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014608637031747855,"rank":355,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.014960307677615489,"rank":355,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.015101094008596744,"rank":355,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.013104952696968597,"rank":357,"remainingConfigurations":398},{"removed":"frontiermath","score":0.015020365529255987,"rank":353,"remainingConfigurations":398},{"removed":"simpleqa","score":0.015543814625858519,"rank":353,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014636841159073514,"rank":355,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.014661098401677305,"rank":355,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.014646574995302008,"rank":355,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.014687504262891178,"rank":355,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01461176561701439,"rank":355,"remainingConfigurations":398}]},"qwen3-vl-4b-thinking--effort-reasoning":{"score":0.014559402866552565,"rank":356,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.017801356738134533,"rank":356,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012304042305003112,"rank":356,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01440842160013338,"rank":356,"remainingConfigurations":398},{"removed":"Scale","score":0.016326547717970298,"rank":356,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01453007763352745,"rank":356,"remainingConfigurations":398},{"removed":"Cognition","score":0.01535217483676274,"rank":357,"remainingConfigurations":398},{"removed":"LiveBench","score":0.014959393612295731,"rank":355,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.015004066166019228,"rank":356,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.014694822456316313,"rank":337,"remainingConfigurations":381},{"removed":"Vals AI","score":0.014155283178111636,"rank":355,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.014560328839931046,"rank":356,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.014544887471965353,"rank":356,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01453352681442472,"rank":356,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014559402866552565,"rank":356,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014517376098536877,"rank":356,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.014618943972297571,"rank":356,"remainingConfigurations":398},{"removed":"briefcase","score":0.014534139882430184,"rank":356,"remainingConfigurations":398},{"removed":"aime","score":0.01491367543976628,"rank":354,"remainingConfigurations":398},{"removed":"apex-agents","score":0.014739459453977588,"rank":356,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.013996094611200605,"rank":358,"remainingConfigurations":398},{"removed":"automationbench","score":0.014563181413529719,"rank":356,"remainingConfigurations":398},{"removed":"critpt","score":0.01345354251335038,"rank":357,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.014600776202908658,"rank":356,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.014768906991666157,"rank":356,"remainingConfigurations":398},{"removed":"gdpval","score":0.014667469389252383,"rank":356,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014727622632528697,"rank":356,"remainingConfigurations":398},{"removed":"gpqa","score":0.014553130561595183,"rank":355,"remainingConfigurations":398},{"removed":"harvey","score":0.014400141190515947,"rank":356,"remainingConfigurations":398},{"removed":"hle","score":0.015272372089732271,"rank":356,"remainingConfigurations":398},{"removed":"ifbench","score":0.01355620862847407,"rank":358,"remainingConfigurations":398},{"removed":"itbench","score":0.014545979417900081,"rank":356,"remainingConfigurations":398},{"removed":"livecodebench","score":0.014828718311976649,"rank":355,"remainingConfigurations":398},{"removed":"math500","score":0.014702882821601227,"rank":356,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01517818405537833,"rank":356,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01527205300880248,"rank":359,"remainingConfigurations":398},{"removed":"omniscience","score":0.013758944188969419,"rank":355,"remainingConfigurations":398},{"removed":"scicode","score":0.014878644548109632,"rank":356,"remainingConfigurations":398},{"removed":"tau-bench","score":0.014820285948350996,"rank":349,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.015164040327286474,"rank":351,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01765376976069211,"rank":356,"remainingConfigurations":398},{"removed":"deepswe","score":0.01231358779001523,"rank":356,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.014563811057751022,"rank":356,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.014457368060868989,"rank":356,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01535217483676274,"rank":357,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014576841566292971,"rank":356,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.014419682515353116,"rank":356,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01453830971061835,"rank":356,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0145037504694295,"rank":356,"remainingConfigurations":398},{"removed":"livebench-math","score":0.014586528665275279,"rank":356,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014431456603267208,"rank":356,"remainingConfigurations":398},{"removed":"livebench-language","score":0.014742450441360114,"rank":356,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01459243537138412,"rank":356,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.014313667704115811,"rank":356,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014455252698484184,"rank":356,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.014801413479270012,"rank":356,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.015004066166019228,"rank":356,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.013762583346451224,"rank":355,"remainingConfigurations":398},{"removed":"frontiermath","score":0.014716975066582724,"rank":356,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01519327425651061,"rank":356,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014482490892472789,"rank":356,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.014504696915925167,"rank":356,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.014494910934087002,"rank":356,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01453180398421011,"rank":356,"remainingConfigurations":398},{"removed":"vibe-code","score":0.014454592371345436,"rank":356,"remainingConfigurations":398}]},"gemma-4-e2b-it--effort-reasoning":{"score":0.014171813947321093,"rank":357,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.017373967543965602,"rank":358,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012008822289817632,"rank":358,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.014030165455706498,"rank":358,"remainingConfigurations":398},{"removed":"Scale","score":0.015906954685053026,"rank":358,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.014146101922852277,"rank":357,"remainingConfigurations":398},{"removed":"Cognition","score":0.014981950727980317,"rank":358,"remainingConfigurations":398},{"removed":"LiveBench","score":0.014569181411914232,"rank":356,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.014623762919730575,"rank":357,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.014312726415848196,"rank":338,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013786684657662017,"rank":356,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01417271253924643,"rank":357,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.014157779391542316,"rank":357,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.014146528195324089,"rank":358,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014171813947321093,"rank":357,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014130892206380368,"rank":357,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01423282540328826,"rank":357,"remainingConfigurations":398},{"removed":"briefcase","score":0.014142128267654886,"rank":358,"remainingConfigurations":398},{"removed":"aime","score":0.014159903685597405,"rank":359,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01435691841057568,"rank":357,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.013958869132455384,"rank":359,"remainingConfigurations":398},{"removed":"automationbench","score":0.01417422416125496,"rank":357,"remainingConfigurations":398},{"removed":"critpt","score":0.012908180727995253,"rank":359,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.014220228079335968,"rank":357,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.014374128901490743,"rank":357,"remainingConfigurations":398},{"removed":"gdpval","score":0.01444447168986509,"rank":357,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014293224515500578,"rank":357,"remainingConfigurations":398},{"removed":"gpqa","score":0.01462176901692345,"rank":354,"remainingConfigurations":398},{"removed":"harvey","score":0.014025988463745009,"rank":357,"remainingConfigurations":398},{"removed":"hle","score":0.014562303824269929,"rank":358,"remainingConfigurations":398},{"removed":"ifbench","score":0.012629436560775581,"rank":360,"remainingConfigurations":398},{"removed":"itbench","score":0.01416854832350506,"rank":357,"remainingConfigurations":398},{"removed":"livecodebench","score":0.014184939259840629,"rank":357,"remainingConfigurations":398},{"removed":"math500","score":0.014327751313128738,"rank":358,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.014697482225215164,"rank":359,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01545713499448647,"rank":357,"remainingConfigurations":398},{"removed":"omniscience","score":0.014545199701605385,"rank":353,"remainingConfigurations":398},{"removed":"scicode","score":0.014485553890405988,"rank":357,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01381294878130198,"rank":356,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.014477509596419767,"rank":357,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01721650706952602,"rank":358,"remainingConfigurations":398},{"removed":"deepswe","score":0.012018139206271657,"rank":358,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.014176115390251043,"rank":357,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.014072799665462885,"rank":358,"remainingConfigurations":398},{"removed":"frontiercode","score":0.014981950727980317,"rank":358,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014190655496958063,"rank":358,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.014036939982338702,"rank":358,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.014151378434942427,"rank":357,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.014117959681287928,"rank":357,"remainingConfigurations":398},{"removed":"livebench-math","score":0.014198197450266329,"rank":357,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014047274454778066,"rank":357,"remainingConfigurations":398},{"removed":"livebench-language","score":0.014350236026173213,"rank":357,"remainingConfigurations":398},{"removed":"livebench-data","score":0.014204136285556805,"rank":357,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.013932355739226373,"rank":357,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014070313054586538,"rank":358,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.014407416910116114,"rank":358,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.014623762919730575,"rank":357,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01341891207803647,"rank":356,"remainingConfigurations":398},{"removed":"frontiermath","score":0.014328131158943838,"rank":358,"remainingConfigurations":398},{"removed":"simpleqa","score":0.014786166852503863,"rank":357,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014096901270081017,"rank":357,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.014118567971743323,"rank":357,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.014108909722370775,"rank":358,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.014145019122024259,"rank":357,"remainingConfigurations":398},{"removed":"vibe-code","score":0.014069722255095533,"rank":357,"remainingConfigurations":398}]},"gpt-5-nano--effort-minimal":{"score":0.014170531748371918,"rank":358,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.010861771671346556,"rank":162,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.017398501518040854,"rank":357,"remainingConfigurations":398},{"removed":"Datacurve","score":0.012100657372270151,"rank":357,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.014110042396134068,"rank":357,"remainingConfigurations":398},{"removed":"Scale","score":0.015924240439937884,"rank":357,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01414145403886071,"rank":358,"remainingConfigurations":398},{"removed":"Cognition","score":0.015469756377273948,"rank":356,"remainingConfigurations":398},{"removed":"LiveBench","score":0.014545607678433221,"rank":357,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.014557284669040854,"rank":358,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.013956489189076651,"rank":340,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013757339157273058,"rank":357,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.014171316560642305,"rank":358,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.014152694272872425,"rank":358,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.014148615272950305,"rank":357,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.014170531748371918,"rank":358,"remainingConfigurations":398},{"removed":"All provider reports","score":0.014129155923539782,"rank":358,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.014218187263906468,"rank":358,"remainingConfigurations":398},{"removed":"briefcase","score":0.01415155327988099,"rank":357,"remainingConfigurations":398},{"removed":"aime","score":0.014309133019709258,"rank":357,"remainingConfigurations":398},{"removed":"apex-agents","score":0.014318549020299704,"rank":358,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.013894088121122784,"rank":360,"remainingConfigurations":398},{"removed":"automationbench","score":0.014162234567048433,"rank":358,"remainingConfigurations":398},{"removed":"critpt","score":0.013546447527986538,"rank":356,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01419791205545447,"rank":358,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.014321223020308386,"rank":358,"remainingConfigurations":398},{"removed":"gdpval","score":0.01424980450906635,"rank":358,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014268255157279168,"rank":359,"remainingConfigurations":398},{"removed":"gpqa","score":0.014455760765014,"rank":356,"remainingConfigurations":398},{"removed":"harvey","score":0.014009181649487874,"rank":358,"remainingConfigurations":398},{"removed":"hle","score":0.015386650055532742,"rank":355,"remainingConfigurations":398},{"removed":"ifbench","score":0.013855385111847819,"rank":357,"remainingConfigurations":398},{"removed":"itbench","score":0.01415510459845602,"rank":358,"remainingConfigurations":398},{"removed":"livecodebench","score":0.013483661650138997,"rank":359,"remainingConfigurations":398},{"removed":"math500","score":0.014258574841302352,"rank":359,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.015637375524961732,"rank":352,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.015786554002619187,"rank":355,"remainingConfigurations":398},{"removed":"omniscience","score":0.013409690286826925,"rank":358,"remainingConfigurations":398},{"removed":"scicode","score":0.014417745025348273,"rank":358,"remainingConfigurations":398},{"removed":"tau-bench","score":0.013624313968269006,"rank":357,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.013669678103985707,"rank":360,"remainingConfigurations":398},{"removed":"arc-agi","score":0.017249457826065722,"rank":357,"remainingConfigurations":398},{"removed":"deepswe","score":0.012109105394401812,"rank":357,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01417460489133729,"rank":358,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01426417784701649,"rank":357,"remainingConfigurations":398},{"removed":"frontiercode","score":0.015469756377273948,"rank":356,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.014194511131679279,"rank":357,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.014042969582034803,"rank":357,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.014150149373631007,"rank":358,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01411464899397727,"rank":358,"remainingConfigurations":398},{"removed":"livebench-math","score":0.014195488416422057,"rank":358,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.014046178397234496,"rank":358,"remainingConfigurations":398},{"removed":"livebench-language","score":0.014345787486832247,"rank":358,"remainingConfigurations":398},{"removed":"livebench-data","score":0.014197225670703998,"rank":358,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.013930582950957676,"rank":358,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.014071710071422888,"rank":357,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0144134984489417,"rank":357,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.014557284669040854,"rank":358,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01307630635832635,"rank":358,"remainingConfigurations":398},{"removed":"frontiermath","score":0.014372811498046057,"rank":357,"remainingConfigurations":398},{"removed":"simpleqa","score":0.014779147356140589,"rank":358,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.014095338578086092,"rank":358,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.014113069309615492,"rank":358,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01411527760404494,"rank":357,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.014137605328186515,"rank":358,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01406436987327356,"rank":358,"remainingConfigurations":398}]},"exaone-4.0-1.2b--effort-reasoning":{"score":0.013671163526817532,"rank":359,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01678094595267828,"rank":359,"remainingConfigurations":398},{"removed":"Datacurve","score":0.011563058858349051,"rank":359,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01353131036153466,"rank":359,"remainingConfigurations":398},{"removed":"Scale","score":0.015342332804946554,"rank":359,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.013640351144850247,"rank":359,"remainingConfigurations":398},{"removed":"Cognition","score":0.014436596025158538,"rank":359,"remainingConfigurations":398},{"removed":"LiveBench","score":0.014044600243263072,"rank":358,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.014105454216056572,"rank":359,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.013692159371692783,"rank":343,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013287081689844299,"rank":358,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.013672032591156326,"rank":359,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.013657532466249225,"rank":359,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.013646892375823555,"rank":359,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.013671163526817532,"rank":359,"remainingConfigurations":398},{"removed":"All provider reports","score":0.013631720707085489,"rank":359,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.013725832770020445,"rank":359,"remainingConfigurations":398},{"removed":"briefcase","score":0.013660837126070193,"rank":359,"remainingConfigurations":398},{"removed":"aime","score":0.012281108919477568,"rank":365,"remainingConfigurations":398},{"removed":"apex-agents","score":0.013844595779293896,"rank":359,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.014363122158237547,"rank":357,"remainingConfigurations":398},{"removed":"automationbench","score":0.013679005484313297,"rank":359,"remainingConfigurations":398},{"removed":"critpt","score":0.012460641079833953,"rank":360,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.013709513298913812,"rank":359,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.013868903073440415,"rank":359,"remainingConfigurations":398},{"removed":"gdpval","score":0.01377221446927508,"rank":359,"remainingConfigurations":398},{"removed":"gmmlu","score":0.013818827656029015,"rank":360,"remainingConfigurations":398},{"removed":"gpqa","score":0.01347799710314932,"rank":360,"remainingConfigurations":398},{"removed":"harvey","score":0.013522198174788507,"rank":359,"remainingConfigurations":398},{"removed":"hle","score":0.013235322484147818,"rank":365,"remainingConfigurations":398},{"removed":"ifbench","score":0.014305052793631265,"rank":356,"remainingConfigurations":398},{"removed":"itbench","score":0.0136601076447174,"rank":359,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011985009782407003,"rank":366,"remainingConfigurations":398},{"removed":"math500","score":0.01379191974833448,"rank":360,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.015257520089729736,"rank":355,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.014715274950931716,"rank":360,"remainingConfigurations":398},{"removed":"omniscience","score":0.013598863987831783,"rank":357,"remainingConfigurations":398},{"removed":"scicode","score":0.013973104310497794,"rank":359,"remainingConfigurations":398},{"removed":"tau-bench","score":0.013826060739334628,"rank":355,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.014669226675367473,"rank":356,"remainingConfigurations":398},{"removed":"arc-agi","score":0.016637998436866423,"rank":359,"remainingConfigurations":398},{"removed":"deepswe","score":0.011572029412349907,"rank":359,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.013675307741418329,"rank":359,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.013575335207584263,"rank":359,"remainingConfigurations":398},{"removed":"frontiercode","score":0.014436596025158538,"rank":359,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.013688274783448142,"rank":359,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.013540428282179995,"rank":359,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.013651367138243874,"rank":359,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.013618665001948907,"rank":359,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01369668579894589,"rank":359,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.013550676815381734,"rank":359,"remainingConfigurations":398},{"removed":"livebench-language","score":0.013843278190992467,"rank":359,"remainingConfigurations":398},{"removed":"livebench-data","score":0.013702340192516099,"rank":359,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01344004584962627,"rank":359,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.013573170880048708,"rank":359,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01389894343172505,"rank":359,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.014105454216056572,"rank":359,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.012907289406899633,"rank":359,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01382322903967765,"rank":359,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01426729023991568,"rank":359,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01359882911025548,"rank":359,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.013619696258791898,"rank":359,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.013610523857853675,"rank":359,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01364516045686867,"rank":359,"remainingConfigurations":398},{"removed":"vibe-code","score":0.013572563051547998,"rank":359,"remainingConfigurations":398}]},"gemma-4-e2b-it--effort-non-reasoning":{"score":0.013616907448845238,"rank":360,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.016676865942526185,"rank":360,"remainingConfigurations":398},{"removed":"Datacurve","score":0.011530135675120243,"rank":360,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.013479588933951306,"rank":360,"remainingConfigurations":398},{"removed":"Scale","score":0.01528997620260484,"rank":360,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.013587819994637733,"rank":360,"remainingConfigurations":398},{"removed":"Cognition","score":0.014395928089384008,"rank":360,"remainingConfigurations":398},{"removed":"LiveBench","score":0.013992629134052139,"rank":359,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.014053880234626294,"rank":360,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.013712057636807043,"rank":342,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013237524907447493,"rank":359,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01361777732260703,"rank":360,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.013603357835573567,"rank":360,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.013592642457816924,"rank":360,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.013616907448845238,"rank":360,"remainingConfigurations":398},{"removed":"All provider reports","score":0.013577559982999208,"rank":360,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.01367413573875279,"rank":360,"remainingConfigurations":398},{"removed":"briefcase","score":0.013603378176320196,"rank":360,"remainingConfigurations":398},{"removed":"aime","score":0.013598199103492243,"rank":362,"remainingConfigurations":398},{"removed":"apex-agents","score":0.013792798544689516,"rank":360,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.013355142220420885,"rank":362,"remainingConfigurations":398},{"removed":"automationbench","score":0.013623743436912326,"rank":360,"remainingConfigurations":398},{"removed":"critpt","score":0.012178228364161998,"rank":362,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.013659528090847499,"rank":360,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.013813919136808317,"rank":360,"remainingConfigurations":398},{"removed":"gdpval","score":0.013688266680925041,"rank":360,"remainingConfigurations":398},{"removed":"gmmlu","score":0.01373799259487607,"rank":361,"remainingConfigurations":398},{"removed":"gpqa","score":0.014299961903210723,"rank":358,"remainingConfigurations":398},{"removed":"harvey","score":0.01347259272707295,"rank":360,"remainingConfigurations":398},{"removed":"hle","score":0.013854699983881112,"rank":363,"remainingConfigurations":398},{"removed":"ifbench","score":0.01259736019916352,"rank":361,"remainingConfigurations":398},{"removed":"itbench","score":0.013613509798774383,"rank":360,"remainingConfigurations":398},{"removed":"livecodebench","score":0.013629190940547422,"rank":358,"remainingConfigurations":398},{"removed":"math500","score":0.013777044378999924,"rank":361,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.014116782409739452,"rank":362,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.015357806330026551,"rank":358,"remainingConfigurations":398},{"removed":"omniscience","score":0.013756619225916015,"rank":356,"remainingConfigurations":398},{"removed":"scicode","score":0.013919007567138092,"rank":360,"remainingConfigurations":398},{"removed":"tau-bench","score":0.012955954324803011,"rank":360,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.013846883874167047,"rank":359,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01652929365817852,"rank":360,"remainingConfigurations":398},{"removed":"deepswe","score":0.011539070765168245,"rank":360,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01362103286433067,"rank":360,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.013521514724801698,"rank":360,"remainingConfigurations":398},{"removed":"frontiercode","score":0.014395928089384008,"rank":360,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01363440099370687,"rank":360,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.013487145732243714,"rank":360,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.013597175374766077,"rank":360,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01356462621370963,"rank":360,"remainingConfigurations":398},{"removed":"livebench-math","score":0.013642298103200464,"rank":360,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.013496981619540572,"rank":360,"remainingConfigurations":398},{"removed":"livebench-language","score":0.013788389862811104,"rank":360,"remainingConfigurations":398},{"removed":"livebench-data","score":0.013647974366324608,"rank":360,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.013386673960995625,"rank":360,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.013519292885199609,"rank":360,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.013843719593525051,"rank":360,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.014053880234626294,"rank":360,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01287649798685262,"rank":360,"remainingConfigurations":398},{"removed":"frontiermath","score":0.013773999513640833,"rank":360,"remainingConfigurations":398},{"removed":"simpleqa","score":0.014208288804979924,"rank":360,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.013544863943600808,"rank":360,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.013565648486047792,"rank":360,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01355647348977937,"rank":360,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.013591011799235518,"rank":360,"remainingConfigurations":398},{"removed":"vibe-code","score":0.013518714279547699,"rank":360,"remainingConfigurations":398}]},"qwen3-4b--effort-reasoning":{"score":0.013521470644119004,"rank":361,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.016574566277571992,"rank":361,"remainingConfigurations":398},{"removed":"Datacurve","score":0.011430518309426181,"rank":361,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01338176285330645,"rank":361,"remainingConfigurations":398},{"removed":"Scale","score":0.01517076925169245,"rank":361,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.013490356002454774,"rank":361,"remainingConfigurations":398},{"removed":"Cognition","score":0.01427075693941719,"rank":361,"remainingConfigurations":398},{"removed":"LiveBench","score":0.013889523220083638,"rank":360,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.013949493887135218,"rank":361,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.013731710507927567,"rank":341,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013140967970756376,"rank":360,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.013522333281487981,"rank":361,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.013507980675217857,"rank":361,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.013497474582787978,"rank":361,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.013521470644119004,"rank":361,"remainingConfigurations":398},{"removed":"All provider reports","score":0.013482463880109893,"rank":361,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.013574750479989383,"rank":361,"remainingConfigurations":398},{"removed":"briefcase","score":0.013503443741716603,"rank":361,"remainingConfigurations":398},{"removed":"aime","score":0.014316668628390242,"rank":356,"remainingConfigurations":398},{"removed":"apex-agents","score":0.013690329381209185,"rank":361,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.014616032718076257,"rank":355,"remainingConfigurations":398},{"removed":"automationbench","score":0.013526858538752328,"rank":361,"remainingConfigurations":398},{"removed":"critpt","score":0.012988135956894476,"rank":358,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.013555630785876696,"rank":361,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.013712619356968983,"rank":361,"remainingConfigurations":398},{"removed":"gdpval","score":0.013668601114312194,"rank":362,"remainingConfigurations":398},{"removed":"gmmlu","score":0.01367686531289094,"rank":362,"remainingConfigurations":398},{"removed":"gpqa","score":0.013200558705534868,"rank":361,"remainingConfigurations":398},{"removed":"harvey","score":0.013372611188756121,"rank":361,"remainingConfigurations":398},{"removed":"hle","score":0.01430330274954278,"rank":360,"remainingConfigurations":398},{"removed":"ifbench","score":0.013095897585557377,"rank":359,"remainingConfigurations":398},{"removed":"itbench","score":0.013508785018207214,"rank":361,"remainingConfigurations":398},{"removed":"livecodebench","score":0.012692726557277495,"rank":363,"remainingConfigurations":398},{"removed":"math500","score":0.012361461067584926,"rank":365,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01407742586041033,"rank":363,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.014608829593500487,"rank":361,"remainingConfigurations":398},{"removed":"omniscience","score":0.01269433585828242,"rank":360,"remainingConfigurations":398},{"removed":"scicode","score":0.013814562571556327,"rank":361,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01348733649220027,"rank":358,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.013642154588996105,"rank":361,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01643467851608801,"rank":361,"remainingConfigurations":398},{"removed":"deepswe","score":0.011439392480194618,"rank":361,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.013525569642674299,"rank":361,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.013426665751237554,"rank":361,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01427075693941719,"rank":361,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.013538250180344331,"rank":361,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.013392084641817403,"rank":361,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.013501887609321582,"rank":361,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.013469504675236957,"rank":361,"remainingConfigurations":398},{"removed":"livebench-math","score":0.013546733770222969,"rank":361,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.013402256276883427,"rank":361,"remainingConfigurations":398},{"removed":"livebench-language","score":0.013691745203503261,"rank":361,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01355227501654957,"rank":361,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01329283861672744,"rank":361,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.013424539571535271,"rank":361,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.013746826474238366,"rank":361,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.013949493887135218,"rank":361,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.012783175983790036,"rank":361,"remainingConfigurations":398},{"removed":"frontiermath","score":0.013668174727995986,"rank":361,"remainingConfigurations":398},{"removed":"simpleqa","score":0.014112183797695153,"rank":361,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.013449905942127178,"rank":361,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.013470544749828397,"rank":361,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.013461488619417634,"rank":361,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.013495734663939015,"rank":361,"remainingConfigurations":398},{"removed":"vibe-code","score":0.013423934952609802,"rank":361,"remainingConfigurations":398}]},"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning":{"score":0.01343338556738956,"rank":362,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.016466663423169065,"rank":362,"remainingConfigurations":398},{"removed":"Datacurve","score":0.011363106207249075,"rank":362,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.013296918053406251,"rank":362,"remainingConfigurations":398},{"removed":"Scale","score":0.015077778380505537,"rank":362,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.013403741142967251,"rank":362,"remainingConfigurations":398},{"removed":"Cognition","score":0.014186025446418256,"rank":362,"remainingConfigurations":398},{"removed":"LiveBench","score":0.013802202893168533,"rank":361,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01385729554107504,"rank":362,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.013641987185778111,"rank":344,"remainingConfigurations":381},{"removed":"Vals AI","score":0.013058212047181302,"rank":361,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.013434238216327212,"rank":362,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.013419981467578978,"rank":362,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01340951918266227,"rank":362,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01343338556738956,"rank":362,"remainingConfigurations":398},{"removed":"All provider reports","score":0.013394598916875075,"rank":362,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.013486831117336973,"rank":362,"remainingConfigurations":398},{"removed":"briefcase","score":0.013389421932531615,"rank":362,"remainingConfigurations":398},{"removed":"aime","score":0.014645321730734023,"rank":355,"remainingConfigurations":398},{"removed":"apex-agents","score":0.013604232374880891,"rank":362,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01336989118817985,"rank":361,"remainingConfigurations":398},{"removed":"automationbench","score":0.013405243252977704,"rank":362,"remainingConfigurations":398},{"removed":"critpt","score":0.012396428983664923,"rank":361,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.013471589524683006,"rank":362,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.013590838479715657,"rank":362,"remainingConfigurations":398},{"removed":"gdpval","score":0.01368424751270377,"rank":361,"remainingConfigurations":398},{"removed":"gmmlu","score":0.014274066336155017,"rank":358,"remainingConfigurations":398},{"removed":"gpqa","score":0.013857894680249417,"rank":359,"remainingConfigurations":398},{"removed":"harvey","score":0.013288717044413026,"rank":362,"remainingConfigurations":398},{"removed":"hle","score":0.01406486206349865,"rank":362,"remainingConfigurations":398},{"removed":"ifbench","score":0.0123959094175601,"rank":364,"remainingConfigurations":398},{"removed":"itbench","score":0.01342289312363619,"rank":362,"remainingConfigurations":398},{"removed":"livecodebench","score":0.013182682484701549,"rank":362,"remainingConfigurations":398},{"removed":"math500","score":0.013533135405964144,"rank":362,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01494857264467313,"rank":357,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.014460725763577957,"rank":362,"remainingConfigurations":398},{"removed":"omniscience","score":0.012771137697383847,"rank":359,"remainingConfigurations":398},{"removed":"scicode","score":0.013694137807334958,"rank":362,"remainingConfigurations":398},{"removed":"tau-bench","score":0.012652221384895003,"rank":362,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012166363266804257,"rank":366,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01632499316933148,"rank":362,"remainingConfigurations":398},{"removed":"deepswe","score":0.011371930225790972,"rank":362,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.013437463138037058,"rank":362,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01333914252069733,"rank":362,"remainingConfigurations":398},{"removed":"frontiercode","score":0.014186025446418256,"rank":362,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01345000209440089,"rank":362,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.013304917752436899,"rank":362,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.013413897887710012,"rank":362,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.013381911579573219,"rank":362,"remainingConfigurations":398},{"removed":"livebench-math","score":0.013458476397150402,"rank":362,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01331499720813869,"rank":362,"remainingConfigurations":398},{"removed":"livebench-language","score":0.013602613336158238,"rank":362,"remainingConfigurations":398},{"removed":"livebench-data","score":0.01346397710109133,"rank":362,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01320615890736026,"rank":362,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.013337071147493522,"rank":362,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.013657289886493335,"rank":362,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01385729554107504,"rank":362,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.012705525746642582,"rank":362,"remainingConfigurations":398},{"removed":"frontiermath","score":0.013579354875211122,"rank":362,"remainingConfigurations":398},{"removed":"simpleqa","score":0.014018917171195237,"rank":362,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.013362269600988665,"rank":362,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.013382783547477765,"rank":362,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.013373763553752594,"rank":362,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.013407828881595371,"rank":362,"remainingConfigurations":398},{"removed":"vibe-code","score":0.013336452600574047,"rank":362,"remainingConfigurations":398}]},"amazon-nova-pro--effort-non-reasoning":{"score":0.012596453981549906,"rank":363,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01541479591099599,"rank":363,"remainingConfigurations":398},{"removed":"Datacurve","score":0.010641281250239448,"rank":363,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.012466082879420881,"rank":363,"remainingConfigurations":398},{"removed":"Scale","score":0.014135539057384565,"rank":363,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.012571595604886437,"rank":363,"remainingConfigurations":398},{"removed":"Cognition","score":0.013285785861772056,"rank":363,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01294616869782395,"rank":362,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012981578647902392,"rank":363,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01271729153166141,"rank":346,"remainingConfigurations":381},{"removed":"Vals AI","score":0.012249351293080335,"rank":363,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.012597256050992331,"rank":363,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.012583853852931384,"rank":363,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.012574033040770228,"rank":363,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.012596453981549906,"rank":363,"remainingConfigurations":398},{"removed":"All provider reports","score":0.012560011098143272,"rank":363,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.012651138063298465,"rank":363,"remainingConfigurations":398},{"removed":"briefcase","score":0.012566361170080078,"rank":363,"remainingConfigurations":398},{"removed":"aime","score":0.013849134531685183,"rank":361,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01275532509869698,"rank":363,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.012054125117941324,"rank":366,"remainingConfigurations":398},{"removed":"automationbench","score":0.012585165087034377,"rank":363,"remainingConfigurations":398},{"removed":"critpt","score":0.01151400030854185,"rank":365,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.012635000128679021,"rank":363,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.012757997474767255,"rank":363,"remainingConfigurations":398},{"removed":"gdpval","score":0.01266920528274834,"rank":365,"remainingConfigurations":398},{"removed":"gmmlu","score":0.012717509658424922,"rank":363,"remainingConfigurations":398},{"removed":"gpqa","score":0.012429911958170751,"rank":367,"remainingConfigurations":398},{"removed":"harvey","score":0.012461993757968248,"rank":363,"remainingConfigurations":398},{"removed":"hle","score":0.014089811769767526,"rank":361,"remainingConfigurations":398},{"removed":"ifbench","score":0.011450031319856382,"rank":370,"remainingConfigurations":398},{"removed":"itbench","score":0.012586328556632434,"rank":363,"remainingConfigurations":398},{"removed":"livecodebench","score":0.013435271044351606,"rank":360,"remainingConfigurations":398},{"removed":"math500","score":0.013320348981650335,"rank":363,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.013101418533240693,"rank":367,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013651261164187212,"rank":364,"remainingConfigurations":398},{"removed":"omniscience","score":0.010668663043617209,"rank":370,"remainingConfigurations":398},{"removed":"scicode","score":0.012853074751880049,"rank":363,"remainingConfigurations":398},{"removed":"tau-bench","score":0.012741681842835221,"rank":361,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012048743512437838,"rank":368,"remainingConfigurations":398},{"removed":"arc-agi","score":0.015285901323530996,"rank":363,"remainingConfigurations":398},{"removed":"deepswe","score":0.010649558021482994,"rank":363,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.012600281703850977,"rank":363,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.012508049590103466,"rank":363,"remainingConfigurations":398},{"removed":"frontiercode","score":0.013285785861772056,"rank":363,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01261176521290567,"rank":363,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.012475263076119748,"rank":363,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.012578229928671992,"rank":363,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01254830912700055,"rank":363,"remainingConfigurations":398},{"removed":"livebench-math","score":0.012620027467587948,"rank":363,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.012485228319097388,"rank":363,"remainingConfigurations":398},{"removed":"livebench-language","score":0.012755419476540126,"rank":363,"remainingConfigurations":398},{"removed":"livebench-data","score":0.012625200859751893,"rank":363,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.012383083260572239,"rank":363,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.012505985838649708,"rank":363,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.012806720492923264,"rank":363,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012981578647902392,"rank":363,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011905248420712578,"rank":363,"remainingConfigurations":398},{"removed":"frontiermath","score":0.012734418088382925,"rank":363,"remainingConfigurations":398},{"removed":"simpleqa","score":0.013148507564772344,"rank":363,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.012529658519449755,"rank":363,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.012548943950287883,"rank":363,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.012540446682797962,"rank":363,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.012572449902654603,"rank":363,"remainingConfigurations":398},{"removed":"vibe-code","score":0.012505454399222841,"rank":363,"remainingConfigurations":398}]},"gpt-4.1-nano--effort-non-reasoning":{"score":0.012589514480922602,"rank":364,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.015394401556441194,"rank":364,"remainingConfigurations":398},{"removed":"Datacurve","score":0.010636858485052766,"rank":364,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01245975456970518,"rank":364,"remainingConfigurations":398},{"removed":"Scale","score":0.014126630778420676,"rank":364,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.012566961811551423,"rank":364,"remainingConfigurations":398},{"removed":"Cognition","score":0.013275074714737864,"rank":364,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01294506946174163,"rank":363,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012972779333776253,"rank":364,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.012722968938224955,"rank":345,"remainingConfigurations":381},{"removed":"Vals AI","score":0.012250981487480543,"rank":362,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.012590311772607367,"rank":364,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.012576938310465744,"rank":364,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.012567062419540207,"rank":364,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.012589514480922602,"rank":364,"remainingConfigurations":398},{"removed":"All provider reports","score":0.012553059688166135,"rank":364,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.012645486675578466,"rank":364,"remainingConfigurations":398},{"removed":"briefcase","score":0.012542391358767514,"rank":364,"remainingConfigurations":398},{"removed":"aime","score":0.012790499414159455,"rank":364,"remainingConfigurations":398},{"removed":"apex-agents","score":0.012750305905430229,"rank":364,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.012122319845672705,"rank":365,"remainingConfigurations":398},{"removed":"automationbench","score":0.01256451811161378,"rank":364,"remainingConfigurations":398},{"removed":"critpt","score":0.011537294864779871,"rank":364,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.012629065894449372,"rank":364,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.012740402401247316,"rank":364,"remainingConfigurations":398},{"removed":"gdpval","score":0.012739079036370005,"rank":364,"remainingConfigurations":398},{"removed":"gmmlu","score":0.01270229666145845,"rank":364,"remainingConfigurations":398},{"removed":"gpqa","score":0.01235619305922842,"rank":368,"remainingConfigurations":398},{"removed":"harvey","score":0.012458051110580884,"rank":364,"remainingConfigurations":398},{"removed":"hle","score":0.013823649665281566,"rank":364,"remainingConfigurations":398},{"removed":"ifbench","score":0.012204271275634818,"rank":365,"remainingConfigurations":398},{"removed":"itbench","score":0.012581696238291118,"rank":364,"remainingConfigurations":398},{"removed":"livecodebench","score":0.012583480817932244,"rank":364,"remainingConfigurations":398},{"removed":"math500","score":0.012763635466366887,"rank":364,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01349716342231406,"rank":365,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013967883423036133,"rank":363,"remainingConfigurations":398},{"removed":"omniscience","score":0.011536043716294174,"rank":365,"remainingConfigurations":398},{"removed":"scicode","score":0.012836081570367718,"rank":364,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01235814871720436,"rank":364,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012479998825052985,"rank":363,"remainingConfigurations":398},{"removed":"arc-agi","score":0.015266531980775959,"rank":364,"remainingConfigurations":398},{"removed":"deepswe","score":0.010645147113308677,"rank":364,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01259335040037784,"rank":364,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.012501243295872341,"rank":364,"remainingConfigurations":398},{"removed":"frontiercode","score":0.013275074714737864,"rank":364,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.012605022500594256,"rank":364,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.012468232425187548,"rank":364,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.012571367048917278,"rank":364,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01254198714269719,"rank":364,"remainingConfigurations":398},{"removed":"livebench-math","score":0.012613052320532206,"rank":364,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.012478495876009956,"rank":364,"remainingConfigurations":398},{"removed":"livebench-language","score":0.012748505761169137,"rank":364,"remainingConfigurations":398},{"removed":"livebench-data","score":0.012618236554548896,"rank":364,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.012376181520001752,"rank":364,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.012499096379217119,"rank":364,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.012799516627482346,"rank":364,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012972779333776253,"rank":364,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01190061480521082,"rank":364,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01272432540835689,"rank":364,"remainingConfigurations":398},{"removed":"simpleqa","score":0.01314093546004176,"rank":364,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.012522738493463442,"rank":364,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.01254205431078305,"rank":364,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.012533501269291715,"rank":364,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.012565604390582666,"rank":364,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01249854848904415,"rank":364,"remainingConfigurations":398}]},"gemma-3-27b-it--effort-non-reasoning":{"score":0.012438019212693883,"rank":365,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01518721528396099,"rank":365,"remainingConfigurations":398},{"removed":"Datacurve","score":0.010510134623300261,"rank":365,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.012310850080824646,"rank":365,"remainingConfigurations":398},{"removed":"Scale","score":0.013960299080299242,"rank":365,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.012417357057689498,"rank":365,"remainingConfigurations":398},{"removed":"Cognition","score":0.013108817149301406,"rank":365,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01279684672320483,"rank":364,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01281368390251309,"rank":365,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.012635090573209393,"rank":347,"remainingConfigurations":381},{"removed":"Vals AI","score":0.012117222119928354,"rank":364,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01243880382521504,"rank":365,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.012425607576315131,"rank":365,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0124157426593348,"rank":365,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.012438019212693883,"rank":365,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01240191578282599,"rank":365,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.012492252146715952,"rank":365,"remainingConfigurations":398},{"removed":"briefcase","score":0.012406658961849627,"rank":365,"remainingConfigurations":398},{"removed":"aime","score":0.0128253144855833,"rank":363,"remainingConfigurations":398},{"removed":"apex-agents","score":0.012600509080192612,"rank":365,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.012442017105760825,"rank":363,"remainingConfigurations":398},{"removed":"automationbench","score":0.01241565765280835,"rank":365,"remainingConfigurations":398},{"removed":"critpt","score":0.011513206105835552,"rank":366,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.012474182400256996,"rank":365,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.012498775066598007,"rank":365,"remainingConfigurations":398},{"removed":"gdpval","score":0.012743880900803457,"rank":363,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011920800597301074,"rank":368,"remainingConfigurations":398},{"removed":"gpqa","score":0.012497150410902463,"rank":366,"remainingConfigurations":398},{"removed":"harvey","score":0.012306075958911733,"rank":365,"remainingConfigurations":398},{"removed":"hle","score":0.013096909422018724,"rank":366,"remainingConfigurations":398},{"removed":"ifbench","score":0.012090326285269182,"rank":366,"remainingConfigurations":398},{"removed":"itbench","score":0.01242997108273639,"rank":365,"remainingConfigurations":398},{"removed":"livecodebench","score":0.013426264014781772,"rank":361,"remainingConfigurations":398},{"removed":"math500","score":0.012187936798228311,"rank":367,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.013224010036455361,"rank":366,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013207069956129169,"rank":366,"remainingConfigurations":398},{"removed":"omniscience","score":0.01166215161444268,"rank":364,"remainingConfigurations":398},{"removed":"scicode","score":0.012586180188065418,"rank":365,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01239681483382696,"rank":363,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0120742351616981,"rank":367,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01506436545560527,"rank":365,"remainingConfigurations":398},{"removed":"deepswe","score":0.01051836680118274,"rank":365,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.012441834213424185,"rank":365,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.012350973749246512,"rank":365,"remainingConfigurations":398},{"removed":"frontiercode","score":0.013108817149301406,"rank":365,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.012453362100683348,"rank":365,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.012317966849713468,"rank":365,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.012420141707827582,"rank":365,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.012392279330614266,"rank":365,"remainingConfigurations":398},{"removed":"livebench-math","score":0.012461189966950828,"rank":365,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.012328685899015398,"rank":365,"remainingConfigurations":398},{"removed":"livebench-language","score":0.012595418876762016,"rank":365,"remainingConfigurations":398},{"removed":"livebench-data","score":0.012466244656426624,"rank":365,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01222700793025736,"rank":365,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.012348702473923542,"rank":365,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.012645283296976681,"rank":365,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01281368390251309,"rank":365,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011768925591791832,"rank":365,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0125656559871348,"rank":365,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012982633876041566,"rank":365,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.012371989131491632,"rank":365,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.012391133540877721,"rank":365,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.012382644018013646,"rank":365,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01241451406944869,"rank":365,"remainingConfigurations":398},{"removed":"vibe-code","score":0.012348061003345739,"rank":365,"remainingConfigurations":398}]},"kimi-linear-48b-a3b-instruct--effort-non-reasoning":{"score":0.01222919621220656,"rank":366,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014999048786932452,"rank":366,"remainingConfigurations":398},{"removed":"Datacurve","score":0.010335630514377305,"rank":366,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.012103760572969172,"rank":366,"remainingConfigurations":398},{"removed":"Scale","score":0.013727499463026488,"rank":366,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.012201240800540039,"rank":366,"remainingConfigurations":398},{"removed":"Cognition","score":0.012907700079421358,"rank":366,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012564297625287638,"rank":365,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012615545401048209,"rank":366,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.012358417433722952,"rank":348,"remainingConfigurations":381},{"removed":"Vals AI","score":0.011886592854887558,"rank":365,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.012229977165691214,"rank":366,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.012216972848469065,"rank":366,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.012207472947301077,"rank":366,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01222919621220656,"rank":366,"remainingConfigurations":398},{"removed":"All provider reports","score":0.012193869633163101,"rank":366,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.012278200340888256,"rank":366,"remainingConfigurations":398},{"removed":"briefcase","score":0.012209598624768047,"rank":366,"remainingConfigurations":398},{"removed":"aime","score":0.011453266538288877,"rank":371,"remainingConfigurations":398},{"removed":"apex-agents","score":0.012381936980262673,"rank":366,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.011116287995832414,"rank":371,"remainingConfigurations":398},{"removed":"automationbench","score":0.012227391417798631,"rank":366,"remainingConfigurations":398},{"removed":"critpt","score":0.011741715784111956,"rank":363,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.012261574824629994,"rank":366,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.012395032553278123,"rank":366,"remainingConfigurations":398},{"removed":"gdpval","score":0.012320963225320572,"rank":366,"remainingConfigurations":398},{"removed":"gmmlu","score":0.012376738210111586,"rank":365,"remainingConfigurations":398},{"removed":"gpqa","score":0.012561267241612393,"rank":365,"remainingConfigurations":398},{"removed":"harvey","score":0.012094837994969255,"rank":366,"remainingConfigurations":398},{"removed":"hle","score":0.014305956901472752,"rank":359,"remainingConfigurations":398},{"removed":"ifbench","score":0.0124501034446601,"rank":362,"remainingConfigurations":398},{"removed":"itbench","score":0.012217698308903112,"rank":366,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011461203276311815,"rank":373,"remainingConfigurations":398},{"removed":"math500","score":0.012324930048226506,"rank":366,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.013821787400962142,"rank":364,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013168814339363658,"rank":367,"remainingConfigurations":398},{"removed":"omniscience","score":0.011495194948163855,"rank":366,"remainingConfigurations":398},{"removed":"scicode","score":0.012487457592610501,"rank":366,"remainingConfigurations":398},{"removed":"tau-bench","score":0.013049776135254066,"rank":359,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010518478487474642,"rank":375,"remainingConfigurations":398},{"removed":"arc-agi","score":0.014871405977865534,"rank":366,"remainingConfigurations":398},{"removed":"deepswe","score":0.010343666097797409,"rank":366,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.012232911338765376,"rank":366,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.012143547538644217,"rank":366,"remainingConfigurations":398},{"removed":"frontiercode","score":0.012907700079421358,"rank":366,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.012244582196227446,"rank":366,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.012112065943981065,"rank":366,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.012211485094238764,"rank":366,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.012182197828081096,"rank":366,"remainingConfigurations":398},{"removed":"livebench-math","score":0.012252111496410575,"rank":366,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.012121038851619276,"rank":366,"remainingConfigurations":398},{"removed":"livebench-language","score":0.012383569311283425,"rank":366,"remainingConfigurations":398},{"removed":"livebench-data","score":0.012257166768023431,"rank":366,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01202193167446896,"rank":366,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.012141295341281208,"rank":366,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.012433582776372284,"rank":366,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012615545401048209,"rank":366,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01155723196533897,"rank":366,"remainingConfigurations":398},{"removed":"frontiermath","score":0.012362397457553506,"rank":366,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012765196775556549,"rank":366,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.012164310778155663,"rank":366,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.012183021672806766,"rank":366,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.012174809481760125,"rank":366,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.012205835869864437,"rank":366,"remainingConfigurations":398},{"removed":"vibe-code","score":0.012140780273582135,"rank":366,"remainingConfigurations":398}]},"gpt-4--effort-non-reasoning":{"score":0.011840105532149174,"rank":367,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014579372311354625,"rank":367,"remainingConfigurations":398},{"removed":"Datacurve","score":0.01002488269753066,"rank":367,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011719670564968726,"rank":367,"remainingConfigurations":398},{"removed":"Scale","score":0.013296281722449491,"rank":367,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.011816925017773844,"rank":367,"remainingConfigurations":398},{"removed":"Cognition","score":0.01252086904896667,"rank":367,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012171271041073446,"rank":366,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012211247087925113,"rank":367,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.011937650290363677,"rank":350,"remainingConfigurations":381},{"removed":"Vals AI","score":0.011517412071876289,"rank":366,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.011840858394541109,"rank":367,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011828292307117001,"rank":367,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.011819044140364545,"rank":367,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.011840105532149174,"rank":367,"remainingConfigurations":398},{"removed":"All provider reports","score":0.011805889234691594,"rank":367,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011893557570984445,"rank":367,"remainingConfigurations":398},{"removed":"briefcase","score":0.01185774477805661,"rank":367,"remainingConfigurations":398},{"removed":"aime","score":0.01163740501778098,"rank":369,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011995249844673003,"rank":367,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.011748051403180205,"rank":367,"remainingConfigurations":398},{"removed":"automationbench","score":0.01187645120343221,"rank":367,"remainingConfigurations":398},{"removed":"critpt","score":0.011428725490329153,"rank":367,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011886793257298656,"rank":367,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.012034439944435038,"rank":367,"remainingConfigurations":398},{"removed":"gdpval","score":0.01141927284902852,"rank":371,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011989234451375187,"rank":367,"remainingConfigurations":398},{"removed":"gpqa","score":0.012874908069621022,"rank":363,"remainingConfigurations":398},{"removed":"harvey","score":0.01172482297258859,"rank":367,"remainingConfigurations":398},{"removed":"hle","score":0.01252283759094912,"rank":367,"remainingConfigurations":398},{"removed":"ifbench","score":0.010728560879488697,"rank":372,"remainingConfigurations":398},{"removed":"itbench","score":0.01183651915411378,"rank":367,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011726699253298117,"rank":368,"remainingConfigurations":398},{"removed":"math500","score":0.01680636237255857,"rank":342,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.014286728129971433,"rank":361,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.0127772610072897,"rank":369,"remainingConfigurations":398},{"removed":"omniscience","score":0.00684454864499124,"rank":390,"remainingConfigurations":398},{"removed":"scicode","score":0.012143870093227123,"rank":367,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01155094570896776,"rank":367,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.011990900277891015,"rank":369,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01444822011974106,"rank":367,"remainingConfigurations":398},{"removed":"deepswe","score":0.010032689388824923,"rank":367,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01184371190898726,"rank":367,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.011757139768315066,"rank":367,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01252086904896667,"rank":367,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.011855759073920715,"rank":367,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.011726880855035036,"rank":367,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.011823045915222046,"rank":367,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.011794891346583883,"rank":367,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011862307607063907,"rank":367,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011735319210502061,"rank":367,"remainingConfigurations":398},{"removed":"livebench-language","score":0.011989774958436505,"rank":367,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011867263630473433,"rank":367,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011639244224084957,"rank":367,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.011754915538275297,"rank":367,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0120380560878778,"rank":367,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012211247087925113,"rank":367,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011228186268367496,"rank":367,"remainingConfigurations":398},{"removed":"frontiermath","score":0.011969316618647944,"rank":367,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012360528917544715,"rank":367,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.011777234828987945,"rank":367,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011795398241212883,"rank":367,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.011787353081783131,"rank":367,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.011817532542997106,"rank":367,"remainingConfigurations":398},{"removed":"vibe-code","score":0.011754448765835016,"rank":367,"remainingConfigurations":398}]},"ministral-3-3b--effort-non-reasoning":{"score":0.01177515912809715,"rank":368,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014387379062444382,"rank":371,"remainingConfigurations":398},{"removed":"Datacurve","score":0.009951578135177044,"rank":368,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011656188045181601,"rank":368,"remainingConfigurations":398},{"removed":"Scale","score":0.013228271922306562,"rank":368,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.011757837145056549,"rank":368,"remainingConfigurations":398},{"removed":"Cognition","score":0.012411410294747162,"rank":369,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012120658379452337,"rank":367,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012146283237825446,"rank":369,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.012040623273014793,"rank":349,"remainingConfigurations":381},{"removed":"Vals AI","score":0.011479054132671104,"rank":367,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.011775901764597056,"rank":368,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011763422179424436,"rank":368,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.011754011190687847,"rank":368,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01177515912809715,"rank":368,"remainingConfigurations":398},{"removed":"All provider reports","score":0.01174093009074386,"rank":368,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011828339958083052,"rank":368,"remainingConfigurations":398},{"removed":"briefcase","score":0.011378630137281008,"rank":371,"remainingConfigurations":398},{"removed":"aime","score":0.01201141445486245,"rank":367,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011934923085833255,"rank":368,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.011433169334691606,"rank":369,"remainingConfigurations":398},{"removed":"automationbench","score":0.011254193082825256,"rank":372,"remainingConfigurations":398},{"removed":"critpt","score":0.010845359569011358,"rank":368,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011813167580830453,"rank":368,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.011924408720069682,"rank":369,"remainingConfigurations":398},{"removed":"gdpval","score":0.01146169952768736,"rank":370,"remainingConfigurations":398},{"removed":"gmmlu","score":0.012217123232078143,"rank":366,"remainingConfigurations":398},{"removed":"gpqa","score":0.011990892446188874,"rank":371,"remainingConfigurations":398},{"removed":"harvey","score":0.01165386738204587,"rank":368,"remainingConfigurations":398},{"removed":"hle","score":0.011687845810591633,"rank":373,"remainingConfigurations":398},{"removed":"ifbench","score":0.011819905069280866,"rank":369,"remainingConfigurations":398},{"removed":"itbench","score":0.011770312689519129,"rank":368,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01228146029185929,"rank":365,"remainingConfigurations":398},{"removed":"math500","score":0.011872523963114806,"rank":369,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.013099950007042135,"rank":368,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013005024270772242,"rank":368,"remainingConfigurations":398},{"removed":"omniscience","score":0.011377431986770693,"rank":367,"remainingConfigurations":398},{"removed":"scicode","score":0.012078154411993806,"rank":368,"remainingConfigurations":398},{"removed":"tau-bench","score":0.011120025832404923,"rank":369,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.011805188371410582,"rank":371,"remainingConfigurations":398},{"removed":"arc-agi","score":0.014270711941387034,"rank":371,"remainingConfigurations":398},{"removed":"deepswe","score":0.00995938874079692,"rank":368,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01177878194973265,"rank":368,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.011692901879343735,"rank":368,"remainingConfigurations":398},{"removed":"frontiercode","score":0.012411410294747162,"rank":369,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01178993513611433,"rank":368,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.011661364583435354,"rank":368,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.011758262502541741,"rank":368,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.011732352996805091,"rank":368,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011797085653828298,"rank":368,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011671624329841923,"rank":368,"remainingConfigurations":398},{"removed":"livebench-language","score":0.01192444192454578,"rank":368,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011801905918314487,"rank":368,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011575087358130556,"rank":368,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0116904879862078,"rank":368,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.011971569371596541,"rank":368,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012146283237825446,"rank":369,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0111619196363022,"rank":368,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01189438796022589,"rank":368,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012290886190369674,"rank":368,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.011712566403547078,"rank":368,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011730716590222028,"rank":368,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.011722660844809135,"rank":368,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.011752908081200462,"rank":368,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01168987938216656,"rank":368,"remainingConfigurations":398}]},"qwen3-1.7b--effort-reasoning":{"score":0.011761536721974506,"rank":369,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014459509779596784,"rank":369,"remainingConfigurations":398},{"removed":"Datacurve","score":0.00994527057684834,"rank":369,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011641327338625789,"rank":369,"remainingConfigurations":398},{"removed":"Scale","score":0.013207369771619043,"rank":369,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.011735092734509171,"rank":369,"remainingConfigurations":398},{"removed":"Cognition","score":0.01242469672659447,"rank":368,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012085713166475933,"rank":368,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01215146369376228,"rank":368,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.011849048497041617,"rank":352,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01143266894736721,"rank":368,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01176228590322051,"rank":369,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011749768119740598,"rank":369,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.011740623593399328,"rank":369,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.011761536721974506,"rank":369,"remainingConfigurations":398},{"removed":"All provider reports","score":0.011727523847905971,"rank":369,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011809647238767013,"rank":369,"remainingConfigurations":398},{"removed":"briefcase","score":0.011756621799342086,"rank":368,"remainingConfigurations":398},{"removed":"aime","score":0.01095469636823885,"rank":373,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011912251215402748,"rank":369,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.012151395302290063,"rank":364,"remainingConfigurations":398},{"removed":"automationbench","score":0.01177430992185395,"rank":368,"remainingConfigurations":398},{"removed":"critpt","score":0.010580446080135473,"rank":369,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011796686054915037,"rank":369,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.011935246891982729,"rank":368,"remainingConfigurations":398},{"removed":"gdpval","score":0.011838343023909605,"rank":368,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011893127627131609,"rank":369,"remainingConfigurations":398},{"removed":"gpqa","score":0.012105655831171238,"rank":369,"remainingConfigurations":398},{"removed":"harvey","score":0.011634638779967075,"rank":369,"remainingConfigurations":398},{"removed":"hle","score":0.011998300194710832,"rank":371,"remainingConfigurations":398},{"removed":"ifbench","score":0.01192805891886295,"rank":368,"remainingConfigurations":398},{"removed":"itbench","score":0.011752714586580448,"rank":369,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01183932567407986,"rank":367,"remainingConfigurations":398},{"removed":"math500","score":0.011232573096798072,"rank":373,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.013019338883601921,"rank":369,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.012665346684033916,"rank":370,"remainingConfigurations":398},{"removed":"omniscience","score":0.011228088137067745,"rank":368,"remainingConfigurations":398},{"removed":"scicode","score":0.012026522660372449,"rank":369,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01082652487868059,"rank":370,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012417522570162503,"rank":364,"remainingConfigurations":398},{"removed":"arc-agi","score":0.014334727605542939,"rank":368,"remainingConfigurations":398},{"removed":"deepswe","score":0.009953003090847207,"rank":369,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.011765114148334017,"rank":369,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.011679024916882401,"rank":369,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01242469672659447,"rank":368,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.01177643289610715,"rank":369,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.01164881794819427,"rank":369,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01174452301365173,"rank":369,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.01171635404584011,"rank":369,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011783586135520685,"rank":369,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011657408832123755,"rank":369,"remainingConfigurations":398},{"removed":"livebench-language","score":0.011910147363805171,"rank":369,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011788502127177629,"rank":369,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011562005719913235,"rank":369,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.011676907874173005,"rank":369,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.011958307640011533,"rank":369,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01215146369376228,"rank":368,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011097336525818761,"rank":370,"remainingConfigurations":398},{"removed":"frontiermath","score":0.011892603287311862,"rank":369,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0122770130244744,"rank":369,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.011699075957944886,"rank":369,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011717091324621393,"rank":369,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.011709182878085434,"rank":369,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.011739044259098254,"rank":369,"remainingConfigurations":398},{"removed":"vibe-code","score":0.011676415420846633,"rank":369,"remainingConfigurations":398}]},"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning":{"score":0.011734371845209556,"rank":370,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014416481567974497,"rank":370,"remainingConfigurations":398},{"removed":"Datacurve","score":0.009926895839681586,"rank":370,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011615194622867095,"rank":370,"remainingConfigurations":398},{"removed":"Scale","score":0.013179225229604167,"rank":370,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.011708756050922343,"rank":370,"remainingConfigurations":398},{"removed":"Cognition","score":0.0124024992464939,"rank":370,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012059139372936477,"rank":369,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01211254880447738,"rank":370,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.011855363366691572,"rank":351,"remainingConfigurations":381},{"removed":"Vals AI","score":0.011407579317768457,"rank":369,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.011735120614471926,"rank":370,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011722621162511724,"rank":370,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.011713472045752087,"rank":370,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.011734371845209556,"rank":370,"remainingConfigurations":398},{"removed":"All provider reports","score":0.011700393884532203,"rank":370,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011782674158146185,"rank":370,"remainingConfigurations":398},{"removed":"briefcase","score":0.011715079086597824,"rank":369,"remainingConfigurations":398},{"removed":"aime","score":0.011683979280073161,"rank":368,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011885712269193513,"rank":370,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.011154501997411845,"rank":370,"remainingConfigurations":398},{"removed":"automationbench","score":0.011736218622544667,"rank":369,"remainingConfigurations":398},{"removed":"critpt","score":0.0105593717101485,"rank":370,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011770280979361338,"rank":370,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.011899139565983196,"rank":370,"remainingConfigurations":398},{"removed":"gdpval","score":0.011822814840811399,"rank":369,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011861401373650578,"rank":370,"remainingConfigurations":398},{"removed":"gpqa","score":0.011752811259625016,"rank":372,"remainingConfigurations":398},{"removed":"harvey","score":0.011609019001561355,"rank":370,"remainingConfigurations":398},{"removed":"hle","score":0.012389910034698004,"rank":369,"remainingConfigurations":398},{"removed":"ifbench","score":0.011937205774208322,"rank":367,"remainingConfigurations":398},{"removed":"itbench","score":0.011726305257391184,"rank":370,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011504328779389837,"rank":371,"remainingConfigurations":398},{"removed":"math500","score":0.011853126410494604,"rank":370,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.01253242292420441,"rank":370,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.012597695319476293,"rank":371,"remainingConfigurations":398},{"removed":"omniscience","score":0.010907457632041309,"rank":369,"remainingConfigurations":398},{"removed":"scicode","score":0.011990126359599439,"rank":370,"remainingConfigurations":398},{"removed":"tau-bench","score":0.01142107705422689,"rank":368,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012412400636897835,"rank":365,"remainingConfigurations":398},{"removed":"arc-agi","score":0.014289465508912315,"rank":370,"remainingConfigurations":398},{"removed":"deepswe","score":0.009934607259016261,"rank":370,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01173793935894979,"rank":370,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.011652166415149622,"rank":370,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0124024992464939,"rank":370,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.011749462876496709,"rank":370,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.011622107179708676,"rank":370,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.011717391984234745,"rank":370,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.011689246155410572,"rank":370,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011756354750453843,"rank":370,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011630527833831061,"rank":370,"remainingConfigurations":398},{"removed":"livebench-language","score":0.011882649056351358,"rank":370,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011761254352790762,"rank":370,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011535287728443713,"rank":370,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.01164994122744484,"rank":370,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01193068414685565,"rank":370,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01211254880447738,"rank":370,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011101925703690377,"rank":369,"remainingConfigurations":398},{"removed":"frontiermath","score":0.011865657001457683,"rank":370,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012248015293722237,"rank":370,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01167205296662234,"rank":370,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011690020324643573,"rank":370,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.011682145283775822,"rank":370,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.011711915487170294,"rank":370,"remainingConfigurations":398},{"removed":"vibe-code","score":0.01164944235925717,"rank":370,"remainingConfigurations":398}]},"qwen3.5-0.8b--effort-non-reasoning":{"score":0.011699931907294576,"rank":371,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.014460504396508653,"rank":368,"remainingConfigurations":398},{"removed":"Datacurve","score":0.009918469882642783,"rank":371,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011588156396991484,"rank":371,"remainingConfigurations":398},{"removed":"Scale","score":0.013150957317706172,"rank":371,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.01167790130253353,"rank":371,"remainingConfigurations":398},{"removed":"Cognition","score":0.012399877042467944,"rank":371,"remainingConfigurations":398},{"removed":"LiveBench","score":0.012030433042643299,"rank":370,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.012088307845456295,"rank":371,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.011815042762176833,"rank":353,"remainingConfigurations":381},{"removed":"Vals AI","score":0.011382194623371531,"rank":370,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.01170067902949728,"rank":371,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011688282673638367,"rank":371,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.011679026874784275,"rank":371,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.011699931907294576,"rank":371,"remainingConfigurations":398},{"removed":"All provider reports","score":0.011666051853996039,"rank":371,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011755414780338647,"rank":371,"remainingConfigurations":398},{"removed":"briefcase","score":0.011700143894448789,"rank":370,"remainingConfigurations":398},{"removed":"aime","score":0.011636145839717525,"rank":370,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011856699737062248,"rank":371,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.011698342891773275,"rank":368,"remainingConfigurations":398},{"removed":"automationbench","score":0.011719793403740299,"rank":370,"remainingConfigurations":398},{"removed":"critpt","score":0.010326600688487243,"rank":371,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011746524863877337,"rank":371,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.011883350633017984,"rank":371,"remainingConfigurations":398},{"removed":"gdpval","score":0.011978134940386442,"rank":367,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011817906224825592,"rank":371,"remainingConfigurations":398},{"removed":"gpqa","score":0.012806929590427457,"rank":364,"remainingConfigurations":398},{"removed":"harvey","score":0.011584903278270572,"rank":371,"remainingConfigurations":398},{"removed":"hle","score":0.01123245011248515,"rank":376,"remainingConfigurations":398},{"removed":"ifbench","score":0.012410294985253638,"rank":363,"remainingConfigurations":398},{"removed":"itbench","score":0.011702804246421538,"rank":371,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011688822000496,"rank":369,"remainingConfigurations":398},{"removed":"math500","score":0.01175975547683817,"rank":371,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.012086342818053835,"rank":372,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.013546937452973038,"rank":365,"remainingConfigurations":398},{"removed":"omniscience","score":0.012030953758410456,"rank":363,"remainingConfigurations":398},{"removed":"scicode","score":0.011977794716107331,"rank":371,"remainingConfigurations":398},{"removed":"tau-bench","score":0.00861271340429375,"rank":380,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.012576405049793593,"rank":362,"remainingConfigurations":398},{"removed":"arc-agi","score":0.014324798538128125,"rank":369,"remainingConfigurations":398},{"removed":"deepswe","score":0.009926178902901752,"rank":371,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.011703493907087331,"rank":371,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01161807328992349,"rank":371,"remainingConfigurations":398},{"removed":"frontiercode","score":0.012399877042467944,"rank":371,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.011715715063502477,"rank":371,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.01158841611472263,"rank":371,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.011683039284568202,"rank":371,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.011655285960770166,"rank":371,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011721828626752848,"rank":371,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011596468273111421,"rank":371,"remainingConfigurations":398},{"removed":"livebench-language","score":0.011847870180651657,"rank":371,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011726800800998388,"rank":371,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011501373753074876,"rank":371,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.011615716427135638,"rank":371,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.011895554075815074,"rank":371,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.012088307845456295,"rank":371,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.011036857824218602,"rank":371,"remainingConfigurations":398},{"removed":"frontiermath","score":0.011833376298168814,"rank":371,"remainingConfigurations":398},{"removed":"simpleqa","score":0.012210360639806248,"rank":371,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.011637797310098593,"rank":371,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011655740262041627,"rank":371,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01164778615353658,"rank":371,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01167761003135988,"rank":371,"remainingConfigurations":398},{"removed":"vibe-code","score":0.011615268430693902,"rank":371,"remainingConfigurations":398}]},"qwen3-vl-4b-instruct--effort-non-reasoning":{"score":0.011283541669531204,"rank":372,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.013825543313308193,"rank":372,"remainingConfigurations":398},{"removed":"Datacurve","score":0.00953212781745958,"rank":372,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.011168221161719309,"rank":372,"remainingConfigurations":398},{"removed":"Scale","score":0.012666949513006462,"rank":372,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.011261090879398208,"rank":372,"remainingConfigurations":398},{"removed":"Cognition","score":0.01190602353268206,"rank":372,"remainingConfigurations":398},{"removed":"LiveBench","score":0.011599144318171092,"rank":371,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.011636234678136482,"rank":372,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01139848114763528,"rank":355,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01097318212838442,"rank":371,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0112842624842159,"rank":372,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.011272242825181257,"rank":372,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.01126342501485253,"rank":372,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.011283541669531204,"rank":372,"remainingConfigurations":398},{"removed":"All provider reports","score":0.011250849318588602,"rank":372,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.011332409518963854,"rank":372,"remainingConfigurations":398},{"removed":"briefcase","score":0.011262382727925048,"rank":372,"remainingConfigurations":398},{"removed":"aime","score":0.010479324137999567,"rank":376,"remainingConfigurations":398},{"removed":"apex-agents","score":0.011426765526258558,"rank":372,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.010992558496539568,"rank":372,"remainingConfigurations":398},{"removed":"automationbench","score":0.011278472730437056,"rank":371,"remainingConfigurations":398},{"removed":"critpt","score":0.010128872068161666,"rank":372,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.011320938063057945,"rank":372,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.011439201084048925,"rank":372,"remainingConfigurations":398},{"removed":"gdpval","score":0.0113565174926257,"rank":372,"remainingConfigurations":398},{"removed":"gmmlu","score":0.011404702293570402,"rank":372,"remainingConfigurations":398},{"removed":"gpqa","score":0.01153131300755184,"rank":373,"remainingConfigurations":398},{"removed":"harvey","score":0.011163024103556145,"rank":372,"remainingConfigurations":398},{"removed":"hle","score":0.012454095278566205,"rank":368,"remainingConfigurations":398},{"removed":"ifbench","score":0.010915570276502815,"rank":371,"remainingConfigurations":398},{"removed":"itbench","score":0.011275219817990902,"rank":372,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011466459572143787,"rank":372,"remainingConfigurations":398},{"removed":"math500","score":0.011391930580509954,"rank":372,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.012222676650731026,"rank":371,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.012211118784555976,"rank":372,"remainingConfigurations":398},{"removed":"omniscience","score":0.010627358651488436,"rank":371,"remainingConfigurations":398},{"removed":"scicode","score":0.011526263764240395,"rank":372,"remainingConfigurations":398},{"removed":"tau-bench","score":0.010570816523292892,"rank":373,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.011975155903063197,"rank":370,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0137085765203007,"rank":372,"remainingConfigurations":398},{"removed":"deepswe","score":0.009539548964491268,"rank":372,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.011286977594923588,"rank":372,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.011204449606613076,"rank":372,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01190602353268206,"rank":372,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.011297478672200536,"rank":372,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.011174880775063607,"rank":372,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01126721773386169,"rank":372,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.011240380212371072,"rank":372,"remainingConfigurations":398},{"removed":"livebench-math","score":0.011304705928242469,"rank":372,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.011183617390370167,"rank":372,"remainingConfigurations":398},{"removed":"livebench-language","score":0.011426286856072491,"rank":372,"remainingConfigurations":398},{"removed":"livebench-data","score":0.011309398515404844,"rank":372,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.011091943316772873,"rank":372,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.011202282058579564,"rank":372,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.011472433009774572,"rank":372,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.011636234678136482,"rank":372,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.01066237648208007,"rank":372,"remainingConfigurations":398},{"removed":"frontiermath","score":0.011407043017447466,"rank":372,"remainingConfigurations":398},{"removed":"simpleqa","score":0.011778765737609337,"rank":372,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.01122356031556708,"rank":372,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.011240868010267331,"rank":372,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.011233251714042347,"rank":372,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01126195338604521,"rank":372,"remainingConfigurations":398},{"removed":"vibe-code","score":0.011201829149242788,"rank":372,"remainingConfigurations":398}]},"gemma-3-12b-it--effort-non-reasoning":{"score":0.010773587956049059,"rank":373,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.013171061066533476,"rank":374,"remainingConfigurations":398},{"removed":"Datacurve","score":0.009103191052587663,"rank":373,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01066440408932179,"rank":373,"remainingConfigurations":398},{"removed":"Scale","score":0.012099101778839487,"rank":373,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.010756446388164692,"rank":373,"remainingConfigurations":398},{"removed":"Cognition","score":0.011359706337217801,"rank":374,"remainingConfigurations":398},{"removed":"LiveBench","score":0.011088310616121207,"rank":372,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.011101474331035066,"rank":373,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.010951190994133312,"rank":356,"remainingConfigurations":381},{"removed":"Vals AI","score":0.010499404911007098,"rank":372,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.010774269794990243,"rank":373,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.010762813543657062,"rank":373,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.010754267545499692,"rank":373,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.010773587956049059,"rank":373,"remainingConfigurations":398},{"removed":"All provider reports","score":0.010742263441515139,"rank":373,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.010821888533573992,"rank":373,"remainingConfigurations":398},{"removed":"briefcase","score":0.010740096477488406,"rank":373,"remainingConfigurations":398},{"removed":"aime","score":0.011101986637079134,"rank":372,"remainingConfigurations":398},{"removed":"apex-agents","score":0.010916006739133849,"rank":373,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.010665205970833662,"rank":374,"remainingConfigurations":398},{"removed":"automationbench","score":0.010701208222172886,"rank":373,"remainingConfigurations":398},{"removed":"critpt","score":0.009841281422345085,"rank":374,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.01080700793313156,"rank":373,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.010530440562500389,"rank":375,"remainingConfigurations":398},{"removed":"gdpval","score":0.010949424834065505,"rank":373,"remainingConfigurations":398},{"removed":"gmmlu","score":0.010694195376359657,"rank":375,"remainingConfigurations":398},{"removed":"gpqa","score":0.010953347356235146,"rank":374,"remainingConfigurations":398},{"removed":"harvey","score":0.010660709693191875,"rank":373,"remainingConfigurations":398},{"removed":"hle","score":0.011334015625472689,"rank":374,"remainingConfigurations":398},{"removed":"ifbench","score":0.00985905622810661,"rank":377,"remainingConfigurations":398},{"removed":"itbench","score":0.010767887650915605,"rank":373,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011542852900915968,"rank":370,"remainingConfigurations":398},{"removed":"math500","score":0.010617145907998803,"rank":375,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.011563089979870579,"rank":373,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.011913699119985828,"rank":373,"remainingConfigurations":398},{"removed":"omniscience","score":0.010190747447506006,"rank":372,"remainingConfigurations":398},{"removed":"scicode","score":0.010973702079570264,"rank":373,"remainingConfigurations":398},{"removed":"tau-bench","score":0.010644189717304653,"rank":372,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010703302737364783,"rank":372,"remainingConfigurations":398},{"removed":"arc-agi","score":0.01306340725852006,"rank":373,"remainingConfigurations":398},{"removed":"deepswe","score":0.009110330812838489,"rank":373,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.010776900093256518,"rank":373,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.01069815240619029,"rank":373,"remainingConfigurations":398},{"removed":"frontiercode","score":0.011359706337217801,"rank":374,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.010787108143232823,"rank":373,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.010669410423829422,"rank":373,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.010758107591703094,"rank":373,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.010734125542352214,"rank":373,"remainingConfigurations":398},{"removed":"livebench-math","score":0.01079373082502036,"rank":373,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.01067849048390039,"rank":373,"remainingConfigurations":398},{"removed":"livebench-language","score":0.010910334543109806,"rank":373,"remainingConfigurations":398},{"removed":"livebench-data","score":0.010798168920022498,"rank":373,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.010590266495345719,"rank":373,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.010695956866966923,"rank":373,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.010953784852673893,"rank":373,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.011101474331035066,"rank":373,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.010191993275470088,"rank":373,"remainingConfigurations":398},{"removed":"frontiermath","score":0.010884910021440847,"rank":374,"remainingConfigurations":398},{"removed":"simpleqa","score":0.011247463411145393,"rank":374,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.010716215595880492,"rank":373,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.010732839763801601,"rank":373,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.010725475388701196,"rank":373,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.010753120936388675,"rank":373,"remainingConfigurations":398},{"removed":"vibe-code","score":0.010695436918392162,"rank":373,"remainingConfigurations":398}]},"qwen3-8b--effort-non-reasoning":{"score":0.010653381866180657,"rank":374,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.011553328592767538,"rank":160,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.013182481608067231,"rank":373,"remainingConfigurations":398},{"removed":"Datacurve","score":0.009101002291569507,"rank":374,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01055900086276742,"rank":374,"remainingConfigurations":398},{"removed":"Scale","score":0.01195673923093734,"rank":374,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.010675282266732387,"rank":374,"remainingConfigurations":398},{"removed":"Cognition","score":0.011362496668457895,"rank":373,"remainingConfigurations":398},{"removed":"LiveBench","score":0.010955512667848973,"rank":373,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.010944758069181952,"rank":374,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.009960739332121797,"rank":359,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01046465312386076,"rank":373,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.010653921911570406,"rank":374,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.010642018500067055,"rank":374,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.010635942044336473,"rank":374,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.010653381866180657,"rank":374,"remainingConfigurations":398},{"removed":"All provider reports","score":0.010623280814261338,"rank":374,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.010694887852389715,"rank":374,"remainingConfigurations":398},{"removed":"briefcase","score":0.010628998576231044,"rank":374,"remainingConfigurations":398},{"removed":"aime","score":0.010683498766559359,"rank":375,"remainingConfigurations":398},{"removed":"apex-agents","score":0.010779309781049712,"rank":374,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01083394882447176,"rank":373,"remainingConfigurations":398},{"removed":"automationbench","score":0.010641040499173639,"rank":374,"remainingConfigurations":398},{"removed":"critpt","score":0.009716755047645416,"rank":376,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.010682336926025096,"rank":374,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.010772035130180933,"rank":373,"remainingConfigurations":398},{"removed":"gdpval","score":0.010685719282673109,"rank":374,"remainingConfigurations":398},{"removed":"gmmlu","score":0.010755725682391101,"rank":373,"remainingConfigurations":398},{"removed":"gpqa","score":0.009887789273445224,"rank":377,"remainingConfigurations":398},{"removed":"harvey","score":0.010533355154798231,"rank":374,"remainingConfigurations":398},{"removed":"hle","score":0.011706942969828082,"rank":372,"remainingConfigurations":398},{"removed":"ifbench","score":0.010521965571522317,"rank":373,"remainingConfigurations":398},{"removed":"itbench","score":0.01064183028070921,"rank":374,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011137117441755466,"rank":375,"remainingConfigurations":398},{"removed":"math500","score":0.010754214490596534,"rank":374,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.011241316840711486,"rank":374,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.011454552875059991,"rank":374,"remainingConfigurations":398},{"removed":"omniscience","score":0.010043846772088678,"rank":373,"remainingConfigurations":398},{"removed":"scicode","score":0.01084471732650985,"rank":374,"remainingConfigurations":398},{"removed":"tau-bench","score":0.009855827668605313,"rank":374,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.01065104365931121,"rank":374,"remainingConfigurations":398},{"removed":"arc-agi","score":0.013051696873187753,"rank":374,"remainingConfigurations":398},{"removed":"deepswe","score":0.00910832070196641,"rank":374,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.01065656990247472,"rank":374,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.010580366422173854,"rank":374,"remainingConfigurations":398},{"removed":"frontiercode","score":0.011362496668457895,"rank":373,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.010675145568113107,"rank":374,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.010548535671802278,"rank":374,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01063845205800529,"rank":374,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.010612150310014988,"rank":374,"remainingConfigurations":398},{"removed":"livebench-math","score":0.010675934921813603,"rank":374,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.010552115266234709,"rank":374,"remainingConfigurations":398},{"removed":"livebench-language","score":0.010787926831967108,"rank":374,"remainingConfigurations":398},{"removed":"livebench-data","score":0.010679715424131748,"rank":374,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.010474467357516537,"rank":374,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.010576138824839836,"rank":374,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.010832690295184784,"rank":374,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.010944758069181952,"rank":374,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.009972930821456423,"rank":375,"remainingConfigurations":398},{"removed":"frontiermath","score":0.010910355189740527,"rank":373,"remainingConfigurations":398},{"removed":"simpleqa","score":0.011273267762196735,"rank":373,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.010596668759172714,"rank":374,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.010614107760851544,"rank":374,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.010604169045717165,"rank":374,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.010633447405211346,"rank":374,"remainingConfigurations":398},{"removed":"vibe-code","score":0.010577967895227936,"rank":374,"remainingConfigurations":398}]},"pixtral-large-2411--effort-non-reasoning":{"score":0.010596067195668362,"rank":375,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.013018599600668618,"rank":375,"remainingConfigurations":398},{"removed":"Datacurve","score":0.008955665162610772,"rank":375,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.01048781802611438,"rank":375,"remainingConfigurations":398},{"removed":"Scale","score":0.011902055964709184,"rank":375,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.010573021708471818,"rank":375,"remainingConfigurations":398},{"removed":"Cognition","score":0.011191141713665203,"rank":375,"remainingConfigurations":398},{"removed":"LiveBench","score":0.010890022501068753,"rank":374,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.010932897999646946,"rank":375,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.01064592813716967,"rank":357,"remainingConfigurations":381},{"removed":"Vals AI","score":0.010302510500156402,"rank":374,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.010596744294227684,"rank":375,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.010585410644393103,"rank":375,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.010577199662045017,"rank":375,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.010596067195668362,"rank":375,"remainingConfigurations":398},{"removed":"All provider reports","score":0.010565342467958733,"rank":375,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.010640442865391725,"rank":375,"remainingConfigurations":398},{"removed":"briefcase","score":0.010586058678149551,"rank":375,"remainingConfigurations":398},{"removed":"aime","score":0.012185360037509611,"rank":366,"remainingConfigurations":398},{"removed":"apex-agents","score":0.01073035231075501,"rank":375,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.010484994836434343,"rank":376,"remainingConfigurations":398},{"removed":"automationbench","score":0.01060001450676242,"rank":375,"remainingConfigurations":398},{"removed":"critpt","score":0.010110554317908952,"rank":373,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.010627132231850293,"rank":375,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.010745578176370717,"rank":374,"remainingConfigurations":398},{"removed":"gdpval","score":0.010679692489536376,"rank":375,"remainingConfigurations":398},{"removed":"gmmlu","score":0.010702818428416616,"rank":374,"remainingConfigurations":398},{"removed":"gpqa","score":0.010189643173559084,"rank":375,"remainingConfigurations":398},{"removed":"harvey","score":0.010482064334972582,"rank":375,"remainingConfigurations":398},{"removed":"hle","score":0.01207995283131245,"rank":370,"remainingConfigurations":398},{"removed":"ifbench","score":0.009546907753710582,"rank":379,"remainingConfigurations":398},{"removed":"itbench","score":0.010587193426515146,"rank":375,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011168325478119306,"rank":374,"remainingConfigurations":398},{"removed":"math500","score":0.011929696372247769,"rank":368,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.010535043004095265,"rank":377,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.010828938628920442,"rank":377,"remainingConfigurations":398},{"removed":"omniscience","score":0.009884120011517308,"rank":374,"remainingConfigurations":398},{"removed":"scicode","score":0.010826643228940261,"rank":375,"remainingConfigurations":398},{"removed":"tau-bench","score":0.008701506027803946,"rank":379,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010656504975246792,"rank":373,"remainingConfigurations":398},{"removed":"arc-agi","score":0.012905036597420727,"rank":375,"remainingConfigurations":398},{"removed":"deepswe","score":0.008962637114535469,"rank":375,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.010599294344825606,"rank":375,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.010521832574007952,"rank":375,"remainingConfigurations":398},{"removed":"frontiercode","score":0.011191141713665203,"rank":375,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.010609785332919721,"rank":375,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.010494544315086604,"rank":375,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.010580749098321537,"rank":375,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.010555214873833102,"rank":375,"remainingConfigurations":398},{"removed":"livebench-math","score":0.010615988321751596,"rank":375,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.010502015101235626,"rank":375,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0107302505701833,"rank":375,"remainingConfigurations":398},{"removed":"livebench-data","score":0.010620381635213038,"rank":375,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.010415947509863074,"rank":375,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.010519667763380612,"rank":375,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.010773763637777297,"rank":375,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.010932897999646946,"rank":375,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.010003881701154039,"rank":374,"remainingConfigurations":398},{"removed":"frontiermath","score":0.010713245632811355,"rank":375,"remainingConfigurations":398},{"removed":"simpleqa","score":0.011063073533552513,"rank":375,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.010539666484565542,"rank":375,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.010555927832970553,"rank":375,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.010548807081860836,"rank":375,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.01057571995261209,"rank":375,"remainingConfigurations":398},{"removed":"vibe-code","score":0.010519232051128312,"rank":375,"remainingConfigurations":398}]},"phi-4--effort-non-reasoning":{"score":0.01036064261848514,"rank":376,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.012698845702119274,"rank":377,"remainingConfigurations":398},{"removed":"Datacurve","score":0.008751073589382282,"rank":377,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.010254800711480124,"rank":376,"remainingConfigurations":398},{"removed":"Scale","score":0.011634466711004017,"rank":376,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.010339191899750104,"rank":377,"remainingConfigurations":398},{"removed":"Cognition","score":0.01093333375876321,"rank":377,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01065023386955201,"rank":375,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.010684170011158933,"rank":376,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.010455157437408264,"rank":358,"remainingConfigurations":381},{"removed":"Vals AI","score":0.010075344108448037,"rank":376,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.010361303235819096,"rank":376,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.010350259308251675,"rank":376,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.010342195159897576,"rank":376,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.01036064261848514,"rank":376,"remainingConfigurations":398},{"removed":"All provider reports","score":0.010330635695136559,"rank":376,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.010405554313782754,"rank":376,"remainingConfigurations":398},{"removed":"briefcase","score":0.010343161025969667,"rank":376,"remainingConfigurations":398},{"removed":"aime","score":0.010734032376755687,"rank":374,"remainingConfigurations":398},{"removed":"apex-agents","score":0.010492340902952124,"rank":376,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.01061396213312648,"rank":375,"remainingConfigurations":398},{"removed":"automationbench","score":0.01035411549122368,"rank":376,"remainingConfigurations":398},{"removed":"critpt","score":0.009214232346317854,"rank":377,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.010395307257416227,"rank":376,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.010496266686656708,"rank":376,"remainingConfigurations":398},{"removed":"gdpval","score":0.010428260304635532,"rank":376,"remainingConfigurations":398},{"removed":"gmmlu","score":0.010462911632807048,"rank":376,"remainingConfigurations":398},{"removed":"gpqa","score":0.009689548491936118,"rank":379,"remainingConfigurations":398},{"removed":"harvey","score":0.010249446826360233,"rank":376,"remainingConfigurations":398},{"removed":"hle","score":0.011221889070471515,"rank":377,"remainingConfigurations":398},{"removed":"ifbench","score":0.010518915917597293,"rank":374,"remainingConfigurations":398},{"removed":"itbench","score":0.010352861723184644,"rank":376,"remainingConfigurations":398},{"removed":"livecodebench","score":0.011010169204324537,"rank":376,"remainingConfigurations":398},{"removed":"math500","score":0.010581092739344227,"rank":376,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.010227837202580924,"rank":378,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.011168971671608121,"rank":375,"remainingConfigurations":398},{"removed":"omniscience","score":0.009190586353342021,"rank":378,"remainingConfigurations":398},{"removed":"scicode","score":0.010576426737427896,"rank":376,"remainingConfigurations":398},{"removed":"tau-bench","score":0.010702635706691818,"rank":371,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010080902326779788,"rank":378,"remainingConfigurations":398},{"removed":"arc-agi","score":0.012591617539625753,"rank":377,"remainingConfigurations":398},{"removed":"deepswe","score":0.008757899807709246,"rank":377,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.010363804193863341,"rank":376,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.010287918058695064,"rank":376,"remainingConfigurations":398},{"removed":"frontiercode","score":0.01093333375876321,"rank":377,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.010373553874974887,"rank":376,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.010260785016706965,"rank":376,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.010345666330762436,"rank":376,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.010321038476551936,"rank":376,"remainingConfigurations":398},{"removed":"livebench-math","score":0.010380138063406106,"rank":376,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.010268615759383827,"rank":376,"remainingConfigurations":398},{"removed":"livebench-language","score":0.010491934620744848,"rank":376,"remainingConfigurations":398},{"removed":"livebench-data","score":0.010384485589031342,"rank":376,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.010184427155219092,"rank":376,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.010285879546465896,"rank":376,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.01053445197042311,"rank":376,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.010684170011158933,"rank":376,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.009785795489865181,"rank":376,"remainingConfigurations":398},{"removed":"frontiermath","score":0.01047478984516024,"rank":377,"remainingConfigurations":398},{"removed":"simpleqa","score":0.010817778395046815,"rank":377,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.010305469238861883,"rank":376,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.010321397256741327,"rank":376,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.010314372514113048,"rank":376,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.010340782441338082,"rank":376,"remainingConfigurations":398},{"removed":"vibe-code","score":0.010285492765363063,"rank":376,"remainingConfigurations":398}]},"qwen3-4b--effort-non-reasoning":{"score":0.010325840342065868,"rank":377,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.014934272839029678,"rank":158,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.012845804749397961,"rank":376,"remainingConfigurations":398},{"removed":"Datacurve","score":0.008878455225208248,"rank":376,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.010237528725768441,"rank":377,"remainingConfigurations":398},{"removed":"Scale","score":0.011587754429319946,"rank":377,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.010341988189175045,"rank":376,"remainingConfigurations":398},{"removed":"Cognition","score":0.011098389667244394,"rank":376,"remainingConfigurations":398},{"removed":"LiveBench","score":0.010611931852983716,"rank":376,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.01059874349636427,"rank":377,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0077474742163003915,"rank":369,"remainingConfigurations":381},{"removed":"Vals AI","score":0.01014641677732442,"rank":375,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.010326410697918936,"rank":377,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.010314653106432519,"rank":377,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.010309222392413603,"rank":377,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.010325840342065868,"rank":377,"remainingConfigurations":398},{"removed":"All provider reports","score":0.010296832375203803,"rank":377,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.010363972552710566,"rank":377,"remainingConfigurations":398},{"removed":"briefcase","score":0.010293809355655171,"rank":377,"remainingConfigurations":398},{"removed":"aime","score":0.010401654919856599,"rank":377,"remainingConfigurations":398},{"removed":"apex-agents","score":0.010447480499218292,"rank":377,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.010154199723890192,"rank":377,"remainingConfigurations":398},{"removed":"automationbench","score":0.010302328742972204,"rank":377,"remainingConfigurations":398},{"removed":"critpt","score":0.009743766638987303,"rank":375,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.010350304019978114,"rank":377,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.010420471959967904,"rank":377,"remainingConfigurations":398},{"removed":"gdpval","score":0.010362420194639368,"rank":377,"remainingConfigurations":398},{"removed":"gmmlu","score":0.010409596810741644,"rank":377,"remainingConfigurations":398},{"removed":"gpqa","score":0.012082049891564056,"rank":370,"remainingConfigurations":398},{"removed":"harvey","score":0.01020855585009338,"rank":377,"remainingConfigurations":398},{"removed":"hle","score":0.011311658783279943,"rank":375,"remainingConfigurations":398},{"removed":"ifbench","score":0.010020220126074323,"rank":375,"remainingConfigurations":398},{"removed":"itbench","score":0.010314780758735544,"rank":377,"remainingConfigurations":398},{"removed":"livecodebench","score":0.01100789687640444,"rank":377,"remainingConfigurations":398},{"removed":"math500","score":0.010198950944600776,"rank":377,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.011200728906309285,"rank":375,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.011051314275243576,"rank":376,"remainingConfigurations":398},{"removed":"omniscience","score":0.009688993121202109,"rank":375,"remainingConfigurations":398},{"removed":"scicode","score":0.010492139225966453,"rank":377,"remainingConfigurations":398},{"removed":"tau-bench","score":0.00978724735006309,"rank":375,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010267364166524679,"rank":377,"remainingConfigurations":398},{"removed":"arc-agi","score":0.012710294436090423,"rank":376,"remainingConfigurations":398},{"removed":"deepswe","score":0.008885635423935815,"rank":376,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.010328919390623512,"rank":377,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.010255380161919727,"rank":377,"remainingConfigurations":398},{"removed":"frontiercode","score":0.011098389667244394,"rank":376,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.010347908128149534,"rank":377,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.010223809778167421,"rank":377,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.01031149385873432,"rank":377,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.010285684393821349,"rank":377,"remainingConfigurations":398},{"removed":"livebench-math","score":0.010348257489551866,"rank":377,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.010225939072054999,"rank":377,"remainingConfigurations":398},{"removed":"livebench-language","score":0.010456251887181736,"rank":377,"remainingConfigurations":398},{"removed":"livebench-data","score":0.010351517436410499,"rank":377,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.01015301654514864,"rank":377,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.010250707340200659,"rank":377,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0105002962522339,"rank":377,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.01059874349636427,"rank":377,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007545678775649138,"rank":385,"remainingConfigurations":398},{"removed":"frontiermath","score":0.010571922816224202,"rank":376,"remainingConfigurations":398},{"removed":"simpleqa","score":0.010932523433986568,"rank":376,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.010270790082409073,"rank":377,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.010287897323490863,"rank":377,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.01027797689986561,"rank":377,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.010306452343752508,"rank":377,"remainingConfigurations":398},{"removed":"vibe-code","score":0.010252843486891951,"rank":377,"remainingConfigurations":398}]},"exaone-4.0-1.2b--effort-non-reasoning":{"score":0.009785809170881033,"rank":378,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.012028111538600637,"rank":378,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0082751688557274,"rank":378,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.00968695059539501,"rank":378,"remainingConfigurations":398},{"removed":"Scale","score":0.010999088222441847,"rank":378,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.009763971482786266,"rank":378,"remainingConfigurations":398},{"removed":"Cognition","score":0.010346633286432608,"rank":378,"remainingConfigurations":398},{"removed":"LiveBench","score":0.01005852972822999,"rank":377,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.010109043269161797,"rank":378,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.009849724008332129,"rank":360,"remainingConfigurations":381},{"removed":"Vals AI","score":0.00951379405209001,"rank":377,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.009786434842810101,"rank":378,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.009775998907990807,"rank":378,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.00976836557077789,"rank":378,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.009785809170881033,"rank":378,"remainingConfigurations":398},{"removed":"All provider reports","score":0.009757443155165397,"rank":378,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.009828284305421028,"rank":378,"remainingConfigurations":398},{"removed":"briefcase","score":0.009777793460345637,"rank":378,"remainingConfigurations":398},{"removed":"aime","score":0.00965246731735596,"rank":381,"remainingConfigurations":398},{"removed":"apex-agents","score":0.009914447371051327,"rank":378,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.010049276523658328,"rank":378,"remainingConfigurations":398},{"removed":"automationbench","score":0.00979256514175735,"rank":378,"remainingConfigurations":398},{"removed":"critpt","score":0.008543394652600008,"rank":379,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.009818949751496478,"rank":378,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.00992844851834005,"rank":378,"remainingConfigurations":398},{"removed":"gdpval","score":0.009856175089329684,"rank":378,"remainingConfigurations":398},{"removed":"gmmlu","score":0.009902722355326408,"rank":378,"remainingConfigurations":398},{"removed":"gpqa","score":0.009788418407057431,"rank":378,"remainingConfigurations":398},{"removed":"harvey","score":0.009683024079483776,"rank":378,"remainingConfigurations":398},{"removed":"hle","score":0.009113787317917772,"rank":383,"remainingConfigurations":398},{"removed":"ifbench","score":0.009879759197997119,"rank":376,"remainingConfigurations":398},{"removed":"itbench","score":0.009781003475042759,"rank":378,"remainingConfigurations":398},{"removed":"livecodebench","score":0.00968827881665439,"rank":379,"remainingConfigurations":398},{"removed":"math500","score":0.009887865678426772,"rank":378,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.011005144708421408,"rank":376,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.010527501266954212,"rank":378,"remainingConfigurations":398},{"removed":"omniscience","score":0.009585355550248706,"rank":376,"remainingConfigurations":398},{"removed":"scicode","score":0.010006072029756419,"rank":378,"remainingConfigurations":398},{"removed":"tau-bench","score":0.009319332617038283,"rank":376,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.010299664133699026,"rank":376,"remainingConfigurations":398},{"removed":"arc-agi","score":0.011922016694471035,"rank":378,"remainingConfigurations":398},{"removed":"deepswe","score":0.008281615905201033,"rank":378,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.009788795656307938,"rank":378,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.009717215904768954,"rank":378,"remainingConfigurations":398},{"removed":"frontiercode","score":0.010346633286432608,"rank":378,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.009798525337886122,"rank":378,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.009691901924356464,"rank":378,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.009771662090981945,"rank":378,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.009748197623484412,"rank":378,"remainingConfigurations":398},{"removed":"livebench-math","score":0.009804223743926395,"rank":378,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.009698784387689044,"rank":378,"remainingConfigurations":398},{"removed":"livebench-language","score":0.009909921557062043,"rank":378,"remainingConfigurations":398},{"removed":"livebench-data","score":0.009808382214208012,"rank":378,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.009619187988030027,"rank":378,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.009715108795941839,"rank":378,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.009950219692407029,"rank":378,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.010109043269161797,"rank":378,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.009235539805777753,"rank":377,"remainingConfigurations":398},{"removed":"frontiermath","score":0.009898511948536958,"rank":378,"remainingConfigurations":398},{"removed":"simpleqa","score":0.010216638661389514,"rank":378,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.00973364563318423,"rank":378,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.009748683995257022,"rank":378,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.009742085008910606,"rank":378,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.009766991131893653,"rank":378,"remainingConfigurations":398},{"removed":"vibe-code","score":0.009714734549185828,"rank":378,"remainingConfigurations":398}]},"gpt-4o-mini--effort-non-reasoning":{"score":0.009483476954716526,"rank":379,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.01165214284157545,"rank":379,"remainingConfigurations":398},{"removed":"Datacurve","score":0.008023153030322859,"rank":379,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.009387738202150468,"rank":379,"remainingConfigurations":398},{"removed":"Scale","score":0.010656348601759602,"rank":379,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.009469391796592555,"rank":379,"remainingConfigurations":398},{"removed":"Cognition","score":0.010023372746129543,"rank":379,"remainingConfigurations":398},{"removed":"LiveBench","score":0.00975806843905881,"rank":378,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.009784459394430406,"rank":379,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.00959243320226979,"rank":361,"remainingConfigurations":381},{"removed":"Vals AI","score":0.009234805130863393,"rank":378,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.009484077170511312,"rank":379,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.009473943844562875,"rank":379,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.009466543048437711,"rank":379,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.009483476954716526,"rank":379,"remainingConfigurations":398},{"removed":"All provider reports","score":0.009455925148039378,"rank":379,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.009529281408435016,"rank":379,"remainingConfigurations":398},{"removed":"briefcase","score":0.009474925358814222,"rank":379,"remainingConfigurations":398},{"removed":"aime","score":0.009962959441071232,"rank":379,"remainingConfigurations":398},{"removed":"apex-agents","score":0.009609816286962997,"rank":379,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.00926441156155045,"rank":379,"remainingConfigurations":398},{"removed":"automationbench","score":0.009487841429215346,"rank":379,"remainingConfigurations":398},{"removed":"critpt","score":0.00911480822165611,"rank":378,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.009525284626352042,"rank":379,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.009619332502909752,"rank":379,"remainingConfigurations":398},{"removed":"gdpval","score":0.009113167120098763,"rank":381,"remainingConfigurations":398},{"removed":"gmmlu","score":0.009576098691795938,"rank":379,"remainingConfigurations":398},{"removed":"gpqa","score":0.009433850289967861,"rank":380,"remainingConfigurations":398},{"removed":"harvey","score":0.00938950729073256,"rank":379,"remainingConfigurations":398},{"removed":"hle","score":0.009819380111221234,"rank":379,"remainingConfigurations":398},{"removed":"ifbench","score":0.00913895062469737,"rank":380,"remainingConfigurations":398},{"removed":"itbench","score":0.009481354586489932,"rank":379,"remainingConfigurations":398},{"removed":"livecodebench","score":0.009893964543787038,"rank":378,"remainingConfigurations":398},{"removed":"math500","score":0.009721446814897726,"rank":379,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.00999190265754882,"rank":379,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.010337746869326222,"rank":380,"remainingConfigurations":398},{"removed":"omniscience","score":0.008951786213897325,"rank":379,"remainingConfigurations":398},{"removed":"scicode","score":0.009696499148609256,"rank":379,"remainingConfigurations":398},{"removed":"tau-bench","score":0.009129869149708928,"rank":377,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.009230669659395304,"rank":381,"remainingConfigurations":398},{"removed":"arc-agi","score":0.011546431109698543,"rank":379,"remainingConfigurations":398},{"removed":"deepswe","score":0.008029422411955095,"rank":379,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.00948638108941136,"rank":379,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.00941708090877693,"rank":379,"remainingConfigurations":398},{"removed":"frontiercode","score":0.010023372746129543,"rank":379,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.00949609277789517,"rank":379,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.009392217277393512,"rank":379,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00946984491008349,"rank":379,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.009447515070548591,"rank":379,"remainingConfigurations":398},{"removed":"livebench-math","score":0.009501323550793707,"rank":379,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.009399215330121268,"rank":379,"remainingConfigurations":398},{"removed":"livebench-language","score":0.009603943462156464,"rank":379,"remainingConfigurations":398},{"removed":"livebench-data","score":0.009505324214817238,"rank":379,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.009321863346575556,"rank":379,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.009414933381878493,"rank":379,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.009642742237292083,"rank":379,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.009784459394430406,"rank":379,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.008963356929380916,"rank":378,"remainingConfigurations":398},{"removed":"frontiermath","score":0.009587320274432253,"rank":379,"remainingConfigurations":398},{"removed":"simpleqa","score":0.009902715010544356,"rank":379,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.009432879333587421,"rank":379,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.009447504183080569,"rank":379,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00944102953007746,"rank":379,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.009465298929042515,"rank":379,"remainingConfigurations":398},{"removed":"vibe-code","score":0.009414557877059403,"rank":379,"remainingConfigurations":398}]},"qwen3.5-0.8b--effort-reasoning":{"score":0.009252001970494772,"rank":380,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.011457519097992544,"rank":380,"remainingConfigurations":398},{"removed":"Datacurve","score":0.007846344265801948,"rank":380,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.009160076922653327,"rank":380,"remainingConfigurations":398},{"removed":"Scale","score":0.010412519984713639,"rank":380,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.009235723504224153,"rank":380,"remainingConfigurations":398},{"removed":"Cognition","score":0.009820083241015555,"rank":380,"remainingConfigurations":398},{"removed":"LiveBench","score":0.009518072174611042,"rank":379,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.009571826097068309,"rank":380,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.009330810403210571,"rank":362,"remainingConfigurations":381},{"removed":"Vals AI","score":0.009004850117714493,"rank":379,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.00925259488359769,"rank":380,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.009242756129455243,"rank":380,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.009235434669070992,"rank":380,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.009252001970494772,"rank":380,"remainingConfigurations":398},{"removed":"All provider reports","score":0.009225134945338335,"rank":380,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.009299261773247398,"rank":380,"remainingConfigurations":398},{"removed":"briefcase","score":0.009262020574799128,"rank":380,"remainingConfigurations":398},{"removed":"aime","score":0.00918269357179035,"rank":382,"remainingConfigurations":398},{"removed":"apex-agents","score":0.009379838052485748,"rank":380,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008945928775654711,"rank":380,"remainingConfigurations":398},{"removed":"automationbench","score":0.009278041811680751,"rank":380,"remainingConfigurations":398},{"removed":"critpt","score":0.007833343006334394,"rank":383,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.009294360135338065,"rank":380,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.009407318563480715,"rank":380,"remainingConfigurations":398},{"removed":"gdpval","score":0.009366364543385023,"rank":379,"remainingConfigurations":398},{"removed":"gmmlu","score":0.009352053520669425,"rank":380,"remainingConfigurations":398},{"removed":"gpqa","score":0.01002303863651805,"rank":376,"remainingConfigurations":398},{"removed":"harvey","score":0.009164860949944531,"rank":380,"remainingConfigurations":398},{"removed":"hle","score":0.01072547375960463,"rank":378,"remainingConfigurations":398},{"removed":"ifbench","score":0.009592409200294836,"rank":378,"remainingConfigurations":398},{"removed":"itbench","score":0.009259073717465177,"rank":380,"remainingConfigurations":398},{"removed":"livecodebench","score":0.009219007126831066,"rank":381,"remainingConfigurations":398},{"removed":"math500","score":0.00927661236399419,"rank":383,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.009541597896848854,"rank":381,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.01051954820215622,"rank":379,"remainingConfigurations":398},{"removed":"omniscience","score":0.009360595324519385,"rank":377,"remainingConfigurations":398},{"removed":"scicode","score":0.00948471224102128,"rank":380,"remainingConfigurations":398},{"removed":"tau-bench","score":0.006648764436169797,"rank":390,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.009814531816950267,"rank":379,"remainingConfigurations":398},{"removed":"arc-agi","score":0.011346347317293039,"rank":380,"remainingConfigurations":398},{"removed":"deepswe","score":0.007852459200513083,"rank":380,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.009254830525003784,"rank":380,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.009187246839973687,"rank":380,"remainingConfigurations":398},{"removed":"frontiercode","score":0.009820083241015555,"rank":380,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.009264890012276615,"rank":380,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.009163727727543453,"rank":380,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00923865455659529,"rank":380,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.009216768416159007,"rank":380,"remainingConfigurations":398},{"removed":"livebench-math","score":0.00926940467608542,"rank":380,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.009169716368866057,"rank":380,"remainingConfigurations":398},{"removed":"livebench-language","score":0.009369526821168352,"rank":380,"remainingConfigurations":398},{"removed":"livebench-data","score":0.00927339896636875,"rank":380,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.009094280695958107,"rank":380,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.009185075176354038,"rank":380,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.00940751901022744,"rank":380,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.009571826097068309,"rank":380,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.00871938076777797,"rank":379,"remainingConfigurations":398},{"removed":"frontiermath","score":0.009361211459666913,"rank":380,"remainingConfigurations":398},{"removed":"simpleqa","score":0.009658213209273953,"rank":380,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.009202636940686362,"rank":380,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.009216883941236289,"rank":380,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00921058105887246,"rank":380,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.009234224393419184,"rank":380,"remainingConfigurations":398},{"removed":"vibe-code","score":0.009184753727577863,"rank":380,"remainingConfigurations":398}]},"amazon-nova-lite--effort-non-reasoning":{"score":0.00916536991789217,"rank":381,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.011242063381234011,"rank":381,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0077407948222423355,"rank":381,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.009072714736653062,"rank":381,"remainingConfigurations":398},{"removed":"Scale","score":0.010296657076149459,"rank":381,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.009148722259114755,"rank":381,"remainingConfigurations":398},{"removed":"Cognition","score":0.00967432148500222,"rank":381,"remainingConfigurations":398},{"removed":"LiveBench","score":0.009426190017224964,"rank":380,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.00945166499657076,"rank":381,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.009255558851596405,"rank":363,"remainingConfigurations":381},{"removed":"Vals AI","score":0.008918162785350776,"rank":380,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.009165955591496978,"rank":381,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.009156163496011699,"rank":381,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.009149021130775231,"rank":381,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.00916536991789217,"rank":381,"remainingConfigurations":398},{"removed":"All provider reports","score":0.009138771565485579,"rank":381,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.009208423821328821,"rank":381,"remainingConfigurations":398},{"removed":"briefcase","score":0.009145776926961825,"rank":381,"remainingConfigurations":398},{"removed":"aime","score":0.009853176134166454,"rank":380,"remainingConfigurations":398},{"removed":"apex-agents","score":0.009285267817302647,"rank":381,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008764378205539118,"rank":381,"remainingConfigurations":398},{"removed":"automationbench","score":0.00915348511787782,"rank":381,"remainingConfigurations":398},{"removed":"critpt","score":0.008075945473310775,"rank":381,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.009199096606208651,"rank":381,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.009281445501191244,"rank":381,"remainingConfigurations":398},{"removed":"gdpval","score":0.009212435010531811,"rank":380,"remainingConfigurations":398},{"removed":"gmmlu","score":0.009245546432033838,"rank":381,"remainingConfigurations":398},{"removed":"gpqa","score":0.009023076706541353,"rank":381,"remainingConfigurations":398},{"removed":"harvey","score":0.009071301100172277,"rank":381,"remainingConfigurations":398},{"removed":"hle","score":0.009429756625725665,"rank":382,"remainingConfigurations":398},{"removed":"ifbench","score":0.008328959328877632,"rank":383,"remainingConfigurations":398},{"removed":"itbench","score":0.009161161338162185,"rank":381,"remainingConfigurations":398},{"removed":"livecodebench","score":0.009677328957751991,"rank":380,"remainingConfigurations":398},{"removed":"math500","score":0.00962826235931174,"rank":381,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.009777677280231984,"rank":380,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.010040274002933438,"rank":381,"remainingConfigurations":398},{"removed":"omniscience","score":0.00854596196423781,"rank":380,"remainingConfigurations":398},{"removed":"scicode","score":0.00935273724851309,"rank":381,"remainingConfigurations":398},{"removed":"tau-bench","score":0.008876229066234828,"rank":378,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.009399695378864032,"rank":380,"remainingConfigurations":398},{"removed":"arc-agi","score":0.011146080321235012,"rank":381,"remainingConfigurations":398},{"removed":"deepswe","score":0.007746841941734062,"rank":381,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.009168172286370018,"rank":381,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.009101116230115931,"rank":381,"remainingConfigurations":398},{"removed":"frontiercode","score":0.00967432148500222,"rank":381,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.009176998882035338,"rank":381,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.009076862684326073,"rank":381,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.009152141359332944,"rank":381,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.00913033885430781,"rank":381,"remainingConfigurations":398},{"removed":"livebench-math","score":0.009182633748060198,"rank":381,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.009083819766249312,"rank":381,"remainingConfigurations":398},{"removed":"livebench-language","score":0.00928181341545092,"rank":381,"remainingConfigurations":398},{"removed":"livebench-data","score":0.009186487755223243,"rank":381,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.009009124243777283,"rank":381,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.009099085314527923,"rank":381,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.009319474449015772,"rank":381,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.00945166499657076,"rank":381,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.008655608026903782,"rank":380,"remainingConfigurations":398},{"removed":"frontiermath","score":0.009266581884907706,"rank":381,"remainingConfigurations":398},{"removed":"simpleqa","score":0.009570707868966374,"rank":381,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.009116452208621032,"rank":381,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.009130561861544163,"rank":381,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.009124345447853684,"rank":381,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.009147741358202654,"rank":381,"remainingConfigurations":398},{"removed":"vibe-code","score":0.009098740483429605,"rank":381,"remainingConfigurations":398}]},"mistral-large-2407--effort-non-reasoning":{"score":0.008780411708098472,"rank":382,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.010798281709295678,"rank":382,"remainingConfigurations":398},{"removed":"Datacurve","score":0.00741931562349745,"rank":382,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.00869163779215029,"rank":382,"remainingConfigurations":398},{"removed":"Scale","score":0.009868746724291843,"rank":382,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.008760838213285042,"rank":382,"remainingConfigurations":398},{"removed":"Cognition","score":0.00927553375806169,"rank":382,"remainingConfigurations":398},{"removed":"LiveBench","score":0.00902558737030337,"rank":381,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.009064226403621806,"rank":382,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.008840896880872924,"rank":364,"remainingConfigurations":381},{"removed":"Vals AI","score":0.008537617482958284,"rank":381,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.008780972994684314,"rank":382,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.008771577011957599,"rank":382,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.008764765265107397,"rank":382,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.008780411708098472,"rank":382,"remainingConfigurations":398},{"removed":"All provider reports","score":0.008754930543149983,"rank":382,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.008818293348800079,"rank":382,"remainingConfigurations":398},{"removed":"briefcase","score":0.008768444414661018,"rank":382,"remainingConfigurations":398},{"removed":"aime","score":0.010004106091534074,"rank":378,"remainingConfigurations":398},{"removed":"apex-agents","score":0.008892992657938173,"rank":382,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008602811748054858,"rank":382,"remainingConfigurations":398},{"removed":"automationbench","score":0.00877853086437967,"rank":382,"remainingConfigurations":398},{"removed":"critpt","score":0.008334586812173316,"rank":380,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.008808045672308204,"rank":382,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.008897682493126245,"rank":382,"remainingConfigurations":398},{"removed":"gdpval","score":0.008843093499765824,"rank":382,"remainingConfigurations":398},{"removed":"gmmlu","score":0.008870330875824168,"rank":382,"remainingConfigurations":398},{"removed":"gpqa","score":0.008412066827339642,"rank":384,"remainingConfigurations":398},{"removed":"harvey","score":0.00868665320608753,"rank":382,"remainingConfigurations":398},{"removed":"hle","score":0.0098049292807639,"rank":380,"remainingConfigurations":398},{"removed":"ifbench","score":0.008286541910830907,"rank":384,"remainingConfigurations":398},{"removed":"itbench","score":0.008773844827123047,"rank":382,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008908667188039792,"rank":382,"remainingConfigurations":398},{"removed":"math500","score":0.009652186390287495,"rank":380,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008854070387911294,"rank":383,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.009438506397678494,"rank":382,"remainingConfigurations":398},{"removed":"omniscience","score":0.008175388744498024,"rank":381,"remainingConfigurations":398},{"removed":"scicode","score":0.008966097065999113,"rank":382,"remainingConfigurations":398},{"removed":"tau-bench","score":0.007205350475118534,"rank":387,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.008823223252665303,"rank":382,"remainingConfigurations":398},{"removed":"arc-agi","score":0.010703882585256471,"rank":382,"remainingConfigurations":398},{"removed":"deepswe","score":0.007425108342376081,"rank":382,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.008783096568672598,"rank":382,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.008718852556550449,"rank":382,"remainingConfigurations":398},{"removed":"frontiercode","score":0.00927553375806169,"rank":382,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.008791832925026387,"rank":382,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.008695984033726315,"rank":382,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.008767729682968555,"rank":382,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.008746666495206994,"rank":382,"remainingConfigurations":398},{"removed":"livebench-math","score":0.008796995517524277,"rank":382,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.00870209743551629,"rank":382,"remainingConfigurations":398},{"removed":"livebench-language","score":0.008891987833051474,"rank":382,"remainingConfigurations":398},{"removed":"livebench-data","score":0.008800712168186627,"rank":382,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0086306542506953,"rank":382,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.00871685272398034,"rank":382,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.008928244797647245,"rank":382,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.009064226403621806,"rank":382,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.008285143060463216,"rank":381,"remainingConfigurations":398},{"removed":"frontiermath","score":0.008877835098307217,"rank":382,"remainingConfigurations":398},{"removed":"simpleqa","score":0.00916961765947145,"rank":382,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.008733512049335332,"rank":382,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.008747042079070228,"rank":382,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00874109867665117,"rank":382,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.008763485733727554,"rank":382,"remainingConfigurations":398},{"removed":"vibe-code","score":0.00871653812430418,"rank":382,"remainingConfigurations":398}]},"deepseek-r1-distill-llama-8b--effort-reasoning":{"score":0.0083732334943921,"rank":383,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.010309142868379374,"rank":383,"remainingConfigurations":398},{"removed":"Datacurve","score":0.007073915513305028,"rank":383,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.008288629094463497,"rank":383,"remainingConfigurations":398},{"removed":"Scale","score":0.009411149603054777,"rank":383,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.008354010512738342,"rank":383,"remainingConfigurations":398},{"removed":"Cognition","score":0.008846940890323033,"rank":383,"remainingConfigurations":398},{"removed":"LiveBench","score":0.008606527505614766,"rank":382,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.00864743867302103,"rank":383,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.008410838972173611,"rank":365,"remainingConfigurations":381},{"removed":"Vals AI","score":0.008140363132209867,"rank":382,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.008373768325946085,"rank":383,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.008364792769381383,"rank":383,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.008358307580717489,"rank":383,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0083732334943921,"rank":383,"remainingConfigurations":398},{"removed":"All provider reports","score":0.00834891183090021,"rank":383,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.00840803781555558,"rank":383,"remainingConfigurations":398},{"removed":"briefcase","score":0.008365162835871284,"rank":383,"remainingConfigurations":398},{"removed":"aime","score":0.006599748971681076,"rank":391,"remainingConfigurations":398},{"removed":"apex-agents","score":0.008479754826470317,"rank":383,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008540137071795297,"rank":383,"remainingConfigurations":398},{"removed":"automationbench","score":0.008372238059635604,"rank":383,"remainingConfigurations":398},{"removed":"critpt","score":0.00796578291391649,"rank":382,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.008398204824530664,"rank":383,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.008485848743242033,"rank":383,"remainingConfigurations":398},{"removed":"gdpval","score":0.008432858419577702,"rank":383,"remainingConfigurations":398},{"removed":"gmmlu","score":0.008476161429443177,"rank":384,"remainingConfigurations":398},{"removed":"gpqa","score":0.00866177648161679,"rank":382,"remainingConfigurations":398},{"removed":"harvey","score":0.00828344177628771,"rank":383,"remainingConfigurations":398},{"removed":"hle","score":0.00885804228860931,"rank":384,"remainingConfigurations":398},{"removed":"ifbench","score":0.008974462353078473,"rank":381,"remainingConfigurations":398},{"removed":"itbench","score":0.008366834647912916,"rank":383,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008848820323898781,"rank":383,"remainingConfigurations":398},{"removed":"math500","score":0.007684334192893327,"rank":386,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.00939450168467928,"rank":382,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.00903788678336335,"rank":383,"remainingConfigurations":398},{"removed":"omniscience","score":0.007792526961643592,"rank":383,"remainingConfigurations":398},{"removed":"scicode","score":0.008552380519157477,"rank":383,"remainingConfigurations":398},{"removed":"tau-bench","score":0.008180478937240986,"rank":382,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.008439494723324087,"rank":384,"remainingConfigurations":398},{"removed":"arc-agi","score":0.010219656625811696,"rank":383,"remainingConfigurations":398},{"removed":"deepswe","score":0.007079439625455095,"rank":383,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.008375795616153424,"rank":383,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.008314508624115846,"rank":383,"remainingConfigurations":398},{"removed":"frontiercode","score":0.008846940890323033,"rank":383,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.008384060178071398,"rank":383,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.008292571951877218,"rank":383,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00836114846896281,"rank":383,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.008340975088363135,"rank":383,"remainingConfigurations":398},{"removed":"livebench-math","score":0.008389063490171123,"rank":383,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.008298471305041721,"rank":383,"remainingConfigurations":398},{"removed":"livebench-language","score":0.008479709131112805,"rank":383,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0083926146456741,"rank":383,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.00823031493912308,"rank":383,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.008312573474212505,"rank":383,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.008514348495554587,"rank":383,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.00864743867302103,"rank":383,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007889004287252203,"rank":382,"remainingConfigurations":398},{"removed":"frontiermath","score":0.008466856399017243,"rank":383,"remainingConfigurations":398},{"removed":"simpleqa","score":0.008745025037242926,"rank":383,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.00832847157677178,"rank":383,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.008341383202169086,"rank":383,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00833572408921831,"rank":383,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.008357067132531473,"rank":383,"remainingConfigurations":398},{"removed":"vibe-code","score":0.008312270021058691,"rank":383,"remainingConfigurations":398}]},"gpt-4-turbo--effort-non-reasoning":{"score":0.00827899274032194,"rank":384,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.010192470411123871,"rank":384,"remainingConfigurations":398},{"removed":"Datacurve","score":0.006995260522871711,"rank":384,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.008195185955296816,"rank":384,"remainingConfigurations":398},{"removed":"Scale","score":0.00930542887112048,"rank":384,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.008260200841889012,"rank":384,"remainingConfigurations":398},{"removed":"Cognition","score":0.008749153100940951,"rank":384,"remainingConfigurations":398},{"removed":"LiveBench","score":0.008509409208226135,"rank":383,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.008542616563863669,"rank":384,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.008268743662006752,"rank":367,"remainingConfigurations":381},{"removed":"Vals AI","score":0.008048641301416326,"rank":383,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.008279518884048718,"rank":384,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.008270618993109383,"rank":384,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.008264251800837842,"rank":384,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.00827899274032194,"rank":384,"remainingConfigurations":398},{"removed":"All provider reports","score":0.008254931685282808,"rank":384,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.008312932720874461,"rank":384,"remainingConfigurations":398},{"removed":"briefcase","score":0.008268829444273708,"rank":384,"remainingConfigurations":398},{"removed":"aime","score":0.008204452104193924,"rank":384,"remainingConfigurations":398},{"removed":"apex-agents","score":0.008386094292598631,"rank":384,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008168253669470677,"rank":385,"remainingConfigurations":398},{"removed":"automationbench","score":0.008279233609257398,"rank":384,"remainingConfigurations":398},{"removed":"critpt","score":0.007783296045096206,"rank":384,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.008302668794607003,"rank":384,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.00838968410903689,"rank":384,"remainingConfigurations":398},{"removed":"gdpval","score":0.008389596706531895,"rank":384,"remainingConfigurations":398},{"removed":"gmmlu","score":0.008371413464060567,"rank":385,"remainingConfigurations":398},{"removed":"gpqa","score":0.008236555766180416,"rank":385,"remainingConfigurations":398},{"removed":"harvey","score":0.008188764605348576,"rank":384,"remainingConfigurations":398},{"removed":"hle","score":0.009533805131758772,"rank":381,"remainingConfigurations":398},{"removed":"ifbench","score":0.008120382418516153,"rank":385,"remainingConfigurations":398},{"removed":"itbench","score":0.008272852678136815,"rank":384,"remainingConfigurations":398},{"removed":"livecodebench","score":0.00792577258129724,"rank":388,"remainingConfigurations":398},{"removed":"math500","score":0.009492421674242855,"rank":382,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.00748301392437278,"rank":390,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008951566171760758,"rank":384,"remainingConfigurations":398},{"removed":"omniscience","score":0.007624020158919941,"rank":384,"remainingConfigurations":398},{"removed":"scicode","score":0.00845556199128373,"rank":384,"remainingConfigurations":398},{"removed":"tau-bench","score":0.008040292462067887,"rank":383,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.00827225805178935,"rank":385,"remainingConfigurations":398},{"removed":"arc-agi","score":0.010104660716842025,"rank":384,"remainingConfigurations":398},{"removed":"deepswe","score":0.007000724710230937,"rank":384,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.008281526916650869,"rank":384,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.008220809904048687,"rank":384,"remainingConfigurations":398},{"removed":"frontiercode","score":0.008749153100940951,"rank":384,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.00828960580830017,"rank":384,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.008199113081844733,"rank":384,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.008267054168868164,"rank":384,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.008247057073954366,"rank":384,"remainingConfigurations":398},{"removed":"livebench-math","score":0.008294665066756815,"rank":384,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.008204996467055683,"rank":384,"remainingConfigurations":398},{"removed":"livebench-language","score":0.008384286097372474,"rank":384,"remainingConfigurations":398},{"removed":"livebench-data","score":0.008298178516366694,"rank":384,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.008137668741007591,"rank":384,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.008218998017991723,"rank":384,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.00841856869455443,"rank":384,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.008542616563863669,"rank":384,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007782013072359793,"rank":383,"remainingConfigurations":398},{"removed":"frontiermath","score":0.008373661753954249,"rank":384,"remainingConfigurations":398},{"removed":"simpleqa","score":0.008648001140953071,"rank":384,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.008234722607021835,"rank":384,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.008247502566865109,"rank":384,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0082418947329193,"rank":384,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.008263003569987,"rank":384,"remainingConfigurations":398},{"removed":"vibe-code","score":0.008218705447305328,"rank":384,"remainingConfigurations":398}]},"tiny-aya-global--effort-non-reasoning":{"score":0.008217484860856614,"rank":385,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.010124861468506757,"rank":385,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0069522822590653045,"rank":385,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.00813584165560081,"rank":385,"remainingConfigurations":398},{"removed":"Scale","score":0.009241029646522236,"rank":385,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.008200918570628565,"rank":385,"remainingConfigurations":398},{"removed":"Cognition","score":0.008691355481482093,"rank":385,"remainingConfigurations":398},{"removed":"LiveBench","score":0.00845174907017654,"rank":384,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.00849828591188293,"rank":385,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.008315354127217962,"rank":366,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007995787044532498,"rank":384,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.00821801227398561,"rank":385,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.008209250449011116,"rank":385,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.008202804325839145,"rank":385,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.008217484860856614,"rank":385,"remainingConfigurations":398},{"removed":"All provider reports","score":0.008193633122623499,"rank":385,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.008257206228777568,"rank":385,"remainingConfigurations":398},{"removed":"briefcase","score":0.00821808955253061,"rank":385,"remainingConfigurations":398},{"removed":"aime","score":0.008153002047023248,"rank":385,"remainingConfigurations":398},{"removed":"apex-agents","score":0.008327057676568847,"rank":385,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.008421814946897784,"rank":384,"remainingConfigurations":398},{"removed":"automationbench","score":0.008223930458647931,"rank":385,"remainingConfigurations":398},{"removed":"critpt","score":0.006717656654820611,"rank":386,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.008253016283068394,"rank":385,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.008338631219641039,"rank":385,"remainingConfigurations":398},{"removed":"gdpval","score":0.008280496220616001,"rank":385,"remainingConfigurations":398},{"removed":"gmmlu","score":0.008497217024787646,"rank":383,"remainingConfigurations":398},{"removed":"gpqa","score":0.008517343377415337,"rank":383,"remainingConfigurations":398},{"removed":"harvey","score":0.008135377679029554,"rank":385,"remainingConfigurations":398},{"removed":"hle","score":0.0071423999133010405,"rank":388,"remainingConfigurations":398},{"removed":"ifbench","score":0.00863157395434771,"rank":382,"remainingConfigurations":398},{"removed":"itbench","score":0.008215918554252747,"rank":385,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008194310801986774,"rank":385,"remainingConfigurations":398},{"removed":"math500","score":0.00824961521353946,"rank":385,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008490453125269746,"rank":386,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008847930571275527,"rank":385,"remainingConfigurations":398},{"removed":"omniscience","score":0.00815211731363414,"rank":382,"remainingConfigurations":398},{"removed":"scicode","score":0.008404015402071792,"rank":385,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0085588108025743,"rank":381,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.008728048440464133,"rank":383,"remainingConfigurations":398},{"removed":"arc-agi","score":0.010031414392997163,"rank":385,"remainingConfigurations":398},{"removed":"deepswe","score":0.006957713429262057,"rank":385,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.008220000594450641,"rank":385,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.008159894552678725,"rank":385,"remainingConfigurations":398},{"removed":"frontiercode","score":0.008691355481482093,"rank":385,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.008228460484857461,"rank":385,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.008138837145823722,"rank":385,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.008205568488220731,"rank":385,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.008186175296659758,"rank":385,"remainingConfigurations":398},{"removed":"livebench-math","score":0.00823300391174925,"rank":385,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.008144168905883488,"rank":385,"remainingConfigurations":398},{"removed":"livebench-language","score":0.008322039540764372,"rank":385,"remainingConfigurations":398},{"removed":"livebench-data","score":0.008236513258428352,"rank":385,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.008077162144600391,"rank":385,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.00815793283166266,"rank":385,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.00835596171150316,"rank":385,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.00849828591188293,"rank":385,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007767517202117095,"rank":384,"remainingConfigurations":398},{"removed":"frontiermath","score":0.00830759206268815,"rank":385,"remainingConfigurations":398},{"removed":"simpleqa","score":0.008580112956904943,"rank":385,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.008173552388628914,"rank":385,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.008186221091689884,"rank":385,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.008180629035247786,"rank":385,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.008201634675068662,"rank":385,"remainingConfigurations":398},{"removed":"vibe-code","score":0.008157655071593268,"rank":385,"remainingConfigurations":398}]},"amazon-nova-micro--effort-non-reasoning":{"score":0.007918913707358371,"rank":386,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.009724550433663956,"rank":386,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0066875267550573865,"rank":386,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.00783946160762346,"rank":386,"remainingConfigurations":398},{"removed":"Scale","score":0.008900558875775587,"rank":386,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.007902925837120317,"rank":386,"remainingConfigurations":398},{"removed":"Cognition","score":0.008361602188807715,"rank":386,"remainingConfigurations":398},{"removed":"LiveBench","score":0.00814357052956764,"rank":385,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.008171354993434956,"rank":386,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.007990398135255872,"rank":368,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007703004603832327,"rank":385,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.00791942036780269,"rank":386,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.007910950343350829,"rank":386,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.007904778453785063,"rank":386,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.007918913707358371,"rank":386,"remainingConfigurations":398},{"removed":"All provider reports","score":0.007895911193897782,"rank":386,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.007955025624252212,"rank":386,"remainingConfigurations":398},{"removed":"briefcase","score":0.007909810513721369,"rank":386,"remainingConfigurations":398},{"removed":"aime","score":0.008534935260492324,"rank":383,"remainingConfigurations":398},{"removed":"apex-agents","score":0.008021852337938763,"rank":386,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.007518726849001762,"rank":388,"remainingConfigurations":398},{"removed":"automationbench","score":0.007917950359551295,"rank":386,"remainingConfigurations":398},{"removed":"critpt","score":0.006814509740992999,"rank":385,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.007948944882269724,"rank":386,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.008027618763128708,"rank":386,"remainingConfigurations":398},{"removed":"gdpval","score":0.007976720688623129,"rank":386,"remainingConfigurations":398},{"removed":"gmmlu","score":0.008006228552042959,"rank":386,"remainingConfigurations":398},{"removed":"gpqa","score":0.007906406209612813,"rank":386,"remainingConfigurations":398},{"removed":"harvey","score":0.007835925156209001,"rank":386,"remainingConfigurations":398},{"removed":"hle","score":0.0077482529710235235,"rank":385,"remainingConfigurations":398},{"removed":"ifbench","score":0.007584982622175344,"rank":386,"remainingConfigurations":398},{"removed":"itbench","score":0.007914392513702352,"rank":386,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008380672870325312,"rank":384,"remainingConfigurations":398},{"removed":"math500","score":0.008617500133596445,"rank":384,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008618628411479238,"rank":384,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008519779845451537,"rank":386,"remainingConfigurations":398},{"removed":"omniscience","score":0.007263360355530599,"rank":385,"remainingConfigurations":398},{"removed":"scicode","score":0.008090202521047132,"rank":386,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0077603054304333785,"rank":384,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.007912548026200823,"rank":386,"remainingConfigurations":398},{"removed":"arc-agi","score":0.009640926437670021,"rank":386,"remainingConfigurations":398},{"removed":"deepswe","score":0.006692756776682694,"rank":386,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.007921340246338103,"rank":386,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.007863325105215499,"rank":386,"remainingConfigurations":398},{"removed":"frontiercode","score":0.008361602188807715,"rank":386,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.007929037139769094,"rank":386,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.007842405228394753,"rank":386,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.007907479611227895,"rank":386,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.007888663405404523,"rank":386,"remainingConfigurations":398},{"removed":"livebench-math","score":0.007933890555802629,"rank":386,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.007848170094304028,"rank":386,"remainingConfigurations":398},{"removed":"livebench-language","score":0.00801972792477767,"rank":386,"remainingConfigurations":398},{"removed":"livebench-data","score":0.007937272808759345,"rank":386,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.00778362401988179,"rank":386,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.007861484822814754,"rank":386,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.008052459832167859,"rank":386,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.008171354993434956,"rank":386,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007474999795503098,"rank":386,"remainingConfigurations":398},{"removed":"frontiermath","score":0.008007078048436433,"rank":386,"remainingConfigurations":398},{"removed":"simpleqa","score":0.008270546789889704,"rank":386,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.007876546468403587,"rank":386,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.00788877308948721,"rank":386,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.007883384411295092,"rank":386,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.007903629159388527,"rank":386,"remainingConfigurations":398},{"removed":"vibe-code","score":0.007861222694799592,"rank":386,"remainingConfigurations":398}]},"gemma-3n-e4b-it--effort-non-reasoning":{"score":0.00754494003513423,"rank":387,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.009267601826281714,"rank":389,"remainingConfigurations":398},{"removed":"Datacurve","score":0.00637319028271266,"rank":388,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.007469901653802683,"rank":387,"remainingConfigurations":398},{"removed":"Scale","score":0.008482094907171509,"rank":387,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.007532402945979209,"rank":387,"remainingConfigurations":398},{"removed":"Cognition","score":0.007967774804436504,"rank":388,"remainingConfigurations":398},{"removed":"LiveBench","score":0.007763466512513675,"rank":386,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.007783908966807755,"rank":388,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.007625456968097265,"rank":370,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007345040525745752,"rank":387,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.007545422066117964,"rank":387,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0075373414143885655,"rank":387,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.007531436384630497,"rank":387,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.00754494003513423,"rank":387,"remainingConfigurations":398},{"removed":"All provider reports","score":0.007522974420164839,"rank":387,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.007581847498197326,"rank":387,"remainingConfigurations":398},{"removed":"briefcase","score":0.007527229734433277,"rank":388,"remainingConfigurations":398},{"removed":"aime","score":0.007711053113867398,"rank":387,"remainingConfigurations":398},{"removed":"apex-agents","score":0.007645682495039943,"rank":387,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.007567996614514984,"rank":386,"remainingConfigurations":398},{"removed":"automationbench","score":0.007530534272276082,"rank":388,"remainingConfigurations":398},{"removed":"critpt","score":0.0064856289517849245,"rank":388,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.007575580777083107,"rank":387,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.007636606107797192,"rank":387,"remainingConfigurations":398},{"removed":"gdpval","score":0.0075787069174983075,"rank":388,"remainingConfigurations":398},{"removed":"gmmlu","score":0.007611025957778792,"rank":390,"remainingConfigurations":398},{"removed":"gpqa","score":0.007676400304205199,"rank":388,"remainingConfigurations":398},{"removed":"harvey","score":0.0074694892567604065,"rank":387,"remainingConfigurations":398},{"removed":"hle","score":0.007521903437100072,"rank":386,"remainingConfigurations":398},{"removed":"ifbench","score":0.007315666022862362,"rank":389,"remainingConfigurations":398},{"removed":"itbench","score":0.007542812224329396,"rank":387,"remainingConfigurations":398},{"removed":"livecodebench","score":0.007899593490353173,"rank":389,"remainingConfigurations":398},{"removed":"math500","score":0.007611453443699759,"rank":389,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008250851124569815,"rank":388,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008285274675248411,"rank":387,"remainingConfigurations":398},{"removed":"omniscience","score":0.00710666001837761,"rank":387,"remainingConfigurations":398},{"removed":"scicode","score":0.007696759832833525,"rank":388,"remainingConfigurations":398},{"removed":"tau-bench","score":0.007417940278512594,"rank":385,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0073911480853802,"rank":390,"remainingConfigurations":398},{"removed":"arc-agi","score":0.009186979781809738,"rank":388,"remainingConfigurations":398},{"removed":"deepswe","score":0.006378177965396265,"rank":388,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.007547255889829738,"rank":387,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.007492002264503161,"rank":387,"remainingConfigurations":398},{"removed":"frontiercode","score":0.007967774804436504,"rank":388,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.007554707016603324,"rank":387,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0074719589286882035,"rank":387,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.007534066008839446,"rank":387,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.007516426206662503,"rank":387,"remainingConfigurations":398},{"removed":"livebench-math","score":0.007559206244146394,"rank":387,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.007477552485117449,"rank":387,"remainingConfigurations":398},{"removed":"livebench-language","score":0.007641095389695998,"rank":387,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0075624293058566515,"rank":387,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.007415927739623462,"rank":387,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.007490189006979356,"rank":387,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.007672224554425802,"rank":387,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.007783908966807755,"rank":388,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.00712465840725147,"rank":387,"remainingConfigurations":398},{"removed":"frontiermath","score":0.007628853441129513,"rank":388,"remainingConfigurations":398},{"removed":"simpleqa","score":0.007880006336086584,"rank":388,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.007504538244472651,"rank":387,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0075162065651086934,"rank":387,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.007511060804432042,"rank":387,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.007530379213726755,"rank":387,"remainingConfigurations":398},{"removed":"vibe-code","score":0.007489930006439489,"rank":387,"remainingConfigurations":398}]},"qwen3-0.6b--effort-reasoning":{"score":0.007528957285643161,"rank":388,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.00928963945281326,"rank":387,"remainingConfigurations":398},{"removed":"Datacurve","score":0.006366059641993296,"rank":389,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.007453645134882349,"rank":388,"remainingConfigurations":398},{"removed":"Scale","score":0.00846924657476265,"rank":388,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.007512595203730016,"rank":388,"remainingConfigurations":398},{"removed":"Cognition","score":0.007965583123369873,"rank":389,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0077413980876353565,"rank":387,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.007785072909136187,"rank":387,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0075092834591696765,"rank":372,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007321826998154307,"rank":388,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0075294395077913565,"rank":388,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.007521378252430387,"rank":388,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.007515514865975519,"rank":388,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.007528957285643161,"rank":388,"remainingConfigurations":398},{"removed":"All provider reports","score":0.007507075586362522,"rank":388,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.007562741308384709,"rank":388,"remainingConfigurations":398},{"removed":"briefcase","score":0.0075275189628450515,"rank":387,"remainingConfigurations":398},{"removed":"aime","score":0.007540249271493316,"rank":389,"remainingConfigurations":398},{"removed":"apex-agents","score":0.007629507667857558,"rank":388,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.007551796471622861,"rank":387,"remainingConfigurations":398},{"removed":"automationbench","score":0.007532854150295423,"rank":387,"remainingConfigurations":398},{"removed":"critpt","score":0.006440563454538598,"rank":389,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.007556663874536018,"rank":388,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.007635670318802561,"rank":388,"remainingConfigurations":398},{"removed":"gdpval","score":0.007586637171676282,"rank":387,"remainingConfigurations":398},{"removed":"gmmlu","score":0.007625384356868146,"rank":389,"remainingConfigurations":398},{"removed":"gpqa","score":0.007737921459385416,"rank":387,"remainingConfigurations":398},{"removed":"harvey","score":0.007451266601599414,"rank":388,"remainingConfigurations":398},{"removed":"hle","score":0.006894341998847704,"rank":390,"remainingConfigurations":398},{"removed":"ifbench","score":0.007465846817458289,"rank":387,"remainingConfigurations":398},{"removed":"itbench","score":0.007526126873658892,"rank":388,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008094719398052544,"rank":386,"remainingConfigurations":398},{"removed":"math500","score":0.007684187098583264,"rank":387,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008510497007388877,"rank":385,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008111064840493546,"rank":389,"remainingConfigurations":398},{"removed":"omniscience","score":0.00718729686818075,"rank":386,"remainingConfigurations":398},{"removed":"scicode","score":0.007696844133835742,"rank":387,"remainingConfigurations":398},{"removed":"tau-bench","score":0.006976045304401451,"rank":388,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.007796186211037066,"rank":387,"remainingConfigurations":398},{"removed":"arc-agi","score":0.009205998655768361,"rank":387,"remainingConfigurations":398},{"removed":"deepswe","score":0.006371033053177003,"rank":389,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.007531264016164017,"rank":388,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.007476143753781833,"rank":388,"remainingConfigurations":398},{"removed":"frontiercode","score":0.007965583123369873,"rank":389,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.007538950132961697,"rank":388,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.007456537839202835,"rank":388,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.007518087271863699,"rank":388,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0075000247684049,"rank":388,"remainingConfigurations":398},{"removed":"livebench-math","score":0.007543202639331124,"rank":388,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.007461623689061731,"rank":388,"remainingConfigurations":398},{"removed":"livebench-language","score":0.007624854633611678,"rank":388,"remainingConfigurations":398},{"removed":"livebench-data","score":0.007546442327245128,"rank":388,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.007400240535473671,"rank":388,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.007474312898320032,"rank":388,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.007656065841864669,"rank":388,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.007785072909136187,"rank":387,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.00710397528416212,"rank":388,"remainingConfigurations":398},{"removed":"frontiermath","score":0.007616424391023494,"rank":389,"remainingConfigurations":398},{"removed":"simpleqa","score":0.007863061485925884,"rank":389,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.007488649358016744,"rank":388,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.007500270967814141,"rank":388,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.007495169301587337,"rank":388,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.007514389464846112,"rank":388,"remainingConfigurations":398},{"removed":"vibe-code","score":0.007474057959600111,"rank":388,"remainingConfigurations":398}]},"qwen3-1.7b--effort-non-reasoning":{"score":0.007462758810520671,"rank":389,"sourceRemovals":[{"removed":"Artificial Analysis","score":0.007900113731021018,"rank":164,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.009269255559628785,"rank":388,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0063875222865766345,"rank":387,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.007396792949532805,"rank":389,"remainingConfigurations":398},{"removed":"Scale","score":0.008389316719400153,"rank":389,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.007484275712069122,"rank":389,"remainingConfigurations":398},{"removed":"Cognition","score":0.007971326084100889,"rank":387,"remainingConfigurations":398},{"removed":"LiveBench","score":0.007683982894912207,"rank":388,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0076740900924169965,"rank":389,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.006982461598661935,"rank":373,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007348715050241382,"rank":386,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.007463150674261558,"rank":389,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.007454814312732187,"rank":389,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.007450381034261352,"rank":389,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.007462758810520671,"rank":389,"remainingConfigurations":398},{"removed":"All provider reports","score":0.007441528975339818,"rank":389,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.007493497204741065,"rank":389,"remainingConfigurations":398},{"removed":"briefcase","score":0.007447963195676738,"rank":389,"remainingConfigurations":398},{"removed":"aime","score":0.00761987159903646,"rank":388,"remainingConfigurations":398},{"removed":"apex-agents","score":0.007553737088928004,"rank":389,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.007469421197039634,"rank":389,"remainingConfigurations":398},{"removed":"automationbench","score":0.007452447719759559,"rank":389,"remainingConfigurations":398},{"removed":"critpt","score":0.006628625160629248,"rank":387,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.007484745152601793,"rank":389,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.007544534612011446,"rank":389,"remainingConfigurations":398},{"removed":"gdpval","score":0.007487965336814616,"rank":389,"remainingConfigurations":398},{"removed":"gmmlu","score":0.00765555367194489,"rank":387,"remainingConfigurations":398},{"removed":"gpqa","score":0.00764319352630682,"rank":389,"remainingConfigurations":398},{"removed":"harvey","score":0.0073806631250535985,"rank":389,"remainingConfigurations":398},{"removed":"hle","score":0.007222732313517011,"rank":387,"remainingConfigurations":398},{"removed":"ifbench","score":0.007457007288677203,"rank":388,"remainingConfigurations":398},{"removed":"itbench","score":0.007456196755466299,"rank":389,"remainingConfigurations":398},{"removed":"livecodebench","score":0.007813065449614935,"rank":390,"remainingConfigurations":398},{"removed":"math500","score":0.007672319148867412,"rank":388,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.00811433833974451,"rank":389,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008024408216574354,"rank":390,"remainingConfigurations":398},{"removed":"omniscience","score":0.007104142432522866,"rank":388,"remainingConfigurations":398},{"removed":"scicode","score":0.0075980905957351965,"rank":389,"remainingConfigurations":398},{"removed":"tau-bench","score":0.006887079533729869,"rank":389,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.007626682645973691,"rank":388,"remainingConfigurations":398},{"removed":"arc-agi","score":0.009171310186875089,"rank":389,"remainingConfigurations":398},{"removed":"deepswe","score":0.006392657804635978,"rank":387,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.007465009537090132,"rank":389,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.007411375276117329,"rank":389,"remainingConfigurations":398},{"removed":"frontiercode","score":0.007971326084100889,"rank":387,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.007478577320607144,"rank":389,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.007389183124107528,"rank":389,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00745226971477516,"rank":389,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0074338893328224145,"rank":389,"remainingConfigurations":398},{"removed":"livebench-math","score":0.007478452151507701,"rank":389,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.007391860352088629,"rank":389,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0075576090579117005,"rank":389,"remainingConfigurations":398},{"removed":"livebench-data","score":0.007481191644183426,"rank":389,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.007336514110511654,"rank":389,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.0074083381668132746,"rank":389,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.007589186699456706,"rank":389,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0076740900924169965,"rank":389,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.006529341421606501,"rank":390,"remainingConfigurations":398},{"removed":"frontiermath","score":0.007679213398987475,"rank":387,"remainingConfigurations":398},{"removed":"simpleqa","score":0.007922840326449724,"rank":387,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.007422785505802192,"rank":389,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.007434978275769684,"rank":389,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.007428224602684825,"rank":389,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.007448617710618648,"rank":389,"remainingConfigurations":398},{"removed":"vibe-code","score":0.007409466090057386,"rank":389,"remainingConfigurations":398}]},"gemma-3-4b-it--effort-non-reasoning":{"score":0.007438273233113396,"rank":390,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.00913520433723348,"rank":390,"remainingConfigurations":398},{"removed":"Datacurve","score":0.006280659062674262,"rank":390,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.007364344507935759,"rank":390,"remainingConfigurations":398},{"removed":"Scale","score":0.008363195549752258,"rank":390,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.007424938314074037,"rank":390,"remainingConfigurations":398},{"removed":"Cognition","score":0.007852787422215382,"rank":390,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0076536055221071535,"rank":389,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.007672721041129112,"rank":390,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0075337311257824245,"rank":371,"remainingConfigurations":381},{"removed":"Vals AI","score":0.007241043865874087,"rank":389,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.007438748505725685,"rank":390,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.007430777953533748,"rank":390,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0074249566889333,"rank":390,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.007438273233113396,"rank":390,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0074166101381462025,"rank":390,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.00747470291788433,"rank":390,"remainingConfigurations":398},{"removed":"briefcase","score":0.0074129452230482775,"rank":390,"remainingConfigurations":398},{"removed":"aime","score":0.007717121310037198,"rank":386,"remainingConfigurations":398},{"removed":"apex-agents","score":0.007537615665218652,"rank":390,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.007216452012997217,"rank":390,"remainingConfigurations":398},{"removed":"automationbench","score":0.007411160269447118,"rank":390,"remainingConfigurations":398},{"removed":"critpt","score":0.006431654467515581,"rank":390,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.007466847181226714,"rank":390,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0075162779693778966,"rank":390,"remainingConfigurations":398},{"removed":"gdpval","score":0.0074681039294600534,"rank":390,"remainingConfigurations":398},{"removed":"gmmlu","score":0.007632014924144834,"rank":388,"remainingConfigurations":398},{"removed":"gpqa","score":0.007570973823037264,"rank":390,"remainingConfigurations":398},{"removed":"harvey","score":0.0073641732686210324,"rank":390,"remainingConfigurations":398},{"removed":"hle","score":0.006976145294206697,"rank":389,"remainingConfigurations":398},{"removed":"ifbench","score":0.007167821470188706,"rank":390,"remainingConfigurations":398},{"removed":"itbench","score":0.00743639267092763,"rank":390,"remainingConfigurations":398},{"removed":"livecodebench","score":0.008005664443775838,"rank":387,"remainingConfigurations":398},{"removed":"math500","score":0.007575634976326621,"rank":390,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.008260359790083103,"rank":387,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.008138160586110858,"rank":388,"remainingConfigurations":398},{"removed":"omniscience","score":0.00702237513279927,"rank":389,"remainingConfigurations":398},{"removed":"scicode","score":0.007575186484457679,"rank":390,"remainingConfigurations":398},{"removed":"tau-bench","score":0.007288833920349947,"rank":386,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.007466586107766564,"rank":389,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0090571297146994,"rank":390,"remainingConfigurations":398},{"removed":"deepswe","score":0.006285576327827319,"rank":390,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.007440557349043069,"rank":390,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.007386011636777147,"rank":390,"remainingConfigurations":398},{"removed":"frontiercode","score":0.007852787422215382,"rank":390,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.007447744818582539,"rank":390,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.007366254289888726,"rank":390,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00742753813840234,"rank":390,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.007410172015351306,"rank":390,"remainingConfigurations":398},{"removed":"livebench-math","score":0.007452338034014311,"rank":390,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.007371846639677726,"rank":390,"remainingConfigurations":398},{"removed":"livebench-language","score":0.007533091056635727,"rank":390,"remainingConfigurations":398},{"removed":"livebench-data","score":0.007455495187660807,"rank":390,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.007311053534184122,"rank":390,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.007384292994171125,"rank":390,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0075637849216856805,"rank":390,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.007672721041129112,"rank":390,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.007024504297625363,"rank":389,"remainingConfigurations":398},{"removed":"frontiermath","score":0.00752010072189549,"rank":390,"remainingConfigurations":398},{"removed":"simpleqa","score":0.007768492369240013,"rank":390,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.007398432967373349,"rank":390,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.00740993470498784,"rank":390,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.007404869826134479,"rank":390,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0074239114980812855,"rank":390,"remainingConfigurations":398},{"removed":"vibe-code","score":0.007384026231332579,"rank":390,"remainingConfigurations":398}]},"phi-4-mini-instruct--effort-non-reasoning":{"score":0.0066877082060350064,"rank":391,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.008220984891569026,"rank":391,"remainingConfigurations":398},{"removed":"Datacurve","score":0.005649355595152633,"rank":391,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.006621644422129013,"rank":391,"remainingConfigurations":398},{"removed":"Scale","score":0.0075211601670335726,"rank":391,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.006676797155783229,"rank":391,"remainingConfigurations":398},{"removed":"Cognition","score":0.0070642590799745485,"rank":391,"remainingConfigurations":398},{"removed":"LiveBench","score":0.006882468584721767,"rank":390,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.006901216490564366,"rank":391,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.006762231756364552,"rank":374,"remainingConfigurations":381},{"removed":"Vals AI","score":0.006511485179694153,"rank":390,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.006688135996213178,"rank":391,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0066809821318962815,"rank":391,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.006675739468293001,"rank":391,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0066877082060350064,"rank":391,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0066682466326337475,"rank":391,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.006721324191498079,"rank":391,"remainingConfigurations":398},{"removed":"briefcase","score":0.0066788625000290475,"rank":391,"remainingConfigurations":398},{"removed":"aime","score":0.007059031383749227,"rank":390,"remainingConfigurations":398},{"removed":"apex-agents","score":0.00677827329379791,"rank":391,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.006195397218432008,"rank":391,"remainingConfigurations":398},{"removed":"automationbench","score":0.006681970028663036,"rank":391,"remainingConfigurations":398},{"removed":"critpt","score":0.005642311843546186,"rank":392,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.006716425905063575,"rank":391,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.00677506686469193,"rank":391,"remainingConfigurations":398},{"removed":"gdpval","score":0.006731288495783629,"rank":391,"remainingConfigurations":398},{"removed":"gmmlu","score":0.006748744783167397,"rank":391,"remainingConfigurations":398},{"removed":"gpqa","score":0.006660730663303419,"rank":391,"remainingConfigurations":398},{"removed":"harvey","score":0.00662181124371817,"rank":391,"remainingConfigurations":398},{"removed":"hle","score":0.006598511242122328,"rank":391,"remainingConfigurations":398},{"removed":"ifbench","score":0.0066921039977162556,"rank":391,"remainingConfigurations":398},{"removed":"itbench","score":0.006686792312472103,"rank":391,"remainingConfigurations":398},{"removed":"livecodebench","score":0.00709697164354089,"rank":391,"remainingConfigurations":398},{"removed":"math500","score":0.007200776050855341,"rank":391,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.007316307950760309,"rank":391,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.007208133083462221,"rank":391,"remainingConfigurations":398},{"removed":"omniscience","score":0.006123203483342376,"rank":391,"remainingConfigurations":398},{"removed":"scicode","score":0.0068290984425275975,"rank":391,"remainingConfigurations":398},{"removed":"tau-bench","score":0.006574628367757428,"rank":391,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.006754248971890392,"rank":391,"remainingConfigurations":398},{"removed":"arc-agi","score":0.008148656754585409,"rank":391,"remainingConfigurations":398},{"removed":"deepswe","score":0.005653783720818943,"rank":391,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.006689764389486067,"rank":391,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.006640769920852333,"rank":391,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0070642590799745485,"rank":391,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0066965032817943235,"rank":391,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.006623007507675406,"rank":391,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.006678076221241595,"rank":391,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.006662460867182379,"rank":391,"remainingConfigurations":398},{"removed":"livebench-math","score":0.006700379941403457,"rank":391,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.006627835064409708,"rank":391,"remainingConfigurations":398},{"removed":"livebench-language","score":0.006773079698184712,"rank":391,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0067032683115096,"rank":391,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.006573172749027082,"rank":391,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.006639085218266202,"rank":391,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.006800746900804976,"rank":391,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.006901216490564366,"rank":391,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.00631496255782102,"rank":391,"remainingConfigurations":398},{"removed":"frontiermath","score":0.006762418175555582,"rank":391,"remainingConfigurations":398},{"removed":"simpleqa","score":0.006985568022440555,"rank":391,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.006651841183948146,"rank":391,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0066621981625254135,"rank":391,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.006657621375490807,"rank":391,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.006674778064611013,"rank":391,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0066388766397883665,"rank":391,"remainingConfigurations":398}]},"phi-4-multimodal-instruct--effort-non-reasoning":{"score":0.005951847430612784,"rank":392,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.007363860077591489,"rank":392,"remainingConfigurations":398},{"removed":"Datacurve","score":0.005036658755451898,"rank":392,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.005893226635013093,"rank":392,"remainingConfigurations":398},{"removed":"Scale","score":0.006700042906644978,"rank":392,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.005940121639329693,"rank":392,"remainingConfigurations":398},{"removed":"Cognition","score":0.006305796542829422,"rank":392,"remainingConfigurations":398},{"removed":"LiveBench","score":0.006122416939138433,"rank":391,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.00615484928580265,"rank":392,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.005945230148571484,"rank":375,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0057910176737568314,"rank":391,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0059522280326333695,"rank":392,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.005945811486750346,"rank":392,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0059411968403068486,"rank":392,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.005951847430612784,"rank":392,"remainingConfigurations":398},{"removed":"All provider reports","score":0.00593447746837972,"rank":392,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.005978741873578708,"rank":392,"remainingConfigurations":398},{"removed":"briefcase","score":0.0059541585298482054,"rank":392,"remainingConfigurations":398},{"removed":"aime","score":0.005883200217505877,"rank":392,"remainingConfigurations":398},{"removed":"apex-agents","score":0.006032156146860589,"rank":392,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.005884031601008702,"rank":392,"remainingConfigurations":398},{"removed":"automationbench","score":0.005957328835678428,"rank":392,"remainingConfigurations":398},{"removed":"critpt","score":0.0056472623653616135,"rank":391,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.005973788554501906,"rank":392,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.0060384915459177025,"rank":392,"remainingConfigurations":398},{"removed":"gdpval","score":0.006001261777319242,"rank":392,"remainingConfigurations":398},{"removed":"gmmlu","score":0.006026695203029079,"rank":392,"remainingConfigurations":398},{"removed":"gpqa","score":0.00585644514391741,"rank":392,"remainingConfigurations":398},{"removed":"harvey","score":0.005891319709894191,"rank":392,"remainingConfigurations":398},{"removed":"hle","score":0.004643102654538136,"rank":396,"remainingConfigurations":398},{"removed":"ifbench","score":0.005798166737285563,"rank":392,"remainingConfigurations":398},{"removed":"itbench","score":0.005949548628251381,"rank":392,"remainingConfigurations":398},{"removed":"livecodebench","score":0.00645039223517199,"rank":392,"remainingConfigurations":398},{"removed":"math500","score":0.006767903138026579,"rank":392,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.006656543020582326,"rank":392,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.006634436443847273,"rank":392,"remainingConfigurations":398},{"removed":"omniscience","score":0.005543562879944275,"rank":392,"remainingConfigurations":398},{"removed":"scicode","score":0.006087802079555202,"rank":392,"remainingConfigurations":398},{"removed":"tau-bench","score":0.00577375959701311,"rank":392,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0059972100817213035,"rank":392,"remainingConfigurations":398},{"removed":"arc-agi","score":0.007294207009722372,"rank":392,"remainingConfigurations":398},{"removed":"deepswe","score":0.005040598488495374,"rank":392,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.0059536759130811275,"rank":392,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0059100941390885925,"rank":392,"remainingConfigurations":398},{"removed":"frontiercode","score":0.006305796542829422,"rank":392,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.005959980499349746,"rank":392,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.005894590686515287,"rank":392,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.005943268162041865,"rank":392,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.005928927612492418,"rank":392,"remainingConfigurations":398},{"removed":"livebench-math","score":0.005963151643603431,"rank":392,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.005898419071768297,"rank":392,"remainingConfigurations":398},{"removed":"livebench-language","score":0.006027885221261198,"rank":392,"remainingConfigurations":398},{"removed":"livebench-data","score":0.005965718468953235,"rank":392,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.005849805440901181,"rank":392,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.005908518836409378,"rank":392,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.006052664279779088,"rank":392,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.00615484928580265,"rank":392,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.005609427726607617,"rank":392,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0060202548788480525,"rank":392,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0062176797005345,"rank":392,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.005919881212975092,"rank":392,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.005929101484422372,"rank":392,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.005925063186139325,"rank":392,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.005940274673777509,"rank":392,"remainingConfigurations":398},{"removed":"vibe-code","score":0.005908323606986875,"rank":392,"remainingConfigurations":398}]},"qwen3-0.6b--effort-non-reasoning":{"score":0.005756971513969169,"rank":393,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.007127235868062066,"rank":393,"remainingConfigurations":398},{"removed":"Datacurve","score":0.004868956464394327,"rank":393,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.005700238290652517,"rank":393,"remainingConfigurations":398},{"removed":"Scale","score":0.006481821280402111,"rank":393,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.005744930110929413,"rank":393,"remainingConfigurations":398},{"removed":"Cognition","score":0.006096616551435456,"rank":393,"remainingConfigurations":398},{"removed":"LiveBench","score":0.005921490546547802,"rank":392,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.005961144266509205,"rank":393,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.005749137071147902,"rank":376,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0056003856122716356,"rank":392,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.005757341172869991,"rank":393,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.005751162064344937,"rank":393,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.005746674168422371,"rank":393,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.005756971513969169,"rank":393,"remainingConfigurations":398},{"removed":"All provider reports","score":0.005740204375173484,"rank":393,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.005784309972839377,"rank":393,"remainingConfigurations":398},{"removed":"briefcase","score":0.00576580319218159,"rank":393,"remainingConfigurations":398},{"removed":"aime","score":0.005838303254298057,"rank":393,"remainingConfigurations":398},{"removed":"apex-agents","score":0.005835890881379074,"rank":393,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.005673893296549795,"rank":393,"remainingConfigurations":398},{"removed":"automationbench","score":0.005770848831957456,"rank":393,"remainingConfigurations":398},{"removed":"critpt","score":0.004749628200553615,"rank":393,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.0057808567252453655,"rank":393,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.005849483399362049,"rank":393,"remainingConfigurations":398},{"removed":"gdpval","score":0.005814877162832933,"rank":393,"remainingConfigurations":398},{"removed":"gmmlu","score":0.005838817173489189,"rank":393,"remainingConfigurations":398},{"removed":"gpqa","score":0.005828063681791766,"rank":393,"remainingConfigurations":398},{"removed":"harvey","score":0.005699533228043722,"rank":393,"remainingConfigurations":398},{"removed":"hle","score":0.005247430928195345,"rank":393,"remainingConfigurations":398},{"removed":"ifbench","score":0.005659243671608312,"rank":393,"remainingConfigurations":398},{"removed":"itbench","score":0.005756300917879536,"rank":393,"remainingConfigurations":398},{"removed":"livecodebench","score":0.006103459633359461,"rank":393,"remainingConfigurations":398},{"removed":"math500","score":0.006398487831188773,"rank":393,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.006408842823160506,"rank":393,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.006214887559490359,"rank":393,"remainingConfigurations":398},{"removed":"omniscience","score":0.005462591030320364,"rank":393,"remainingConfigurations":398},{"removed":"scicode","score":0.005897585834222834,"rank":393,"remainingConfigurations":398},{"removed":"tau-bench","score":0.005522940597520888,"rank":393,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.005895765035305932,"rank":393,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0070613495513282805,"rank":393,"remainingConfigurations":398},{"removed":"deepswe","score":0.004872767820474641,"rank":393,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.005758740753859754,"rank":393,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.005716590308460425,"rank":393,"remainingConfigurations":398},{"removed":"frontiercode","score":0.006096616551435456,"rank":393,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.005764802534063898,"rank":393,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.005701547793502374,"rank":393,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0057486664727308566,"rank":393,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.005734878785147474,"rank":393,"remainingConfigurations":398},{"removed":"livebench-math","score":0.005767904810210097,"rank":393,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.005705271193641666,"rank":393,"remainingConfigurations":398},{"removed":"livebench-language","score":0.005830545554654169,"rank":393,"remainingConfigurations":398},{"removed":"livebench-data","score":0.005770412341909603,"rank":393,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.005658229826113355,"rank":393,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.005715036968347041,"rank":393,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.00585453288147382,"rank":393,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.005961144266509205,"rank":393,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0054291715899454016,"rank":393,"remainingConfigurations":398},{"removed":"frontiermath","score":0.005825319760492297,"rank":393,"remainingConfigurations":398},{"removed":"simpleqa","score":0.0060136780325731965,"rank":393,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.005726046023509426,"rank":393,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.005734960600761146,"rank":393,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00573104828679066,"rank":393,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.005745777720450027,"rank":393,"remainingConfigurations":398},{"removed":"vibe-code","score":0.005714860393195416,"rank":393,"remainingConfigurations":398}]},"gemma-3n-e2b-it--effort-non-reasoning":{"score":0.005507655450983053,"rank":394,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.006779964569081111,"rank":394,"remainingConfigurations":398},{"removed":"Datacurve","score":0.004651407387280129,"rank":394,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.005453868937656074,"rank":394,"remainingConfigurations":398},{"removed":"Scale","score":0.006196675607489783,"rank":394,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0054972397098231535,"rank":394,"remainingConfigurations":398},{"removed":"Cognition","score":0.005820051270418472,"rank":394,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0056668560402361595,"rank":393,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.005688285747655277,"rank":394,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.005560197952144245,"rank":377,"remainingConfigurations":381},{"removed":"Vals AI","score":0.005359957343723462,"rank":393,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.0055080090026500585,"rank":394,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.005502098129016141,"rank":394,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.005497800219547617,"rank":394,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.005507655450983053,"rank":394,"remainingConfigurations":398},{"removed":"All provider reports","score":0.005491610819833532,"rank":394,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.005534581861957554,"rank":394,"remainingConfigurations":398},{"removed":"briefcase","score":0.005508263419223529,"rank":394,"remainingConfigurations":398},{"removed":"aime","score":0.005586735378420346,"rank":395,"remainingConfigurations":398},{"removed":"apex-agents","score":0.005581440430889036,"rank":394,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.005404303122083804,"rank":394,"remainingConfigurations":398},{"removed":"automationbench","score":0.005509338305331942,"rank":394,"remainingConfigurations":398},{"removed":"critpt","score":0.004485566109034646,"rank":394,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.005532189613494182,"rank":394,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.005585373115800049,"rank":394,"remainingConfigurations":398},{"removed":"gdpval","score":0.005545716383630377,"rank":394,"remainingConfigurations":398},{"removed":"gmmlu","score":0.005561859947860584,"rank":394,"remainingConfigurations":398},{"removed":"gpqa","score":0.005575702310837632,"rank":394,"remainingConfigurations":398},{"removed":"harvey","score":0.005452108082453084,"rank":394,"remainingConfigurations":398},{"removed":"hle","score":0.005459978219599063,"rank":392,"remainingConfigurations":398},{"removed":"ifbench","score":0.0053910305283925535,"rank":394,"remainingConfigurations":398},{"removed":"itbench","score":0.005505991231340056,"rank":394,"remainingConfigurations":398},{"removed":"livecodebench","score":0.005853738533812813,"rank":394,"remainingConfigurations":398},{"removed":"math500","score":0.005958900605941157,"rank":395,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.006056129439916497,"rank":394,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.00592395443745163,"rank":394,"remainingConfigurations":398},{"removed":"omniscience","score":0.005110173812714011,"rank":394,"remainingConfigurations":398},{"removed":"scicode","score":0.005629988845755253,"rank":394,"remainingConfigurations":398},{"removed":"tau-bench","score":0.005460192508948942,"rank":394,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.005460841207426881,"rank":394,"remainingConfigurations":398},{"removed":"arc-agi","score":0.006720212105706937,"rank":394,"remainingConfigurations":398},{"removed":"deepswe","score":0.0046550543711342445,"rank":394,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.005509350042643593,"rank":394,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.005468991757138411,"rank":394,"remainingConfigurations":398},{"removed":"frontiercode","score":0.005820051270418472,"rank":394,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.005514913086111454,"rank":394,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.005454334739893051,"rank":394,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.00549971190495177,"rank":394,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.0054866756919224255,"rank":394,"remainingConfigurations":398},{"removed":"livebench-math","score":0.0055181249684967465,"rank":394,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.005458171952454442,"rank":394,"remainingConfigurations":398},{"removed":"livebench-language","score":0.005578092120118381,"rank":394,"remainingConfigurations":398},{"removed":"livebench-data","score":0.005520518259278154,"rank":394,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.005413145589652029,"rank":394,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.005467516441674279,"rank":394,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.005601019400711167,"rank":394,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.005688285747655277,"rank":394,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.005197343131936091,"rank":394,"remainingConfigurations":398},{"removed":"frontiermath","score":0.005569777375087035,"rank":394,"remainingConfigurations":398},{"removed":"simpleqa","score":0.005753849423333225,"rank":394,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.005478053267759368,"rank":394,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.005486593348647592,"rank":394,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.005482831193313598,"rank":394,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.005496952888568159,"rank":394,"remainingConfigurations":398},{"removed":"vibe-code","score":0.0054673579856622774,"rank":394,"remainingConfigurations":398}]},"gemma-3-1b-it--effort-non-reasoning":{"score":0.005387313954317847,"rank":395,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.00663327545638042,"rank":395,"remainingConfigurations":398},{"removed":"Datacurve","score":0.004548081553277927,"rank":395,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.005334832834292233,"rank":395,"remainingConfigurations":398},{"removed":"Scale","score":0.006062166830917086,"rank":395,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.005377065296772194,"rank":395,"remainingConfigurations":398},{"removed":"Cognition","score":0.005691297700530368,"rank":395,"remainingConfigurations":398},{"removed":"LiveBench","score":0.005543077667374952,"rank":394,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.005562668650045396,"rank":395,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.005432963672523854,"rank":378,"remainingConfigurations":381},{"removed":"Vals AI","score":0.005242938908506707,"rank":394,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.005387659751686366,"rank":395,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0053818754335284704,"rank":395,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.005377669702744749,"rank":395,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.005387313954317847,"rank":395,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0053716126973753055,"rank":395,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.005413922121472734,"rank":395,"remainingConfigurations":398},{"removed":"briefcase","score":0.005384238274175691,"rank":395,"remainingConfigurations":398},{"removed":"aime","score":0.005645334174423605,"rank":394,"remainingConfigurations":398},{"removed":"apex-agents","score":0.00545999909745127,"rank":395,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.005278744924622144,"rank":395,"remainingConfigurations":398},{"removed":"automationbench","score":0.005385574732408306,"rank":395,"remainingConfigurations":398},{"removed":"critpt","score":0.004411249519076538,"rank":395,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.005409623094445234,"rank":395,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.005460397484645225,"rank":395,"remainingConfigurations":398},{"removed":"gdpval","score":0.005426581050105363,"rank":395,"remainingConfigurations":398},{"removed":"gmmlu","score":0.005504222319520733,"rank":395,"remainingConfigurations":398},{"removed":"gpqa","score":0.005407510243296307,"rank":395,"remainingConfigurations":398},{"removed":"harvey","score":0.005333430404282966,"rank":395,"remainingConfigurations":398},{"removed":"hle","score":0.004734870719324452,"rank":395,"remainingConfigurations":398},{"removed":"ifbench","score":0.005357954634636537,"rank":395,"remainingConfigurations":398},{"removed":"itbench","score":0.005386151273553758,"rank":395,"remainingConfigurations":398},{"removed":"livecodebench","score":0.005783355228905582,"rank":395,"remainingConfigurations":398},{"removed":"math500","score":0.0060139441492787216,"rank":394,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.005998170390316881,"rank":395,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.005808881350422466,"rank":395,"remainingConfigurations":398},{"removed":"omniscience","score":0.005076197083411786,"rank":395,"remainingConfigurations":398},{"removed":"scicode","score":0.005503857582108861,"rank":395,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0051517314131940125,"rank":395,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.005459001154447775,"rank":395,"remainingConfigurations":398},{"removed":"arc-agi","score":0.006575336022274693,"rank":395,"remainingConfigurations":398},{"removed":"deepswe","score":0.0045516489254728955,"rank":395,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.005388972349316706,"rank":395,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.005349447126599876,"rank":395,"remainingConfigurations":398},{"removed":"frontiercode","score":0.005691297700530368,"rank":395,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.005394313085870667,"rank":395,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.005335109372729495,"rank":395,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.005379535023871403,"rank":395,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.005366800944560726,"rank":395,"remainingConfigurations":398},{"removed":"livebench-math","score":0.005397555120047248,"rank":395,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.005338915396612388,"rank":395,"remainingConfigurations":398},{"removed":"livebench-language","score":0.005456229709535946,"rank":395,"remainingConfigurations":398},{"removed":"livebench-data","score":0.005399885041646426,"rank":395,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.005294843974924063,"rank":395,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.005348047335204442,"rank":395,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.005478658467744805,"rank":395,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.005562668650045396,"rank":395,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0050842157194862765,"rank":395,"remainingConfigurations":398},{"removed":"frontiermath","score":0.005447999017772977,"rank":395,"remainingConfigurations":398},{"removed":"simpleqa","score":0.00562807668010644,"rank":395,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.0053583506901634876,"rank":395,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.0053667043676950575,"rank":395,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.005363028101805546,"rank":395,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.005376841188493701,"rank":395,"remainingConfigurations":398},{"removed":"vibe-code","score":0.005347885592753049,"rank":395,"remainingConfigurations":398}]},"gemma-3-270m-it--effort-non-reasoning":{"score":0.004812848735359122,"rank":396,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.005936446181103737,"rank":396,"remainingConfigurations":398},{"removed":"Datacurve","score":0.004067509854974468,"rank":396,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.004766179368459106,"rank":396,"remainingConfigurations":398},{"removed":"Scale","score":0.005416757418961258,"rank":396,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.004804119870402059,"rank":396,"remainingConfigurations":398},{"removed":"Cognition","score":0.0050901891032340526,"rank":396,"remainingConfigurations":398},{"removed":"LiveBench","score":0.004953227875343398,"rank":395,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0049771608520081416,"rank":396,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.004861083835913648,"rank":379,"remainingConfigurations":381},{"removed":"Vals AI","score":0.004685129466569816,"rank":395,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.004813158433587834,"rank":396,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.004807990877499235,"rank":396,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.004804227291467708,"rank":396,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.004812848735359122,"rank":396,"remainingConfigurations":398},{"removed":"All provider reports","score":0.004798816476752738,"rank":396,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.00483747020682548,"rank":396,"remainingConfigurations":398},{"removed":"briefcase","score":0.004821321819189384,"rank":396,"remainingConfigurations":398},{"removed":"aime","score":0.005069117065075122,"rank":396,"remainingConfigurations":398},{"removed":"apex-agents","score":0.004878506333121129,"rank":396,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.004650408119638845,"rank":396,"remainingConfigurations":398},{"removed":"automationbench","score":0.004823656281844017,"rank":396,"remainingConfigurations":398},{"removed":"critpt","score":0.003720183588825216,"rank":397,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.004836465854860272,"rank":396,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.004890993612374686,"rank":396,"remainingConfigurations":398},{"removed":"gdpval","score":0.004852773761653635,"rank":396,"remainingConfigurations":398},{"removed":"gmmlu","score":0.004864178670310811,"rank":396,"remainingConfigurations":398},{"removed":"gpqa","score":0.004858971414287421,"rank":396,"remainingConfigurations":398},{"removed":"harvey","score":0.004765643409875757,"rank":396,"remainingConfigurations":398},{"removed":"hle","score":0.004911083171514555,"rank":394,"remainingConfigurations":398},{"removed":"ifbench","score":0.004845783144499355,"rank":396,"remainingConfigurations":398},{"removed":"itbench","score":0.004812308102591044,"rank":396,"remainingConfigurations":398},{"removed":"livecodebench","score":0.005203758235743495,"rank":396,"remainingConfigurations":398},{"removed":"math500","score":0.004824072194969531,"rank":396,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.00542264556168746,"rank":396,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.005175124970479807,"rank":396,"remainingConfigurations":398},{"removed":"omniscience","score":0.004542404479387074,"rank":396,"remainingConfigurations":398},{"removed":"scicode","score":0.004930524426364156,"rank":396,"remainingConfigurations":398},{"removed":"tau-bench","score":0.004577233598757973,"rank":396,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.004846720921120601,"rank":396,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0058822170707368065,"rank":396,"remainingConfigurations":398},{"removed":"deepswe","score":0.00407070002206295,"rank":396,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.004814331119107147,"rank":396,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.004779112460881042,"rank":396,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0050901891032340526,"rank":396,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.004819396947578503,"rank":396,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.004766375975754249,"rank":396,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.004805905875016402,"rank":396,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.004794565363708612,"rank":396,"remainingConfigurations":398},{"removed":"livebench-math","score":0.004822004476742693,"rank":396,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.004769550405586961,"rank":396,"remainingConfigurations":398},{"removed":"livebench-language","score":0.004874478771158759,"rank":396,"remainingConfigurations":398},{"removed":"livebench-data","score":0.004824110609621277,"rank":396,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0047301524512817225,"rank":396,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.004777723841550564,"rank":396,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.004894557808519499,"rank":396,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0049771608520081416,"rank":396,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0045442352379567895,"rank":396,"remainingConfigurations":398},{"removed":"frontiermath","score":0.004867053440268295,"rank":396,"remainingConfigurations":398},{"removed":"simpleqa","score":0.005027964602954167,"rank":396,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.004786947561927048,"rank":396,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.004794415317168889,"rank":396,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.00479113188103944,"rank":396,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.004803474986757835,"rank":396,"remainingConfigurations":398},{"removed":"vibe-code","score":0.004777587383749352,"rank":396,"remainingConfigurations":398}]},"deepseek-r1-distill-qwen-1.5b--effort-reasoning":{"score":0.004433723250093207,"rank":397,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.0054879860915824676,"rank":397,"remainingConfigurations":398},{"removed":"Datacurve","score":0.0037484261189704095,"rank":397,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.004390846617537185,"rank":397,"remainingConfigurations":398},{"removed":"Scale","score":0.004992300975347779,"rank":397,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.004424547900657262,"rank":397,"remainingConfigurations":398},{"removed":"Cognition","score":0.004693269553872227,"rank":397,"remainingConfigurations":398},{"removed":"LiveBench","score":0.0045612898971702075,"rank":396,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.004589056539601223,"rank":397,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.004451896090627257,"rank":380,"remainingConfigurations":381},{"removed":"Vals AI","score":0.004314245574157487,"rank":396,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.004434007858605186,"rank":397,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.004429231998741525,"rank":397,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.00442578757034521,"rank":397,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.004433723250093207,"rank":397,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0044207859858844565,"rank":397,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.004454733641830129,"rank":397,"remainingConfigurations":398},{"removed":"briefcase","score":0.004438830692421487,"rank":397,"remainingConfigurations":398},{"removed":"aime","score":0.0038076504214509116,"rank":397,"remainingConfigurations":398},{"removed":"apex-agents","score":0.004493157092541031,"rank":397,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.003962614433052153,"rank":397,"remainingConfigurations":398},{"removed":"automationbench","score":0.004442987985865748,"rank":397,"remainingConfigurations":398},{"removed":"critpt","score":0.004182706711086403,"rank":396,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.004451806505019179,"rank":397,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.004503026012607386,"rank":397,"remainingConfigurations":398},{"removed":"gdpval","score":0.004470772750372221,"rank":397,"remainingConfigurations":398},{"removed":"gmmlu","score":0.004494790802009052,"rank":397,"remainingConfigurations":398},{"removed":"gpqa","score":0.0044769567212189455,"rank":397,"remainingConfigurations":398},{"removed":"harvey","score":0.004389177130909171,"rank":397,"remainingConfigurations":398},{"removed":"hle","score":0.004581663211949682,"rank":397,"remainingConfigurations":398},{"removed":"ifbench","score":0.004438290699342401,"rank":397,"remainingConfigurations":398},{"removed":"itbench","score":0.004432853526687092,"rank":397,"remainingConfigurations":398},{"removed":"livecodebench","score":0.004751445860807376,"rank":397,"remainingConfigurations":398},{"removed":"math500","score":0.004819605921575967,"rank":397,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.0049196695252105675,"rank":397,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.004783438499259261,"rank":397,"remainingConfigurations":398},{"removed":"omniscience","score":0.0041328024364607795,"rank":397,"remainingConfigurations":398},{"removed":"scicode","score":0.004540894114911251,"rank":397,"remainingConfigurations":398},{"removed":"tau-bench","score":0.004317880550192215,"rank":397,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.004474184999687177,"rank":397,"remainingConfigurations":398},{"removed":"arc-agi","score":0.005437134750163755,"rank":397,"remainingConfigurations":398},{"removed":"deepswe","score":0.0037513665435670324,"rank":397,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.004435089429207018,"rank":397,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.004402655716125358,"rank":397,"remainingConfigurations":398},{"removed":"frontiercode","score":0.004693269553872227,"rank":397,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.0044398212190561405,"rank":397,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.004390954519019221,"rank":397,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.004427335630753756,"rank":397,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.004416739886248344,"rank":397,"remainingConfigurations":398},{"removed":"livebench-math","score":0.004442175077974,"rank":397,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.004393768040648365,"rank":397,"remainingConfigurations":398},{"removed":"livebench-language","score":0.004490530512361211,"rank":397,"remainingConfigurations":398},{"removed":"livebench-data","score":0.004444112673274269,"rank":397,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.004357497742053424,"rank":397,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.004401342140868456,"rank":397,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.0045090719507375485,"rank":397,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.004589056539601223,"rank":397,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.004177405782687893,"rank":397,"remainingConfigurations":398},{"removed":"frontiermath","score":0.004484011553126244,"rank":397,"remainingConfigurations":398},{"removed":"simpleqa","score":0.00463266830143925,"rank":397,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.004409843090790412,"rank":397,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.004416730101003362,"rank":397,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.004413707124109475,"rank":397,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.004425073157500149,"rank":397,"remainingConfigurations":398},{"removed":"vibe-code","score":0.004401217189046072,"rank":397,"remainingConfigurations":398}]},"gpt-3.5-turbo--effort-non-reasoning":{"score":0.0031382959067198664,"rank":398,"sourceRemovals":[{"removed":"Artificial Analysis","score":null,"rank":null,"remainingConfigurations":164},{"removed":"ARC Prize","score":0.003916795491021864,"rank":398,"remainingConfigurations":398},{"removed":"Datacurve","score":0.002653305772493788,"rank":398,"remainingConfigurations":398},{"removed":"LiveCodeBench","score":0.0031087401926940873,"rank":398,"remainingConfigurations":398},{"removed":"Scale","score":0.003537165832511381,"rank":398,"remainingConfigurations":398},{"removed":"Terminal-Bench","score":0.0031317633428988474,"rank":398,"remainingConfigurations":398},{"removed":"Cognition","score":0.0033251327545513625,"rank":398,"remainingConfigurations":398},{"removed":"LiveBench","score":0.003228733582623322,"rank":397,"remainingConfigurations":397},{"removed":"SWE-rebench","score":0.0032535866066944626,"rank":398,"remainingConfigurations":398},{"removed":"Epoch AI","score":0.0030883817764465263,"rank":381,"remainingConfigurations":381},{"removed":"Vals AI","score":0.0030537762177068484,"rank":397,"remainingConfigurations":397},{"removed":"Provider reports · Anthropic","score":0.003138496996934368,"rank":398,"remainingConfigurations":398},{"removed":"Provider reports · Moonshot AI","score":0.0031351061686208117,"rank":398,"remainingConfigurations":398},{"removed":"Provider reports · Meta","score":0.0031326759775215578,"rank":398,"remainingConfigurations":398},{"removed":"Provider reports · Mistral","score":0.0031382959067198664,"rank":398,"remainingConfigurations":398},{"removed":"All provider reports","score":0.0031291234710509783,"rank":398,"remainingConfigurations":398}],"familyRemovals":[{"removed":"analyst-agent","score":0.0031532693116440775,"rank":398,"remainingConfigurations":398},{"removed":"briefcase","score":0.003146043500116801,"rank":398,"remainingConfigurations":398},{"removed":"aime","score":0.0031044894589332558,"rank":398,"remainingConfigurations":398},{"removed":"apex-agents","score":0.003182029505429234,"rank":398,"remainingConfigurations":398},{"removed":"aa-lcr","score":0.0031175347576758196,"rank":398,"remainingConfigurations":398},{"removed":"automationbench","score":0.0031469325394554385,"rank":398,"remainingConfigurations":398},{"removed":"critpt","score":0.0029809992070230448,"rank":398,"remainingConfigurations":398},{"removed":"enterprise-ops","score":0.00315116131652606,"rank":398,"remainingConfigurations":398},{"removed":"gdp-pdf","score":0.003188284327845531,"rank":398,"remainingConfigurations":398},{"removed":"gdpval","score":0.003163198106648776,"rank":398,"remainingConfigurations":398},{"removed":"gmmlu","score":0.0031934986547811762,"rank":398,"remainingConfigurations":398},{"removed":"gpqa","score":0.002454637332507498,"rank":398,"remainingConfigurations":398},{"removed":"harvey","score":0.003106754428898075,"rank":398,"remainingConfigurations":398},{"removed":"hle","score":0.0032431634726562426,"rank":398,"remainingConfigurations":398},{"removed":"ifbench","score":0.0030701045624517732,"rank":398,"remainingConfigurations":398},{"removed":"itbench","score":0.0031387683330222076,"rank":398,"remainingConfigurations":398},{"removed":"livecodebench","score":0.0031118182693719407,"rank":398,"remainingConfigurations":398},{"removed":"math500","score":0.00440988909960446,"rank":398,"remainingConfigurations":398},{"removed":"mmlu-pro","score":0.002954322037353981,"rank":398,"remainingConfigurations":398},{"removed":"mmmu-pro","score":0.003381392839111496,"rank":398,"remainingConfigurations":398},{"removed":"omniscience","score":0.0029098082509807555,"rank":398,"remainingConfigurations":398},{"removed":"scicode","score":0.003215281553025875,"rank":398,"remainingConfigurations":398},{"removed":"tau-bench","score":0.0030754130171961355,"rank":398,"remainingConfigurations":398},{"removed":"terminal-bench","score":0.0032061714606187084,"rank":398,"remainingConfigurations":398},{"removed":"arc-agi","score":0.0038803352301588767,"rank":398,"remainingConfigurations":398},{"removed":"deepswe","score":0.002655390743952635,"rank":398,"remainingConfigurations":398},{"removed":"swe-bench-pro","score":0.003139265042924858,"rank":398,"remainingConfigurations":398},{"removed":"arc-agi-3","score":0.0031162187763620346,"rank":398,"remainingConfigurations":398},{"removed":"frontiercode","score":0.0033251327545513625,"rank":398,"remainingConfigurations":398},{"removed":"enigma-eval","score":0.003142603637476805,"rank":398,"remainingConfigurations":398},{"removed":"swe-atlas-qna","score":0.0031079206726215476,"rank":398,"remainingConfigurations":398},{"removed":"swe-atlas-refactoring","score":0.0031337792235797608,"rank":398,"remainingConfigurations":398},{"removed":"swe-atlas-test-writing","score":0.003126244382616359,"rank":398,"remainingConfigurations":398},{"removed":"livebench-math","score":0.003144304149652498,"rank":398,"remainingConfigurations":398},{"removed":"livebench-coding","score":0.003109905149460021,"rank":398,"remainingConfigurations":398},{"removed":"livebench-language","score":0.0031786012354139193,"rank":398,"remainingConfigurations":398},{"removed":"livebench-data","score":0.0031456869349730785,"rank":398,"remainingConfigurations":398},{"removed":"multi-swe-bench","score":0.0030842226075590354,"rank":398,"remainingConfigurations":398},{"removed":"livebench-reasoning","score":0.003115313819379869,"rank":398,"remainingConfigurations":398},{"removed":"livebench-instructions","score":0.003191778111409419,"rank":398,"remainingConfigurations":398},{"removed":"swe-rebench","score":0.0032535866066944626,"rank":398,"remainingConfigurations":398},{"removed":"epoch-game-puzzles","score":0.0029494265562210395,"rank":398,"remainingConfigurations":398},{"removed":"frontiermath","score":0.0031768528838816983,"rank":398,"remainingConfigurations":398},{"removed":"simpleqa","score":0.003280184575669785,"rank":398,"remainingConfigurations":398},{"removed":"vals-finance-agent","score":0.003121350614807258,"rank":398,"remainingConfigurations":398},{"removed":"vals-code-migration","score":0.00312624244169522,"rank":398,"remainingConfigurations":398},{"removed":"vals-legal-research","score":0.0031240865757185808,"rank":398,"remainingConfigurations":398},{"removed":"vals-excel-modeling","score":0.0031321541441947445,"rank":398,"remainingConfigurations":398},{"removed":"vibe-code","score":0.00311523863421952,"rank":398,"remainingConfigurations":398}]}},"rankedConfigurations":398,"rankedModels":215,"topModels":[{"rank":1,"id":"claude-fable-5-1--effort-max","score":0.8576392906630036},{"rank":2,"id":"gpt-6-astra--effort-xhigh","score":0.8305846911657017},{"rank":3,"id":"claude-opus-5--effort-medium","score":0.756588545187245},{"rank":4,"id":"claude-fable-5--effort-high","score":0.7395423399417836},{"rank":5,"id":"gpt-5.6-sol--effort-xhigh","score":0.7200558869962235},{"rank":6,"id":"muse-spark-1.3--effort-xhigh","score":0.7034116319092588},{"rank":7,"id":"gemini-3.8-flash--effort-medium","score":0.7002495102547243},{"rank":8,"id":"gpt-5.5-pro--effort-xhigh","score":0.655099015064508},{"rank":9,"id":"grok-4.6--effort-high","score":0.6242971525570876},{"rank":10,"id":"kimi-k3--effort-max","score":0.6199710263061422},{"rank":11,"id":"gemini-3.7-flash--effort-medium","score":0.6008659847874989},{"rank":12,"id":"glm-5.3--effort-max","score":0.5751539158922038},{"rank":13,"id":"gpt-5.5--effort-xhigh","score":0.5486217356893452},{"rank":14,"id":"gpt-5.6-terra--effort-max","score":0.5473326004506027},{"rank":15,"id":"claude-opus-4-8--effort-max","score":0.5154012816616055},{"rank":16,"id":"qwen-3.8-max--effort-xhigh","score":0.4987155368393635},{"rank":17,"id":"muse-spark-1.2--effort-xhigh","score":0.4560441657225609},{"rank":18,"id":"deepseek-v4-pro--effort-max","score":0.4481709832879668},{"rank":19,"id":"qwen3.8-2.4t-a95b--effort-reasoning","score":0.4352195473111215},{"rank":20,"id":"glm-5.3-flash--effort-reasoning","score":0.4209109290604369},{"rank":21,"id":"claude-opus-4-6--effort-max","score":0.42017033135830634},{"rank":22,"id":"muse-spark-1.1--effort-xhigh","score":0.41129890156180154},{"rank":23,"id":"gpt-5.6-luna--effort-max","score":0.4074665735133989},{"rank":24,"id":"qwen3.8-flash-next--effort-reasoning","score":0.4070235787925161},{"rank":25,"id":"claude-sonnet-5--effort-xhigh","score":0.3993635488772256}],"independentFamiliesByArea":{"agentic":["analyst-agent","briefcase","apex-agents","automationbench","enterprise-ops","gdp-pdf","gdpval","harvey","itbench","tau-bench","livebench-data","vals-finance-agent","vals-legal-research","vals-excel-modeling"],"hard_reasoning":["aime","critpt","gpqa","hle","math500","arc-agi","arc-agi-3","enigma-eval","livebench-math","livebench-reasoning","epoch-game-puzzles","frontiermath"],"long_context":["aa-lcr"],"knowledge":["gmmlu","ifbench","mmlu-pro","omniscience","livebench-language","livebench-instructions","simpleqa"],"coding":["livecodebench","scicode","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-opus-4-6--effort-max","lowerRanked":"gemini-3.1-pro--effort-high","sharedFamilies":4,"losses":6,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"claude-sonnet-4-6--effort-max","lowerRanked":"gemini-3.1-flash-lite--effort-high","sharedFamilies":3,"losses":3,"ties":0,"weightedIndependentHeadToHead":0,"weightedAllHeadToHead":0,"explanation":"Different opponents and family coverage reverse the shared-benchmark order in the joint fit"},{"higherRanked":"claude-sonnet-4-6--effort-max","lowerRanked":"qwen3.7-flash--effort-non-reasoning","sharedFamilies":3,"losses":3,"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":0.061087438992940855,"weightedAllHeadToHead":0.061087438992940855,"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":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","lowerRanked":"gpt-4o--effort-non-reasoning","sharedFamilies":3,"losses":1,"ties":2,"weightedIndependentHeadToHead":0.2378463065802128,"weightedAllHeadToHead":0.2378463065802128,"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":0.12697387499011414,"weightedAllHeadToHead":0.12697387499011414,"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":0.1646910950892935,"weightedAllHeadToHead":0.1646910950892935,"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":0.8305846911657017,"lowerScore":0.7761279033001186,"sharedUnits":21,"sharedFamilies":18,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI","Terminal-Bench"],"higherWins":6,"lowerWins":14,"ties":1,"higherOnlyUnits":2,"lowerOnlyUnits":39},{"higherRanked":"gpt-6-astra--effort-high","lowerRanked":"gpt-6-astra--effort-max","higherScore":0.8083096377180565,"lowerScore":0.7761279033001186,"sharedUnits":21,"sharedFamilies":18,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI","Terminal-Bench"],"higherWins":2,"lowerWins":16,"ties":3,"higherOnlyUnits":0,"lowerOnlyUnits":39},{"higherRanked":"gpt-6-astra--effort-medium","lowerRanked":"gpt-6-astra--effort-max","higherScore":0.796076035284861,"lowerScore":0.7761279033001186,"sharedUnits":21,"sharedFamilies":18,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI","Terminal-Bench"],"higherWins":2,"lowerWins":19,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":39},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-xhigh","higherScore":0.756588545187245,"lowerScore":0.7327225480424163,"sharedUnits":18,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":14,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":2},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-high","higherScore":0.756588545187245,"lowerScore":0.7242879139590591,"sharedUnits":18,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":5,"lowerWins":13,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":3},{"higherRanked":"claude-opus-5--effort-medium","lowerRanked":"claude-opus-5--effort-max","higherScore":0.756588545187245,"lowerScore":0.6903251978361186,"sharedUnits":18,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":14,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":40},{"higherRanked":"claude-fable-5--effort-high","lowerRanked":"claude-fable-5--effort-max","higherScore":0.7395423399417836,"lowerScore":0.6904521243576524,"sharedUnits":5,"sharedFamilies":4,"sharedSources":["ARC Prize","Cognition","Datacurve","Epoch AI"],"higherWins":2,"lowerWins":3,"ties":0,"higherOnlyUnits":5,"lowerOnlyUnits":54},{"higherRanked":"claude-fable-5--effort-high","lowerRanked":"claude-fable-5--effort-xhigh","higherScore":0.7395423399417836,"lowerScore":0.6812306339389292,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":0,"lowerWins":4,"ties":0,"higherOnlyUnits":6,"lowerOnlyUnits":5},{"higherRanked":"claude-opus-5--effort-xhigh","lowerRanked":"claude-opus-5--effort-max","higherScore":0.7327225480424163,"lowerScore":0.6903251978361186,"sharedUnits":18,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":4,"lowerWins":14,"ties":0,"higherOnlyUnits":2,"lowerOnlyUnits":40},{"higherRanked":"claude-opus-5--effort-high","lowerRanked":"claude-opus-5--effort-max","higherScore":0.7242879139590591,"lowerScore":0.6903251978361186,"sharedUnits":19,"sharedFamilies":16,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":3,"lowerWins":16,"ties":0,"higherOnlyUnits":2,"lowerOnlyUnits":39},{"higherRanked":"gpt-5.6-sol--effort-xhigh","lowerRanked":"gpt-5.6-sol--effort-max","higherScore":0.7200558869962235,"lowerScore":0.698487650282616,"sharedUnits":22,"sharedFamilies":17,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":2,"lowerWins":19,"ties":1,"higherOnlyUnits":1,"lowerOnlyUnits":44},{"higherRanked":"muse-spark-1.3--effort-xhigh","lowerRanked":"muse-spark-1.3--effort-max","higherScore":0.7034116319092588,"lowerScore":0.5617102430924915,"sharedUnits":13,"sharedFamilies":12,"sharedSources":["Artificial Analysis"],"higherWins":4,"lowerWins":8,"ties":1,"higherOnlyUnits":31,"lowerOnlyUnits":1},{"higherRanked":"gemini-3.8-flash--effort-medium","lowerRanked":"gemini-3.8-flash--effort-high","higherScore":0.7002495102547243,"lowerScore":0.6889002380190533,"sharedUnits":17,"sharedFamilies":15,"sharedSources":["Artificial Analysis","Cognition","Datacurve"],"higherWins":6,"lowerWins":10,"ties":1,"higherOnlyUnits":0,"lowerOnlyUnits":40},{"higherRanked":"claude-fable-5--effort-max","lowerRanked":"claude-fable-5--effort-xhigh","higherScore":0.6904521243576524,"lowerScore":0.6812306339389292,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":1,"lowerWins":3,"ties":0,"higherOnlyUnits":55,"lowerOnlyUnits":5},{"higherRanked":"claude-fable-5--effort-medium","lowerRanked":"claude-fable-5--effort-xhigh","higherScore":0.6902082179471911,"lowerScore":0.6812306339389292,"sharedUnits":4,"sharedFamilies":3,"sharedSources":["ARC Prize","Cognition","Datacurve"],"higherWins":0,"lowerWins":4,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":5},{"higherRanked":"grok-4.6--effort-high","lowerRanked":"grok-4.6--effort-xhigh","higherScore":0.6242971525570876,"lowerScore":0.547225173220304,"sharedUnits":19,"sharedFamilies":17,"sharedSources":["ARC Prize","Artificial Analysis","Datacurve","Epoch AI"],"higherWins":9,"lowerWins":10,"ties":0,"higherOnlyUnits":14,"lowerOnlyUnits":4},{"higherRanked":"gemini-3.7-flash--effort-medium","lowerRanked":"gemini-3.7-flash--effort-high","higherScore":0.6008659847874989,"lowerScore":0.5762273256525265,"sharedUnits":14,"sharedFamilies":13,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve"],"higherWins":6,"lowerWins":8,"ties":0,"higherOnlyUnits":1,"lowerOnlyUnits":46},{"higherRanked":"grok-4.6--effort-medium","lowerRanked":"grok-4.6--effort-xhigh","higherScore":0.5960357182482909,"lowerScore":0.547225173220304,"sharedUnits":15,"sharedFamilies":14,"sharedSources":["ARC Prize","Artificial Analysis","Datacurve"],"higherWins":4,"lowerWins":9,"ties":2,"higherOnlyUnits":2,"lowerOnlyUnits":8},{"higherRanked":"claude-sonnet-5--effort-xhigh","lowerRanked":"claude-sonnet-5--effort-max","higherScore":0.3993635488772256,"lowerScore":0.38026735724676114,"sharedUnits":18,"sharedFamilies":17,"sharedSources":["Artificial Analysis","Cognition","Datacurve","Epoch AI"],"higherWins":5,"lowerWins":13,"ties":0,"higherOnlyUnits":23,"lowerOnlyUnits":19},{"higherRanked":"grok-4.3--effort-medium","lowerRanked":"grok-4.3--effort-high","higherScore":0.24117507149820527,"lowerScore":0.18441296084940173,"sharedUnits":9,"sharedFamilies":9,"sharedSources":["Artificial Analysis"],"higherWins":2,"lowerWins":7,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":28},{"higherRanked":"claude-sonnet-4-6--effort-max","lowerRanked":"claude-sonnet-4-6--effort-high","higherScore":0.2322996393999656,"lowerScore":0.1871136302154405,"sharedUnits":6,"sharedFamilies":5,"sharedSources":["ARC Prize","Cognition","Epoch AI"],"higherWins":2,"lowerWins":4,"ties":0,"higherOnlyUnits":32,"lowerOnlyUnits":2},{"higherRanked":"claude-sonnet-4-6--effort-max","lowerRanked":"claude-sonnet-4-6--effort-medium","higherScore":0.2322996393999656,"lowerScore":0.17140037618560014,"sharedUnits":5,"sharedFamilies":4,"sharedSources":["Cognition","Epoch AI"],"higherWins":2,"lowerWins":3,"ties":0,"higherOnlyUnits":33,"lowerOnlyUnits":23},{"higherRanked":"gpt-5.6-terra--effort-low","lowerRanked":"gpt-5.6-terra--effort-medium","higherScore":0.1840047266994124,"lowerScore":0.17966497894323227,"sharedUnits":23,"sharedFamilies":19,"sharedSources":["ARC Prize","Artificial Analysis","Cognition","Datacurve","Epoch AI"],"higherWins":3,"lowerWins":20,"ties":0,"higherOnlyUnits":4,"lowerOnlyUnits":0},{"higherRanked":"gemma-4-e4b-it--effort-non-reasoning","lowerRanked":"gemma-4-e4b-it--effort-reasoning","higherScore":0.024763792649207528,"lowerScore":0.023074250162811036,"sharedUnits":9,"sharedFamilies":9,"sharedSources":["Artificial Analysis"],"higherWins":2,"lowerWins":7,"ties":0,"higherOnlyUnits":0,"lowerOnlyUnits":2}]},"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":1562.01},{"id":"claude-fable-5-1--effort-max","score":1661.82}]},{"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":1580.2},{"id":"claude-fable-5-1--effort-max","score":1763.64}]},{"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-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-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-scicode","family":"scicode","source":"Artificial Analysis","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":56.4814814814815},{"id":"claude-fable-5-1--effort-max","score":63.078703703703695}]},{"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-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-chess-puzzles-1-1-6-model-extracted-exact-match","family":"epoch-game-puzzles","source":"Epoch AI","higherIsBetter":true,"values":[{"id":"gpt-6-astra--effort-max","score":72},{"id":"claude-fable-5-1--effort-max","score":47}]},{"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}]}],"gaps":{"rosterModelsWithoutMeasuredEfforts":["deepseek-r1-distill-qwen-7b","deepseek-v4-flash-vision-exp","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","muse-glimmer-30b","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","qwen3.8-flash","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-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","hy4-preview","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"],"unadmittedEffortMeasurements":[{"id":"5eca0b0dc509f3d924e864a1","model":"agnes-2.5-pro-alpha","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dbcffb6add1d04899e8b3269","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"83d446faabe43549fc8be324","model":"amazon-nova-2-lite","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"05bbf3b36c46a5d97b7af99f","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":"5e48ea7bbae50fbfc4709191","model":"amazon-nova-2-pro-preview","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f918288816d545d015333d7a","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":"9966b462b29331ecbde42490","model":"claude-fable-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"35674df3f02b7941e8620349","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"597a3f60fc7069ecd1b62427","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"58328d3a42b280731f127b87","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"37d9e698a4a4cb9b195ba794","model":"claude-fable-5-1","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"896645ed1ede361c8c0efe9a","model":"claude-fable-5-1","benchmark":"aa-omniscience","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":"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":"67766ea16f853c7ff84a817a","model":"claude-opus-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"46b85c1426a94560e8491464","model":"claude-opus-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"032009afa3dbd206c24621a1","model":"claude-opus-4-7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0fec6d78078202d2ff626c29","model":"claude-opus-4-7","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"e2f0cc5a86febfa51defe5db","model":"claude-opus-4-8","benchmark":"aa-omniscience","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":"6142b61150b247770757b261","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ca4fe51d6a460da93435b44d","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8aebe6222eb321d01c1e6248","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"95767f397055c93498b7aab3","model":"claude-opus-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"87c811d366c5fbaaaa3975bc","model":"claude-opus-5","benchmark":"aa-omniscience","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":"95567387bc84bd43e2e17443","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":"eeca2c029f49887d2f8de42c","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":"68cd3fa6809265041ab4e058","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":"bac7982cd94b783ce9937b37","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":"9faede113e168f7e102e28b7","model":"claude-sonnet-4-6","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"bd9dc8c11e74dcf4d21c0355","model":"claude-sonnet-4-6","benchmark":"aa-gpqa-diamond","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"08964d53879fda33454d92be","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":"fbaf3e468a069edc24595e53","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":"7b9a5ed9afd89f3d3dc7c7d9","model":"claude-sonnet-4-6","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cb52c6337e6d1ca83f782771","model":"claude-sonnet-4-6","benchmark":"aa-ifbench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"53a70f8e8f39a9bf4b309039","model":"claude-sonnet-4-6","benchmark":"aa-mlcr-aa","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b302bedcd3669528b4703126","model":"claude-sonnet-4-6","benchmark":"aa-mlcr-aa","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0eab8dfd0579ff09141f58f1","model":"claude-sonnet-4-6","benchmark":"aa-mmmu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c9790672cda25468a59d855a","model":"claude-sonnet-4-6","benchmark":"aa-mmmu-pro","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2b79a8be3c4816ae5e4126d1","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3c8824c30ba25df9377473e9","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8ff03bd6cf18ff4fdd035fca","model":"claude-sonnet-4-6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"089295a829a4b2eea0c45567","model":"claude-sonnet-4-6","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"524488ae2a2507b68ea71d3d","model":"claude-sonnet-4-6","benchmark":"aa-omniscience-accuracy","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"4f4c2f07253b00381b8a7e93","model":"claude-sonnet-4-6","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"687f063bf51789c89c7d6efd","model":"claude-sonnet-4-6","benchmark":"aa-tau2-bench","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"382f610161294070630b7fc4","model":"claude-sonnet-4-6","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cb333ca12130594126273d1d","model":"claude-sonnet-4-6","benchmark":"aa-terminalbench-hard","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c21f43cdc9b325847d265d03","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c121d252aead88218ae94083","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9421851310be4d5cc39103da","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"26874b9f4b82ced0f4d4b331","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d7cff7448ac9d293e5b872bd","model":"claude-sonnet-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1df0b890fcab062c13afeeda","model":"claude-sonnet-5","benchmark":"aa-omniscience","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":"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":"35b25adff9293e9983993576","model":"deepseek-v4-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"020337d791c025678d7f669e","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c35fc22fbf62c8255fd2ce70","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"28f74cffb85616a21ef0466f","model":"deepseek-v4-flash-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1556f05dd2908433d9fc662b","model":"deepseek-v4-pro","benchmark":"aa-omniscience","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":"e2d986dd108115769c871ef2","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"daf424f4f812afb14ebb9d27","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cf19915c5fd19c9700e73691","model":"deepseek-v4-pro-0424","benchmark":"aa-omniscience","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":"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":"87ade12107a80c21624bd73f","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":"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":"6a904d86ad7c12c3aac7713b","model":"gemini-3.1-pro","benchmark":"aa-omniscience","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":"8591301a5ba5c21a75e096ac","model":"gemini-3.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"43b3aefe7350df929f9338ae","model":"gemini-3.5-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2bcf32e69932a11f901a5098","model":"gemini-3.5-flash","benchmark":"aa-omniscience","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":"01c9c562ca1e20be38366b5e","model":"gemini-3.6-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d286dd08c71ca1a94b6b4312","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2165aa4444d69b835f683bdf","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cca0a6b63d00776b6e87dae5","model":"gemini-3.7-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b362fc4da74b513f0c9e56aa","model":"gemini-3.8-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"349a9170a6967dde2f69d616","model":"gemini-3.8-flash","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"29918922aae0f8078778c893","model":"gemini-3.8-flash","benchmark":"aa-omniscience","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":"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":"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":"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":"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":"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":"0deb219d986680fe5482eff9","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":"8dff0f2b52603e6e86eb2d04","model":"glm-5.3","benchmark":"aa-omniscience","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":"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":"9b00496d4476acb1c38c5a4b","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3f1e0619a146ac6e6cbb8e2f","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2b26c17405cd2af3cd3e0ce8","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"fb32628f32aa74c40826c44f","model":"gpt-5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"987e8a0057a72933ce78e8fa","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f7bce3e28e655c5285f0b018","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"07d410b5a7664b7b7f3f10c0","model":"gpt-5-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"24ff7126b123fbe6a2c9c298","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0879c8d5d665baf326d041f1","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b9c929a6fa6f2e980e735683","model":"gpt-5-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f7c1b35ac1102f446ec8ef52","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":"02827ac803609d1fcaaf7843","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":"9ecf2868fb35108a7e7ef152","model":"gpt-5.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d2c8a67afe8f17e6b041971b","model":"gpt-5.3-codex","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d716b0e63c7c102a4901c761","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":"c500501b1945eea9d57c2159","model":"gpt-5.4","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3e51606290704088b2cbfc50","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"cfa95e087695c99aed69bc84","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3cd56c92a3dde88ea9a3b202","model":"gpt-5.4-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2278d8f84915981206e7d284","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3ff8dee9b631894975c131fd","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"c4db83fda20000c64985fe3b","model":"gpt-5.4-nano","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"66b92c7f427f88d6d7904ffa","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"77b7eba99ad5a5fc3fec1ac5","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"02e59ffc919ccd6442705b12","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":"c69cdc7db016bd0188152763","model":"gpt-5.5","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dfc8b492223a91f50b185df9","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7d33a31cfbe100e831b57b44","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5d9a53e8e9e01657919bbbeb","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"715aacb5bd2e20f8cce59472","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":"0c21ef5ec77360271acb025c","model":"gpt-5.6-luna","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"a3575021ed42f7eefce75c85","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8a235fa1b4c25978fa241e47","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"280829df0609ed1382ed4a5d","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7e0039eb395cbe91e7c8810d","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":"6e384940f06acf726078ee36","model":"gpt-5.6-sol","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"9e70e59a6c4a148a62a6807b","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"db529af327cadbebe82b4ea7","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"64b892a9ca7a6bbcc0c53e7e","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"42f39e504fc7276c2c18798c","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":"ec4c04a5ed6eda9a62523050","model":"gpt-5.6-terra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"7f3b750498047bc39d9bfb71","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"dfb7acba10dca5fc82abe032","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"d30acb40bb5196501ac2761d","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3642c13a42011ffb84ffeb73","model":"gpt-6-astra","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"100886d649a4b50d59ef79b2","model":"gpt-6-astra","benchmark":"aa-omniscience","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":"b31454600a41bac85df8781b","model":"gpt-oss-120b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"44174058a335a21db34cab7b","model":"gpt-oss-120b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"1127c1a85f619737a188828f","model":"gpt-oss-20b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"783912f707a26b3b11a91fbc","model":"gpt-oss-20b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b15b56bf252797d3b5d91e95","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"326e7b3889e629aeda2d9b20","model":"grok-4.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"abd3c444a2f68677d8e6225b","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":"49ddf105c76cb6c65c9788e6","model":"grok-4.5","benchmark":"aa-omniscience","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":"bf44cf9030f95307456d203b","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"8286b65e9f1a497934f4c1a7","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"b887a18f999764706e64138e","model":"grok-4.6","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"2542d8a122e2175ba2a75e90","model":"grok-4.6","benchmark":"aa-omniscience","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":"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":"ce73d0e7d12c5a142ddb9708","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":"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":"3f8fd7e249ce407ffe388a4c","model":"kimi-k2.6","benchmark":"aa-omniscience","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":"2add98bb74de8a6d6249d272","model":"kimi-k3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"3cfd24aceb01fe71d063a78e","model":"kimi-k3","benchmark":"aa-omniscience","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":"7eec6f4e726f2ac2843e4d31","model":"llama-4-maverick","benchmark":"aa-omniscience","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":"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":"f20dd3ebb423e6ee03f6caee","model":"mimo-v2.5-pro","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"f8d44cda02c43ae2b8612813","model":"mimo-v2.5-pro","benchmark":"aa-omniscience","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":"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":"4fe2dbb70cb706ac86051368","model":"minimax-m3","benchmark":"aa-omniscience","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":"928da08d1319107c56189f07","model":"ministral-3-3b","benchmark":"aa-omniscience","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":"fe1a4682c062f12dbe7de410","model":"mistral-large-3","benchmark":"aa-omniscience","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":"df8c0054af3ea000e16148ed","model":"mistral-medium-3.5","benchmark":"aa-omniscience","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":"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":"1155696d61f97ace1c6685cb","model":"muse-spark-1.1","benchmark":"aa-omniscience","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":"0ae131704ad1ec5583eb3702","model":"muse-spark-1.2","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"0ee617d3b595752a50038d11","model":"muse-spark-1.3","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"87a7cbeaeaa3a7635be20077","model":"muse-spark-1.3","benchmark":"aa-omniscience","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":"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":"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":"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":"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":"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":"db1badd09c0ec2742a1bda68","model":"o3-mini","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"ed11d2a6911024075e30eda3","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":"58633d857fd008646f1cc6eb","model":"qwen-3.8-max","benchmark":"aa-omniscience","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":"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":"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":"864945a3e7a9e02b314d1f06","model":"qwen3-32b","benchmark":"aa-omniscience","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":"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":"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":"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":"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":"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":"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":"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":"1d6fc7a9f857efb4ea8a4d09","model":"qwen3.7-plus","benchmark":"aa-omniscience","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":"a03d4ad0bd3a804b66a9b24a","model":"qwen3.8-27b","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"5d47e816e792f15b47d77830","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":"035420d05ec2253ac495caa6","model":"qwen3.8-27b","benchmark":"aa-omniscience","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":"12f82b95be07624d144534f1","model":"seed-oss-36b-instruct","benchmark":"aa-omniscience","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":"4c646f44d8a2f54dd28f759a","model":"solar-pro3-260323","benchmark":"aa-omniscience","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"00db4ada432af3c8ba91468f","model":"solar-pro4-260806","benchmark":"aa-omniscience","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":"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":"21ee231589903749e98387ba","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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":"276a6edb836c21a802685b40","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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":"2d2cb54f2cced8ad23e6d7f8","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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":"67d76f5adea449a9001331d3","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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":"b99056688b2b172aff603206","model":"gpt-6-astra","benchmark":"arc3-provider-adapter","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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":"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":"epoch-run-26q7yB8XHAcmxWgEMFPMHP","model":"nemotron-3-ultra","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-2AxSH8gojpyyzADeWfuSqu","model":"deepseek-r1-distill-qwen-14b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"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-2jTRxz7rW3B66a8smtz7Ya","model":"claude-opus-4-5-20251101","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-3asQZd87VuKoH95e4x5Yfg","model":"phi-3-mini-4k-instruct","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-3y52KdaFo7gQZCccCQnNxp","model":"qwen3.6-35b-a3b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-4MWuvJB4YXGnGz27Y74cqW","model":"kimi-k2.6","benchmark":"epoch-chess-puzzles-1-1-4-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-4QfM9qyeWGqNc8YTcQNV76","model":"gemini-3.1-pro","benchmark":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","reason":"Run-specific qualification requires review: In the initial run, 53 samples did not complete. These were rerun until 51 of them completed. The remaining samples are scored as incorrect."},{"id":"epoch-run-4vjzjypxWVWBVdAnwaDQYX","model":"qwen3.5-9b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-5Ax3kMh4Lmw8KsrJVWbXqn","model":"qwen3.7-flash","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-7czodbcgEF5zN68ppPFzBN","model":"glm-5","benchmark":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-7iH4kjDYrjgRwQdKYgNACT","model":"qwen3-235b-a22b-thinking-2507","benchmark":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","reason":"Run-specific qualification requires review: Two samples did not complete, which is > than our 2% tolerance. As such, the score has been manually edited to grade them as incorrect."},{"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-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-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-a5YYZ3NSBGCUuALngGHhfZ","model":"deepseek-r1-distill-qwen-1.5b","benchmark":"epoch-chess-puzzles-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-amkBg66TZcYjF26HaRAXfs","model":"claude-opus-4-6","benchmark":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-AoYLH4gxsYmhLYi9gyduiM","model":"qwen3-30b-a3b-thinking-2507","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-bAR85KQmEATQP8j764jpBA","model":"claude-fable-5","benchmark":"epoch-chess-puzzles-1-1-5-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-bggkB6SQyMaVNvB2Txr9Nd","model":"seed-oss-36b-instruct","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-bzuVVvmLtPCgofXqY7mTVR","model":"glm-4.7","benchmark":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","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-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-cUim7Aqc8ifJMM69uXSeSn","model":"deepseek-r1-distill-qwen-32b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-dagNWyu57ksu7gB7Q86eCx","model":"qwen3.5-397b-a17b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-DMei2tkTbCqecGNjYCYYoW","model":"grok-4.20-0309-reasoning","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-doo2bL7TEHLCNNMwf7NbYN","model":"qwen3-14b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-DPwt4tRRKyqEjPE8Jc2Co9","model":"qwen3-8b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-dWG8tET6WnzXeT2WjcjWvT","model":"gemma-3-27b-it","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-dWndu92zERWxzbpNa4BdJy","model":"qwen3.5-flash","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-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-FNMFJuzKKuNsWx9gQoLerW","model":"llama-3.2-1b-instruct","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-fubPj2m5aKLCeXZAwb3xeD","model":"phi-4","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-g64kPFtWB7Adto8Y8Hi3XE","model":"qwen3.6-flash","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-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-hFRxCUnXRNMcpQzUy8GYL5","model":"qwen3.7-plus","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-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-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-JcgBDysccQrAnWQaUmoehs","model":"qwen3-4b-instruct-2507","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-JCwFm63cUipLHBfM6BdssQ","model":"qwen3-30b-a3b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-JfkPdo29um2NkxdhT79AK2","model":"qwen3.7-max","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-k5CCeHstJwo5wKpbMFZtfw","model":"claude-opus-4-6","benchmark":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-k7EnhoBbZyVFUVRBowA5Pm","model":"kimi-k2.7-code","benchmark":"epoch-chess-puzzles-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-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-KB62zrQQ5ccd7hCcUwkX8j","model":"claude-sonnet-4-5-20250929","benchmark":"epoch-chess-puzzles-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-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-kHUvo7vG9JDf7fQvWpeP7s","model":"qwen3-30b-a3b-instruct-2507","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-KKzu5PGJQTEtfgMTqe7pnp","model":"glm-4.7-flash","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-kmHbjBrwGgEKNr65JrXcGX","model":"glm-5.1","benchmark":"epoch-chess-puzzles-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-KxxB8kDa9obqrPuec4PEiv","model":"qwen3.5-35b-a3b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-mQ3UwD6hUioWSp2s2oELY4","model":"gemini-2.5-pro","benchmark":"epoch-chess-puzzles-1-0-0-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-MYGuFuvkWEwLC7US5UR363","model":"qwen3-32b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-NaNEVAYahYyobdLPgCeNK9","model":"gemma-3-12b-it","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-opus-4-7-chess-puzzles-prelim-lower-bound","model":"claude-opus-4-7","benchmark":"epoch-chess-puzzles-1-1-1-model-extracted-exact-match","reason":"Run-specific qualification requires review: Opus 4.7 hit its max_tokens limit of 128K without responding on 31/100 samples. We intend to improve elicitation in the future, and this score should be understood as a lower bound."},{"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-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-Q8RAfong7NRCvww73BB3AT","model":"llama-3.1-8b-instruct","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-QyJe5cEG4rYmwvZv9b3oyG","model":"gemma-3-4b-it","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-RXsYuuSedkYZ5ubc8swxGp","model":"qwen3.6-plus","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-UbTx6Qbh6T2uXoQbpGV8i3","model":"gemma-3-1b-it","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-UgqBt5cFjsC96ALwiTFCPR","model":"qwen3.5-plus","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-UxakyoDNbLKtxnxeMsa7cU","model":"claude-opus-5","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-Wh3JxFdvxP688EWwE3t2Uk","model":"qwen3.6-27b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-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-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-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-XwemU6ABotEuG9o5TRLG2r","model":"minimax-m3","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-Yd3YzZmLa8D7eiZWo77WSm","model":"deepseek-r1-0528-qwen3-8b","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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-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-ZMRExFd2WEEwTRSQPLXXwu","model":"gemini-3-flash-preview","benchmark":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","reason":"No admitted matched unit: unreviewed benchmark/source, conflicting value, or insufficient distinct models"},{"id":"epoch-run-ZS6cAYkdeNAeRNz7AWQ4LR","model":"magistral-small-2509","benchmark":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","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:kimi/kimi-k3","model":"kimi-k3","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-5.2","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: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:kimi/kimi-k3","model":"kimi-k3","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-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: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:kimi/kimi-k3","model":"kimi-k3","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-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: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:kimi/kimi-k3","model":"kimi-k3","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-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"}],"launchEffortLabels":[{"model":"gpt-6-astra","labels":{"Best across efforts":34,"Not specified":26}},{"model":"claude-fable-5-1","labels":{"Max":25,"Not specified":33,"Medium":3,"Auto thinking":2,"XHigh":4,"High":1}}]}}