{"version":"configuration-source-6","evidencePolicy":"documented","snapshotId":"sha256-e384eba3603ee0338d26052e22db513e17d16719d2af7d2444a3f89e18cd1b99","effortDatasetId":"sha256-49305f3d640f7387a764d95d62f10bbce44aeff4a4012ddba973eddf1e57a707+sha256-443256461e035ccdee585c01fdbd68b4b26545d45e2bd6b2bd93e1e913a2d41a+sha256-32c6374f8a0cdb9cd64f17244f1a697dd35d31cff071002599f3e1226d1e027d+sha256-9b7bfe52f0cba33df0362a330cb12551ea2f5853bf843931b08dad98e5d8d15c+sha256-c4f243913106bee769c57849d3cb4662fee3097206d30d3c8d4d37d687f8e556+sha256-c6f9cb8b67b4289e79e621b65d529e5f57eee55d89d86915f397859092051dad+sha256-78cb5ce46bffe96a698a9a7117551eafb90b2c3d05066722f4a703be2680aa55+sha256-e34a2de55476481fa69ea734e4027620fbc14df27f896c3bcec6c07275b0da42","scope":"All collected observations, not a claim that every public result has been collected. Contributing means positive graph weight, not sufficient evidence for a rank.","models":[{"id":"muse-wonder","collected":46,"contributing":40,"admittedWithoutWeight":0,"excluded":6}],"observations":[{"id":"e2f5630b078937ae5c53af35","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"409f64db18ddf3ebbbdb5c1f","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14f57fb9ba5c08e88680727f","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95e7a4ba29c6c86b27d71097","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7972ff078593589a9b53c45e","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cd9b0ce6dbfe3dd8a4d7eed","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62285399003445302807f39d","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f1ee21fbb1b83cea7ef3bd4","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a702440f484ecf067ab37730","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0f58b6fee38fc8e39f5342e5","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2494c3776c4a648aac942118","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"b2f531240ffd5178f869f695","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e689a062d192adbe930392e1","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-25fa2338b585e4d5e24aaf70","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ebadb48e181f168f04a307b1","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-74766c587c80763ddfc4e0ea","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c69e0aad188d1ebf54683cc3","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c67eba384acc4ed30aef4730","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-54e4e1da32d5723495e597ea","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7ce2e0d0b83d48ac917a163a","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fbf6974aa029bb3328653ff9","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d89fbdd1388539c6a6c35abd","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ca12f749d0bae5cb876bb122","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-18a7565596dfecd68f676d6a","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-20dee3cbee18a22247270619","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9900ad797a426c46f91cdc10","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dca032e1e3b8025ad77f46f2","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d3299870468757c818165bba","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8a5c3b62302b72bf46b1755f","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-399e44bafc57b20172daf0ad","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-83bbb59d6ada1aae15c5feeb","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fef023790048111cf5d004c6","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2644d92decaf8c527130b880","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0b01edf83568515503d6ecd0","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-53adcf37a1fd967c5d7edbdb","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-tax-agent-bench-v1:meta/muse-wonder","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56b7367f12ba25eff56d498e","modelId":"muse-wonder","configurationId":"muse-wonder--effort-max","sourceUrl":"https://surgehq.ai/benchmarks/sudo-l7","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"s-automationbench-muse-wonder-aeb8c17003ec","modelId":"muse-wonder","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-hss-muse-wonder-max-8bb7442ceaba","modelId":"muse-wonder","configurationId":null,"sourceUrl":"https://labs.scale.com/leaderboard/hss","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-lmarena-agent-muse-wonder-max-c750d8bd5563","modelId":"muse-wonder","configurationId":null,"sourceUrl":"https://arena.ai/leaderboard/agent","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"}]}