{"version":"configuration-source-5","evidencePolicy":"documented","snapshotId":"sha256-df858793dcb753b0f77beb223fce04e1de99a2c08f2c7b5f14534efcafa8c7c5","effortDatasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","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":"claude-sonnet-4-6","collected":151,"contributing":80,"admittedWithoutWeight":1,"excluded":70}],"observations":[{"id":"e332f1b2228e9266a71d05ad","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3ee41fb89c6ccb1e66adf8f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b93039d4563fe3b157d15d5","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d8faf0c2e0685f2c87902f3","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95567387bc84bd43e2e17443","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"eeca2c029f49887d2f8de42c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8fec0dac751edaf179a65615","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f405b80c050b037ebb56264","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a850dc6ae782aabcb69a92e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"754ae6038c192fcc20e15317","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dab21af4216ac279722b33bf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa8db74b95a531e6228d4cdb","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d6261c518f3a5cb2d3aa799","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68cd3fa6809265041ab4e058","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bac7982cd94b783ce9937b37","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"6ee50ff3940f843b316a11ca","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9faede113e168f7e102e28b7","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bd9dc8c11e74dcf4d21c0355","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"451dd11af5aa03b51c7df735","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e5f7bf21fd13c70b5963400","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7ef923a70da041c042f467c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08964d53879fda33454d92be","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"fbaf3e468a069edc24595e53","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"5802b72f96fd2bc36b68b3b6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b9a5ed9afd89f3d3dc7c7d9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"cb52c6337e6d1ca83f782771","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e75ab74cf5a997095d1f3380","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7f4aba36323901ba9da5ab4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53a70f8e8f39a9bf4b309039","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b302bedcd3669528b4703126","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2753a36a2d9898ee83a2c7e0","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eab8dfd0579ff09141f58f1","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c9790672cda25468a59d855a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2b79a8be3c4816ae5e4126d1","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3c8824c30ba25df9377473e9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8ff03bd6cf18ff4fdd035fca","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cef67cc03b37e5d955687879","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"089295a829a4b2eea0c45567","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"524488ae2a2507b68ea71d3d","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"af900336d45849b431b9cad3","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b286a9e0d17ba5da81669d3e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f4c2f07253b00381b8a7e93","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"687f063bf51789c89c7d6efd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"3f305729d1c2d29db2f9101c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e7ecd187c6d64aaaf7a121c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"382f610161294070630b7fc4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"cb333ca12130594126273d1d","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e9118d28b3767fb3d536c9bc","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87726611ca55ead407ddd84c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fc5dd5ad41a965cc918cdf2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1a628a019bde02cfbdacf5e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46adf8595dc3ea458bbcbb0e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ed4c92e4aa05c76200a18bc","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46f65324a766a154476a00ad","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50b7158c541e4c1686f7c817","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6dd3175afce39f643aa12476","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4313e77019bc32a716730f9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7d96566d6b6b34d9e314f79","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd377043899ff0ae0b462963","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f069bb43a49e2e73d5a979fd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-727e4929c5b77b8d68e9616f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5c66ecc29c060d251f32641f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8e215924ae06b331fbc47123","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-30450bbe2cd94e48badcae38","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a9cff8685184797af933836","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e9fc47dbe181087a7a1a77db","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-239cfd267c6875696e83c9cb","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d4d1042248b561833a92f2c4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-61b37a37ffa13a56ab533193","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d9064929591d93f9978bec5","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c1f148c80800c7bb48207f5e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-57c9d66e18c45c4f050a462a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c9dec434280ecd1032922f0a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7395d6919946c2adfaf7424b","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a0dacead0b0fff9e77e638df","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-97a9005f0a93edb4193e1c8a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-10dfde1dfd55d1050db26ccd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2159cc97a8071f41f95b2bac","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a6622acee6854a8492d2d048","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e5f6c6af7b7b6563cbd85d04","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f97c66befa16467a34a3d8f2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-21d30b7156f9abf0cc4dad65","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9d65818b1f976a7825472a2f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-58eQmyCfPa3FufhXJFvAL2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-5Q9RNC2JfEmmvNFFE5CQCf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9LWdzVN5w4ihNvncsaCWMu","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-DmdKPD9Z9RXwYyATAoG4Uw","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-e8MXnAM8HMF8eEzYtYA7xv","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eJBzZyT5ohb8ieaJCum5rK","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kDNNbUYXhrAH5uDBGykFaf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LJyKf8Xy4dymxNHbGLwNdA","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-N5beL4W3WahAubJgDKivnE","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"epoch-run-oXZ7ZVZtADrwFPKAe6zTvL","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SEePRKRcv8oqn5HpD2KFxB","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TDT98jZXHbUMFYTphGEpqC","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VjfWxdhdNerrh4huSHT8PT","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XnQVH5qSfxVjpzoPwUEmnh","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YdyvoMQ4mA5V8Ymg6Tksxu","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Zs5fCvNzaz8LhqgwDSAztU","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--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:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--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:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--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:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--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:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-microsoft-1376","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1385","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1393","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1399","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1408","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1410","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1412","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1414","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1416","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1418","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1420","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1422","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1424","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1426","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1428","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1697","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1718","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1731","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1752","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1760","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1783","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1789","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1795","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1821","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1829","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1834","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1841","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1847","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1852","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1866","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1444","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1449","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1454","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1459","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1463","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1468","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1473","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1478","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1483","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1488","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-sonnet-4-6-efebf61be277","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-sonnet-4-6-eb88d1c756c0","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-sonnet-4-6-465fe8c26c46","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-claude-sonnet-4-6-42c386263956","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}