{"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":"o3-mini","collected":35,"contributing":31,"admittedWithoutWeight":0,"excluded":4}],"observations":[{"id":"01a156003da2d47b7c81895a","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e677a3227e6bacc4a0e9a40","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d80aa65c5a1e66963cd6340","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4250ae81639657e77c36aaf","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5b3e40b7466bcdf13bd150c","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2841993d80a9999de9f6ee7f","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42f4c2c9076d696f07dc6783","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"811d9c240ea23b82e185a589","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a7f79808eefcb014ec3f0be","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e161b5a9b646a096149330a7","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a9234b7c969c2c1abb86d31","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d65babdfac67d23efa92d48","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"318e34735b7b00c4d11a9a09","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"745e69c691f9b694b7c9353f","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b03c9376d3f09d3c80e63a54","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00d8df98308d9c695c029966","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e266c73c6ec784e58caaf44a","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db1badd09c0ec2742a1bda68","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8d5a35515e13598e754d8782","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdf870defc76ce206427d252","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9939fced55db051e5e0be0c6","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19eb94c3b4a5578e45bc7056","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5d59a1795d09f33dd6e3fee","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14aa700efe22f08ce992bfb4","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4da7c16ca683432d6e1cd5ba","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c0182a63d8db78a905b0380","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06585d01215ca9d0bce0d3f5","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2c3b8b661de8636e2ceca83","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78ba06f11057b6bec4542c33","modelId":"o3-mini","configurationId":"o3-mini--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e76fe3fd7aff227cd9253390","modelId":"o3-mini","configurationId":"o3-mini--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c457ac399b0c7c755bf0adbb","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"caa92a3ee80886991f302d07","modelId":"o3-mini","configurationId":"o3-mini--effort-medium","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-arc2-o3-mini-efebf61be277","modelId":"o3-mini","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-lcb-o3-mini-ad3f286332a4","modelId":"o3-mini","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-o3-mini-465fe8c26c46","modelId":"o3-mini","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"}]}