{"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","collected":22,"contributing":17,"admittedWithoutWeight":0,"excluded":5}],"observations":[{"id":"370cf31a2407efae21be583a","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f466d671d2eef974ea005b2b","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75946bb5200d898db3265c34","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f70a218b1f6a8fc2114d48e","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e92ab090534be36366d3ec","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd4f93e7f4f1a45735079084","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30ee4a241c6f54cb0ca85362","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"019b987204bf0a37c545c13c","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99c65e088b8907331a5c2554","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6f4e33c7c2b7b4ca2e20e28","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"350484fd270e9192ba0525d4","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7cf10f4304e8d80bbcf66d39","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a1204eb9a9a16442ef47947","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"001226139bfffd4e21b870af","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7e49807f538aef93f8c591f","modelId":"o3","configurationId":"o3--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4c43e9a8ca07f6c7e48de89","modelId":"o3","configurationId":"o3--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44ec3c5d0da4e3f62912c05f","modelId":"o3","configurationId":"o3--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de6fe228603e9238b659ea7d","modelId":"o3","configurationId":"o3--effort-high","sourceUrl":"https://livecodebench.github.io/performances_generation.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-arc2-o3-efebf61be277","modelId":"o3","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-ad3f286332a4","modelId":"o3","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-osworld-o3-42c386263956","modelId":"o3","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"},{"id":"s-swev-o3-077d8c0cfcca","modelId":"o3","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}