{"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":"gpt-5.1","collected":54,"contributing":34,"admittedWithoutWeight":0,"excluded":20}],"observations":[{"id":"239fa90dfb33619a5081e9f9","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6abab40890aa0c0372d0f089","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4f454e9391cd595d2c59a94","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"242467cf8ae03ca5317cf999","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cebcc0d24f668fcc1ea52594","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9268c5b8746b04887ef9d764","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47fb804697213949c1022802","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"245233a893e0114ab6b3d52f","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bd1a0bd70e4ab77e4a980c7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fcc61e29b95a07ac78e5842","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a159bfc6abd91a7c701560d","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cf4aa2e67a6c7ef11ed452d","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f2435a7d3956433073252a2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cf752361e0a75cc3c1dc615","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36f6e69708f8a4a10940441e","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1596ea955bb7e7d0db23d9a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5dc3af27f6bddfad8d051e8","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15ccd3e2bad00dbe4d513d94","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94dfe52c82affb9fd3334eb7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ecc1a5e9d3e0bc1554f7e5a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7c1b35ac1102f446ec8ef52","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ad964ce0ca054e729c02f3c7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"753b9a8a6643e8cc1e4b81f8","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcb6c1cfb154e6dfd47677c2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31bc5bcd1fc862e3317e60bc","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"301d76c19099e4fcffbb57c5","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f211d243e12f56bc1a5a756","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e264fcbbf9c34586e7b6dfb4","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f32ac719f9f42f00e7041db0","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67f77366629a3d4d08cce1e7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fbbe06ee7a41a332409a02a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f99ee8a4e9e3a03a96cb7c2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be4f45a2511f61842abfae20","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29c08eeadae8b2d685b7f079","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25753b4cde30cf31c9192afb","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b65412a084daf79b87e4b34","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-amazon-1540","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1541","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1542","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1543","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1544","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1591","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1592","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1593","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1594","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1643","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1644","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1645","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1646","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1681","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1682","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1683","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.1-465fe8c26c46","modelId":"gpt-5.1","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-mmlu-pro-gpt-5.1-df03094a9acf","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}