{"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-4o","collected":43,"contributing":5,"admittedWithoutWeight":0,"excluded":38}],"observations":[{"id":"60cd4a91f69f107025375b3f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bc7edbd7f528efe446e8db18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"870a8a46a2b531f6c5af62e8","modelId":"gpt-4o","configurationId":"gpt-4o--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":"ca8731b9c382bd00c0d8665b","modelId":"gpt-4o","configurationId":"gpt-4o--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":"fddc09f5e0e8bc06d04874e4","modelId":"gpt-4o","configurationId":"gpt-4o--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":"2ae788a49fc1d3e582e9f839","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2e74edde37a3d7442f9667e","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24a10eeb3a46c7763c5a63b2","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"4e82b51b3daf5aa1c8d98aee","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"ba806794d6c0ebc1b2585e8f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c88594bf8e16a074cc837dfb","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e0c41d17488dc4ec4ba0f0b7","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"5b174d58d4c658ab3d23b8bd","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"676bf2b6f6b8d425be537a91","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c5b33db9dc0245a7fa091824","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c611da33ffcd9a9e78304e4b","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"fd73d709f3bb83bda7f56ac0","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"adfbe98a4535a8b4dcbba8db","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e8a8172c365961fe52158eb8","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"111a771f0c518f482817be18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8d6af27176cb848c0da30e16","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"952674fc62e371988760c75e","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e26cd77447c8fea5c2954d73","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"08df3f3cdd6b93731cef3bfe","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"51e4170d40d5c177fe0231db","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"60f11419a7766054a4108a18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"67323d93d4710a1a34a75f0f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"93d23dcf1ef65f2e23f876f9","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"26a5dad1362342e4f74d3ddc","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8196e10e1bf2c6ab7a48896c","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"893141e7225b21e42fa2ce7d","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"ce9dd7a47db415076cf5f8f6","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b8d0d0d98797b082257d92e1","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39324a10e110c667372e0e04","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a9b3da7256fa223acaa958e2","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"750e957428961c84d14679b0","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b29b60a9d0d8925b03ed31d5","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"007fbaa1f184a893e7a405b1","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"79b4fb7fde5db57eeb15ccdc","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"893788f0d9759cc5abf9ec76","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d041de7b25693c5693bff38","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-arc2-gpt-4o-efebf61be277","modelId":"gpt-4o","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-gpt-4o-ad3f286332a4","modelId":"gpt-4o","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"}]}