{"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":"step-3.7-flash","collected":19,"contributing":17,"admittedWithoutWeight":0,"excluded":2}],"observations":[{"id":"4e4f7f66e12fa41c88b4ae62","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d03747357d4b99762e3c2c12","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05f9d1f4588607425107e0cd","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3f1d0a35cc4c49e68376e7f","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3bb0f7ade7fc2865154e49c7","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aea0451a4896d102b0043d1d","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7871ad7a9b4fdaee2e2800fd","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eaec21698f9c763849fc748","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a23d7538799febe12d9a6925","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9006b356b7c4957dcf096d9e","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c87c7ea70afb04af4f026773","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f10ed77c5f2a457b4875815a","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4cb090aa5d8a78b6a18f80f0","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31c949451c135ca26418dd9e","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6ad7a16a5446adada0a8818","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b38eb1018caf6cb002d9ea9","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d29adfa107dd249d7fdf48ea","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee468fde2438f81f9d3a5096","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-gdpval-step-3.7-flash-58c478670eac","modelId":"step-3.7-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}