{"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":"hy3","collected":16,"contributing":13,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"4b52e57716284a426b20e616","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbe2f8f3df27510117453b6d","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"725cf8be083eeea3761a0746","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed230f269f79598168400161","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"875ff8bc105e8938ba3ab493","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d88716d3f6022775ca0349b","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c62d7142b2955f3cccde331b","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7a35fd1ba65fa084a53bfff","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e3737c70846342ba1f20656","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"02867ce545a79d28fdca774c","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05c2f7fcf387f4cfcc374ac1","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42aa341468210b376e09693e","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c802eac5e2f5b0cc14a4b3d2","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9c96fd0e4307f0a3d58c1b2","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-gdpval-hy3-58c478670eac","modelId":"hy3","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"},{"id":"s-lmarena-hy3-465fe8c26c46","modelId":"hy3","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"}]}