{"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":"phi-4","collected":18,"contributing":12,"admittedWithoutWeight":0,"excluded":6}],"observations":[{"id":"77b72d8bb8f6229c4935bd1d","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7913c6e2413a96102bbbf1fe","modelId":"phi-4","configurationId":"phi-4--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":"834342d113eaeacdec6c68c2","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c45844e7e930f528caf96218","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92a3672a2fcdd9eae2cfe4c8","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70dd1ef196043632b7c37a03","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2fa14f24036f5ed63850347","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1300da3198b950627b64868","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e87a2d3e2af83fbba103ecc7","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4d5188cfd91b9b6ddb85ec5","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"aff564f7946147cb44a15141","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68eef27c9393c82acd930591","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0d8027ad98e252733a703ca","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5mmrBSQb7hVSJ9VYtNm46i","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-fubPj2m5aKLCeXZAwb3xeD","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-RAwuPRwJedy7P2KeQhEmr8","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"s-lmarena-phi-4-465fe8c26c46","modelId":"phi-4","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-phi-4-df03094a9acf","modelId":"phi-4","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"}]}