{"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-mini-instruct","collected":15,"contributing":14,"admittedWithoutWeight":0,"excluded":1}],"observations":[{"id":"516823481eb1495f3fb3c99c","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"601f36f2404c745b7bc714e7","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--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":"ab4cc6c2aa36c216f8568f92","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2627d43541d47421d317811","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5438058f26b61c57fa0f9afc","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d6bf305ef56bc9d7d14e527","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1959c33d56b49b87d365a30","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cad43079054208b6d9bfa144","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9dfce1492ec029021a05b9e","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8aa58d9564291e79f8c7d5aa","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ec4c88a12f8e0d0998cc68b9","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"70e69f2115f632139a54d1c0","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c13bc87ea7fbb9edee07b054","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64dbb96bbf3ee55255c6a592","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53b7d3d06cae0753bfaa177b","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"}]}