{"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":"qwen3-4b-thinking-2507","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1}],"observations":[{"id":"96ebe1b6fbf2e0d343e3a601","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5545ac10fac2b93cda828d1","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73326f7b5805389fbe29ad4d","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e11def07dfa9e995c73e1bac","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15a62e80d61f958a5049ebf7","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8942418d355ebf98c867b34b","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db6ac46ae5700dbe44444c52","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b9744f8d20c3175afe7b407","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3a3f857a9b6c30c32f5e781","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fa0a36c238b7bcee88d55771","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cd71124c6978766c9d6d511","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6478507eb9c1b358f3b4a3c","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"}]}