{"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":"glm-5","collected":30,"contributing":18,"admittedWithoutWeight":0,"excluded":12}],"observations":[{"id":"371e32e413b5c1e2b63024dc","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3428cabd424a2de0154d82fe","modelId":"glm-5","configurationId":"glm-5--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":"fe7a9aae7813ba9b022e0a72","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08067a5c23ad9c568ec00812","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae84ac005a4fdeda6ace0f05","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"498eceb3c7be3ce505460dd0","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7755d2a416f32e67386047d","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a1cabde7a1e7348cc33f64","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16de6f0d8d08fe75b8727d3a","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fa3e46f37c7db7f5e084225","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13e503950411783d5ec9b173","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2025179161cc4f662dcc530","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ee2916f2a458729d0bf1b6b","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9d54baf80501bc9f77e431c4","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5a3b5525815de32a23e559dd","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c3a2030b1af48fb9ae3dde5","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9229265b86c1968b93d86775","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cbdf43c125960c2074118eb","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad5cb316707e497431201b78","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e99d17495fc238ef6244f56","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7czodbcgEF5zN68ppPFzBN","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ccbx7KQY9bTD563vzBXwSg","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Run-specific qualification requires review: Two samples did not complete, which is greater than our 2% error tolerance setting. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-n4hyz75SVpwPEisKVVjvNg","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"launch-mistral-1446","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1451","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1456","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-arc2-glm-5-efebf61be277","modelId":"glm-5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-5-465fe8c26c46","modelId":"glm-5","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-glm-5-df03094a9acf","modelId":"glm-5","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"},{"id":"s-swev-glm-5-077d8c0cfcca","modelId":"glm-5","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}