{"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-5.3","collected":60,"contributing":34,"admittedWithoutWeight":0,"excluded":26}],"observations":[{"id":"be4dbe3360dd3f02bd332d2c","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03589e0cd6d71614dbdee7a5","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e6fdbe329769f9b2d1bc773","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b2b1bb5c7a2e87c08d5a4c1","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"395626c3695359937c7d12a8","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7f416a17884df7aef90f9f4","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d421e3e8a95478bc0e53938b","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8d48be7c4b3b312fd3982fd","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"580cd529e7bf91092259785c","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c030d58ba58b16f1f98af31d","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dff0f2b52603e6e86eb2d04","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"815c075d82fa152d7eecba36","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc1e10b808769dbc5b58076f","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e0077d4dc5e45d0d02cd521","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa57afbaecfad6b6f2b99ee3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c1ac3e144270be20ee96d03","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e2a553a0ef9312c689f04ed","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f796e96bd180b4dd9bd12eff","modelId":"glm-5.3","configurationId":"glm-5.3--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"d783859010d571f133e77356","modelId":"glm-5.3","configurationId":"glm-5.3--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"3bde5c20893b402a0e56ffb5","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"118142e09fa2bec781ac751e","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"739cb0ae8374d5569ce1d129","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3b6ec43cb1015de697c37c0","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4S3ZrJDkwh4gmGrmJQdvzR","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9RfS3yHmzmP3azirghceFL","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dLDBahYBTGRNjbsXA5pyr3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-goZR5yGxZic9TZ23ezCL3w","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iXvqUzwxAiA3Rg3dwnutFs","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TY8R8FV7zCwByEipkqyg2P","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UUq99Qhq3qizcoJo5vdhuK","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-zai-1198","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1206","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-zai-1212","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1220","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1226","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1233","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1237","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1243","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1249","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1257","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1258","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1271","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1278","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1286","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1294","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1302","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1310","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"s-deepswe-glm-5.3-eb88d1c756c0","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-glm-5.3-41e862296ea6","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-high-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-low-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-max-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"}]}