Zhipu (GLM) · model
GLM-5.1 benchmark scores
As of 2026-10-07, GLM-5.1 (Zhipu (GLM)) has measured scores on 38 benchmarks and estimated scores on 77 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 86.8% | measured |
| AA-HLE | 30.1% | measured |
| AA-SciCode | 44.8% | measured |
| AIME26 | 95.3% | measured |
| Artificial Analysis Intelligence Index | 26.1% | measured |
| CritPt | 4.6% | measured |
| GDPval-AA | 31.0% | measured |
| GPQA Diamond | 86.2% | measured |
| HLE | 52.3% | measured |
| IFBench | 74.9% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 73.7% | measured |
| LiveCodeBench v6 | 88.9% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 23.7% | measured |
| SciCode | 39.5% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 74.1% | estimated ± 6.9 pp, medium confidence |
| BrowseComp | 68.0% | measured |
| HLE w/ tools | 36.6% | estimated ± 4.6 pp, high confidence |
| IFEval | 93.7% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 44.9% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 97.7% | measured |
| AA Coding Index | 55.8% | measured |
| APEX-Agents | 27.3% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 14.5% | estimated ± 4.6 pp, high confidence |
| BioMysteryBench (human-difficult) | 30.3% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 87.2% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 78.5% | estimated ± 2.4 pp, high confidence |
| AutomationBench | 28.4% | estimated ± 5.8 pp, low confidence |
| BFCL v4 | 75.3% | estimated ± 2.6 pp, high confidence |
| CyberGym | 68.7% | measured |
| JobBench | 42.4% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 58.4% | measured |
| τ³-bench results | 70.6% | measured |
| WideResearch | 72.0% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 25.2% | measured |
| MMLU-Pro | 85.5% | estimated ± 3.5 pp, high confidence |
| FrontierMath v2 (Tier 4) | 12.5% | measured |
| FrontierMath v2 (Tiers 1-3) | 33.4% | measured |
| GPQA | 86.2% | estimated ± 0.1 pp, high confidence |
| AA-IFBench | 76.3% | measured |
| Gert Labs | 60.1% | measured |
| AA-AnalystAgent | 22.4% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 51.4% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 84.0% | estimated ± 1.2 pp, medium confidence |
| ApprenticeBench | 0.7% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 82.8% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 42.9% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 31.2% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 55.9% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 4.2% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 25.6% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 12.3% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 76.0% | estimated ± 4.7 pp, high confidence |
| Vals GPQA Diamond | 84.5% | measured |
| Vals LiveCodeBench | 81.4% | measured |
| Vals MMLU-Pro | 86.9% | measured |
| Vals SWE-bench | 76.4% | measured |
| Terminal-Bench 2.1 (Vals AI) | 56.9% | measured |
| VulcanBench v3 | 81.6% | estimated ± 5.6 pp, low confidence |
| AA AutomationBench | 2.7% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, medium confidence |
| AA ITBench | 40.0% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 72.4% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 10.2% | estimated ± 14.0 pp, low confidence |
| CursorBench 4.0 | 19.6% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 40.8% | estimated ± 6.9 pp, medium confidence |
| DeepSWE | 24.1% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 23.8% | estimated ± 4.4 pp, high confidence |
| OSWorld 2.0 | 7.4% | estimated ± 4.5 pp, medium confidence |
| PostTrainBench v1.1 | 24.0% | estimated ± 2.7 pp, high confidence |
| Toolathlon-Verified | 70.2% | estimated ± 2.2 pp, low confidence |
| Vibe Code Bench | 31.5% | measured |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 62.3% | measured |
| DeepPlanning | 35.4% | estimated ± 8.3 pp, low confidence |
| HMMT Feb 2025 | 95.3% | estimated ± 1.6 pp, medium confidence |
| HMMT Feb 2026 | 82.6% | measured |
| HMMT Nov 2025 | 94.0% | measured |
| MCP Atlas | 71.8% | measured |
| MCP-Tasks | 76.9% | estimated ± 0.6 pp, low confidence |
| MMAnswerBench | 83.8% | measured |
| MMLU-Redux | 94.3% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 42.7% | measured |
| QwenClawBench | 60.5% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 68.7% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.0 | 63.5% | measured |
| Toolathlon | 41.4% | estimated ± 3.5 pp, high confidence |
| HealthBench Hard | 20.1% | estimated ± 7.7 pp, low confidence |
| LiveCodeBench Pro | 82.5% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 44.2% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 85.6% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 75.4% | estimated ± 2.4 pp, medium confidence |
| ResearchClawBench | 18.2% | measured |
| SWE-Rebench | 62.7% | measured |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| FrontierMath (legacy) | 34.1% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| DRACO | 74.3% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 24.5% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 39.3% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 58.1% | estimated ± 1.3 pp, medium confidence |
| HealthBench Professional (raw) | 50.4% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 81.4% | estimated ± 1.8 pp, low confidence |
| AIME 2025 | 95.9% | estimated ± 1.5 pp, medium confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| Agents' Last Exam | 24.0% | estimated ± 2.1 pp, medium confidence |
| OpenHarmony Bench | 52.3% | measured |
| IMOAnswerBench | 79.5% | estimated ± 5.9 pp, medium confidence |
| MMMLU | 88.3% | estimated ± 1.1 pp, medium confidence |
| MMLU | 88.3% | estimated ± 1.1 pp, medium confidence |
| MATH-500 | 97.7% | estimated ± 3.1 pp, medium confidence |