Zhipu (GLM) · model
GLM-5.1 benchmark scores
As of 2026-11-22, GLM-5.1 (Zhipu (GLM)) has measured scores on 42 benchmarks and estimated scores on 124 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 | 30.8% | measured |
| GPQA Diamond | 86.2% | measured |
| HLE | 31.0% | measured |
| IFBench | 74.6% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 73.7% | measured |
| LiveCodeBench v6 | 88.7% | estimated ± 1.7 pp, high confidence |
| AA-Omniscience Accuracy | 23.7% | measured |
| SciCode | 39.5% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 74.3% | estimated ± 6.7 pp, medium confidence |
| BrowseComp | 68.0% | measured |
| HLE w/ tools | 52.3% | measured |
| IFEval | 93.1% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 60.8% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 38.9% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 97.7% | measured |
| AA Coding Index | 55.8% | measured |
| APEX-Agents | 23.1% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 15.1% | estimated ± 4.4 pp, high confidence |
| BioMysteryBench (human-difficult) | 36.2% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 87.2% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 79.5% | estimated ± 2.3 pp, high confidence |
| AutomationBench | 48.6% | estimated ± 9.1 pp, low confidence |
| BFCL v4 | 74.5% | estimated ± 2.7 pp, high confidence |
| CyberGym | 68.7% | measured |
| JobBench | 44.1% | estimated ± 7.9 pp, medium confidence |
| SkillsBench | 39.7% | estimated ± 4.1 pp, low confidence |
| SWE-bench Pro | 58.4% | measured |
| τ³-bench results | 70.6% | measured |
| WideResearch | 82.1% | estimated ± 1.6 pp, medium confidence |
| AA Agentic Index | 25.2% | measured |
| MMLU-Pro | 86.0% | estimated ± 4.8 pp, high confidence |
| AA-IFBench | 76.3% | measured |
| FailureSensorIQ | 67.1% | estimated ± 1.7 pp, high confidence |
| GPQA | 86.1% | estimated ± 1.2 pp, high confidence |
| MMLU | 90.4% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 84.5% | measured |
| Vals LiveCodeBench | 81.4% | measured |
| Vals MMLU-Pro | 86.9% | measured |
| MATH-500 | 97.7% | estimated ± 3.1 pp, medium confidence |
| MMMLU | 88.3% | estimated ± 0.7 pp, medium confidence |
| Chess Puzzles | 20.0% | measured |
| AIME 2025 | 96.6% | estimated ± 1.8 pp, medium confidence |
| AA MMLU-Pro | 84.9% | estimated ± 0.7 pp, high confidence |
| Gert Labs | 36.4% | measured |
| AA-AnalystAgent | 46.5% | estimated ± 3.7 pp, low confidence |
| AA Harvey LAB v1.0 | 84.0% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 27.6% | estimated ± 3.6 pp, low confidence |
| AA Terminal-Bench 2.1 | 80.3% | estimated ± 2.5 pp, medium confidence |
| ApprenticeBench | 4.3% | estimated ± 4.0 pp, high confidence |
| ARC-AGI-1 | 83.0% | estimated ± 2.5 pp, medium confidence |
| ARC-AGI-2 | 36.2% | estimated ± 9.7 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 |
| EBR-bench | 19.9% | estimated ± 9.1 pp, low confidence |
| Terminal-Bench 3.0 | 4.2% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 13.8% | estimated ± 4.3 pp, low confidence |
| FrontierMath v2 (Tier 4) | 6.5% | estimated ± 4.0 pp, high confidence |
| FrontierMath v2 (Tiers 1-3) | 36.8% | measured |
| FrontierSWE v2 | 12.8% | estimated ± 8.3 pp, medium confidence |
| Furniture Assembly | 26.9% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 40.3% | estimated ± 10.3 pp, low confidence |
| MazeBench | 0.1% | estimated ± 2.7 pp, high confidence |
| Mystery Game Puzzles | 30.8% | estimated ± 9.8 pp, medium confidence |
| NYT Connections | 77.7% | measured |
| OSWorld-Verified | 70.4% | estimated ± 3.8 pp, medium confidence |
| Terminal-Bench 4.1 | 10.4% | estimated ± 14.9 pp, low confidence |
| Terminal-Bench Hard | 46.7% | estimated ± 3.9 pp, high confidence |
| 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 |
| CWE-Bench-AA | 53.5% | estimated ± 5.2 pp, medium confidence |
| AA Cyber Index | 16.6% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 11.6% | estimated ± 8.2 pp, medium confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 53.8% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 40.2% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 40.3% | measured |
| Bug Hunt Bench | 11.8% | estimated ± 7.2 pp, low confidence |
| CursorBench 4.0 | 34.4% | estimated ± 3.3 pp, medium confidence |
| CWE-bench v1 | 43.1% | estimated ± 5.7 pp, medium confidence |
| DeepSWE | 24.1% | estimated ± 6.4 pp, low confidence |
| DRACO | 76.5% | estimated ± 2.0 pp, medium confidence |
| FrontierCode 2.0 | 20.7% | estimated ± 6.7 pp, low confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| HLE w/o tools | 34.3% | estimated ± 2.7 pp, medium confidence |
| OSWorld 2.0 | 6.3% | estimated ± 6.9 pp, low confidence |
| OSWorld 2.1 | 28.1% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 Offline | 8.0% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 21.0% | estimated ± 3.7 pp, medium confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, medium confidence |
| StealthMark | 37.0% | estimated ± 9.7 pp, low confidence |
| Toolathlon-Verified | 70.2% | estimated ± 2.2 pp, low confidence |
| VulcanBench Frontier v4 | 75.0% | estimated ± 6.8 pp, low confidence |
| AA AutomationBench | 41.9% | estimated ± 7.9 pp, low confidence |
| GDP.pdf | 15.7% | estimated ± 4.2 pp, high confidence |
| AA Terminal-Bench 4.0 | 3.0% | estimated ± 13.7 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.3 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| CWE-bench | 37.9% | estimated ± 6.2 pp, low confidence |
| MKA | 33.2% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 58.4% | measured |
| BinaryAudit | 43.8% | estimated ± 12.0 pp, low confidence |
| OTelBench | 22.5% | estimated ± 6.6 pp, medium confidence |
| Vibe Code Bench | 31.5% | measured |
| FACTS Multimodal | 43.9% | estimated ± 4.0 pp, high confidence |
| Hermes Bench | 69.0% | estimated ± 1.8 pp, medium confidence |
| Hermes Index | 24.3% | estimated ± 5.7 pp, low confidence |
| ExploitBench | 20.3% | estimated ± 13.4 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| C-Eval | 93.5% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 62.3% | measured |
| DeepPlanning | 35.4% | estimated ± 8.3 pp, low confidence |
| HMMT Feb 2025 | 92.5% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 82.6% | measured |
| HMMT Nov 2025 | 94.0% | measured |
| MCP Atlas | 71.8% | measured |
| MCP-Tasks | 74.4% | estimated ± 3.6 pp, medium confidence |
| MMAnswerBench | 83.8% | measured |
| MMLU-Redux | 94.0% | estimated ± 0.8 pp, medium confidence |
| NL2Repo | 42.7% | measured |
| PostTrainBench v1 | 19.0% | estimated ± 3.1 pp, medium confidence |
| QwenClawBench | 60.5% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 71.4% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.0 | 63.5% | measured |
| Toolathlon | 38.2% | estimated ± 4.2 pp, high confidence |
| AA LiveCodeBench | 89.6% | estimated ± 2.6 pp, high confidence |
| HealthBench Hard | 23.0% | estimated ± 8.6 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 | 75.8% | estimated ± 3.0 pp, medium confidence |
| ResearchClawBench | 18.2% | measured |
| SWE-Rebench | 62.7% | measured |
| PostTrainBench | 18.5% | estimated ± 3.7 pp, medium confidence |
| DAYJOB | 0.4% | estimated ± 6.3 pp, medium confidence |
| DAYJOB Healthcare | 0.1% | estimated ± 6.1 pp, low confidence |
| Finance Agent v2 | 55.2% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 55.5% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 39.0% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 49.8% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.8% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 50.2% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 0.3% | estimated ± 4.6 pp, low confidence |
| LABBench2 | 81.4% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 25.2% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, low confidence |
| Cookie-Bench | 77.0% | estimated ± 2.5 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 23.2% | estimated ± 4.3 pp, medium confidence |
| Agents' Last Exam | 23.6% | estimated ± 3.3 pp, low confidence |
| OpenHarmony Bench v1.0 | 52.3% | measured |
| SEC-Bench Pro | 30.5% | estimated ± 12.3 pp, low confidence |
| IMOAnswerBench | 79.1% | estimated ± 5.6 pp, medium confidence |
| MRCRv2 | 82.9% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.1% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |
| LifeVal | 53.7% | estimated ± 1.6 pp, medium confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |
| PinchBench | 89.5% | estimated ± 3.6 pp, medium confidence |