Zhipu (GLM) · model
GLM-4.7 benchmark scores
As of 2026-11-21, GLM-4.7 (Zhipu (GLM)) has measured scores on 31 benchmarks and estimated scores on 112 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 85.9% | measured |
| AA-HLE | 27.4% | measured |
| AA-SciCode | 42.7% | estimated ± 3.4 pp, high confidence |
| AIME26 | 95.6% | estimated ± 1.0 pp, medium confidence |
| Artificial Analysis Intelligence Index | 22.2% | measured |
| CritPt | 1.7% | measured |
| GDPval-AA | 25.7% | measured |
| GPQA Diamond | 85.7% | estimated ± 0.1 pp, medium confidence |
| HLE | 24.8% | measured |
| IFBench | 66.0% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 71.0% | measured |
| LiveCodeBench v6 | 84.9% | measured |
| AA-Omniscience Accuracy | 29.3% | measured |
| SciCode | 41.1% | estimated ± 2.9 pp, low confidence |
| BrowseComp | 52.0% | measured |
| HLE w/ tools | 46.2% | estimated ± 5.3 pp, low confidence |
| IFEval | 92.7% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 59.1% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 15.5% | measured |
| τ²-bench results | 95.9% | measured |
| AA Coding Index | 45.3% | measured |
| APEX-Agents | 18.6% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 8.5% | estimated ± 4.4 pp, medium confidence |
| BioMysteryBench (human-difficult) | 23.5% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 75.4% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 73.8% | measured |
| BFCL v4 | 73.6% | estimated ± 2.7 pp, high confidence |
| CyberGym | 53.5% | estimated ± 6.0 pp, medium confidence |
| JobBench | 23.1% | estimated ± 8.7 pp, medium confidence |
| SkillsBench | 27.0% | estimated ± 4.1 pp, low confidence |
| SWE-bench Pro | 51.6% | estimated ± 4.5 pp, high confidence |
| WideResearch | 61.6% | estimated ± 3.5 pp, medium confidence |
| AA Agentic Index | 19.8% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 84.3% | measured |
| AA-IFBench | 67.9% | measured |
| AIME 2024 | 94.8% | estimated ± 2.6 pp, high confidence |
| BBH | 98.4% | estimated ± 2.8 pp, medium confidence |
| FailureSensorIQ | 66.2% | estimated ± 1.8 pp, medium confidence |
| GPQA | 85.7% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 80.1% | measured |
| Vals LiveCodeBench | 82.2% | measured |
| Vals MMLU-Pro | 82.7% | measured |
| MATH-500 | 98.9% | estimated ± 2.0 pp, high confidence |
| MMMLU | 87.0% | estimated ± 0.7 pp, medium confidence |
| Chess Puzzles | 21.0% | measured |
| AIME 2025 | 95.7% | measured |
| AA MMLU-Pro | 85.6% | measured |
| Gert Labs | 40.0% | measured |
| AA Harvey LAB v1.0 | 83.3% | estimated ± 9.8 pp, low confidence |
| AA Tau3 Banking | 30.5% | estimated ± 4.1 pp, high confidence |
| ARC-AGI-1 | 67.9% | estimated ± 6.5 pp, medium confidence |
| ARC-AGI-2 | 25.8% | estimated ± 10.9 pp, low confidence |
| CursorBench 3.1 | 43.3% | estimated ± 5.8 pp, low confidence |
| CursorBench 3.2 | 30.5% | estimated ± 4.4 pp, medium confidence |
| EBR-bench | 10.0% | estimated ± 12.7 pp, low confidence |
| FrontierCode 1.1 Main | 16.5% | estimated ± 4.2 pp, low confidence |
| FrontierSWE v2 | 6.2% | estimated ± 9.5 pp, low confidence |
| Furniture Assembly | 27.2% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 41.0% | estimated ± 10.3 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| Mystery Game Puzzles | 15.1% | estimated ± 2.2 pp, low confidence |
| NYT Connections | 63.8% | estimated ± 12.6 pp, low confidence |
| OSWorld-Verified | 55.8% | estimated ± 5.5 pp, medium confidence |
| Terminal-Bench Hard | 41.5% | estimated ± 4.0 pp, medium confidence |
| Vals SWE-bench | 69.4% | measured |
| Terminal-Bench 2.1 (Vals AI) | 35.5% | estimated ± 6.4 pp, medium confidence |
| VulcanBench v3 | 82.0% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 36.1% | estimated ± 6.4 pp, medium confidence |
| AA Cyber Index | 26.8% | estimated ± 13.5 pp, low confidence |
| DeepsecBench-AA | 1.5% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 52.6% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 57.3% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 36.4% | estimated ± 2.8 pp, high confidence |
| CursorBench 4.0 | 30.8% | estimated ± 3.4 pp, medium confidence |
| CWE-bench v1 | 35.2% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 56.3% | estimated ± 7.2 pp, low confidence |
| DRACO | 73.1% | estimated ± 2.0 pp, medium confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| HLE w/o tools | 26.3% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.1 Offline | 2.8% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 14.8% | estimated ± 3.7 pp, medium confidence |
| SpireClimb | 0.0% | estimated ± 10.3 pp, low confidence |
| StealthMark | 37.5% | estimated ± 9.7 pp, low confidence |
| Toolathlon-Verified | 51.9% | estimated ± 3.1 pp, medium confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| MKA | 21.7% | estimated ± 6.4 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 49.4% | estimated ± 6.2 pp, medium confidence |
| BinaryAudit | 24.6% | measured |
| OTelBench | 13.0% | measured |
| Vibe Code Bench | 20.6% | estimated ± 6.6 pp, low confidence |
| FACTS Multimodal | 36.6% | estimated ± 5.6 pp, medium confidence |
| Hermes Bench | 56.4% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 23.5% | estimated ± 8.7 pp, medium confidence |
| ExploitBench | 21.4% | estimated ± 13.4 pp, low confidence |
| ExploitGym | 1.1% | estimated ± 10.6 pp, low confidence |
| C-Eval | 91.6% | estimated ± 0.9 pp, medium confidence |
| Claw-Eval | 62.7% | estimated ± 6.4 pp, low confidence |
| DeepPlanning | 26.2% | estimated ± 9.1 pp, low confidence |
| HMMT Feb 2025 | 97.1% | measured |
| HMMT Feb 2026 | 87.4% | estimated ± 1.2 pp, medium confidence |
| HMMT Nov 2025 | 94.9% | estimated ± 1.5 pp, high confidence |
| MCP Atlas | 48.8% | estimated ± 10.3 pp, low confidence |
| MMAnswerBench | 82.9% | estimated ± 2.0 pp, low confidence |
| MMLU-Redux | 92.8% | estimated ± 0.6 pp, high confidence |
| NL2Repo | 36.1% | estimated ± 3.4 pp, high confidence |
| PostTrainBench v1 | 11.2% | estimated ± 3.6 pp, medium confidence |
| QwenClawBench | 52.0% | estimated ± 2.0 pp, low confidence |
| SuperGPQA | 65.6% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.0 | 41.0% | measured |
| Toolathlon | 26.1% | estimated ± 4.2 pp, medium confidence |
| AA LiveCodeBench | 89.4% | measured |
| HealthBench Hard | 13.9% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 83.5% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 76.9% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 16.0% | estimated ± 2.2 pp, medium confidence |
| SWE-Rebench | 58.7% | measured |
| PostTrainBench | 12.4% | 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 |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 36.1% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 48.8% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 47.5% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 23.8% | estimated ± 7.1 pp, low confidence |
| LABBench2 | 79.0% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, medium confidence |
| Cookie-Bench | 77.3% | estimated ± 2.5 pp, medium confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 30.9% | estimated ± 4.3 pp, medium confidence |
| LiveCodeBench | 75.4% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench v1.0 | 45.3% | estimated ± 2.8 pp, medium confidence |
| SEC-Bench Pro | 31.8% | estimated ± 12.3 pp, low confidence |
| MRCRv2 | 77.6% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.0% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |
| LifeVal | 20.7% | estimated ± 1.6 pp, low confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |
| PinchBench | 88.0% | estimated ± 3.6 pp, medium confidence |