Zhipu (GLM) · model
GLM-4.6 benchmark scores
As of 2026-10-07, GLM-4.6 (Zhipu (GLM)) has measured scores on 14 benchmarks and estimated scores on 48 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 63.2% | measured |
| AA-HLE | 5.5% | measured |
| AA-SciCode | 46.2% | estimated ± 3.8 pp, high confidence |
| AIME26 | 95.5% | estimated ± 0.6 pp, medium confidence |
| Artificial Analysis Intelligence Index | 14.9% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 10.7% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 81.4% | estimated ± 1.7 pp, medium confidence |
| HLE | 19.0% | estimated ± 9.5 pp, medium confidence |
| IFBench | 55.6% | estimated ± 6.9 pp, low confidence |
| AA-LCR | 26.3% | measured |
| AA-Omniscience Accuracy | 21.4% | measured |
| SciCode | 38.8% | estimated ± 2.9 pp, low confidence |
| IFEval | 86.9% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 0.0% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 76.9% | measured |
| AA Coding Index | 40.3% | estimated ± 6.8 pp, medium confidence |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 28.3% | estimated ± 5.9 pp, low confidence |
| SWE-bench Verified | 72.2% | estimated ± 4.4 pp, high confidence |
| BFCL v4 | 54.5% | estimated ± 9.8 pp, low confidence |
| SWE-bench Pro | 50.3% | estimated ± 2.1 pp, high confidence |
| AA Agentic Index | 17.8% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 85.2% | estimated ± 3.5 pp, high confidence |
| FrontierMath v2 (Tier 4) | 2.1% | measured |
| FrontierMath v2 (Tiers 1-3) | 3.8% | measured |
| GPQA | 86.2% | estimated ± 1.6 pp, high confidence |
| AA-IFBench | 36.7% | measured |
| AA EnterpriseOps-Gym | 18.8% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 17.6% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 12.6 pp, low confidence |
| CursorBench 3.2 | 59.1% | estimated ± 7.2 pp, low confidence |
| FrontierCode 1.1 Main | 1.2% | estimated ± 4.3 pp, low confidence |
| Vals GPQA Diamond | 74.5% | measured |
| Vals LiveCodeBench | 81.0% | measured |
| Vals MMLU-Pro | 82.2% | measured |
| Vals SWE-bench | 63.8% | estimated ± 6.3 pp, medium confidence |
| VulcanBench v3 | 81.4% | estimated ± 5.6 pp, low confidence |
| AA ITBench | 62.1% | estimated ± 3.6 pp, low confidence |
| HLE w/o tools | 26.0% | estimated ± 5.1 pp, medium confidence |
| PostTrainBench v1.1 | 19.9% | estimated ± 10.5 pp, low confidence |
| Vibe Code Bench | 3.1% | measured |
| C-Eval | 88.4% | estimated ± 1.0 pp, low confidence |
| HMMT Nov 2025 | 96.7% | estimated ± 2.6 pp, medium confidence |
| MCP-Tasks | 77.8% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 82.4% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 93.7% | estimated ± 1.1 pp, medium confidence |
| SuperGPQA | 66.0% | estimated ± 7.5 pp, medium confidence |
| HealthBench Hard | 1.6% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 27.9% | estimated ± 3.0 pp, low confidence |
| SWE-Rebench | 0.0% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| FrontierMath (legacy) | 4.9% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 8.6% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 49.9% | estimated ± 1.3 pp, low confidence |
| HealthBench Professional (raw) | 22.6% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 78.7% | estimated ± 1.8 pp, low confidence |
| MMLU | 87.1% | estimated ± 1.1 pp, medium confidence |