Zhipu (GLM) · model
GLM-4.6V benchmark scores
As of 2026-11-19, GLM-4.6V (Zhipu (GLM)) has measured scores on 4 benchmarks and estimated scores on 20 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-MMMU-Pro | 65.3% | estimated ± 1.5 pp, high confidence |
| MMMU | 76.0% | measured |
| ParseBench-1 | 45.8% | estimated ± 8.4 pp, medium confidence |
| ParseBench-2 | 53.2% | estimated ± 5.0 pp, medium confidence |
| CharXiv | 61.7% | estimated ± 5.1 pp, medium confidence |
| CharXiv w/o tools | 73.4% | estimated ± 2.1 pp, high confidence |
| AI2D_TEST | 89.7% | estimated ± 2.0 pp, high confidence |
| CountBench | 94.1% | estimated ± 3.0 pp, high confidence |
| DynaMath | 82.5% | estimated ± 5.3 pp, low confidence |
| ERQA | 47.1% | estimated ± 5.2 pp, low confidence |
| MathVision | 73.6% | estimated ± 2.9 pp, high confidence |
| MLVU (M-Avg) | 80.5% | estimated ± 2.2 pp, high confidence |
| MMMU-Pro | 66.0% | measured |
| RealWorldQA | 81.2% | estimated ± 2.8 pp, high confidence |
| ScreenSpot Pro | 55.3% | estimated ± 7.9 pp, low confidence |
| SimpleVQA | 57.0% | estimated ± 7.1 pp, medium confidence |
| Video-MME (w/o subtitle) | 76.8% | estimated ± 1.2 pp, high confidence |
| Video-MME (with subtitle) | 80.9% | estimated ± 3.0 pp, high confidence |
| VideoMMMU | 74.7% | measured |
| We-Math | 77.8% | estimated ± 7.2 pp, low confidence |
| MedXpertQA (MM) | 40.9% | estimated ± 2.4 pp, medium confidence |
| MMVU | 69.4% | estimated ± 2.7 pp, medium confidence |
| OCRBench V2 | 65.1% | measured |
| MMMU-Pro w/ Python | 72.7% | estimated ± 2.6 pp, medium confidence |