Alibaba (Qwen) · model
Qwen2.5-VL-32B benchmark scores
As of 2026-10-10, Qwen2.5-VL-32B (Alibaba (Qwen)) has measured scores on 3 benchmarks and estimated scores on 41 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 45.3% | estimated ± 4.7 pp, high confidence |
| AA-HLE | 5.1% | estimated ± 5.3 pp, medium confidence |
| Artificial Analysis Intelligence Index | 8.8% | estimated ± 6.3 pp, medium confidence |
| CritPt | 0.6% | estimated ± 3.8 pp, high confidence |
| GPQA Diamond | 46.0% | estimated ± 0.4 pp, high confidence |
| HLE | 0.5% | estimated ± 6.4 pp, low confidence |
| AA-Omniscience Accuracy | 10.3% | estimated ± 8.5 pp, low confidence |
| AA-MMMU-Pro | 49.6% | estimated ± 4.5 pp, high confidence |
| MMLU-Pro | 68.8% | measured |
| GPQA | 46.0% | measured |
| ARC-AGI-1 | 0.0% | estimated ± 6.9 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 pp, low confidence |
| Vals GPQA Diamond | 27.7% | estimated ± 4.8 pp, medium confidence |
| Vals MMLU-Pro | 0.2% | estimated ± 1.2 pp, medium confidence |
| HLE w/o tools | 6.1% | estimated ± 4.9 pp, medium confidence |
| CharXiv | 21.7% | estimated ± 5.2 pp, low confidence |
| CharXiv w/o tools | 51.4% | estimated ± 1.8 pp, low confidence |
| AI2D_TEST | 74.1% | estimated ± 2.0 pp, low confidence |
| C-Eval | 70.7% | estimated ± 1.3 pp, low confidence |
| CountBench | 90.1% | estimated ± 5.5 pp, low confidence |
| DynaMath | 41.4% | estimated ± 2.7 pp, low confidence |
| ERQA | 1.6% | estimated ± 5.3 pp, low confidence |
| MathVision | 53.2% | estimated ± 3.3 pp, medium confidence |
| MLVU (M-Avg) | 70.5% | estimated ± 2.7 pp, low confidence |
| MMLU-Redux | 83.7% | estimated ± 0.6 pp, high confidence |
| MMMU | 65.0% | estimated ± 1.0 pp, high confidence |
| MMMU-Pro | 49.5% | measured |
| RealWorldQA | 76.9% | estimated ± 6.8 pp, medium confidence |
| ScreenSpot Pro | 15.5% | estimated ± 10.0 pp, low confidence |
| SimpleVQA | 48.4% | estimated ± 7.5 pp, medium confidence |
| SuperGPQA | 37.8% | estimated ± 8.2 pp, low confidence |
| Video-MME (w/o subtitle) | 68.8% | estimated ± 1.8 pp, low confidence |
| Video-MME (with subtitle) | 65.4% | estimated ± 2.4 pp, medium confidence |
| VideoMMMU | 84.1% | estimated ± 0.9 pp, medium confidence |
| We-Math | 61.2% | estimated ± 6.2 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| MedXpertQA (MM) | 10.2% | estimated ± 2.4 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| HealthBench Professional | 1.5% | estimated ± 4.8 pp, low confidence |
| MMLU | 83.3% | estimated ± 2.2 pp, high confidence |
| SimpleQA | 16.1% | estimated ± 10.9 pp, low confidence |
| MMVU | 72.5% | estimated ± 1.7 pp, low confidence |
| MMMU-Pro w/ Python | 62.5% | estimated ± 0.6 pp, medium confidence |
| BBH | 98.2% | estimated ± 3.2 pp, low confidence |