# Qwen3-VL-235B-A22B Instruct benchmark scores

Alibaba (Qwen) · model · https://benchgap.net/model/qwen3-vl-235b-a22b-instruct · data retrieved 2026-11-19

As of 2026-11-19, Qwen3-VL-235B-A22B Instruct (Alibaba (Qwen)) has measured scores on 8 benchmarks and estimated scores on 20 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-MMMU-Pro](https://benchgap.net/b/aa-mmmu-pro/current.md) | 67.4% | estimated ± 1.5 pp, high confidence |
| [MMMU](https://benchgap.net/b/mmmu/current.md) | 78.7% | measured |
| [ParseBench-1](https://benchgap.net/b/parse-bench-llama-index/current.md) | 50.0% | estimated ± 5.2 pp, low confidence |
| [ParseBench-2](https://benchgap.net/b/parsebench/current.md) | 55.7% | estimated ± 5.0 pp, medium confidence |
| [CharXiv](https://benchgap.net/b/charxiv/current.md) | 72.5% | estimated ± 3.3 pp, high confidence |
| [CharXiv w/o tools](https://benchgap.net/b/charxivnotools/current.md) | 74.2% | estimated ± 2.1 pp, high confidence |
| [AI2D_TEST](https://benchgap.net/b/ai2dtest/current.md) | 87.8% | estimated ± 1.4 pp, medium confidence |
| [CountBench](https://benchgap.net/b/countbench/current.md) | 97.4% | estimated ± 1.6 pp, low confidence |
| [DynaMath](https://benchgap.net/b/dynamath/current.md) | 79.1% | estimated ± 1.0 pp, medium confidence |
| [ERQA](https://benchgap.net/b/erqa/current.md) | 53.8% | estimated ± 4.2 pp, high confidence |
| [MathVision](https://benchgap.net/b/mathvision/current.md) | 76.0% | estimated ± 2.9 pp, high confidence |
| [MLVU (M-Avg)](https://benchgap.net/b/mlvuavg/current.md) | 81.5% | estimated ± 2.2 pp, high confidence |
| [MMMU-Pro](https://benchgap.net/b/mmmu-pro/current.md) | 68.1% | measured |
| [OmniDocBench 1.5](https://benchgap.net/b/omnidocbench15/current.md) | 90.7% | estimated ± 1.5 pp, low confidence |
| [RealWorldQA](https://benchgap.net/b/realworldqa/current.md) | 79.3% | measured |
| [ScreenSpot Pro](https://benchgap.net/b/screenspot-pro/current.md) | 62.0% | measured |
| [SimpleVQA](https://benchgap.net/b/simplevqa/current.md) | 59.2% | estimated ± 7.1 pp, medium confidence |
| [V*](https://benchgap.net/b/vstar/current.md) | 90.9% | estimated ± 6.5 pp, low confidence |
| [Video-MME (w/o subtitle)](https://benchgap.net/b/videommenosub/current.md) | 79.2% | measured |
| [Video-MME (with subtitle)](https://benchgap.net/b/videommewithsub/current.md) | 82.0% | estimated ± 3.0 pp, high confidence |
| [VideoMMMU](https://benchgap.net/b/videommmu/current.md) | 74.7% | measured |
| [We-Math](https://benchgap.net/b/wemath/current.md) | 75.6% | estimated ± 5.5 pp, low confidence |
| [MedXpertQA (MM)](https://benchgap.net/b/medxpertqamm/current.md) | 46.1% | estimated ± 2.4 pp, medium confidence |
| [MMVU](https://benchgap.net/b/mmvu/current.md) | 70.9% | estimated ± 2.7 pp, medium confidence |
| [CC-OCR](https://benchgap.net/b/ccocr/current.md) | 82.2% | measured |
| [RefCOCO (avg)](https://benchgap.net/b/refcocoavg/current.md) | 93.5% | estimated ± 1.8 pp, low confidence |
| [OCRBench V2](https://benchgap.net/b/ocrbenchv2/current.md) | 67.1% | measured |
| [MMMU-Pro w/ Python](https://benchgap.net/b/mmmupropython/current.md) | 74.1% | estimated ± 2.6 pp, high confidence |
