Model card
Qwen3-VL-235B-A22B-Instruct.
QwenLarge language model1 current SOTA
Added from Papers with Code MMLU-Pro refresh on 2026-05-19.
§ 02 · Benchmarks
Every benchmark Qwen3-VL-235B-A22B-Instruct has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | DocVQA | Computer Vision · Document Understanding | anls | 97.1% | #1 | — | source ↗ |
| 02 | MVBench | Multimodal · Video Understanding | accuracy | 76.5% | #4 | — | source ↗ |
| 03 | MMBench | Multimodal · Visual Question Answering | accuracy | 89.3% | #5 | — | source ↗ |
| 04 | Video-MME | Multimodal · Video Understanding | accuracy | 79.2% | #7 | — | source ↗ |
| 05 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 79.2% | #9 | — | source ↗ |
| 06 | MMStar | Multimodal · Image-Text-to-Text | accuracy | 78.4% | #10 | — | source ↗ |
| 07 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 78.7% | #12 | — | source ↗ |
| 08 | AIME 2025 | Reasoning · Mathematical Reasoning | accuracy | 74.7% | #17 | — | source ↗ |
| 09 | OSWorld | Agentic AI · Web & Desktop Agents | success-rate | 31.6% | #18 | — | source ↗ |
| 10 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 68.1% | #19 | — | source ↗ |
| 11 | LiveCodeBench | Computer Code · Code Generation | pass-1 | 54.3% | #22 | — | source ↗ |
| 12 | MMLU-Pro | Reasoning · Commonsense Reasoning | accuracy | 81.8% | #41 | 2025-11-26 | source ↗ |
| 13 | MMLU-Pro | Reasoning · Commonsense Reasoning | accuracy | 81.8% | #41 | — | source ↗ |
| 14 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 74.3% | #42 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Qwen3-VL-235B-A22B-Instruct actually performs.
§ 04 · Papers
1 paper with results for Qwen3-VL-235B-A22B-Instruct.
- 2025-11-26· 13 results
Qwen3-VL Technical Report
§ 05 · Related models
Other Qwen models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
13
results
paperswithcode
1
result
0 of 14 rows marked verified.