Alibaba
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Qwen model releasesRank #292 across 566
No rank
Rank #202 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 14.3 | #292 |
| Artificial Analysis Math Index | math | 70.7 | #95 |
| MMLU-Pro | reasoning | 82.3% | #75 |
| GPQA | reasoning | 71.2% | #245 |
| Humanity's Last Exam |
| reasoning |
| 6.3% |
| #288 |
| LiveCodeBench | coding | 59.4% | #117 |
| SciCode | coding, reasoning | 35.9% | #228 |
| Output Speed | speed | 49.7 tok/s | #264 |
| Time to First Token | speed | 1.07s | #154 |
| Blended Price | cost | $1.23/M | #202 |
| Input Price | cost | $0.700/M | #210 |
| Output Price | cost | $2.80/M | #203 |
| Value Index | cost, overall | 11.7 | #226 |