Alibaba
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Qwen model releasesRank #360 across 566
No rank
Rank #94 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 | 10.0 | #360 |
| Artificial Analysis Math Index | math | 72.3 | #91 |
| MMLU-Pro | reasoning | 76.4% | #165 |
| GPQA | reasoning | 69.5% | #260 |
| Humanity's Last Exam |
| reasoning |
| 6.4% |
| #283 |
| LiveCodeBench | coding | 47.6% | #155 |
| SciCode | coding, reasoning | 30.8% | #290 |
| Output Speed | speed | 117.9 tok/s | #114 |
| Time to First Token | speed | 0.97s | #127 |
| Blended Price | cost | $0.350/M | #94 |
| Input Price | cost | $0.200/M | #94 |
| Output Price | cost | $0.800/M | #103 |
| Value Index | cost, overall | 28.6 | #123 |