Alibaba
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...
Qwen model releasesRank #403 across 566
No rank
Rank #84 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 | 8.4 | #403 |
| Artificial Analysis Math Index | math | 27.3 | #191 |
| MMLU-Pro | reasoning | 68.6% | #241 |
| GPQA | reasoning | 42.7% | #435 |
| Humanity's Last Exam |
| reasoning |
| 2.9% |
| #531 |
| LiveCodeBench | coding | 33.2% | #208 |
| SciCode | coding, reasoning | 17.4% | #442 |
| Output Speed | speed | 135.8 tok/s | #92 |
| Time to First Token | speed | 1.02s | #145 |
| Blended Price | cost | $0.310/M | #84 |
| Input Price | cost | $0.180/M | #76 |
| Output Price | cost | $0.700/M | #95 |
| Value Index | cost, overall | 27.1 | #126 |