Alibaba
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
Qwen model releasesRank #407 across 566
Rank #206 across 222
Rank #133 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 | 8.3 | #407 |
| Artificial Analysis Coding Index | coding | 9.0 | #206 |
| Artificial Analysis Math Index | math | 19.0 | #212 |
| MMLU-Pro | reasoning | 74.3% | #195 |
| reasoning |
| 58.9% |
| #341 |
| Humanity's Last Exam | reasoning | 4.2% | #456 |
| LiveCodeBench | coding | 40.6% | #177 |
| SciCode | coding, reasoning | 22.6% | #405 |
| MATH-500 | math | 90.4% | #71 |
| AIME | math | 74.7% | #33 |
| Output Speed | speed | 64.5 tok/s | #208 |
| Time to First Token | speed | 1.39s | #197 |
| Blended Price | cost | $0.660/M | #133 |
| Input Price | cost | $0.180/M | #75 |
| Output Price | cost | $2.10/M | #163 |
| Value Index | cost, overall | 12.6 | #215 |