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 #474 across 566
Rank #205 across 222
Rank #83 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 | 5.1 | #474 |
| Artificial Analysis Coding Index | coding | 9.0 | #205 |
| Artificial Analysis Math Index | math | 24.3 | #199 |
| MMLU-Pro | reasoning | 64.3% | #263 |
| reasoning |
| 45.2% |
| #424 |
| Humanity's Last Exam | reasoning | 2.8% | #533 |
| LiveCodeBench | coding | 20.2% | #269 |
| SciCode | coding, reasoning | 16.8% | #446 |
| MATH-500 | math | 82.8% | #102 |
| AIME | math | 24.3% | #95 |
| Output Speed | speed | 65.2 tok/s | #206 |
| Time to First Token | speed | 1.28s | #186 |
| Blended Price | cost | $0.310/M | #83 |
| Input Price | cost | $0.180/M | #74 |
| Output Price | cost | $0.700/M | #94 |
| Value Index | cost, overall | 16.5 | #187 |