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 #507 across 600
Rank #247 across 266
Rank #85 across 379
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 5.1 | #507 |
| Artificial Analysis Coding Index | coding | 9.0 | #247 |
| Artificial Analysis Math Index | math | 24.3 | #199 |
| MMLU-Pro | reasoning | 64.3% | #226 |
| reasoning |
| 45.2% |
| #438 |
| Humanity's Last Exam | reasoning | 2.8% | #548 |
| LiveCodeBench | coding | 20.2% | #269 |
| SciCode | coding, reasoning | 16.8% | #460 |
| MATH-500 | math | 82.8% | #102 |
| AIME | math | 24.3% | #95 |
| Blended Price | cost | $0.310/M | #85 |
| Input Price | cost | $0.180/M | #76 |
| Output Price | cost | $0.700/M | #96 |
| Value Index | cost, overall | 16.5 | #196 |