Alibaba
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Qwen model releasesRank #433 across 566
Rank #191 across 222
Rank #132 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 | 7.0 | #433 |
| Artificial Analysis Coding Index | coding | 13.8 | #191 |
| Artificial Analysis Math Index | math | 58.0 | #121 |
| MMLU-Pro | reasoning | 67.5% | #248 |
| reasoning |
| 47.0% |
| #415 |
| Humanity's Last Exam | reasoning | 4.2% | #457 |
| LiveCodeBench | coding | 28.0% | #236 |
| SciCode | coding, reasoning | 26.5% | #359 |
| MATH-500 | math | 87.1% | #86 |
| AIME | math | 28.0% | #89 |
| Output Speed | speed | 62.1 tok/s | #214 |
| Time to First Token | speed | 0.99s | #131 |
| Blended Price | cost | $0.612/M | #132 |
| Input Price | cost | $0.350/M | #146 |
| Output Price | cost | $1.40/M | #137 |
| Value Index | cost, overall | 11.4 | #227 |