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 #354 across 566
Rank #190 across 222
Rank #205 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 | 10.4 | #354 |
| Artificial Analysis Coding Index | coding | 13.8 | #190 |
| Artificial Analysis Math Index | math | 55.7 | #131 |
| MMLU-Pro | reasoning | 77.4% | #156 |
| reasoning |
| 60.4% |
| #329 |
| Humanity's Last Exam | reasoning | 4.3% | #442 |
| LiveCodeBench | coding | 52.3% | #142 |
| SciCode | coding, reasoning | 31.6% | #284 |
| MATH-500 | math | 96.1% | #34 |
| AIME | math | 76.3% | #29 |
| Output Speed | speed | 62.5 tok/s | #213 |
| Time to First Token | speed | 1.07s | #155 |
| Blended Price | cost | $1.31/M | #205 |
| Input Price | cost | $0.350/M | #145 |
| Output Price | cost | $4.20/M | #227 |
| Value Index | cost, overall | 7.9 | #267 |