Alibaba
A new generation of open-source, non-thinking mode model powered by Qwen3. This version demonstrates superior Chinese text understanding, augmented logical reasoning, and enhanced capabilities in text generation tasks over the previous iteration (Qwen3-235B-A22B-Instruct-2507).
Qwen model releasesRank #243 across 526
Rank #260 across 436
Rank #196 across 357
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 | 20.1 | #243 |
| Artificial Analysis Coding Index | coding | 15.3 | #260 |
| Artificial Analysis Math Index | math | 66.3 | #105 |
| MMLU-Pro | reasoning | 81.9% | #80 |
| reasoning |
| 73.8% |
| #185 |
| Humanity's Last Exam | reasoning | 7.3% | #217 |
| LiveCodeBench | coding | 68.4% | #82 |
| SciCode | coding, reasoning | 30.7% | #256 |
| Output Speed | speed | 131.1 tok/s | #99 |
| Time to First Token | speed | 1.06s | #134 |
| Blended Price | cost | $0.875/M | #196 |
| Input Price | cost | $0.500/M | #197 |
| Output Price | cost | $2.00/M | #185 |
| Value Index | cost, overall | 23.0 | #209 |