Alibaba
The Qwen 3 series Max model has undergone specialized upgrades in agent programming and tool invocation compared to the preview version. The officially released model this time has achieved state-of-the-art (SOTA) performance in its field and is better suited to meet the demands of agents operating in more complex scenarios.
Qwen model releasesRank #136 across 526
Rank #154 across 436
Rank #275 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 | 31.4 | #136 |
| Artificial Analysis Coding Index | coding | 26.4 | #154 |
| Artificial Analysis Math Index | math | 80.7 | #63 |
| MMLU-Pro | reasoning | 84.1% | #43 |
| reasoning |
| 76.4% |
| #158 |
| Humanity's Last Exam | reasoning | 11.1% | #152 |
| LiveCodeBench | coding | 76.7% | #42 |
| SciCode | coding, reasoning | 38.3% | #148 |
| Output Speed | speed | 48.2 tok/s | #245 |
| Time to First Token | speed | 1.98s | #226 |
| Blended Price | cost | $3.05/M | #275 |
| Input Price | cost | $1.66/M | #283 |
| Output Price | cost | $7.23/M | #272 |
| Value Index | cost, overall | 10.3 | #269 |