Alibaba
Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.
Qwen model releasesRank #30 across 687
Rank #23 across 330
Rank #313 across 432
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 | 45.4 | #30 |
| Artificial Analysis Coding Index | coding | 76.2 | #23 |
| LiveBench Mathematics | math | 91.3% | #20 |
| GPQA | reasoning | 92.8% | #31 |
| Humanity's Last Exam |
| reasoning |
| 43.1% |
| #44 |
| SciCode | coding, reasoning | 52.1% | #69 |
| Output Speed | speed | 41.6 tok/s | #169 |
| Time to First Token | speed | 1.95s | #111 |
| Blended Price | cost | $3.00/M | #313 |
| Input Price | cost | $2.00/M | #358 |
| Output Price | cost | $6.00/M | #308 |
| Value Index | cost, overall | 15.1 | #226 |