Alibaba
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
Qwen model releasesRank #176 across 566
No rank
Rank #249 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 | 25.0 | #176 |
| Artificial Analysis Math Index | math | 82.3 | #59 |
| MMLU-Pro | reasoning | 82.4% | #74 |
| GPQA | reasoning | 77.6% | #172 |
| Humanity's Last Exam |
| reasoning |
| 12.0% |
| #171 |
| LiveCodeBench | coding | 53.5% | #138 |
| SciCode | coding, reasoning | 38.7% | #171 |
| Output Speed | speed | 51.1 tok/s | #261 |
| Time to First Token | speed | 1.68s | #216 |
| Blended Price | cost | $2.40/M | #249 |
| Input Price | cost | $1.20/M | #242 |
| Output Price | cost | $6.00/M | #260 |
| Value Index | cost, overall | 10.4 | #234 |