Alibaba
Qwen3.6 Max Preview
Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.
Qwen model releasesModel Snapshot
TypeLanguage
ReleaseApr 20, 2026
Context240,000
Tagsreasoning, tool-use, implicit-caching, file-input
Overall
Rank #13 across 526
51.8
Coding
Rank #33 across 436
44.9
Blended Price
Rank #266 across 357
$2.93/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed40.9 tok/s
First Token1.91s
Max Output64,000
Pricing
Blended$2.93/M
Input$1.30/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 51.8 | #13 |
| Artificial Analysis Coding Index | coding | 44.9 | #33 |
| GPQA | reasoning | 88.8% | #29 |
| Humanity's Last Exam | reasoning | 28.9% | #35 |
| SciCode |