Alibaba
Qwen3.5 397B A17B (Non-reasoning)
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Qwen model releasesModel Snapshot
ReleaseFeb 16, 2026
Context262,144
Overall
Rank #140 across 600
32.0
Coding
Rank #105 across 266
48.2
Blended Price
Rank #218 across 379
$1.35/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 Speed60.1 tok/s
First Token1.49s
Max Output65,536
Pricing
Blended$1.35/M
Input$0.600/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 32.0 | #140 |
| Artificial Analysis Coding Index | coding | 48.2 | #105 |
| GPQA | reasoning | 86.1% | #84 |
| Humanity's Last Exam | reasoning | 18.8% | #125 |
| SciCode |