Alibaba
Qwen3.5 122B A10B (Reasoning)
The Qwen3.5 122B-A10B 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. In terms of...
Qwen model releasesModel Snapshot
ReleaseFeb 24, 2026
Context262,144
Overall
Rank #138 across 600
32.3
Coding
Rank #115 across 266
45.7
Blended Price
Rank #199 across 379
$1.10/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 Speed138.1 tok/s
First Token1.00s
Max Output65,536
Pricing
Blended$1.10/M
Input$0.400/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 32.3 | #138 |
| Artificial Analysis Coding Index | coding | 45.7 | #115 |
| GPQA | reasoning | 85.7% | #90 |
| Humanity's Last Exam | reasoning | 23.4% | #100 |
| SciCode |