Alibaba
Qwen3 235B A22B 2507 (Reasoning)
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
Qwen model releasesModel Snapshot
ReleaseJul 25, 2025
Context262,144
Overall
Rank #227 across 566
19.6
Coding
Rank #158 across 222
22.1
Blended Price
Rank #253 across 371
$2.63/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 Speed58.3 tok/s
First Token1.18s
Max Output16,384
Pricing
Blended$2.63/M
Input$0.700/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 19.6 | #227 |
| Artificial Analysis Coding Index | coding | 22.1 | #158 |
| Artificial Analysis Math Index | math | 91.0 | #22 |
| MMLU-Pro | reasoning | 84.3% | #43 |