Alibaba
Qwen3 235B A22B (Non-reasoning)
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Qwen model releasesModel Snapshot
ReleaseApr 28, 2025
Context131,072
Overall
Rank #346 across 566
10.9
Coding
No rank
n/a
Blended Price
Rank #199 across 371
$1.23/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 Speed65 tok/s
First Token1.14s
Max Output8,192
Pricing
Blended$1.23/M
Input$0.700/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 10.9 | #346 |
| Artificial Analysis Math Index | math | 23.7 | #202 |
| MMLU-Pro | reasoning | 76.2% | #170 |
| GPQA | reasoning | 61.3% | #323 |
| Humanity's Last Exam |