Qwen: Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.3 |
| Output / 1M | $3 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $3.30 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | always on |
| Open weights | yes |
| Released | 2025-07-25 |
| Knowledge cutoff | 2025-06-30 |
| Retires | — |
| Catalog id | qwen/qwen3-235b-a22b-thinking-2507 |
Benchmarks
| source | epoch |
|---|---|
| gpqa | 0.801 |
| gpqaStderr | 0.026 |
| aime | 0.867 |
| aimeStderr | 0.0512 |
| simpleQA | 0.501 |
| simpleQAStderr | 0.0158 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.