← All benchmarks
Qwen3 235B A22B 2507 (Reasoning)
Alibaba · Released 2025-07-25 · Independent benchmark scores from Artificial Analysis
Intelligence Index
19.6
Output speed
0.0
tokens/sec
Blended price
$2.63
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | f6ccbe1d-bd7e-484b-9795-18cc9f91552d |
|---|---|
| Slug | qwen3-235b-a22b-instruct-2507-reasoning |
| Release date | 2025-07-25 |
| Provider | Alibaba |
| Provider slug | alibaba |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $2.63 |
| Input price ($/1M) | $0.70 |
| Output price ($/1M) | $8.40 |
All evaluation scores (17)
| aime | 94.0% |
|---|---|
| aime 25 | 91.0% |
| artificial analysis coding index | 22.10 |
| artificial analysis intelligence index | 19.60 |
| artificial analysis math index | 91.00 |
| gpqa | 79.0% |
| hle | 15.0% |
| ifbench | 51.2% |
| lcr | 67.0% |
| livecodebench | 78.8% |
| math 500 | 98.4% |
| mmlu pro | 84.3% |
| scicode | 42.4% |
| tau banking | 7.8% |
| tau2 | 53.2% |
| terminalbench hard | 13.6% |
| terminalbench v2 1 | 12.0% |
Source: artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning
Benchmark data from Artificial Analysis.