← All benchmarks
Qwen3 4B 2507 (Reasoning)
Alibaba · Released 2025-08-06 · Independent benchmark scores from Artificial Analysis
Intelligence Index
8.8
Output speed
0.0
tokens/sec
Blended price
$0.00
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | 2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb |
|---|---|
| Slug | qwen3-4b-2507-instruct-reasoning |
| Release date | 2025-08-06 |
| Provider | Alibaba |
| Provider slug | alibaba |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $0.00 |
| Input price ($/1M) | $0.00 |
| Output price ($/1M) | $0.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 82.7% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 8.80 |
| artificial analysis math index | 82.70 |
| gpqa | 66.7% |
| hle | 6.2% |
| ifbench | 49.8% |
| lcr | 37.3% |
| livecodebench | 64.1% |
| math 500 | — |
| mmlu pro | 74.3% |
| scicode | — |
| tau banking | — |
| tau2 | 25.4% |
| terminalbench hard | 1.5% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning
Benchmark data from Artificial Analysis.