← All benchmarks
Qwen3.5 4B (Non-reasoning)
Alibaba · Released 2026-03-02 · Independent benchmark scores from Artificial Analysis
Intelligence Index
10.8
Output speed
16.8
tokens/sec
Blended price
$0.06
per 1M tokens
Time to first token
0.67s
Model metadata
| Model ID | 30c9ba61-d0a1-4794-938e-35865f379d15 |
|---|---|
| Slug | qwen3-5-4b-non-reasoning |
| Release date | 2026-03-02 |
| Provider | Alibaba |
| Provider slug | alibaba |
| Output speed | 16.8 tok/s |
| Time to first token | 0.67s |
| Time to first answer | 0.67s |
| Blended price ($/1M) | $0.06 |
| Input price ($/1M) | $0.03 |
| Output price ($/1M) | $0.15 |
All evaluation scores (18)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 20.30 |
| artificial analysis intelligence index | 10.80 |
| artificial analysis math index | — |
| gpqa | 71.2% |
| hle | 8.0% |
| ifbench | 33.3% |
| lcr | 34.7% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | — |
| tau banking | 4.3% |
| tau2 | 87.7% |
| terminalbench hard | 11.4% |
| terminalbench v2 1 | 21.3% |
| terminalbench v4 0 | — |
Source: artificialanalysis.ai/models/qwen3-5-4b-non-reasoning
Benchmark data from Artificial Analysis.