← All comparisons
GPT-5.4 nano (medium) vs Qwen3 30B A3B 2507 (Reasoning)
OpenAI vs Alibaba — side-by-side benchmark comparison
| GPT-5.4 nano (medium) | Qwen3 30B A3B 2507 (Reasoning) | |
|---|---|---|
| Intelligence Index | 38.1 | 22.4 |
| Coding Index | 35.0 | 14.6 |
| Math Index | — | 56.3 |
| Output speed (tok/s) | 152.6 | 155.3 |
| Blended price ($/1M) | $0.46 | $0.67 |
| Time to first token (s) | 2.09s | 1.02s |
| aime | — | 90.7% |
| aime 25 | — | 56.3% |
| artificial analysis coding index | 35.00 | 14.60 |
| artificial analysis intelligence index | 38.10 | 22.40 |
| artificial analysis math index | — | 56.30 |
| gpqa | 76.1% | 70.7% |
| hle | 14.7% | 9.8% |
| ifbench | 64.4% | 50.7% |
| lcr | 57.3% | 59.0% |
| livecodebench | — | 70.7% |
| math 500 | — | 97.6% |
| mmlu pro | — | 80.5% |
| scicode | 38.4% | 33.3% |
| tau2 | 52.6% | 28.1% |
| terminalbench hard | 33.3% | 5.3% |
Benchmark data from Artificial Analysis.