← All comparisons
GPT-5.4 nano (medium) vs Qwen3.6 35B A3B (Reasoning)
OpenAI vs Alibaba — side-by-side benchmark comparison
| GPT-5.4 nano (medium) | Qwen3.6 35B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 38.1 | 43.5 |
| Coding Index | 35.0 | 35.2 |
| Math Index | — | — |
| Output speed (tok/s) | 152.6 | 159.1 |
| Blended price ($/1M) | $0.46 | $0.56 |
| Time to first token (s) | 2.09s | 1.50s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 35.00 | 35.20 |
| artificial analysis intelligence index | 38.10 | 43.50 |
| artificial analysis math index | — | — |
| gpqa | 76.1% | 84.1% |
| hle | 14.7% | 20.2% |
| ifbench | 64.4% | 64.4% |
| lcr | 57.3% | 63.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 38.4% | 35.8% |
| tau2 | 52.6% | 95.3% |
| terminalbench hard | 33.3% | 34.8% |
Benchmark data from Artificial Analysis.