← All comparisons
GPT-5.4 nano (xhigh) vs Qwen3.5 0.8B (Non-reasoning)
OpenAI vs Alibaba — side-by-side benchmark comparison
| GPT-5.4 nano (xhigh) | Qwen3.5 0.8B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 44.0 | 9.9 |
| Coding Index | 43.9 | 1.0 |
| Math Index | — | — |
| Output speed (tok/s) | 150.8 | 96.3 |
| Blended price ($/1M) | $0.46 | $0.02 |
| Time to first token (s) | 2.87s | 0.26s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 43.90 | 100.0% |
| artificial analysis intelligence index | 44.00 | 9.90 |
| artificial analysis math index | — | — |
| gpqa | 81.7% | 23.6% |
| hle | 26.5% | 4.9% |
| ifbench | 75.9% | 21.6% |
| lcr | 66.0% | 6.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 46.9% | 2.9% |
| tau2 | 76.0% | 65.2% |
| terminalbench hard | 42.4% | 0.0% |
Benchmark data from Artificial Analysis.