← All comparisons
Qwen3.5 0.8B (Reasoning) vs GPT-5.4 (Non-reasoning)
Alibaba vs OpenAI — side-by-side benchmark comparison
| Qwen3.5 0.8B (Reasoning) | GPT-5.4 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 10.5 | 35.4 |
| Coding Index | 0.0 | 41.0 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 70.9 |
| Blended price ($/1M) | $0.02 | $5.63 |
| Time to first token (s) | 0.00s | 0.60s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 0.0% | 41.00 |
| artificial analysis intelligence index | 10.50 | 35.40 |
| artificial analysis math index | — | — |
| gpqa | 11.1% | 74.8% |
| hle | 1.2% | 10.6% |
| ifbench | 21.5% | 48.4% |
| lcr | 5.3% | 47.3% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 0.0% | 47.1% |
| tau2 | 47.7% | 35.1% |
| terminalbench hard | 0.0% | 37.9% |
Benchmark data from Artificial Analysis.