← All comparisons
Qwen3.5 35B A3B (Non-reasoning) vs GPT-5 (low)
Alibaba vs OpenAI — side-by-side benchmark comparison
| Qwen3.5 35B A3B (Non-reasoning) | GPT-5 (low) | |
|---|---|---|
| Intelligence Index | 30.7 | 39.2 |
| Coding Index | 16.8 | 30.7 |
| Math Index | — | 83.0 |
| Output speed (tok/s) | 147.9 | 88.9 |
| Blended price ($/1M) | $0.69 | $3.44 |
| Time to first token (s) | 1.18s | 8.32s |
| aime | — | 83.0% |
| aime 25 | — | 83.0% |
| artificial analysis coding index | 16.80 | 30.70 |
| artificial analysis intelligence index | 30.70 | 39.20 |
| artificial analysis math index | — | 83.00 |
| gpqa | 81.9% | 80.8% |
| hle | 12.8% | 18.4% |
| ifbench | 44.5% | 66.6% |
| lcr | 55.3% | 58.7% |
| livecodebench | — | 76.3% |
| math 500 | — | 98.7% |
| mmlu pro | — | 86.0% |
| scicode | 29.3% | 39.1% |
| tau2 | 86.3% | 84.2% |
| terminalbench hard | 10.6% | 26.5% |
Benchmark data from Artificial Analysis.