← All comparisons
Qwen3.5 122B A10B (Non-reasoning) vs GPT-5 (ChatGPT)
Alibaba vs OpenAI — side-by-side benchmark comparison
| Qwen3.5 122B A10B (Non-reasoning) | GPT-5 (ChatGPT) | |
|---|---|---|
| Intelligence Index | 35.9 | 21.8 |
| Coding Index | 31.6 | 21.2 |
| Math Index | — | 48.3 |
| Output speed (tok/s) | 165.9 | 208.2 |
| Blended price ($/1M) | $1.10 | $3.44 |
| Time to first token (s) | 1.06s | 0.48s |
| aime | — | — |
| aime 25 | — | 48.3% |
| artificial analysis coding index | 31.60 | 21.20 |
| artificial analysis intelligence index | 35.90 | 21.80 |
| artificial analysis math index | — | 48.30 |
| gpqa | 82.7% | 68.6% |
| hle | 14.8% | 5.8% |
| ifbench | 50.8% | 45.0% |
| lcr | 56.0% | 63.7% |
| livecodebench | — | 54.3% |
| math 500 | — | — |
| mmlu pro | — | 82.0% |
| scicode | 35.6% | 37.8% |
| tau2 | 84.5% | 0.0% |
| terminalbench hard | 29.5% | 12.9% |
Benchmark data from Artificial Analysis.