← All comparisons
Qwen3.5 2B (Non-reasoning) vs GPT-4o (ChatGPT)
Alibaba vs OpenAI — side-by-side benchmark comparison
| Qwen3.5 2B (Non-reasoning) | GPT-4o (ChatGPT) | |
|---|---|---|
| Intelligence Index | 14.7 | 14.1 |
| Coding Index | 4.9 | — |
| Math Index | — | — |
| Output speed (tok/s) | 272.0 | 0.0 |
| Blended price ($/1M) | $0.04 | $0.00 |
| Time to first token (s) | 0.27s | 0.00s |
| aime | — | 10.3% |
| aime 25 | — | — |
| artificial analysis coding index | 4.90 | — |
| artificial analysis intelligence index | 14.70 | 14.10 |
| artificial analysis math index | — | — |
| gpqa | 43.8% | 51.1% |
| hle | 4.9% | 3.7% |
| ifbench | 29.1% | — |
| lcr | 13.7% | 53.0% |
| livecodebench | — | — |
| math 500 | — | 79.7% |
| mmlu pro | — | 77.3% |
| scicode | 7.2% | 33.4% |
| tau2 | 81.6% | — |
| terminalbench hard | 3.8% | — |
Benchmark data from Artificial Analysis.