← All comparisons
GPT-3.5 Turbo vs Qwen3 1.7B (Non-reasoning)
OpenAI vs Alibaba — side-by-side benchmark comparison
| GPT-3.5 Turbo | Qwen3 1.7B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 9.0 | 6.8 |
| Coding Index | 10.7 | 2.3 |
| Math Index | — | 7.3 |
| Output speed (tok/s) | 116.9 | 137.6 |
| Blended price ($/1M) | $0.75 | $0.19 |
| Time to first token (s) | 0.56s | 0.93s |
| aime | — | 9.7% |
| aime 25 | — | 7.3% |
| artificial analysis coding index | 10.70 | 2.30 |
| artificial analysis intelligence index | 9.00 | 6.80 |
| artificial analysis math index | — | 7.30 |
| gpqa | 29.7% | 28.3% |
| hle | — | 5.2% |
| ifbench | — | 21.1% |
| lcr | — | 0.0% |
| livecodebench | — | 12.6% |
| math 500 | 44.1% | 71.7% |
| mmlu pro | 46.2% | 41.1% |
| scicode | — | 6.9% |
| tau2 | — | 21.6% |
| terminalbench hard | — | 0.0% |
Benchmark data from Artificial Analysis.