← All comparisons
GPT-5.5 (low) vs DeepSeek R1 Distill Qwen 14B
OpenAI vs DeepSeek — side-by-side benchmark comparison
| GPT-5.5 (low) | DeepSeek R1 Distill Qwen 14B | |
|---|---|---|
| Intelligence Index | 50.8 | 15.8 |
| Coding Index | 52.1 | — |
| Math Index | — | 55.7 |
| Output speed (tok/s) | 58.8 | 0.0 |
| Blended price ($/1M) | $11.25 | $0.00 |
| Time to first token (s) | 1.64s | 0.00s |
| aime | — | 66.7% |
| aime 25 | — | 55.7% |
| artificial analysis coding index | 52.10 | — |
| artificial analysis intelligence index | 50.80 | 15.80 |
| artificial analysis math index | — | 55.70 |
| gpqa | 91.0% | 48.4% |
| hle | 31.0% | 4.4% |
| ifbench | 64.4% | 22.1% |
| lcr | 72.0% | 7.0% |
| livecodebench | — | 37.6% |
| math 500 | — | 94.9% |
| mmlu pro | — | 74.0% |
| scicode | 51.6% | 23.9% |
| tau2 | 83.9% | — |
| terminalbench hard | 52.3% | — |
Benchmark data from Artificial Analysis.