← All comparisons
GPT-4o (May '24) vs DeepSeek R1 Distill Qwen 14B
OpenAI vs DeepSeek — side-by-side benchmark comparison
| GPT-4o (May '24) | DeepSeek R1 Distill Qwen 14B | |
|---|---|---|
| Intelligence Index | 14.5 | 15.8 |
| Coding Index | 24.2 | — |
| Math Index | — | 55.7 |
| Output speed (tok/s) | 111.8 | 0.0 |
| Blended price ($/1M) | $7.50 | $0.00 |
| Time to first token (s) | 0.61s | 0.00s |
| aime | 11.0% | 66.7% |
| aime 25 | — | 55.7% |
| artificial analysis coding index | 24.20 | — |
| artificial analysis intelligence index | 14.50 | 15.80 |
| artificial analysis math index | — | 55.70 |
| gpqa | 52.6% | 48.4% |
| hle | 2.8% | 4.4% |
| ifbench | — | 22.1% |
| lcr | — | 7.0% |
| livecodebench | 33.4% | 37.6% |
| math 500 | 79.1% | 94.9% |
| mmlu pro | 74.0% | 74.0% |
| scicode | 30.9% | 23.9% |
| tau2 | — | — |
| terminalbench hard | — | — |
Benchmark data from Artificial Analysis.