DeepSeek R1 scores 17.9 on the Respan Index (#107), ahead of GPT-5 nano at 17.3 (#109). DeepSeek R1 leads on 4 of the 7 benchmarks both report. GPT-5 nano has the larger context window (400K tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 1373 |
| 1338 |
| AIME 2025 | 70% | 85% |
| SWE-bench Verified | 49.2% | 54.7% |
Higher is better. Each score links to where it was published.