GPT-4o scores 13.9 on the Respan Index (#130), ahead of DeepSeek V3 at 12.4 (#132). DeepSeek V3 leads on 6 of the 7 benchmarks both report.
* Estimated: no published scores in that category. How the Respan Index works
| 1346 |
| AIME 2025 | 25% | 11.7% |
| MMLU | 88.5% | 85.7% |
Higher is better. Each score links to where it was published.