o3
Benchmark scores
| Benchmark | Category | Rank | Score | Captured |
|---|---|---|---|---|
| Aider Polyglot | code | #2 | 84.9% | 2025-06-28 |
| METR Time Horizon | agents | #10 | 1h60m | 2025-04-16 |
| SWE-bench Verified | agents | #22 | 58.4% | 2025-07-26 |
| Chatbot Arena | chat | #31 | 1410 | 2026-09-13 |
| OpenRouter · Weekly Usage | usage | #46 | #239 | 2026-06-09 |