GPT-4o
Benchmark scores
| Benchmark | Category | Rank | Score | Captured |
|---|---|---|---|---|
| METR Time Horizon | agents | #17 | 7m | 2024-05-13 |
| Aider Polyglot | code | #19 | 45.3% | 2025-03-29 |
| Chatbot Arena | chat | #22 | 1453 | 2026-06-10 |
| SWE-bench Verified | agents | #29 | 38.8% | 2024-10-28 |
| OpenRouter · Weekly Usage | usage | #33 | #110 | 2026-06-09 |
| AA Coding Index | code | #39 | 24.2% | 2026-06-15 |