GPT-4
Benchmark scores
| Benchmark | Category | Rank | Score | Captured |
|---|---|---|---|---|
| METR Task Horizon (HCAST) | agents | #10 | 7m | 2025-07-12 |
| Chatbot Arena · Open Weights | chat | #19 | 956 | 2026-04-30 |
| SWE-bench Verified | agents | #30 | 22.4% | 2024-04-02 |
| OpenRouter · Weekly Usage | usage | #48 | #325 | 2026-05-02 |
| Chatbot Arena | chat | #53 | 1262 | 2026-04-30 |