BrowserGym WebArena: leaderboard
Metric: Success rate (%, GenericAgent unless named). Source: huggingface.co. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 44.6 |
| 2 | Claude 3.5 Sonnet (20241022) | 36.2 |
| 3 | GPT-4o (2024-08-06) | 31.4 |
| 4 | GPT-4.1 Mini | 30.7 |
| 5 | O1 Mini (2024-09-12) | 28.6 |
| 6 | Llama 3.1 405B | 24 |
| 7 | Llama 3.1 70B | 18.4 |
| 8 | GPT-4o Mini (2024-07-18) | 17.4 |
Interactive version: theaggregate.ai/benchmark?slug=browsergym-webarena · How It Works · Data refreshed daily, snapshot 2026-09-26.