BrowserGym WebArena: leaderboard
WebArena's tasks on self-hosted e-commerce, forum, code-hosting, content-management and map sites as run on ServiceNow's BrowserGym leaderboard. Scored as task success rate (%); higher is better. Runs use AgentLab's GenericAgent scaffold unless the row names another framework.
Metric: Success rate (%, GenericAgent unless named). Source: huggingface.co. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 44.6 | #399 |
| 2 | Claude 3.5 Sonnet (20241022) | 36.2 | #635 |
| 3 | GPT-4o (2024-08-06) | 31.4 | #731 |
| 4 | GPT-4.1 Mini | 30.7 | #775 |
| 5 | O1 Mini (2024-09-12) | 28.6 | #794 |
| 6 | Llama 3.1 405B | 24 | #1083 |
| 7 | Llama 3.1 70B | 18.4 | #1493 |
| 8 | GPT-4o Mini (2024-07-18) | 17.4 | #1512 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=browsergym-webarena · How It Works · Data refreshed daily, snapshot 2026-11-12.