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

#ModelScoreOverall rank
1Claude 3.7 Sonnet (20250219)44.6#399
2Claude 3.5 Sonnet (20241022)36.2#635
3GPT-4o (2024-08-06)31.4#731
4GPT-4.1 Mini30.7#775
5O1 Mini (2024-09-12)28.6#794
6Llama 3.1 405B24#1083
7Llama 3.1 70B18.4#1493
8GPT-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.