WebArena
Self-hosted web environment with realistic sites (shopping, forums, code hosting, maps) for testing web agents.
Reference by Carnegie Mellon University researchers
IndexedApache-2.0★ 1,635
About
Whether an agent can complete natural-language tasks by navigating and acting on realistic, self-hosted websites.
Use cases: llm-evaluation, browser-automation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
About the benchmark
- Benchmark site
- webarena.dev/
- Maintainer
- Carnegie Mellon University researchersarxiv.org
- Launched
- 2023-07arxiv.org
We link to the official leaderboard instead of copying scores. Benchmarks get gamed and saturate; we never use them to rank listings.
Signals
- Stars
- 1,635
- Forks
- 246
- Open issues
- 86
- Last commit
- Nov 26, 2025 (11 months ago)
- Last release
- Oct 21, 2023 (3 years ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/web-arena-x/webarena
- Website
- webarena.dev/
- Docs
- webarena.dev/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
WebArena benchmark. Agent Mart. https://agentmart.dev/reference/webarena (last updated 2026-10-24)