websitebench
A benchmark that tests whether AI agents can rebuild a real website just by exploring it in a browser.
View tiger-ai-lab/websitebench on GitHub- GitHub stars
- 306
- Forks
- —
- Language
- Python
Project details
- Repository
- tiger-ai-lab/websitebench
- Licence
- Apache-2.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Can AI agents rebuild websites through browser exploration?
Explore by topic
More tools in AI agents
- reverify
2akouwu · MIT
Reverify pairs an AI model with deterministic binary-analysis tools that check every claim against the real file, so reverse-engineering output is grounded in the…
- hermes-agent
nousresearch · MIT
Hermes Agent is Nous Research's self-improving AI agent: it creates and improves its own skills from experience, remembers users across sessions, and runs from a…
- deer-flow
bytedance · MIT
An open-source AI super-agent that researches a topic, writes and tests code, and produces finished deliverables like reports or podcasts, running on its own for…
- ai-engineering-from-scratch
rohitg00 · MIT
A free, open-source course that walks you through building modern AI systems from scratch, 511 lessons spanning LLMs, RAG, agents and transformers.