steel-dev/leaderboard

Open leaderboard for browser agents

49
/ 100
Emerging

This leaderboard helps you compare how well different AI agents can perform tasks on websites, like navigating pages or filling out forms. It takes the agent's performance on the WebVoyager benchmark and outputs a clear ranking based on their success rate across 643 diverse tasks. AI researchers, developers building agentic applications, and anyone evaluating off-the-shelf web agents would find this useful.

Use this if you need to quickly assess and compare the performance of various browser-based AI agents on real-world web interaction tasks.

Not ideal if you are looking for a tool to develop or test your own browser agents, rather than just evaluate existing ones.

AI agent development web automation agent evaluation browser automation AI research
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

31

Forks

6

Language

Astro

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/steel-dev/leaderboard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.