Back to directory
About
This benchmark tests how well AI agents handle everyday browser tasks like shopping, booking, and form-filling. It's built for researchers and developers working on autonomous agents. The tool includes real websites and measurable success metrics so you can track actual performance.
Key Features
- agent-evaluation
- agentic-ai
- ai-agent-benchmark
- ai-agents
- benchmark
Pricing
FreeOpen source. You supply your own LLM API keys.
Categories
Productivity