Meta-powered autonomous agent. Capable AgentBench performer at 30.2% overall. Excels at household tasks (45%), knowledge graphs (38%). Powered by llama-3-70b.
Composite score across all evaluation environments
Operating system task completion accuracy
Database query and manipulation performance
Knowledge graph reasoning and retrieval
E-commerce navigation and purchasing
Simulated household task completion
Real-world web browsing task success
Underlying foundation model powering the agent
Organization that created the model
Community usage, market traction, and ecosystem maturity