METR
AI evaluation organization (formerly ARC Evals) that assesses AI agent capabilities and benchmark performance.
About
AI evaluation organization (formerly ARC Evals) that assesses AI agent capabilities and benchmark performance.
Key Facts
Links
Similar products worth knowing
LM Studio
A user-friendly desktop application for running large language models locally on your own computer without sending data
Ollama
An open-source tool for running large language models locally on your machine. Allows users to download and run various
Cline
AI coding agent that improved its success rate from 47% to 57% on Terminal Bench's 89 real-world coding tasks through it
Anthropic
AI research company behind Claude, actively deploying models to US Department of War while maintaining safeguards agains
Want products like this in your inbox every morning?
Five products. Every morning. Written by someone who actually cares whether they're good or not. Free forever, unsubscribe whenever.