Framework for evaluating and improving agents
- evals
- rl-environments
- terminal-bench
132,241 visible repositories in the index
1–8 of 8 · Most stars
Framework for evaluating and improving agents
A benchmark for LLMs on complicated tasks in the terminal
Measuring and evolving with the frontier of agent work
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub
Can AI agents rebuild websites through browser exploration?
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
How many bugs can LMs find & fix in large codebases?