This repository accepts leaderboard submissions for Terminal-Bench 2.0.
Fork this repository
Create a new branch for your submission
Add your submission (a job or folder of jobs) under submissions/terminal-bench/2.0/
__<model(s)>/
Open a Pull Request
submissions/
terminal-bench/
2.0/
__/
metadata.yaml # Required: agent and model info… See the full description on the dataset page: https://huggingface.co/datasets/willowyll/terminal-bench-2-leaderboard.