Usage

uv tool install terminal-bench

pip install terminal-bench

tb run \
  --dataset terminal-bench-core==head \
  --agent terminus \
  --model-name anthropic/claude-sonnet-4-20250514 \
  --task-id cron-broken-network \
  --livestream

New to terminal-bench? See our quickstart guide.

Demo

Instruction

For some reason I can't /usr/bin/curl example.com, can you figure out why and fix it so I can /usr/bin/curl example.com?

Tags

sys-admin, networking, troubleshooting