Usage

Install the terminal-bench CLI

uv tool install terminal-bench

Run the benchmark

tb run \
  --dataset-name terminal-bench-core \
  --dataset-version head \
  --agent terminus \
  --model-name anthropic/claude-3-7-sonnet-latest \
  --livestream \
  --task-id django__django-16642

New to terminal-bench? See our quickstart guide.

Instructions

Improper guessing of Mime Type for "br" and "Z" file types Description Below FileResponse will set the content type as text/html, even if the last file extension is "Z' or "br". FileResponse(open('test.html.Z', 'rb')) FileResponse(open('test.html.br', 'rb'))

Tags

debugging, swe-bench