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-14373

New to terminal-bench? See our quickstart guide.

Instructions

DateFormat.Y() is not zero-padded. Description The Y specifier for django.utils.dateformat.DateFormat is supposed to always return a four-digit year padded with zeros. This doesn't seem to be the case for year < 1000.

Tags

debugging, swe-bench