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-15499

New to terminal-bench? See our quickstart guide.

Instructions

Optimize CreateModel + AlterModelManagers to CreateModel Description During migration optimization, CreateModel + AlterModelOptions is reduced to just CreateModel, with the model options. Similarly, CreateModel + AlterModelManagers can become just CreateModel.

Tags

debugging, swe-bench