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 oom

New to terminal-bench? See our quickstart guide.

Demo

Instructions

I want you to cache the `albert/albert-base-v2` model and tokenizer from huggingface so that I can use it offline when I'm on my next flight. Keep the cache location the default so that transformers.AutoModel.from_pretrained("albert/albert-base-v2", local_files_only=True) will work.

Tags

coding, data-processing, data-science