{"data":{"kind":"file","path":"README.md","version_id":"fzrt7ha09nyi2mce3w5oitr2","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":733,"modified_at":"2025-10-05T23:25:19.635000","content_hash":"ddb56b5b7ccc2991e25e83aaed71ea1d3dfe4630cbdba73ce00707d94838ab0f"},"entries":[],"content":"# crackbench-prime\n\n### Overview\n- **Environment ID**: `crackbench-prime`\n- **Short description**: The benchmark for those who like to do crack.\n- **Tags**: crack\n\n### Datasets\n- **Primary dataset(s)**: A benchmark to test the cracking abilities of LLMs.\n- **Source links**:\n- **Split sizes**:\n\n### Task\n- **Type**: tool use\n- **Parser**:\n- **Rubric overview**:\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval crackbench-prime\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval crackbench-prime   -m gpt-4.1-mini   -n 20 -r 3 -t 1024 -T 0.7   -a '{\"key\": \"value\"}'  # env-specific args as JSON\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.","encoding":"utf-8","truncated":false,"total_bytes":733},"status":null}