{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "alanhuangyoo-crux--compare-agent-versions-task-by-task",
 "repo": "alanhuangyoo/crux",
 "repo_url": "https://github.com/alanhuangyoo/crux",
 "repo_slug": "alanhuangyoo-crux",
 "title": "Test whether an agent change helps, task by task",
 "page_title": "How to test whether an agent change helps, task by task with Crux",
 "summary": "Compare two agent versions on the same tasks with a paired sign test instead of one total score.",
 "who": "An engineer changing the agent layer of a pi-based coding agent who needs to know whether an edit is a real improvement or noise.",
 "problem": "A single pass rate can move by chance, so an edit can look like a gain or a loss without being one.",
 "outcome": "A task-by-task comparison of two agent versions with a paired sign test that shows which changes are meaningful.",
 "steps": [
  "Clone the repository and open the benchmark folder with `cd benchmark`.",
  "Install the harness dependencies with `uv sync`.",
  "Run the baseline version and the changed version with `harbor run --dataset terminal-bench/terminal-bench-2-1 --agent crux.pi_agent:CruxPiAgent --model openai/<your-model>`, keeping the model and dataset the same. (inferred, check the README)",
  "Use the harness comparison step in the benchmark folder to compare the two runs task by task with the paired sign test. (inferred, check the README)"
 ],
 "agent_prompt": "Use the alanhuangyoo/crux repository benchmark folder. Run the same Terminal-Bench 2.1 dataset and model for two agent versions, <baseline> and <changed>, then compare them task by task with the paired sign test. Output the per-task outcome counts and the test result, and verify that both runs used the same model and task set.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "240 minutes",
 "basis": "readme",
 "caveat": "The README describes the paired sign test but does not show the exact command for it, so check the benchmark folder for how to invoke the comparison.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "typescript",
 "requirements": [
  "uv installed, since the benchmark is set up with `uv sync`",
  "harbor installed, since the benchmark runs through `harbor run`",
  "Access to the terminal-bench/terminal-bench-2-1 dataset",
  "A model endpoint you can reach through the `openai/` model prefix used in the README command"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/alanhuangyoo-crux/compare-agent-versions-task-by-task/",
 "md": "https://dedupedai.com/use-cases/alanhuangyoo-crux/compare-agent-versions-task-by-task/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/alanhuangyoo-crux--compare-agent-versions-task-by-task.json",
 "api_version": "v1"
}