{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "kaiwu5-awesome-ai4ai--pick-agent-benchmarks-for-evaluation",
 "repo": "KaiWU5/Awesome-AI4AI",
 "repo_url": "https://github.com/KaiWU5/Awesome-AI4AI",
 "repo_slug": "kaiwu5-awesome-ai4ai",
 "title": "Choose benchmarks to test a long-horizon coding agent",
 "page_title": "How to choose benchmarks to test a long-horizon coding agent with Awesome AI4 AI",
 "summary": "Shortlist benchmarks from the catalog that match the agent capability you need to test.",
 "who": "An ML engineer evaluating a terminal or coding agent who needs benchmarks beyond a single demo task.",
 "problem": "Picking a benchmark from a large, unsorted list of papers takes time and is easy to get wrong.",
 "outcome": "A shortlist of two or three benchmarks with links to their papers and code.",
 "steps": [
  "Open the Benchmarks section, which the README says lists 136 benchmarks.",
  "Filter the entries by the capability you need, such as command line tasks or tool use.",
  "Open the Terminal-Bench entry and note its code link and star count.",
  "Shortlist two or three benchmarks and copy their paper and code links.",
  "Record the shortlist with the README snapshot date of 2026-10-22."
 ],
 "agent_prompt": "Using the repo KaiWU5/Awesome-AI4AI, list benchmarks from the Benchmarks section that involve command line or tool use for <target agent>. Expected output: a shortlist of three entries, each with its paper and code link. Verify that each link opens the benchmark named in its entry.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The repo is a catalog of papers and does not run any benchmark, so you still need to set up and run the benchmark yourself.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "A web browser, or an agent that can read GitHub pages",
  "A place to save a short list or table of entries"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/kaiwu5-awesome-ai4ai/pick-agent-benchmarks-for-evaluation/",
 "md": "https://dedupedai.com/use-cases/kaiwu5-awesome-ai4ai/pick-agent-benchmarks-for-evaluation/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/kaiwu5-awesome-ai4ai--pick-agent-benchmarks-for-evaluation.json",
 "api_version": "v1"
}