{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "phuryn/bug-hunt-bench",
 "name": "bug-hunt-bench",
 "owner": "phuryn",
 "slug": "phuryn-bug-hunt-bench",
 "github": "https://github.com/phuryn/bug-hunt-bench",
 "what": "A benchmark of 105 real bugs in two production codebases that grades frontier AI coding models, each run in its own agentic CLI, with blind grading against a withheld answer key.",
 "why": "164 stars, launched 62 days ago",
 "language": "JavaScript",
 "requirements": [
  "A web browser to open the live leaderboard at bughunt.productcompass.pm",
  "Access to the results/ folder on GitHub or a local copy of the repo for the raw data"
 ],
 "audience_note": "Written for engineering leads, researchers, and agents who need to compare AI coding models on bug fixing before spending money or time on them.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "phuryn-bug-hunt-bench--pick-coding-model-for-bug-fixing",
   "title": "Choose a coding model for bug fixing by score and cost",
   "best": true,
   "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/pick-coding-model-for-bug-fixing/",
   "json": "https://dedupedai.com/use-cases/u/phuryn-bug-hunt-bench/pick-coding-model-for-bug-fixing.json"
  },
  {
   "id": "phuryn-bug-hunt-bench--compare-one-model-across-coding-clis",
   "title": "Compare one model across different coding CLIs",
   "best": false,
   "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/compare-one-model-across-coding-clis/",
   "json": "https://dedupedai.com/use-cases/u/phuryn-bug-hunt-bench/compare-one-model-across-coding-clis.json"
  },
  {
   "id": "phuryn-bug-hunt-bench--study-the-25-bugs-no-model-fixed",
   "title": "Study the 25 bugs no model has fixed",
   "best": false,
   "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/study-the-25-bugs-no-model-fixed/",
   "json": "https://dedupedai.com/use-cases/u/phuryn-bug-hunt-bench/study-the-25-bugs-no-model-fixed.json"
  },
  {
   "id": "phuryn-bug-hunt-bench--audit-model-fix-claims-against-receipts",
   "title": "Audit a model's bug-fix claims against the receipts",
   "best": false,
   "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/audit-model-fix-claims-against-receipts/",
   "json": "https://dedupedai.com/use-cases/u/phuryn-bug-hunt-bench/audit-model-fix-claims-against-receipts.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}