{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "AMAP-ML/LoopArena",
 "name": "LoopArena",
 "owner": "AMAP-ML",
 "slug": "amap-ml-looparena",
 "github": "https://github.com/AMAP-ML/LoopArena",
 "what": "LoopArena is a Python benchmark that tests how well AI models work as runtime Controllers that guide a separate coding Worker through a Loop Engineering task.",
 "why": "152 stars, launched 56 days ago",
 "language": "Python",
 "requirements": [
  "Python 3.10 or newer",
  "An OpenAI-compatible model endpoint, its base URL, and an API key",
  "The model ID you want to test",
  "For Type II/III only: the pinned upstream task data, starting workspaces, and Docker runtimes described in docs/setup.md"
 ],
 "audience_note": "Written for AI researchers and engineers who need to compare models as Controllers, and for agents asked to run the benchmark.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/amap-ml-looparena/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "amap-ml-looparena--smoke-test-controller-model-type1",
   "title": "Check a Controller model on Type I questions",
   "best": true,
   "url": "https://dedupedai.com/use-cases/amap-ml-looparena/smoke-test-controller-model-type1/",
   "json": "https://dedupedai.com/use-cases/u/amap-ml-looparena/smoke-test-controller-model-type1.json"
  },
  {
   "id": "amap-ml-looparena--compare-controller-models-coding-tasks",
   "title": "Compare Controller models on paired coding tasks",
   "best": false,
   "url": "https://dedupedai.com/use-cases/amap-ml-looparena/compare-controller-models-coding-tasks/",
   "json": "https://dedupedai.com/use-cases/u/amap-ml-looparena/compare-controller-models-coding-tasks.json"
  },
  {
   "id": "amap-ml-looparena--pick-controller-from-published-results",
   "title": "Pick a Controller model from published results",
   "best": false,
   "url": "https://dedupedai.com/use-cases/amap-ml-looparena/pick-controller-from-published-results/",
   "json": "https://dedupedai.com/use-cases/u/amap-ml-looparena/pick-controller-from-published-results.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."
}