{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "amap-ml-looparena--pick-controller-from-published-results",
 "repo": "AMAP-ML/LoopArena",
 "repo_url": "https://github.com/AMAP-ML/LoopArena",
 "repo_slug": "amap-ml-looparena",
 "title": "Pick a Controller model from published results",
 "page_title": "How to pick a Controller model from published results with Loop Arena",
 "summary": "Compare six Controller models on Type I, II, and III before running anything.",
 "who": "A technical lead choosing which model to test or deploy as a coding Controller and needing a quick, cost-aware comparison.",
 "problem": "Running the benchmark takes setup and budget. The published leaderboard and data show how the models compare first.",
 "outcome": "A short shortlist of Controller models based on the published Type I accuracy and Type II/III Strict Success Rate, with the estimated cost in view.",
 "steps": [
  "Open the README results table and note the Type I accuracy, Type II SSR, and Type III SSR for each of the six Controller models.",
  "Open the interactive leaderboard at https://amap-ml.github.io/LoopArena/#results to see reference policies and estimated costs.",
  "Open docs/data/results.json to check the aggregate data for all three settings.",
  "Shortlist the models that score well on Type II and III, and note that costs are normalized no-cache inference estimates, not invoices."
 ],
 "agent_prompt": "Using the AMAP-ML/LoopArena README results table and docs/data/results.json, rank the six Controller models by Type III Strict Success Rate and list their Type I accuracy and estimated cost side by side. Report the ranking as a table and note that the costs are normalized estimates, not invoices.",
 "agents": [
  "any"
 ],
 "difficulty": "Beginner",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "The published scores use the primary Core-based metric and a shared Qwen3.7-Plus Worker, so they may not match your own Worker setup.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "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"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/amap-ml-looparena/pick-controller-from-published-results/",
 "md": "https://dedupedai.com/use-cases/amap-ml-looparena/pick-controller-from-published-results/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/amap-ml-looparena--pick-controller-from-published-results.json",
 "api_version": "v1"
}