{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "tongyi-mai-qwen-planner-agent--compare-mobile-planner-benchmark-scores",
 "repo": "Tongyi-MAI/Qwen-Planner-Agent",
 "repo_url": "https://github.com/Tongyi-MAI/Qwen-Planner-Agent",
 "repo_slug": "tongyi-mai-qwen-planner-agent",
 "title": "Compare planner systems on MobilePA-Bench by category",
 "page_title": "How to compare planner systems on MobilePA-Bench by category with Qwen Planner Agent",
 "summary": "Read the Overall and category scores to shortlist planner systems for a phone automation project.",
 "who": "A product lead or analyst choosing which planner model to evaluate further for a mobile task automation product.",
 "problem": "A single overall score hides differences in tool use, memory, Skills, and sub-agent coordination.",
 "outcome": "A shortlist of systems ranked by the category that matters for your use case, with the cost caveat noted.",
 "steps": [
  "Open the Performance section of the README in the Tongyi-MAI/Qwen-Planner-Agent repository.",
  "Compare the Overall column with the Tool Use, Memory, Skills, and Sub-agent columns for the systems you care about.",
  "Read the footnote that says cost covers output tokens only, excluding input tokens, external tool charges, device execution, and extra Harness processing.",
  "Record the systems that lead in your priority category and mark them for a separate evaluation."
 ],
 "agent_prompt": "Read the Performance table in the README of the Tongyi-MAI/Qwen-Planner-Agent repository and produce a ranked list of systems for <priority category: Tool Use, Memory, Skills, or Sub-agent>. Expected output: a table with system name, the priority score, and the Overall score. Verify that the scores match the README values and that you state the cost exclusions.",
 "agents": [
  "any"
 ],
 "difficulty": "Beginner",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "The scores are the authors' reported results on MobilePA-Bench, and the repo does not include the benchmark or code to reproduce them.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "html",
 "requirements": [
  "A web browser to open the project website and the arXiv page",
  "A BibTeX file or reference manager if you plan to cite the paper"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/compare-mobile-planner-benchmark-scores/",
 "md": "https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/compare-mobile-planner-benchmark-scores/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/tongyi-mai-qwen-planner-agent--compare-mobile-planner-benchmark-scores.json",
 "api_version": "v1"
}