{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "phuryn-bug-hunt-bench--compare-one-model-across-coding-clis",
 "repo": "phuryn/bug-hunt-bench",
 "repo_url": "https://github.com/phuryn/bug-hunt-bench",
 "repo_slug": "phuryn-bug-hunt-bench",
 "title": "Compare one model across different coding CLIs",
 "page_title": "How to compare one model across different coding CLIs with Bug Hunt Bench",
 "summary": "See whether the tool wrapped around a model changes its bug-fixing score.",
 "who": "A developer who runs the same model in several coding tools and sees different results from each.",
 "problem": "A model's score can reflect the harness it runs in, so a score from one tool may not carry over to another.",
 "outcome": "A clear view of how the same model scores across harnesses and effort levels, which helps decide which tool to use.",
 "steps": [
  "Open the leaderboard at bughunt.productcompass.pm.",
  "Find one model in the table, for example DeepSeek V4.1 Flash 1017, and note its Harness and Effort values.",
  "Compare its Fixed /105 scores across harnesses: DeepSeek Harness, Pi, Claude Code and OpenCode at max effort score 42.7, 42.2, 39.1 and 37.6.",
  "Check the Effort column to see whether the same harness scores differently at high, low or max effort."
 ],
 "agent_prompt": "Using the bug-hunt-bench README table, list every row for <model name> with its Harness, Effort, and Fixed /105 score, sorted by score. Output a table. Verify that each row's harness and effort match the source table.",
 "agents": [
  "any"
 ],
 "difficulty": "Beginner",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "Run counts differ across rows, so a difference of one or two points between harnesses may be noise.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "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"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/compare-one-model-across-coding-clis/",
 "md": "https://dedupedai.com/use-cases/phuryn-bug-hunt-bench/compare-one-model-across-coding-clis/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/phuryn-bug-hunt-bench--compare-one-model-across-coding-clis.json",
 "api_version": "v1"
}