{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "frontier-harness-eval/eval",
 "name": "eval",
 "owner": "frontier-harness-eval",
 "slug": "frontier-harness-eval-eval",
 "github": "https://github.com/frontier-harness-eval/eval",
 "what": "A public results set and task definitions for comparing coding-agent harnesses that run the same Kimi K3 model on 30 software-engineering tasks, plus a workflow for evaluating your own harness.",
 "why": "",
 "language": "JavaScript",
 "requirements": [
  "A Runta account, with the runta CLI installed and authenticated via runta login",
  "jq, Node.js 18 or newer, and Python 3.9 or newer",
  "A provider API key for Kimi K3 (FIREWORKS_API_KEY, MOONSHOT_API_KEY, OPENROUTER_API_KEY, or TOGETHER_API_KEY)",
  "A harness repository you can build on a clean Linux box, plus an install script"
 ],
 "audience_note": "Engineers and researchers choosing or building a coding-agent harness who need to compare pass rate and cost on the same model and tasks.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/frontier-harness-eval-eval/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "frontier-harness-eval-eval--browse-live-harness-results",
   "title": "Compare 12 coding-agent harness results side by side",
   "best": true,
   "url": "https://dedupedai.com/use-cases/frontier-harness-eval-eval/browse-live-harness-results/",
   "json": "https://dedupedai.com/use-cases/u/frontier-harness-eval-eval/browse-live-harness-results.json"
  },
  {
   "id": "frontier-harness-eval-eval--evaluate-own-harness-on-published-tasks",
   "title": "Score your own coding harness on the 30-task set",
   "best": false,
   "url": "https://dedupedai.com/use-cases/frontier-harness-eval-eval/evaluate-own-harness-on-published-tasks/",
   "json": "https://dedupedai.com/use-cases/u/frontier-harness-eval-eval/evaluate-own-harness-on-published-tasks.json"
  },
  {
   "id": "frontier-harness-eval-eval--check-result-comparability-before-citing",
   "title": "Check if a harness score is comparable before citing it",
   "best": false,
   "url": "https://dedupedai.com/use-cases/frontier-harness-eval-eval/check-result-comparability-before-citing/",
   "json": "https://dedupedai.com/use-cases/u/frontier-harness-eval-eval/check-result-comparability-before-citing.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."
}