{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "fstandhartinger/jevbench",
 "name": "jevbench",
 "owner": "fstandhartinger",
 "slug": "fstandhartinger-jevbench",
 "github": "https://github.com/fstandhartinger/jevbench",
 "what": "JevBench is a benchmark and leaderboard for AI decision models that measures typed decision accuracy, calibration, latency and cost.",
 "why": "",
 "language": "Python",
 "requirements": [
  "A web browser to read the public boards and release manifest",
  "Git and Python for the local repo steps",
  "Your decision model reachable from your own machine if you run the option-order test"
 ],
 "audience_note": "Useful for teams choosing a decision model for a workload and for researchers who need to test how a model handles answer option order.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/fstandhartinger-jevbench/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "fstandhartinger-jevbench--shortlist-decision-models-from-jevbench-board",
   "title": "Shortlist decision models from the JevBench board",
   "best": true,
   "url": "https://dedupedai.com/use-cases/fstandhartinger-jevbench/shortlist-decision-models-from-jevbench-board/",
   "json": "https://dedupedai.com/use-cases/u/fstandhartinger-jevbench/shortlist-decision-models-from-jevbench-board.json"
  },
  {
   "id": "fstandhartinger-jevbench--test-option-order-sensitivity-before-deploy",
   "title": "Test a decision model for option-order sensitivity",
   "best": false,
   "url": "https://dedupedai.com/use-cases/fstandhartinger-jevbench/test-option-order-sensitivity-before-deploy/",
   "json": "https://dedupedai.com/use-cases/u/fstandhartinger-jevbench/test-option-order-sensitivity-before-deploy.json"
  },
  {
   "id": "fstandhartinger-jevbench--compare-local-models-with-stuntdouble-import",
   "title": "Compare local decision models with stuntdouble",
   "best": false,
   "url": "https://dedupedai.com/use-cases/fstandhartinger-jevbench/compare-local-models-with-stuntdouble-import/",
   "json": "https://dedupedai.com/use-cases/u/fstandhartinger-jevbench/compare-local-models-with-stuntdouble-import.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."
}
