{
  "id": 10602335,
  "title": "Jev in Medicine: A Benchmark Evaluation. Preliminary Results",
  "url": "https://urgent.news/2026/09/27/jev-in-medicine-a-benchmark-evaluation-preliminary-results",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-27T23:33:04.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.34024v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Jev is a non-generative \"System One\" model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and calibration on medical question-answering and case-based diagnostic-reasoning tasks are unknown. We evaluated Jev 1.13 on four medical benchmarks: MetaMedQA, PubMedQA, DiagnosisArena-MCQ and the NEJM Case Challenges. GPT-6 Sol, with (medium) and…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}