{
  "id": 18075447,
  "title": "MedPhysBench: A Benchmark for Evaluating Language Models on Medical Physics Calculations and Error Detection",
  "url": "https://urgent.news/2026/11/03/medphysbench-a-benchmark-for-evaluating-language-models-on-medical",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-03T18:40:35.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.05340v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Medical physicists turn a prescription into a delivered dose and check one another's calculations, because one error in a beam calibration or a monitor-unit (MU) calculation can affect every patient treated with it. MedPhysBench has ten seeded generators of calculation items in radiation therapy, diagnostic imaging, nuclear medicine and radiation protection, up to clinical tasks such as a TG-51…",
  "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."
}