statnews.com
Clinical chatbots vs generalist LLMs in healthcare: a benchmark rethink for AI builders
Tech News••
1 min read
Published by AINave Editorial • Reviewed by Ramit
TL;DRNYU Langone Health researchers found general LLMs outperformed clinical AI tools like OpenEvidence on clinical questions, prompting a rethink of deployment strategies.
What happened
Hundreds of thousands of U.S. doctors use clinical large language models from companies like OpenEvidence, Doximity, and UpToDate, marketed as safer alternatives to generalist chatbots. Yet a head-to-head study from NYU Langone Health, [published in Nature Medicine in June](https://www.statnews.com
Sources
- Clinical chatbots are taking medicine by storm. Should doctors trust them?
- AI Chatbots vs. Physicians: What the Evidence Says About Diagnostic ...
- Patients, Doctors, and Chatbots - ScienceDirect
- Doctors' Views on AI Chatbots in Clinical Decisions
- Critical care doctor says patients' reliance on chatbots reflects ...
- Inside the Trump-backed push to bring AI doctors into American medicine
- Please don't trust your chatbot for medical advice - Marcus on AI
- Should you trust AI chatbots for medical advice? Expert weighs in | Health News – India TV
- Physician’s medical decisions benefit from AI, Stanford Medicine-led research finds
- AI in healthcare: Can a chatbot answer your medical questions? - Harvard Health
- Chatbots outperform doctors in diagnosing many diseases, study finds
- Hospitals are deploying AI chatbots. Doctors are divided
- Clinical chatbots are taking medicine by storm. Should doctors...
- AI chatbots are pretty bad at dishing out health... | The Straits Times
- Healthcare AI in 2026: From Chatbots to Clinical Tools
