{"id":"doi:10.1056/aidbp2500120","kind":"article","title":"Assessment of Large Language Models in Clinical Reasoning: A Novel Benchmarking Study","authors":["Liam G. McCoy","Rajiv Swamy","Nidhish Sagar","Minjia Wang","Stephen Bacchi","Jie Ming Nigel Fong","Nigel CK Tan","Kevin Tan","Thomas A. Buckley","Peter G. Brodeur","Leo Anthony Celi","Arjun Kumar Manrai","Aloysius J. Humbert","Adam M. Rodman"],"author_count":14,"year":2025,"published":"2025-09-25","venue":"NEJM AI","cited_by":65,"doi":"10.1056/aidbp2500120","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1056/aidbp2500120","archive_url":"https://space-kitty.com/papers/doi:10.1056/aidbp2500120","updated":null,"pmid":"42932606","pmcid":null,"openalex_id":"W4414499338","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","domain_slug":"ai"}],"cited_in_dossiers":[]}