Holistic evaluation of large language models for medical tasks with MedHELM

Tue, 20 Jan 2026 00:00:00 +0000

BibTeX

@article{bedi2026medhelm,
title={Holistic evaluation of large language models for medical tasks with MedHELM},
author={Bedi, Suhana and Cui, Hejie and Fuentes, Miguel and Unell, Alyssa and Wornow, Michael and Banda, Juan M. and Kotecha, Nikesh and Keyes, Timothy and Mai, Yifan and Oez, Mert and Qiu, Hao and Jain, Shrey and Schettini, Leonardo and Kashyap, Mehr and Fries, Jason Alan and Swaminathan, Akshay and Chung, Philip and Nateghi Haredasht, Fateme and Lopez, Ivan and Aali, Asad and Tse, Gabriel and Nayak, Ashwin and Vedak, Shivam and Jain, Sneha S. and Patel, Birju and Fayanju, Oluseyi and Shah, Shreya and Goh, Ethan and Yao, Dong-Han and Soetikno, Brian and Reis, Eduardo and Gatidis, Sergios and Divi, Vasu and Capasso, Robson and Saralkar, Rachna and Chiang, Chia-Chun and Jindal, Jenelle and Pham, Tho and Ghoddusi, Faraz and Lin, Steven and Chiou, Albert S. and Hong, Hyo Jung and Roy, Mohana and Gensheimer, Michael F. and Patel, Hinesh and Schulman, Kevin and Dash, Dev and Char, Danton and Downing, Lance and Grolleau, Francois and Black, Kameron and Mieso, Bethel and Zahedivash, Aydin and Yim, Wen-Wai and Sharma, Harshita and Lee, Tony and Kirsch, Hannah and Lee, Jennifer and Ambers, Nerissa and Lugtu, Carlene and Sharma, Aditya and Mawji, Bilal and Alekseyev, Alex and Zhou, Vicky and Kakkar, Vikas and Helzer, Jarrod and Revri, Anurang and Bannett, Yair and Daneshjou, Roxana and Chen, Jonathan and Alsentzer, Emily and Morse, Keith and Ravi, Nirmal and Aghaeepour, Nima and Kennedy, Vanessa and Chaudhari, Akshay and Wang, Thomas and Koyejo, Sanmi and Lungren, Matthew P. and Horvitz, Eric and Liang, Percy and Pfeffer, Michael A. and Shah, Nigam H.},
journal={Nature Medicine},
volume={32},
number={3},
pages={943--951},
year={2026},
doi={10.1038/s41591-025-04151-2},
url={https://www.nature.com/articles/s41591-025-04151-2}
}

Roxana Daneshjou | Harshita Sharma

Holistic evaluation of large language models for medical tasks with MedHELM

BibTeX