Journal article · 2026 · Open access

Large Language Model Performance and Clinical Reasoning Tasks

Arya S. Rao, Kaiz P. Esmail, Richard Sean Lee, Sharon Jiang, Bianca Arraiza Carlo, Jasleen Gill, Praneet Khanna, Ezra Kalmowitz, Basile Montagnese, Kimia Heydari, Qiao Jiao, Ethan Bott and 5 more

JAMA Network Open, 9(4), e264003 · Published 13 April 2026 · DOI 10.1001/jamanetworkopen.2026.4003

Open full textCite this paper

In brief

“Large Language Model Performance and Clinical Reasoning Tasks” is a 2026 journal article by Arya S. Rao and 16 co-authors, published in JAMA Network Open. OpenAlex counts 99 citations as of 19 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at JAMA Network Open.

Citations
99
Most cited in
2026 (97)
Field-weighted impact
89.95
References
26
Authors
17

Abstract

Importance: Large language models (LLMs) are increasingly marketed for clinical use, yet their ability to replicate full-spectrum clinical reasoning remains uncertain. Existing evaluations often rely on multiple-choice examinations that do not reflect the complexity of patient care. Objectives: To evaluate the longitudinal clinical reasoning ability of state-of-the-art LLMs and to introduce a multidimensional, clinically meaningful benchmark for clinical-grade artificial intelligence (AI). Design, Setting, and Participants: In this cross-sectional study, performance was evaluated using standardized clinical vignettes from the January 2025 update of MSD Manual vignettes. A total of 21 off-the-shelf LLMs, including recently released GPT-5, Claude 4.5 Opus, Gemini 3.0 Flash and Pro, and Grok 4, were evaluated. Models were assessed by medical student scorers in triplicate across sequential stages of the standard clinical workflow. Analyses were performed from January to December 2025. Main Outcomes and Measures: The primary outcome was the Proportional Index of Medical Evaluation for LLMs (PrIME-LLM) score, defined as the normalized polygonal area representing balanced accuracy across 5 domains of clinical reasoning as follows: differential diagnosis, diagnostic testing, final diagnosis, management, and miscellaneous clinical reasoning questions. Analyses including analyses of variance, t tests, and regression models were used to compare AI model performance and demographic associations. Results: LLMs were tested across 29 clinical vignettes (representing 16 254 responses in total). PrIME-LLM scores ranged from 0.64 (range, 0.63-0.65) (Gemini 1.5 Flash) to 0.78 (range, 0.77-0.79) (Grok 4), with reasoning-optimized models outperforming nonreasoning models and GPT models scoring highest overall. Differential diagnosis was less accurate than diagnostic testing, while final diagnosis, management, and miscellaneous reasoning were more accurate. Failure rates exceeded 0.80 (range, 0.90-1.00) for differential diagnosis in all models but were less than 0.40 (range, 0.09-0.39) for final diagnosis. Multimodal performance was robust; most LLM models showed improved accuracy with image inputs. Conclusions and Relevance: In this cross-sectional study of 21 LLMs, frontier LLMs achieved high accuracy on final diagnoses but performed poorly in generating differential diagnoses and navigating uncertainty relative to other reasoning stages. The PrIME-LLM framework provided greater separation than raw accuracy, revealing critical reasoning gaps obscured by traditional benchmarks. Thus, despite version-based improvements and advantages in reasoning-optimized models, off-the-shelf LLMs have not yet achieved the intelligence required for safe deployment and remain limited in demonstrating advanced clinical reasoning.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Rao, A. S., Esmail, K. P., Lee, R. S., Jiang, S., Carlo, B. A., Gill, J., Khanna, P., Kalmowitz, E., Montagnese, B., Heydari, K., Jiao, Q., Bott, E., Nguyen, D., Wang, G., Hood, M. C., Landman, A., & Succi, M. D. (2026). Large Language Model Performance and Clinical Reasoning Tasks. JAMA Network Open, 9(4), e264003. https://doi.org/10.1001/jamanetworkopen.2026.4003

MLA 9

Rao, Arya S., et al. “Large Language Model Performance and Clinical Reasoning Tasks.” JAMA Network Open, vol. 9, no. 4, 2026, p. e264003. https://doi.org/10.1001/jamanetworkopen.2026.4003.

Chicago

Rao, Arya S., Kaiz P. Esmail, Richard Sean Lee, Sharon Jiang, Bianca Arraiza Carlo, Jasleen Gill, Praneet Khanna, et al. 2026. “Large Language Model Performance and Clinical Reasoning Tasks.” JAMA Network Open 9 (4): e264003. https://doi.org/10.1001/jamanetworkopen.2026.4003.

Harvard

Rao, A. S. et al. (2026) ‘Large Language Model Performance and Clinical Reasoning Tasks’, JAMA Network Open, 9(4), p. e264003. doi:10.1001/jamanetworkopen.2026.4003.

IEEE

A. S. Rao et al., “Large Language Model Performance and Clinical Reasoning Tasks,” JAMA Network Open, vol. 9, no. 4, p. e264003, 2026, doi: 10.1001/jamanetworkopen.2026.4003.

BibTeX

@article{rao2026large,
  title     = {{Large Language Model Performance and Clinical Reasoning Tasks}},
  author    = {Rao, Arya S. and Esmail, Kaiz P. and Lee, Richard Sean and Jiang, Sharon and Carlo, Bianca Arraiza and Gill, Jasleen and Khanna, Praneet and Kalmowitz, Ezra and Montagnese, Basile and Heydari, Kimia and Jiao, Qiao and Bott, Ethan and Nguyen, Dan and Wang, Grace and Hood, Michael C. and Landman, Adam and Succi, Marc D.},
  journal   = {JAMA Network Open},
  year      = {2026},
  volume    = {9},
  number    = {4},
  pages     = {e264003},
  doi       = {10.1001/jamanetworkopen.2026.4003},
  url       = {https://doi.org/10.1001/jamanetworkopen.2026.4003}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • large language models
  • clinical reasoning
  • clinical vignettes
  • differential diagnosis
  • diagnostic testing
  • final diagnosis
  • clinical management
  • multimodal large language models

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Rao, A. S., Esmail, K. P., Lee, R. S., Jiang, S., Carlo, B. A., Gill, J., Khanna, P., Kalmowitz, E., Montagnese, B., Heydari, K., Jiao, Q., Bott, E., Nguyen, D., Wang, G., Hood, M. C., Landman, A., & Succi, M. D. (2026). Large Language Model Performance and Clinical Reasoning Tasks. JAMA Network Open, 9(4), e264003. https://doi.org/10.1001/jamanetworkopen.2026.4003

How many times has this paper been cited?

99 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at JAMA Network Open: sign in and open the full text from this page.

Who wrote this paper?

Arya S. Rao, Kaiz P. Esmail, Richard Sean Lee, Sharon Jiang, Bianca Arraiza Carlo, Jasleen Gill, Praneet Khanna, Ezra Kalmowitz, Basile Montagnese, Kimia Heydari, Qiao Jiao, Ethan Bott and 5 more.

What is the DOI of this paper?

10.1001/jamanetworkopen.2026.4003, permanently at https://doi.org/10.1001/jamanetworkopen.2026.4003. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.