EUVIMEDEUVIMED entdecken
Open Access

Performance of 5 AI Models on United States Medical Licensing Examination Step 1 Questions: Comparative Observational Study

Dania El Natour iD, Mohamad Abou Alfa iD, Ahmad Chaaban iD, Reda Assi iD, Toufic Dally iD, Bahaa Bou Dargham iD

JMIR AI · 09.03.2026 · 5 · e76928

DOI: 10.2196/76928 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR AI, online erschienen am 09.03.2026. Verfasst von Dania El Natour und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Medicine, Beirut Arab University, Beirut, Lebanon. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) models are increasingly being used in medical education. Although models like ChatGPT have previously demonstrated strong performance on United States Medical Licensing Examination (USMLE)–style questions, newer AI tools with enhanced capabilities are now available, necessitating comparative evaluations of their accuracy and reliability across different medical domains and question formats.

Objective

This study aimed to evaluate and compare the performance of 5 publicly available AI models: Grok, ChatGPT-4, Copilot, Gemini, and DeepSeek, on the USMLE Step 1 free 120-question set, assessing their accuracy and consistency across question types and medical subjects.

Methods

This cross-sectional observational study was conducted between February 10 and March 5, 2025. Each of the 119 USMLE-style questions (excluding 1 audio-based item) was presented to each AI model by using a standardized prompt cycle. Models answered each question 3 times to assess confidence and consistency. Questions were categorized as text-based or image-based and as case-based or information-based. Statistical analysis was performed using chi-square and Fisher exact tests, with Bonferroni adjustment for pairwise comparisons.

Results

Grok achieved the highest score (109/119, 91.6%), followed by Copilot (101/119, 84.9%), Gemini (100/119, 84%), ChatGPT-4 (95/119, 79.8%), and DeepSeek (86/119, 72.3%). DeepSeek’s lower score was due to an inability to process visual media, resulting in 0% accuracy on image-based items. When limited to text-only questions (n=96), DeepSeek’s accuracy increased to 89.6% (86/96), matching Copilot. Grok showed the highest accuracy on image-based (21/23, 91.3%) and case-based questions (70/78, 89.7%), with statistically significant differences observed between Grok and DeepSeek on case-based items (P=.01). The models performed best in biostatistics and epidemiology (5.8/6, 96.7%) and worst in musculoskeletal, skin, and connective tissue (4.4/7, 62.9%). Grok maintained 100% consistency in responses, while Copilot demonstrated the most self-correction (112/119, 94.1% consistency), improving its accuracy to 89.9% (107/119) on the third attempt.

Conclusions

AI models showed varying strengths across domains, with Grok demonstrating the highest accuracy and consistency in this dataset, particularly for image-based and reasoning-heavy questions. Although ChatGPT-4 remains widely used, newer models like Grok and Copilot also performed competitively. Continuous evaluation is essential as AI tools rapidly evolve.

Schlagwörter

Stichwörter der Autor:innen

ChatGPTCopilotDeepSeekGeminiGrokUSMLEartificial intelligencecase-based reasoningimage-based questionslarge language modelsmedical education

Autor:innen und Institutionen

  • Faculty of Medicine, Beirut Arab University, Beirut, Lebanon.
  • Department of Anesthesiology, Hammoud Hospital University Medical Center, Saida, Lebanon.

ORCID-Profile: Dania El Natour, Mohamad Abou Alfa, Ahmad Chaaban, Reda Assi, Toufic Dally, Bahaa Bou Dargham

Zitieren

APA

El Natour, D., Abou Alfa, M., Chaaban, A., Assi, R., Dally, T., & Bou Dargham, B. (2026). Performance of 5 AI Models on United States Medical Licensing Examination Step 1 Questions: Comparative Observational Study. JMIR AI, 5, e76928. https://doi.org/10.2196/76928

Vancouver

El Natour D, Abou Alfa M, Chaaban A, Assi R, Dally T, Bou Dargham B. Performance of 5 AI Models on United States Medical Licensing Examination Step 1 Questions: Comparative Observational Study. JMIR AI. 2026;5:e76928. doi:10.2196/76928

BibTeX
@article{ElNatour2026,
  author = {El Natour, Dania and Abou Alfa, Mohamad and Chaaban, Ahmad and Assi, Reda and Dally, Toufic and Bou Dargham, Bahaa},
  title = {Performance of 5 AI Models on United States Medical Licensing Examination Step 1 Questions: Comparative Observational Study},
  journal = {JMIR AI},
  year = {2026},
  volume = {5},
  pages = {e76928},
  doi = {10.2196/76928}
}
Kostenlos starten →