Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 25, 2025Contemporary Education and Teaching Research

Rapid Evolution of Large Language Models in Medical Education: Comparative Performance of ChatGPT-3.5, ChatGPT-5, and DeepSeek on Medical Microbiology MCQs

View Full Paper
Ask AI
Bookmark
Share

Authors

MSMalik SallamAIAmal IrshaidJSJohan Snygg

Discussion

Loading...

Member takes

Overview

Evaluation reveals generative AI models ChatGPT-5 and DeepSeek outperform traditional students in medical microbiology, indicating their educational potential.

Key Points

  • ChatGPT-5 scored 96.0, significantly outperforming ChatGPT-3.5 in medical microbiology assessments, underscoring its effectiveness.
  • The analysis included evaluating 80 MCQs classified by Bloom’s taxonomy, revealing varying performance in cognitive domains across models.
  • Content quality assessed by the CLEAR tool indicated a strong correlation between model accuracy and higher scores for correct answers.
  • Regular performance benchmarking is crucial for the responsible integration of genAI into medical education and assessments.

Cite This Study

Sallam et al. (2025) studied this question.

synapsesocial.com/papers/68af7b1f7567bf4f94ff2d15https://doi.org/10.61360/bonicetr252018770801
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Benchmarking large language models on the United States medical licensing examination for clinical reasoning and medical licensing scenarios2025 · 23 citations
  2. 2Evaluation of DeepSeek-R1 and ChatGPT on the Chinese National Medical Licensing Examination: A Multi-Year Comparative Study2025
  3. 3Comparative Assessment of Large Language Models in Optics and Refractive Surgery: Performance on Multiple-Choice Questions2025 · 1 citations
  4. 4Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients2025
  5. 5Performance of DeepSeek and ChatGPT on the Chinese Health Professional and Technical Examination: A comparative study2026 · 2 citations