Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 12, 2025VisionOpen Access

Comparative Assessment of Large Language Models in Optics and Refractive Surgery: Performance on Multiple-Choice Questions

View Full Paper
Ask AI
Bookmark
Share

Authors

LALeah AttalESElad ShvartzAGAlon Gorenshtein

Discussion

Loading...

Member takes

Overview

Comparative analysis of AI models' accuracy in multiple-choice questions in optics, suggesting their role in medical education.

Key Points

  • ChatGPT O1 achieved the highest accuracy (83.5%), excelling particularly in calculations and optics questions.
  • DeepSeek V3 performed best on refractive surgery questions, with an accuracy of 89.7%, highlighting its competency.
  • ChatGPT O3 Mini led in image analysis, demonstrating its strength with an 88.2% accuracy in related MCQs.
  • The findings suggest the utility of advanced AI models in enhancing ophthalmology education, particularly for complex topics.

Cite This Study

Attal et al. (2025) studied this question.

synapsesocial.com/papers/68ebe3d6becc64ad52fdac48https://doi.org/10.3390/vision9040085
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. 1The Performance of Artificial Intelligence-based Large Language Models on Ophthalmology-related Questions in Swedish Proficiency Test for Medicine: ChatGPT-4 omni vs Gemini 1.5 Pro2024 · 20 citations
  2. 2Evaluating ChatGPT-4’s Diagnostic Accuracy: Impact of Visual Data Integration2024 · 54 citations
  3. 3The impact of artificial intelligence in medicine on the future role of the physician2019 · 814 citations
  4. 4An Evaluation of the Performance of OpenAI-o1 and GPT-4o in the Japanese National Examination for Physical Therapists2025 · 5 citations
  5. 5Evaluating search engines and large language models for answering health questions2025 · 31 citations