Can OpenAI o1 Reason Well in Ophthalmology? A 6,990-Question Head-to-Head Evaluation Study

TL;DR

This study evaluates OpenAI o1's performance and reasoning in ophthalmology questions, finding it excels in accuracy but has limitations in reasoning capabilities, highlighting the need for domain-specific improvements.

Contribution

It provides a comprehensive head-to-head comparison of OpenAI o1 with other LLMs in ophthalmology, revealing strengths and areas for improvement.

Findings

O1 achieved the highest accuracy (0.88) and macro-F1 score.

O1 ranked first in Lens and Glaucoma subtopics.

O1 performed better on queries with longer explanations.

Abstract

Question: What is the performance and reasoning ability of OpenAI o1 compared to other large language models in addressing ophthalmology-specific questions? Findings: This study evaluated OpenAI o1 and five LLMs using 6,990 ophthalmological questions from MedMCQA. O1 achieved the highest accuracy (0.88) and macro-F1 score but ranked third in reasoning capabilities based on text-generation metrics. Across subtopics, o1 ranked first in ``Lens'' and ``Glaucoma'' but second to GPT-4o in ``Corneal and External Diseases'', ``Vitreous and Retina'' and ``Oculoplastic and Orbital Diseases''. Subgroup analyses showed o1 performed better on queries with longer ground truth explanations. Meaning: O1's reasoning enhancements may not fully extend to ophthalmology, underscoring the need for domain-specific refinements to optimize performance in specialized fields like ophthalmology.