Pith

open record

sign in
Browse

arxiv: 2501.13949 · v1 · pith:XEGRWJMY · submitted 2025-01-20 · cs.CL · cs.AI

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:XEGRWJMYrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords openaiophthalmologyreasoningdiseasesperformancequestionquestionsranked
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.