Post

New research · Ophthalmology
Arquivos brasileiros de oftalmologia · 1d
AI / informaticsArquivos brasileiros de oftalmologia · 2026

Assessing a large language model for glaucoma knowledge: ChatGPT-5 versus residents.

Mauro Gobira, Rodrigo Moreira, Flavio J L Galhardo Carvalho Filho … Ivan M Tavares
Read paper
OphthalmologyAI / informatics

ChatGPT-5 had higher odds of correctly answering glaucoma questions than ophthalmology residents.

Assessing a large language model for glaucoma knowledge: ChatGPT-5 versus residents.

Mauro Gobira et al. · Arquivos brasileiros de oftalmologia · 2026
Purpose

To assess the performance of a contemporary large language model (ChatGPT-5) against ophthalmology residents on a standardized set of glaucoma multiple-choice questions.

Methods

We conducted a cross-sectional comparative study with 189 text-only glaucoma multiple-choice questions from the Cybersight question bank.

Results
ChatGPT-5 was more likely to correctly answer glaucoma questions than eye doctor trainees
More results

ChatGPT-5 received 164 of 189 correct responses (86.8%; 95% CI, 81.2-90.9).

Residents' overall accuracy was 62.9% (713/1,134; 95% CI, 60.0-65.6).

The top-performing resident earned 76.7%.

More results

ChatGPT-5 correctly answered 17/189 items (9.0%), but fewer than half of residents were correct ("large language model-only wins"), whereas residents were more successful on items that ChatGPT-5 overlooked.

“
Conclusion · 1 of 3

ChatGPT-5 outperformed ophthalmology residents on text-based glaucoma multiple-choice questions, indicating its potential as a subspecialty education and assessment tool.

Conclusion · 2 of 3

Generalizability is limited by the single question bank, text-only items, a small resident cohort, and the evaluation of one large language model version at a single time point.

Conclusion · 3 of 3

Before incorporating these findings into clinical decision-making, larger, multimodal, and longitudinal studies are required.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Cohort Study
median 9
optometry referrals contained more complete documentation for glaucoma
Study
71.27%
medical students' higher accuracy in identifying eye infections after artificial intelligence training
Cross-sectional
64%
most patients reported little difficulty with their eye injections
Cross-sectional
37%
Only 37% of primary care providers and endocrinologists correctly identified diabetic retinopathy status.
Randomized Trial
adjusted difference -4.97
Baduanjin exercise led to a better overall quality of life than routine care
Study
58.26%
Qwen-7B correctly found eye diseases in over half of cases without specific training
Case Report
24 months
the patient's eye cancer remained gone for this period after treatment
Study
Mean 184 vs. 137
Residents in subsidized programs performed more cataract surgeries as primary surgeon.