Moderate evidence
Published recordHealthProblem Space
More
Comparative evaluation of GPT 5.2 Pro and Gemini 3 Pro large multimodal models for retinal optical coherence tomography interpretation
- Truvace record
- TRV-2026-2992raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Benchmark or lab evaluation
- Sources
- 1 sourcePeer-reviewed
- sha256
- b002266629f1…check it
Purpose: Large multimodal models (LMMs) capable of interpreting medical images are increasingly accessible to patients, yet their reliability for retinal optical coherence tomography (OCT) interpretation remains uncertain. This study evaluated the performance of two state-of-the-art LMMs in detecting OCT features and generating diagnostic interpretations. Methods: In this cross-sectional study, 330 publicly available retinal OCT B-scans spanning 12 diagnostic categories, including normal scans and common retinal…
The problem
In a cross-sectional study of 330 retinal OCT scans, GPT 5.2 Pro reached 32.1% diagnostic accuracy and Gemini 3 Pro 58.8%, and GPT 5.2 Pro failed to correctly identify any normal scan.
What this doesn’t fix
The study used publicly available scans and zero-shot prompting of two models, so results may not reflect other models or clinical use; the authors say careful validation is still needed.
Sources
1 on file- Graefe's Archive for Clinical and Experimental Ophthalmologydoi:10.1007/s00417-026-07604-7
Cite this record
v1Truvace Impact Record TRV-2026-2992, v1: “Comparative evaluation of GPT 5.2 Pro and Gemini 3 Pro large multimodal models for retinal optical coherence tomography interpretation.” Truvace, 2026-11-17. /record/TRV-2026-2992 (accessed on the day you copy it). sha256 b002266629f11de3…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2992 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace