LoMeVQA - Progress Description: leaderboard
LoMeVQA (2026) poses longitudinal visual questions about two or more chest radiographs of the same patient taken at different times. This board scores free-text descriptions of the change between two studies by F1-RadGraph, the overlap of clinical entities and relations with the reference, in percent; higher is better.
Metric: F1-RadGraph clinical efficacy (%; free-text description of the change between two radiographs, clinical entities and relations matched against the reference; LoMeVQA-test, 2,500 expert-reviewed longitudinal chest radiograph samples over five tasks, zero-shot; higher is better). Source: arxiv.org. Saturation forecast: Around 2033. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 23.55 | #453 |
| 2 | MedGemma-4B | 20.95 | #2444 |
| 3 | GPT-5 | 18.3 | #167 |
| 4 | GPT-4o | 14.36 | #741 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=lomevqa-progress-description · How It Works · Data refreshed daily, snapshot 2026-11-13.