NeuroVL medical VLM trained on 1M neuroimaging studies claims to beat OpenAI and Google models

Dr_Alex_Crimi · x · 2026-11-20

NeuroVL is a vision-language model for neuroradiology trained on 1 million clinical neuroimaging studies (450k patients, 10M scans paired with reports). It reads whole exams across slice/scan/study hierarchies, writes radiology reports, and was evaluated across 24 datasets in 21 countries with longitudinal disease monitoring and red-teaming. The authors report it outperforms frontier models from OpenAI and Google on these tasks.

Original post →

More from Models

Models channel →