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.
More from Models
- Datalab shows ParseBench is gameable: a 650M model hit near the top with a few RL steps — VikParuchuri · 2026-11-20
- Datalab's 25-min OCR eval guide: why 'everyone is #1' and how to benchmark on your own documents — VikParuchuri · 2026-11-20
- Datalab CEO on benchmark gaming: a 7-point checklist to audit any OCR leaderboard claim — VikParuchuri · 2026-11-20
- Cloudflare releases Clairic on Hugging Face: single-pass extraction beyond decision models — multimodalart · 2026-11-20
- GPT-6.2 Astra matches predecessor's MazeBench score at $225 vs $840 — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Sol narrows gap with Astra but still scores less at same price — patience_cave · 2026-11-20