# GPT-6 scores over 85% on medical image alignment assessment

> A new study shows frontier multimodal models like GPT-6 can reliably judge anatomical correspondence in medical images, reaching 85% accuracy.

Oossa · 2026-10-07 · https://oossa.com/en/gpt-6-scores-over-85-on-medical-image-alignment-assessment

Researchers evaluated recent multimodal large language models on the task of medical image alignment assessment, which checks whether two scans show the same anatomy. The study found that GPT‑6 achieved more than 85% accuracy across almost all test scenarios. Older frontier models performed only slightly better than random guessing, while a locally fine‑tuned model matched GPT‑6 on its trained tasks but struggled with new settings. The authors suggest this ability could support quality‑control checks in medical imaging pipelines.

## The facts

- GPT‑6 achieved >85% accuracy on medical image alignment tasks (2026 study).
- Paper submitted on 28 Sep 2026 and published 07 Oct 2026.

## Why it matters

Hospitals could use advanced generalist models to automate image‑quality checks, reducing reliance on scarce specialist operators.

## Sources & references

1. [Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models](https://arxiv.org/abs/2610.06896) – arXiv cs.CV, 2026-10-07

Last updated: 2026-10-07