August 13, 2025

One Year On: Assessing Progress of Multimodal Large Language Model Performance on RSNA 2024 Case of the Day Questions

Key Points

OpenAI's latest models achieved an accuracy comparable to expert radiologists, showing significant performance improvement.
In the past year, multimodal large language models have advanced notably in the context of RSNA Case Questions.
Performance comparison highlights that OpenAI outperforms both Google and Meta, indicating shifts in competitive landscape.
These advancements suggest that the integration of multimodal capabilities may enhance diagnostic accuracy in radiology.

Abstract

Multimodal large language models have significantly improved in assessing RSNA Case of the Day Questions over the past year, with OpenAI’s latest models outperforming those from Google and Meta; notably, OpenAI o1 had an accuracy comparable to expert radiologists.

AI से पूछें

Bookmark