Current medical multimodal models, including GPT-4o and Claude 3.5 Sonnet, fail simple perceptual tasks on medical images that human experts solve almost perfectly.
These models combine text and image understanding and are typ- ically evaluated using visual question answering (VQA) tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine
Current medical multimodal models, including GPT-4o and Claude 3.5 Sonnet, fail simple perceptual tasks on medical images that human experts solve almost perfectly.