MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
Open paper
Benchmark
Model
Rank
Results
medical-visual-question-answering-on-pathvqa
LLaVA-Tri with MedTrinity (extra data)
#2
Closed-Ended Accuracy: 92.7
Rank counts only results with a code link.