KOSMOS-2.5: A Multimodal Literate Model

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-on-docvqa-test	Kosmos-2.5-chat	#68	ANLS: 0.811
chart-question-answering-on-chartqa	Kosmos-2.5-chat	#107	1:1 Accuracy: 62.3