Glossary
Multimodal
Able to take in or produce more than one kind of data, such as text, images, audio, and video.
A multimodal model works with several kinds of data. It might read a photo and answer questions about it, listen to speech and reply aloud, or generate images from a text description.
Many recent general-purpose models are multimodal. The term covers a range of abilities, so it helps to check which inputs and outputs a model actually supports and whether all of them are available to the public.
A model may handle one mode well and another poorly. Benchmark results for text do not tell you how well it reads medical images or diagrams.