The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems?
Percept-V is introduced, a dataset containing 6000 program-generated uncontaminated images divided into 30 domains, where each domain tests one or more TVPS-4 skills, and shows a weak performance of SoTA proprietary and open-source MLLMs compared to very high human performance on Percept-V.
Sam Ghosh, Ashish Goswami, Naman Agarwal et al.
· 0 citations