A new bilingual 1,314-question benchmark finds the best multimodal model scores about 60%, below the average human score of 62%, beating humans only on knowledge and basic image-text tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MANBench: Is Your Multimodal Model Smarter than Human?
A new bilingual 1,314-question benchmark finds the best multimodal model scores about 60%, below the average human score of 62%, beating humans only on knowledge and basic image-text tasks.