OmniDocBench

Study / Research

A popular benchmark for document understanding used by frontier and open-source models, considered somewhat saturated and rigid for agent evaluation.

Mentioned in 1 video

Videos Mentioning OmniDocBench

AI Dev 26 x SF | Jerry Liu: My Agent Can't Read a PDF?

AI Dev 26 x SF | Jerry Liu: My Agent Can't Read a PDF?

DeepLearningAI

A popular benchmark for document understanding used by frontier and open-source models, considered somewhat saturated and rigid for agent evaluation.