Jul 2026
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
PerceptionBench provides a capability-level standard for measuring and diagnosing the visual perception boundaries of MLLMs, by diagnosing the earliest failure points in the responses of frontier MLLMs across 42 existing benchmarks and constructing an error taxonomy whose perception branch defines ten atomic perceptual capabilities.
Zichao Lin, Yifeng Xie, Bowen Qu et al.
· arXiv.org · 2 citations