While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.
@article{arxiv.2601.06521,
title = {BabyVision: Visual Reasoning Beyond Language},
author = {Liang Chen and Weichu Xie and Yiyan Liang and Hongfeng He and Hans Zhao and Zhibo Yang and Zhiqi Huang and Haoning Wu and Haoyu Lu and Y. charles and Yiping Bao and Yuantao Fan and Guopeng Li and Haiyang Shen and Xuanzhong Chen and Wendong Xu and Shuzheng Si and Zefan Cai and Wenhao Chai and Ziqi Huang and Fangfu Liu and Tianyu Liu and Baobao Chang and Xiaobo Hu and Kaiyuan Chen and Yixin Ren and Yang Liu and Yuan Gong and Kuan Li},
journal= {arXiv preprint arXiv:2601.06521},
year = {2026}
}
Comments
26 pages, Homepage at https://unipat.ai/blog/BabyVision