BabyVision: Visual Reasoning Beyond Language

BabyVision benchmarks core visual reasoning without language and finds top MLLMs score far below human children.

Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. Charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Xiaobo Hu, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li

Published Jan 10, 20261 citation▲ 201 on Hugging Face Code ★ 257 arXiv ↗

80%

OverallMust read

OverallMust readVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel12/20reviewers recommend it

lenient 4/5

medium 7/10

strict 1/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

BabyVision delivers a rigorous 22-subclass taxonomy that exposes a stark 49.7-to-94.1 visual-reasoning gap in leading MLLMs, though its 388-item scale and BabyVision-Gen pipeline remain under-ablated and insufficiently proven to transcend linguistic priors.

Abstract

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.