KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?

TL;DR

This paper introduces KidVis, a benchmark based on human visual development, revealing that current multimodal large language models lack fundamental visual primitives compared to children, and scaling model size alone does not improve these capabilities.

Contribution

The paper presents KidVis, a novel benchmark to evaluate basic visual primitives in MLLMs, highlighting their deficiencies relative to human children and uncovering the limitations of scaling model size.

Findings

Children score around 95.32 on KidVis tasks.

GPT-5 scores only 67.33, showing a performance gap.

Scaling model size does not linearly improve visual primitives.

Abstract

While Multimodal Large Language Models (MLLMs) have demonstrated impressive proficiency in high-level reasoning tasks, such as complex diagrammatic interpretation, it remains an open question whether they possess the fundamental visual primitives comparable to human intuition. To investigate this, we introduce KidVis, a novel benchmark grounded in the theory of human visual development. KidVis deconstructs visual intelligence into six atomic capabilities - Concentration, Tracking, Discrimination, Memory, Spatial, and Closure - already possessed by 6-7 year old children, comprising 10 categories of low-semantic-dependent visual tasks. Evaluating 20 state-of-the-art MLLMs against a human physiological baseline reveals a stark performance disparity. Results indicate that while human children achieve a near-perfect average score of 95.32, the state-of-the-art GPT-5 attains only 67.33. Crucially, we observe a "Scaling Law Paradox": simply increasing model parameters fails to yield linear improvements in these foundational visual capabilities. This study confirms that current MLLMs, despite their reasoning prowess, lack the essential physiological perceptual primitives required for generalized visual intelligence.