Saved in:
Bibliographic Details
Main Authors: Ye, Hengwei, Guan, Yuanting, Ge, Yuxuan, Zhu, Tianying, Guan, Zhenhan, Zhong, Yijia, Zhang, Yijing, Zhang, Han, Wu, Yingna, Tian, Zheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918422784245760
author Ye, Hengwei
Guan, Yuanting
Ge, Yuxuan
Zhu, Tianying
Guan, Zhenhan
Zhong, Yijia
Zhang, Yijing
Zhang, Han
Wu, Yingna
Tian, Zheng
author_facet Ye, Hengwei
Guan, Yuanting
Ge, Yuxuan
Zhu, Tianying
Guan, Zhenhan
Zhong, Yijia
Zhang, Yijing
Zhang, Han
Wu, Yingna
Tian, Zheng
contents Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20209
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
Ye, Hengwei
Guan, Yuanting
Ge, Yuxuan
Zhu, Tianying
Guan, Zhenhan
Zhong, Yijia
Zhang, Yijing
Zhang, Han
Wu, Yingna
Tian, Zheng
Computation and Language
Artificial Intelligence
Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.
title Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.20209