mlsanityData to 7 Oct 2026

Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs

arXiv 2603.20209 ↗First posted 2 Mar 2026cs.CL cs.AIcited by 2

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

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/.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 51 of its 70 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

51 of 70 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward8 Jun
  2. 2024A Survey on Evaluation of Multimodal Large Language Models28 Aug
  3. 2024LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts6 Jul
  4. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models25 Jun
  5. 2024Cantor: Inspiring Multimodal Chain-of-Thought of MLLM24 Apr
  6. 2024Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image22 Feb
  7. 2023InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models20 Nov

Other references · 44

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  4. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  5. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  6. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  7. 2025OpenAI GPT-5 System Cardcited by 910
  8. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  9. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  10. 2022Using cognitive psychology to understand GPT-3cited by 389
  11. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 320
  12. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
32 more
  1. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  2. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  3. 2023OneLLM: One Framework to Align All Modalities with Languagecited by 185
  4. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158
  5. 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editingcited by 132
  6. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  7. 2023SmartPlay: A Benchmark for LLMs as Intelligent Agentscited by 123
  8. 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
  9. 2023SEED-Bench-2: Benchmarking Multimodal Large Language Modelscited by 96
  10. 2024GameBench: Evaluating Strategic Reasoning Abilities of LLM Agentscited by 89
  11. 2024MileBench: Benchmarking MLLMs in Long Contextcited by 86
  12. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 81
  13. 2023EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planningcited by 66
  14. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 64
  15. 2024ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhancecited by 64
  16. 2023LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoningcited by 59
  17. 2019Obstacle Tower: A Generalization Challenge in Vision, Control, and Planningcited by 54
  18. 2024Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Modelscited by 53
  19. 2024Elysium: Exploring Object-level Perception in Videos via MLLMcited by 48
  20. 2024Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReIDcited by 39
  21. 2024PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planningcited by 38
  22. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  23. 2023Link-Context Learning for Multimodal LLMscited by 24
  24. 2024Human-like object concept representations emerge naturally in multimodal large language modelscited by 24
  25. 2024Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboardcited by 22
  26. 2024LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Modelscited by 19
  27. 2025Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLMcited by 14
  28. 2024MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrievalcited by 9
  29. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 8
  30. 2024Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidencecited by 5
  31. 2024Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluationcited by 4
  32. 2023The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Researchcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Evaluating Cognitive Age Alignment in Interactive AI Agentscited by 2
  2. 2026An Exam for Active Observerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?
  2. 2026LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")
  3. 2026BabyVision: Visual Reasoning Beyond Language
  4. 2025MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
  5. 2024Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens
  6. 2025MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models
  7. 2023Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses
  8. 2025IQBench: How "Smart'' Are Vision-Language Models? A Study with Human IQ Tests