# LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

arXiv: https://arxiv.org/abs/2503.19990 · HTML: https://mlsanity.com/paper/2503.19990/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 48 of its 80 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 48)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)

## Built on by (most cited first, 30 of 49)

- [MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence](https://mlsanity.com/paper/2505.23764/) (2025)
- [Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing](https://mlsanity.com/paper/2504.02826/) (2025)
- [How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective](https://mlsanity.com/paper/2509.18905/) (2025)
- [Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning](https://mlsanity.com/paper/2510.12712/) (2025)
- [STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs](https://mlsanity.com/paper/2505.15804/) (2025)
- [SpaceVista: All-Scale Visual Spatial Reasoning from mm to km](https://mlsanity.com/paper/2510.09606/) (2025)
- [SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards](https://mlsanity.com/paper/2511.07403/) (2025)
- [GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs](https://mlsanity.com/paper/2505.17653/) (2025)
- [ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations](https://mlsanity.com/paper/2505.14404/) (2025)
- [Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models](https://mlsanity.com/paper/2511.01618/) (2025)
- [Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models](https://mlsanity.com/paper/2505.20728/) (2025)
- [CharacterShot: Controllable and Consistent 4D Character Animation](https://mlsanity.com/paper/2508.07409/) (2025)
- [A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis](https://mlsanity.com/paper/2510.05414/) (2025)
- [Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2510.13394/) (2025)
- [CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion](https://mlsanity.com/paper/2509.19979/) (2025)
- [ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints](https://mlsanity.com/paper/2511.18450/) (2025)
- [Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions](https://mlsanity.com/paper/2601.03590/) (2026)
- [What's Holding Back Latent Visual Reasoning?](https://mlsanity.com/paper/2605.18445/) (2026)
- [Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation](https://mlsanity.com/paper/2602.11635/) (2026)
- [Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs](https://mlsanity.com/paper/2507.11932/) (2025)
- [Vesta: A Generalist Embodied Reasoning Model](https://mlsanity.com/paper/2606.20905/) (2026)
- [Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models](https://mlsanity.com/paper/2511.19032/) (2025)
- [GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks](https://mlsanity.com/paper/2512.22207/) (2025)
- [TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning](https://mlsanity.com/paper/2601.16520/) (2026)
- [MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents](https://mlsanity.com/paper/2505.20148/) (2025)
- [Unleashing Perception-Time Scaling to Multimodal Reasoning Models](https://mlsanity.com/paper/2510.08964/) (2025)
- [GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation](https://mlsanity.com/paper/2510.22118/) (2025)
- [Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark](https://mlsanity.com/paper/2601.00092/) (2025)
- [Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles](https://mlsanity.com/paper/2601.13705/) (2026)
- [TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models](https://mlsanity.com/paper/2602.18884/) (2026)

## Abstract (arXiv)

Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential steps. However, the extent to which current Multimodal Large Language Models (MLLMs) possess this capability remains largely unexplored. Inspired by LEGO construction, a recreational activity that critically relies on multi-step spatial reasoning, we introduce LEGO-Puzzles: a benchmark designed to systematically evaluate the spatial reasoning capabilities of MLLMs from basic spatial understanding to multi-step planning. LEGO-Puzzles contains two task sets. The Elementary set covers 11 visual question-answering (VQA) tasks with 1,100 carefully curated samples to test elementary spatial reasoning skills that are cruical for LEGO assembly. The Planning set directly requires the model to generate a step-by-step plan for assembling a target LEGO structure, where the tasks are organized into subsets with different planning horizons ranging up to 8. Our evaluation of 29 state-of-the-art MLLMs shows that even the strongest models struggle with elementary reasoning tasks in LEGO construction, falling at least 20% behind human performance. The planning accuracy also quickly drops to 0% as the number of planning steps increases, whereas our human participants solve all the tasks perfectly. Switching the output format from multiple choice to image generation degrades model performance even further, leading to zero accuracy even for planning 3 steps. Overall, LEGO-Puzzles reveals critical limitations in current MLLMs' spatial reasoning capabilities and highlights the need for substantial advances.