# Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

arXiv: https://arxiv.org/abs/2506.04633 · HTML: https://mlsanity.com/paper/2506.04633/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 65 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 33)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [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)
- [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)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning](https://mlsanity.com/paper/2105.04165/) (2021)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models](https://mlsanity.com/paper/2306.05179/) (2023)
- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [Stratified Rule-Aware Network for Abstract Visual Reasoning](https://mlsanity.com/paper/2002.06838/) (2020)
- [Perception Tokens Enhance Visual Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2412.03548/) (2024)
- [Does Spatial Cognition Emerge in Frontier Models?](https://mlsanity.com/paper/2410.06468/) (2024)
- [Abstract Visual Reasoning with Tangram Shapes](https://mlsanity.com/paper/2211.16492/) (2022)
- [IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations](https://mlsanity.com/paper/2404.01266/) (2024)
- [KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models](https://mlsanity.com/paper/2407.17773/) (2024)
- [Visual analogy: Deep learning versus compositional models](https://mlsanity.com/paper/2105.07065/) (2021)
- [SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments](https://mlsanity.com/paper/2108.06180/) (2021)

## Built on by (most cited first, 21 of 21)

- [ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.27492/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [STEP3-VL-10B Technical Report](https://mlsanity.com/paper/2601.09668/) (2026)
- [Holistic Evaluation of Multimodal LLMs on Spatial Intelligence](https://mlsanity.com/paper/2508.13142/) (2025)
- [Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods](https://mlsanity.com/paper/2511.15722/) (2025)
- [Mull-Tokens: Modality-Agnostic Latent Thinking](https://mlsanity.com/paper/2512.10941/) (2025)
- [Imagination Helps Visual Reasoning, But Not Yet in Latent Space](https://mlsanity.com/paper/2602.22766/) (2026)
- [Toward Cognitive Supersensing in Multimodal Large Language Model](https://mlsanity.com/paper/2602.01541/) (2026)
- [MentisOculi: Revealing the Limits of Reasoning with Mental Imagery](https://mlsanity.com/paper/2602.02465/) (2026)
- [Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning](https://mlsanity.com/paper/2604.04746/) (2026)
- [Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation](https://mlsanity.com/paper/2602.11635/) (2026)
- [MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints](https://mlsanity.com/paper/2603.20194/) (2026)
- [SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments](https://mlsanity.com/paper/2604.14144/) (2026)
- [Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning](https://mlsanity.com/paper/2509.23744/) (2025)
- [TangramSR: Can Vision-Language Models Reason in Continuous Geometric Space?](https://mlsanity.com/paper/2602.05570/) (2026)
- [Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study](https://mlsanity.com/paper/2510.21160/) (2025)
- [HumanCLAW: Can Vision-Language Models Act Through a Body?](https://mlsanity.com/paper/2607.27180/) (2026)
- [PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought](https://mlsanity.com/paper/2606.24539/) (2026)
- [MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations](https://mlsanity.com/paper/2602.19357/) (2026)
- [Spatial Competence Benchmark](https://mlsanity.com/paper/2604.09594/) (2026)
- [VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis](https://mlsanity.com/paper/2605.22570/) (2026)

## Abstract (arXiv)

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation. We introduce STARE(Spatial Transformations and Reasoning Evaluation), a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through multi-step visual simulation. STARE features 4K tasks spanning foundational geometric transformations (2D and 3D), integrated spatial reasoning (cube net folding and tangram puzzles), and real-world spatial reasoning (perspective and temporal reasoning), reflecting practical cognitive challenges like object assembly, mechanical diagram interpretation, and everyday spatial navigation. Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks like 3D cube net folding and tangram puzzles that require multi-step visual simulations. Humans achieve near-perfect accuracy but take considerable time (up to 28.9s) on complex tasks, significantly speeding up (down by 7.5 seconds on average) with intermediate visual simulations. In contrast, models exhibit inconsistent performance gains from visual simulations, improving on most tasks but declining in specific cases like tangram puzzles (GPT-4o, o1) and cube net folding (Claude-3.5, Gemini-2.0 Flash), indicating that models may not know how to effectively leverage intermediate visual information.