# Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models

arXiv: https://arxiv.org/abs/2503.19707 · HTML: https://mlsanity.com/paper/2503.19707/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 66 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/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning](https://mlsanity.com/paper/2410.16162/) (2024)
- [Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics](https://mlsanity.com/paper/2502.11859/) (2025)
- [Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning](https://mlsanity.com/paper/2411.16761/) (2024)

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

- [SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.23075/) (2025)
- [Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models](https://mlsanity.com/paper/2601.12626/) (2026)
- [Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models](https://mlsanity.com/paper/2505.20728/) (2025)
- [11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis](https://mlsanity.com/paper/2508.20068/) (2025)
- [Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression](https://mlsanity.com/paper/2511.11239/) (2025)
- [ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints](https://mlsanity.com/paper/2511.18450/) (2025)
- [Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap](https://mlsanity.com/paper/2604.16256/) (2026)
- [InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity](https://mlsanity.com/paper/2511.18200/) (2025)
- [See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning](https://mlsanity.com/paper/2603.23864/) (2026)
- [Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation](https://mlsanity.com/paper/2510.03863/) (2025)
- [A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments](https://mlsanity.com/paper/2512.13517/) (2025)
- [How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning](https://mlsanity.com/paper/2603.24866/) (2026)
- [BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models](https://mlsanity.com/paper/2506.05440/) (2025)
- [It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2603.08011/) (2026)
- [Do multimodal models imagine electric sheep?](https://mlsanity.com/paper/2605.09693/) (2026)
- [Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models](https://mlsanity.com/paper/2606.05531/) (2026)
- [Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation](https://mlsanity.com/paper/2608.17512/) (2026)
- [Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding](https://mlsanity.com/paper/2509.21922/) (2025)
- [A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics](https://mlsanity.com/paper/2510.27033/) (2025)
- [SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation](https://mlsanity.com/paper/2511.00054/) (2025)
- [Tri-Bench: Stress-Testing VLM Reliability on Spatial Reasoning under Camera Tilt and Object Interference](https://mlsanity.com/paper/2512.08860/) (2025)
- [Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures](https://mlsanity.com/paper/2603.17333/) (2026)
- [SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems](https://mlsanity.com/paper/2604.16022/) (2026)
- [SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization](https://mlsanity.com/paper/2605.14704/) (2026)
- [Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely](https://mlsanity.com/paper/2605.31387/) (2026)
- [The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning](https://mlsanity.com/paper/2606.11918/) (2026)
- [Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning](https://mlsanity.com/paper/2606.12830/) (2026)
- [OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning](https://mlsanity.com/paper/2606.30378/) (2026)
- [OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment](https://mlsanity.com/paper/2607.17657/) (2026)
- [MindTopo: Can Foundation Models Reason in Topological Space?](https://mlsanity.com/paper/2609.11900/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing benchmarks for VLMs include spatial components, which often fail to isolate spatial reasoning from related tasks such as object detection or semantic comprehension. In this paper, we address these deficiencies with a multi-faceted approach towards understanding spatial reasoning. Informed by the diverse and multi-dimensional nature of human spatial reasoning abilities, we present a detailed analysis that first delineates the core elements of spatial reasoning: spatial relations, orientation and navigation, mental rotation, and spatial visualization, and then assesses the performance of these models in both synthetic and real-world images, bridging controlled and naturalistic contexts. We analyze 13 state-of-the-art Vision-Language Models, uncovering pivotal insights into their spatial reasoning performance. Our results reveal profound shortcomings in current VLMs, with average accuracy across the 13 models approximating random chance, highlighting spatial reasoning as a persistent obstacle. This work not only exposes the pressing need to advance spatial reasoning within VLMs but also establishes a solid platform for future exploration. Code available on GitHub (https://github.com/stogiannidis/srbench) and dataset available on HuggingFace (https://huggingface.co/datasets/stogiannidis/srbench).