mlsanityData to 14 Oct 2026

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

arXiv 2506.03135 ↗First posted 3 Jun 2025cs.CV cs.AI cs.CLcited by 114

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Spatial reasoning is a key aspect of cognitive psychology and remains a bottleneck for current vision-language models (VLMs). While extensive research has aimed to evaluate or improve VLMs' understanding of basic spatial relations, such as distinguishing left from right, near from far, and object counting, these tasks cover only the most elementary layer of spatial reasoning and are largely approaching saturation in the latest reasoning models. In this work, we introduce OmniSpatial, a comprehensive and challenging benchmark for spatial reasoning, grounded in cognitive psychology. OmniSpatial covers four major categories: dynamic reasoning, complex spatial logic, spatial interaction, and perspective-taking, with 50 fine-grained subcategories. Through careful manual annotation, we construct over 8.4K question-answer pairs. Extensive experiments show that both open- and closed-source VLMs exhibit significant limitations in comprehensive spatial reasoning. We also explore two strategies-PointGraph (explicit scene graph cues) and SpatialCoT (novel-view chain-of-thought)-to bolster spatial reasoning.

Key facts. Cited by 114 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 95 of its 132 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

95 of 132 references.

Closest ancestors · 20

Same direction, newest first

  1. 2025ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models27 May
  2. 2025Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation24 Apr
  3. 2025CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting21 Apr
  4. 2025Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas3 Mar
  5. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation18 Feb
  6. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  7. 2024An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models9 Nov
  8. 2024AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation1 Oct
  9. 2024Multi-modal Situated Reasoning in 3D Scenes4 Sep
  10. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation3 Sep
  11. 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models21 Jun
  12. 2024GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs19 Jun
8 more
  1. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models3 Jun
  2. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors18 Mar
  3. 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs12 Feb
  4. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities22 Jan
  5. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoning30 Oct
  6. 2023Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models18 Aug
  7. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought24 May
  8. 2022Visual Spatial Reasoning30 Apr

Other references · 75

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  9. 2023Segment Anythingcited by 8,234
  10. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  11. 2023Visual Instruction Tuningcited by 7,869
  12. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
38 more
  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  11. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  12. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  13. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  14. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  15. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  16. 2025Gemma 3 Technical Reportcited by 1,824
  17. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
  18. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  19. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,109
  20. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  21. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  22. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 550
  23. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  24. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  25. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  26. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  27. 2023Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4Vcited by 299
  28. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 297
  29. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 251
  30. 2024World Model on Million-Length Video And Language With Blockwise RingAttentioncited by 198
  31. 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 194
  32. 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understandingcited by 182
  33. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 164
  34. 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understandingcited by 160
  35. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 152
  36. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 137
  37. 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticscited by 136
  38. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 29; 2026: 85.

114 papers.

Sort:

By area:

  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  2. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  3. 2025Self-Rewarding Vision-Language Model via Reasoning Decompositioncited by 97
  4. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 82
  5. 2025G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoningcited by 44
  6. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  7. 2025Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmarkcited by 43
  8. 2025MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligencecited by 38
  9. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 33
  10. 2026STEP3-VL-10B Technical Reportcited by 32
  11. 2025Holistic Evaluation of Multimodal LLMs on Spatial Intelligencecited by 29
  12. 2025Geometrically-Constrained Agent for Spatial Reasoningcited by 26
38 more
  1. 2025SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligencecited by 23
  2. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methodscited by 23
  3. 2025Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenescited by 20
  4. 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoningcited by 18
  5. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoningcited by 17
  6. 2025SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMscited by 14
  7. 2025DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Actioncited by 12
  8. 2025From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMscited by 12
  9. 2025Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Modelscited by 12
  10. 2025SpatialTree: How Spatial Abilities Branch Out in MLLMscited by 12
  11. 2026CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environmentscited by 11
  12. 2026SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?cited by 11
  13. 2025Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligencecited by 10
  14. 2026MLLM-4D: Towards Visual-based Spatial-Temporal Intelligencecited by 10
  15. 2025Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Modelscited by 9
  16. 2025Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regressioncited by 8
  17. 2026Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomaliescited by 8
  18. 2026Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agentscited by 7
  19. 2026Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluationcited by 6
  20. 2026Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimizationcited by 6
  21. 2026Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMscited by 6
  22. 2026OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMscited by 6
  23. 2025InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexitycited by 5
  24. 2026Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representationscited by 5
  25. 2025Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoningcited by 4
  26. 2025Spatial-aware Vision Language Model for Autonomous Drivingcited by 4
  27. 2026A2Eval: Agentic and Automated Evaluation for Embodied Braincited by 4
  28. 2026World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoningcited by 4
  29. 2026MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMscited by 4
  30. 2025MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Imagescited by 3
  31. 2025Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspectivecited by 3
  32. 2026Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spacescited by 3
  33. 2026VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observationscited by 3
  34. 2026MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Modelcited by 3
  35. 2026SPACENUM: Revisiting Spatial Numerical Understanding in VLMscited by 3
  36. 20254D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillationcited by 2
  37. 2026SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoningcited by 2
  38. 2026How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoningcited by 2

50 most cited of 114 All 114 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
  2. 2024SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation
  3. 2025Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models
  4. 2025InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
  5. 2026Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images
  6. 2026SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
  7. 2025Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
  8. 2024Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models