Spatial Reasoning Benchmarks

Overview

These benchmarks measure whether AI systems can go beyond recognizing objects to reason about geometry, direction, topology, perspective, and how scenes change over time. They use controlled synthetic puzzles, annotated images and videos, maps, and simulated or real embodied tasks, often with hierarchical tests and executable checks for precise answers or actions. Current models can handle some local relations but often fail at multi-step composition, consistent spatial maps across viewpoints, metric judgments, and long-horizon navigation. Structured representations, tools, active exploration, and targeted training can help, but reliable grounding in visual evidence and fair, standardized evaluation remain open challenges.

Latest papers

CardsList

178 papers15 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.

  1. SpatialCast: Reading the 3D World via Cast Shadows

    Nov 17, 2026Enhan Li, Jinghao Zhou, Jiaze Zhang +1Spatial Reasoning in Language Models3D Spatial Reasoning

  2. From Perception to Simulation: Unveiling and Empowering Mental Spatial Dynamics in MLLMs

    Nov 17, 2026Jiachun Li, Zhuoran Jin, Kang Liu +1Spatial ReasoningMLLM Reasoning

  3. Lost in the Hallway: Benchmarking Persistent Spatial Memory Across Revisits

    Nov 16, 2026Henry Zheng, Weibo Gong, Yang Yue +3Spatial Reasoning BenchmarksEmbodied Agent Benchmarks

  4. Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models

    Nov 10, 2026J. Zach Gazak, Ryan Swindle, Justin FletcherVisual Spatial ReasoningSpatial Reasoning Benchmarks

  5. GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation

    Nov 9, 2026Jinghe Wang, Xinrui Cao, Duo Wu +5Spatial Reasoning BenchmarksRobot Manipulation Benchmarks

  6. Seeing What Execution Needs: Benchmarking Task-Conditioned Actionable Spatial Belief for Manipulation

    Nov 6, 2026Yina Jian, Mingkun XuRobot Manipulation BenchmarksActive Vision for Robot Manipulation

  7. Where and Why is Grounded Reasoning Useful?

    Nov 5, 2026David Yan, Le Xue, Forrest Huang +4Visually Grounded ReasoningVisual Reasoning

  8. CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal Transition On-Policy Self-Distillation

    Nov 5, 2026Ying Li, Yongle Cheng, Jing Li +2Spatial Reasoning BenchmarksMultimodal Spatial Reasoning

  9. ConceptARC at Scale: Studying Conceptual Understanding in Reasoning Models

    Nov 4, 2026Philipp Mondorf, Adrien Deliège, Solim LeGris +5Spatial Reasoning BenchmarksLarge Reasoning Models

  10. Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in Large Vision-Language Models

    Nov 1, 2026Junfei Wu, Qiuyue Wang, Xuhong Huang +8Spatial Reasoning BenchmarksMultimodal Spatial Reasoning

  11. Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding

    Oct 26, 2026Rui Yang, Yanwei Li, Sili Chen +3Spatial Reasoning3D Spatial Reasoning

  12. Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?

    Oct 25, 2026Tianchen Guo, Tengyue Zhang, Chen Liu +2Spatial Reasoning BenchmarksMultimodal Spatial Reasoning

  13. BEHAVIOR-Spatial Benchmark: Evaluating Spatial Understanding for Robotics

    Oct 25, 2026Sirui Chen, Huang Huang, Qineng Wang +5Spatial Reasoning BenchmarksSpatial Grounding for VLAs

  14. VoxProg: 3D Spatial Reasoning through Voxel Programming

    Oct 21, 2026Zhichao Zhai, Menglei Zhao, Guikun Chen +43D Spatial Reasoning3D Scene Layout Generation

  15. MindView: Benchmarking Generative Multi-View Spatial Intelligence

    Oct 20, 2026Yanbo Wang, Siqi Luo, Siyu Zhang +9Spatial Reasoning BenchmarksMulti-View Image Synthesis

  16. SENRI: Understanding the Space-Event Nexus in Real-Life Videos

    Oct 18, 2026Kehan Lan, Kaining Ying, Henghui Ding +1Egocentric Video UnderstandingSpatiotemporal Reasoning

  17. Grid-Bench: Can LLMs Predict How Discrete Worlds Change?

    Oct 15, 2026Zixiang Xu, Zirui Song, Wanrong Zheng +16Spatial Reasoning BenchmarksLLM Evaluation

  18. Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation

    Oct 15, 2026Weilin Ruan, Bohan Zhou, Jinghao Li +12Embodied Spatial ReasoningEmbodied Reasoning

  19. LED-BENCH: A Benchmark for Large-format Engineering Drawing Understanding

    Oct 14, 2026Ke Li, Tianyi Wang, Enning You +4Document UnderstandingDocument Image Understanding

  20. Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning

    Oct 14, 2026Chunxi Luo, Qishuai Ding, Xingchen Peng +6Spatial Reasoning BenchmarksSpatial Reasoning

  21. Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models

    Oct 13, 2026Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh +2Multimodal Spatial ReasoningMultimodal Large Language Models

  22. Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?

    Oct 13, 2026Qingan Liu, Juntong Feng, Yue Zhu +6VLM EvaluationVisually Grounded Reasoning

  23. RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment

    Oct 13, 2026Qingchuan Ma, Yuexiao Ma, Xiang Meng +73D Spatial ReasoningSpatial Reasoning Benchmarks

  24. MemAct: Streaming Spatial Understanding with Memory and Active Exploration

    Oct 13, 2026Yuxi Wei, Wei Huang, Qirui Chen +2Memory-Augmented AgentsEmbodied Reasoning

  25. SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning

    Oct 12, 2026Chenlong Wei, Hanling Wang, Mingjin Lou +6Spatial AudioSpatial Reasoning Benchmarks

  26. Geometric Parrots: Rule Absence vs. Rule Fragility in Spatial and Physical Reasoning for Vision-Language Models

    Oct 12, 2026Bilal Jawaid, Hamza Hanif, Muhammad Maaz Uddin +8Sycophancy in VLMsVLM Reasoning