Spatial Reasoning Benchmarks

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 83

All topics

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
May 27, 2026Zhikai Pan, Chih-Ting Liao, Chunrui Liu +5LLM World Models Multilingual Language Model Evaluation
University of New South Wales · Essential Energy · University of Alabama at Birmingham +3
EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy
May 23, 2026Jinzhao Li, Yinuo Chen, Dongxu Piao +9Spatial Reasoning Benchmarks LLM Evaluation
College of AI, Tsinghua University · 2ByteDance · 3State Key Laboratory of General Artificial Intelligence, BIGAI
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
May 21, 2026Xiaolong Zhou, Yifei Liu, Ziyang Gong +8VLM Robustness Spatial Reasoning Benchmarks
2Shanghai Artificial Intelligence Laboratory · University of Electronic Science and Technology of China · 6Beihang University +4
ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models
May 20, 2026Qirui Shen, Wenda Wang, Jiachen Lu +5VLM Evaluation Spatial Reasoning Benchmarks
School of Architecture, Tsinghua University
Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?
May 19, 2026Animesh Maheshwari, Divyansh Sahu, Nishit VermaVLM Evaluation Spatial Reasoning Benchmarks
Deccan AI
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
May 18, 2026Yining Hong, Jiageng Liu, Han Yin +5Active Perception Spatial Reasoning Benchmarks
1Stanford University · 2UCLA · 3Northwestern University
QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi
May 18, 2026Anthony G. Cohn, Robert E. BlackwellSpatial Reasoning Benchmarks LLM Evaluation
School of Computer Science, The University of Leeds, Woodhouse Lane, Leeds, LS2 9JT, UK · The Alan Turing Institute, British Library, 96 Euston Road, London, NW1 2DB, UK · Tongji University, Shanghai, China
CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
May 13, 2026Amirreza Mohseni, Mona Mohammadi, Morteza Saghafian +1VLM Evaluation Spatial Reasoning Benchmarks
Maastricht University · Cornell University · TU Wien +1
3D Primitives are a Spatial Language for VLMs
May 12, 2026Junze Liu, Kun Qian, Florian Dubost +8Spatial Reasoning Benchmarks 3D Spatial Reasoning
Unity Technologies
Beyond Localization: A Comprehensive Benchmark of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images
May 12, 2026Yuangong Chen, Wai Keung Wong, Jiaxing Li +2Spatial Reasoning Benchmarks Visual Spatial Reasoning
The Hong Kong Polytechnic University Hong Kong, China · Guangzhou University Guangzhou, China · Queen Mary, University of London London, United Kingdom +1
SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation
May 11, 2026Niyati Rawal, Sushant Ravva, Shah Alam Abir +5VLM Evaluation Spatial Reasoning Benchmarks
† Indian AI Research Organization (IAIRO), India · ⋆ĸragya Lab, BITS Pilani Goa, India · ¶ University of Dhaka, Bangladesh +3
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
May 11, 2026Xia Hu, Zhenrui Yue, Brian Potetz +4VLM Evaluation Spatial Reasoning Benchmarks
Google DeepMind · Stanford University · Google Research
From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs
May 4, 2026Le Zhang, Jihan Yang, Soundarya Krishnan +11Spatial Reasoning Benchmarks Visual Spatial Reasoning
1Mila - Qu´ebec AI Institute, UdeM · 2NYU · 3Apple +1
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Apr 27, 2026Yiming Zhang, Jiacheng Chen, Jiaqi Tan +3VLM Evaluation Spatial Reasoning Benchmarks
1Simon Fraser University · 2Hong Kong University of Science and Technology · University of Waterloo +1
SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments
Apr 24, 2026Chih-Ting Liao, Xi Xiao, Chunlei Meng +6Spatial Reasoning Benchmarks Visual Spatial Reasoning
The University of New South Wales · The University of Alabama at Birmingham · Fudan University +4
Exploring Spatial Intelligence from a Generative Perspective
Apr 22, 2026Muzhi Zhu, Shunyao Jiang, Huanyi Zheng +9Spatial Reasoning Benchmarks Unified Multimodal Models
Zhejiang University, State Key Laboratory of CAD & CG · Ant Group · Zhejiang University of Technology +1
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Apr 17, 2026Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian +1Spatial Reasoning Benchmarks Visual Spatial Reasoning
IIT, Hyderabad · Microsoft Research India
Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Apr 17, 2026Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti +2Spatial Reasoning Benchmarks Visual Spatial Reasoning
CSE Dept., IIT Hyderabad Hyderabad, India · Microsoft Research Bengaluru, India
Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks
Apr 13, 2026Arun SharmaSpatial Reasoning Benchmarks Question Answering
University of Minnesota, Twin Cities
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
Jan 16, 2026Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl +2Spatial Reasoning Benchmarks Visual Spatial Reasoning
Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland. · Doctoral School of Exact and Natural Sciences, Jagiellonian University, Kraków, Poland. · AGH University of Krakow, Kraków, Poland. +3
Think, Then Look: Active Spatial Reasoning for House-Scale 3D Scene Understanding
Dec 2, 2025Hongpei Zheng, Shijie Li, Lin Qian +4Spatial Reasoning Benchmarks 3D Spatial Reasoning
University of Manchester · Institute for Infocomm Research (I2R), A*STAR, Singapore · University of Bedfordshire
MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
Nov 24, 2025Qirui Wang, Jingyi He, Yining Pan +3Spatial Reasoning Benchmarks Visual Spatial Reasoning
Technical University of Munich, Germany · A*STAR Institute of Advanced Intelligence and Computing, Singapore · Singapore University of Technology and Design, Singapore +1
RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
Nov 22, 2025Jun Zhang, Xin Zhang, Jie Feng +5VLM Evaluation Spatial Reasoning Benchmarks
Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China · Zhongguancun Academy · Amap, Alibaba Group, Beijing, China

May 27, 2026, cs.AIJ/K move · Enter open · S save

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

Zhikai Pan, Chih-Ting Liao, Chunrui Liu, Xi Xiao+4

University of New South Wales · Essential Energy · University of Alabama at Birmingham+3

LLM World Models Multilingual Language Model Evaluation Spatial Reasoning Benchmarks World Model Learning Cross-Lingual Reasoning in Language Models Spatial Reasoning

Open paper AskPDF arXiv

Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages has not been systematically studied. We introduce MentalMap, a multilingual diagnostic benchmark with a six-level capability hierarchy (L0-L5) spanning atomic spatial facts to generative world-graph construction, together with four diagnostic axes probing frame of reference, reading-direction bias, reasoning-effort allocation, and hallucination. MentalMap is built from 100 ProcTHOR household scenes, covers eight typologically diverse languages plus a structured-text control, and contains 39 task families across 1,950 evaluation cells. Evaluating thirteen LLMs across scales and model families, we identify a universal L3 reasoning cliff: no model retains even half of its L0 performance on viewpoint reasoning once baseline atomic accuracy exceeds 40%. The cliff persists across languages, scales, and prompting strategies, while structured-output failures and reasoning patterns vary substantially across models. Human evaluation under the identical pure-text protocol reproduces the same failure pattern, suggesting that the bottleneck arises from text-only working memory constraints rather than being specific to current LLM architectures. Our findings reframe pure-text spatial reasoning as a multi-axis world-modeling problem and motivate multimodal and scratchpad-augmented reasoning as future directions.

Momentum

Related topics

Latest papers 83