# CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments arXiv: https://arxiv.org/abs/2601.14339 ยท HTML: https://mlsanity.com/paper/2601.14339/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 20 of its 50 references that are in the map. - First posted on arXiv 20 Jan 2026. ## 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, 20 of 20) - [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017) - [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025) - [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024) - [MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence](https://mlsanity.com/paper/2505.23764/) (2025) - [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024) - [ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models](https://mlsanity.com/paper/2505.21500/) (2025) - [OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models](https://mlsanity.com/paper/2506.03135/) (2025) - [Scaling Spatial Intelligence with Multimodal Foundation Models](https://mlsanity.com/paper/2511.13719/) (2025) - [Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes](https://mlsanity.com/paper/2509.06266/) (2025) - [EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment](https://mlsanity.com/paper/2410.09604/) (2024) - [Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/2510.27606/) (2025) - [Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space](https://mlsanity.com/paper/2503.11094/) (2025) - [UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces](https://mlsanity.com/paper/2503.06157/) (2025) - [Holistic Evaluation of Multimodal LLMs on Spatial Intelligence](https://mlsanity.com/paper/2508.13142/) (2025) - [Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs](https://mlsanity.com/paper/2504.15280/) (2025) - [UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding](https://mlsanity.com/paper/2506.23219/) (2025) - [CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing](https://mlsanity.com/paper/2506.00530/) (2025) - [UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective](https://mlsanity.com/paper/2509.22228/) (2025) ## Built on by (most cited first, 11 of 11) - [Are VLMs Lost Between Sky and Space? LinkS2Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence](https://mlsanity.com/paper/2604.02020/) (2026) - [AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration](https://mlsanity.com/paper/2606.28049/) (2026) - [SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes](https://mlsanity.com/paper/2605.31148/) (2026) - [Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method](https://mlsanity.com/paper/2609.08402/) (2026) - [m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning](https://mlsanity.com/paper/2601.19099/) (2026) - [CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming](https://mlsanity.com/paper/2606.22476/) (2026) - [AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience](https://mlsanity.com/paper/2606.31467/) (2026) - [SpatialSkill: Self-Evolving Skills for Cross-View Spatial Reasoning](https://mlsanity.com/paper/2609.34124/) (2026) - [SpatialASM: Internalizing Active Mentalization for Spatial Reasoning](https://mlsanity.com/paper/2610.13832/) (2026) - [CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations](https://mlsanity.com/paper/2610.18342/) (2026) - [Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning](https://mlsanity.com/paper/2610.19564/) (2026) ## Abstract (arXiv) Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique challenges of open-ended urban spaces characterized by rich semantics, complex geometries, and view variations. To address this, we introduce CityCube, a systematic benchmark designed to probe cross-view reasoning capabilities of current VLMs in urban settings. CityCube integrates four viewpoint dynamics to mimic camera movements and spans a wide spectrum of perspectives from multiple platforms, e.g., vehicles, drones and satellites. For a comprehensive assessment, it features 5,022 meticulously annotated multi-view QA pairs categorized into five cognitive dimensions and three spatial relation expressions. A comprehensive evaluation of 33 VLMs reveals a significant performance disparity with humans: even large-scale models struggle to exceed 54.1% accuracy, remaining 34.2% below human performance. By contrast, small-scale fine-tuned VLMs achieve over 60.0% accuracy, highlighting the necessity of our benchmark. Further analyses indicate the task correlations and fundamental cognitive disparity between VLMs and human-like reasoning.