CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments

ACL ARR 2026 January Submission944 Authors

Keywords: Cross-view Spatial Reasoning, Vision-Language Models, Urban Scene Understanding, Spatial Intelligence Benchmark

Abstract: 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.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: vision question answering, cross-modal application, vision language navigation

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Submission Number: 944