Abstract
We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introduce the first benchmark that probes geographical layout understanding from real-world videos, spanning up to 1km distances. Inspired by the cognitive science literature, we evaluate models against the hierarchical stages of human spatial awareness: anchoring via landmarks, connecting them through routes, and integrating these into global mental maps. Extensive experiments reveal a fundamental divergence in how current AI models process spatial information. Instead of utilising true path integration or forming geometric survey knowledge, we find that VLMs rely almost entirely on 2D visual recognition and text-matching to bypass complex spatial reasoning. The benchmark is publicly available at https://perception-test-challenge.github.io/kilometervision.html.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mahendran, A., King, M., Grimes, M. K., Yang, A., Zhu, T., Heyward, J., Han, T., Ginosar, S., Sun, C., Damen, D., Osindero, S., Snavely, N., Lynen, S., Carreira, J., & Pătrăucean, V. (2026). KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs. https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms
MLA 9
Mahendran, Aravindh, et al. "KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs." https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms.
Chicago (author–date)
Mahendran, Aravindh, Michael King, Matthew Koichi Grimes, Antoine Yang, Tyler Zhu, Joseph Heyward, Tengda Han, Shiry Ginosar, Chen Sun, Dima Damen, Simon Osindero, Noah Snavely, Simon Lynen, João Carreira, and Viorica Pătrăucean. 2026. "KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs." https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms.
Harvard
Mahendran, A., King, M., Grimes, M. K., Yang, A., Zhu, T., Heyward, J., Han, T., Ginosar, S., Sun, C., Damen, D., Osindero, S., Snavely, N., Lynen, S., Carreira, J. and Pătrăucean, V. (2026) 'KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs', Available at: https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms.
Vancouver
Mahendran A, King M, Grimes MK, Yang A, Zhu T, Heyward J, et al. KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs. https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms
IEEE
A. Mahendran, M. King, M. K. Grimes, A. Yang, T. Zhu, J. Heyward, T. Han, S. Ginosar, C. Sun, D. Damen, S. Osindero, N. Snavely, S. Lynen, J. Carreira, and V. Pătrăucean, "KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs," https://omanscience.com/en/articles/kilometervision-a-new-frontier-for-large-scale-spatial-intelligence-in-vlms.