DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

ICLR 2026 Conference Submission16746 Authors

Keywords: Spatial Intelligence, Computer Vision, Multimodal Large Language Models

Abstract: Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenarios, their ability to fully understand dynamic 3D scenarios remains limited. We introduce \textbf{D}ynamic \textbf{S}patial \textbf{I}ntelligence and propose DSI-Bench, a benchmark with nearly 1,000 dynamic videos and over 1,700 manually annotated questions covering nine decoupled motion patterns of observers and objects. Spatially and temporally symmetric designs reduce biases and enable systematic evaluation of models’ reasoning about self-motion and object motion. Our evaluation of 14 VLMs and expert models reveals key limitations: models often conflate observer and object motion, exhibit semantic biases, and fail to accurately infer relative relationships in dynamic scenarios. Our DSI-Bench provides valuable findings and insights about the future development of general and expertise models with dynamic spatial intelligence.

Primary Area: datasets and benchmarks

Submission Number: 16746