GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra

ICLR 2026 Conference Submission1799 Authors

Keywords: Geometric Reasoning, Benchmarking, Foundation Models

TL;DR: We introduce a new geometric benchmark (GIQ) that reveals state-of-the-art vision and vision-language models fundamentally misunderstand 3D geometry, failing at basic reconstruction, classification, and reasoning tasks.

Abstract:

Monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet their true understanding of geometric properties remains unclear. We introduce GIQ, a comprehensive benchmark specifically designed to evaluate the geometric reasoning capabilities of vision and vision-language foundation models. GIQ comprises synthetic and real-world images and corresponding 3D meshes of diverse polyhedra—including Platonic, Archimedean, Johnson, and Catalan solids, as well as stellations and compound shapes—covering varying levels of complexity and symmetry. Through systematic experiments involving monocular 3D reconstruction, 3D symmetry detection, mental rotation tests, and zero-shot shape classification tasks, we reveal significant shortcomings in current models. State-of-the-art reconstruction algorithms trained on extensive 3D datasets struggle to reconstruct even basic geometric forms accurately. While foundation models effectively detect specific 3D symmetry elements via non-linear probing, they falter significantly in tasks requiring detailed geometric differentiation, such as mental rotation.
Moreover, advanced vision-language assistants exhibit remarkably low accuracy on complex polyhedra, systematically misinterpreting basic properties like face geometry, convexity, and compound structures. GIQ will be publicly available
, providing a structured platform to highlight and address critical gaps in geometric intelligence, facilitating future progress in robust, geometry-aware representation learning.

Primary Area: datasets and benchmarks

Submission Number: 1799