GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks
Published:Dec 22, 2025 01:07
•1 min read
•ArXiv
Analysis
This article introduces GamiBench, a benchmark designed to assess the spatial reasoning and 2D-to-3D planning abilities of Multimodal Large Language Models (MLLMs) using origami folding tasks. The focus on origami provides a concrete and challenging domain for evaluating these capabilities. The use of ArXiv as the source suggests this is a research paper.
Key Takeaways
Reference
“”