JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles
arXiv:2607.27670
The paper introduces JigShape, a benchmark of interlocking jigsaw puzzles designed to test visual‑geometric reasoning in vision‑language models, and shows that current zero‑shot and fine‑tuned models struggle as puzzle size grows.
Abstract
Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \textit{\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances at four grid densities (44 to 1616), we find that \textbf{zero-shot VLMs largely lack geometric reasoning}: only one of five frontier models (GPT-5.5) exceeds random baseline on 44 puzzles, while all others perform at chance level. While supervised fine-tuning achieves 97\% on 44, \textbf{all models collapse on larger grids}: GPT-5.5 drops from 70\% to near-random on 88, and even fine-tuned models fall below 5\% on 1212. This ``scaling cliff'' suggests current architectures cannot maintain consistent constraint satisfaction as the number of pieces increases. \ours{} establishes scalable geometric reasoning as an open challenge for vision-language models.