Salvato in:
Dettagli Bibliografici
Autori principali: Spencer, Ryan, Yaari, Roey, Vemavarapu, Ritvik, Yang, Joyce, Ngo, Steven, Sharma, Utkarsh
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.22207
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908733844488192
author Spencer, Ryan
Yaari, Roey
Vemavarapu, Ritvik
Yang, Joyce
Ngo, Steven
Sharma, Utkarsh
author_facet Spencer, Ryan
Yaari, Roey
Vemavarapu, Ritvik
Yang, Joyce
Ngo, Steven
Sharma, Utkarsh
contents Multimodal large language models (MLLMs) are proficient in perception and instruction-following, but they still struggle with spatial reasoning: the ability to mentally track and manipulate objects across multiple views and over time. Spatial reasoning is a key component of human intelligence, but most existing benchmarks focus on static images or final outputs, failing to account for the sequential and viewpoint-dependent nature of this skill. To close this gap, we introduce GamiBench, a benchmark designed to evaluate spatial reasoning and 2D-to-3D planning in MLLMs through origami-inspired folding tasks. GamiBench includes 186 regular and 186 impossible 2D crease patterns paired with their corresponding 3D folded shapes, produced from six distinct viewpoints across three visual question-answering (VQA) tasks: predicting 3D fold configurations, distinguishing valid viewpoints, and detecting impossible patterns. Unlike previous benchmarks that assess only final predictions, GamiBench holistically evaluates the entire reasoning process--measuring cross-view consistency, physical feasibility through impossible-fold detection, and interpretation of intermediate folding steps. It further introduces new diagnostic metrics--viewpoint consistency (VC) and impossible fold selection rate (IFSR)--to measure how well models handle folds of varying complexity. Our experiments show that even leading models such as GPT-5 and Gemini-2.5-Pro struggle on single-step spatial understanding. These contributions establish a standardized framework for evaluating geometric understanding and spatial reasoning in MLLMs. Dataset and code: https://github.com/stvngo/GamiBench.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22207
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks
Spencer, Ryan
Yaari, Roey
Vemavarapu, Ritvik
Yang, Joyce
Ngo, Steven
Sharma, Utkarsh
Artificial Intelligence
Multimodal large language models (MLLMs) are proficient in perception and instruction-following, but they still struggle with spatial reasoning: the ability to mentally track and manipulate objects across multiple views and over time. Spatial reasoning is a key component of human intelligence, but most existing benchmarks focus on static images or final outputs, failing to account for the sequential and viewpoint-dependent nature of this skill. To close this gap, we introduce GamiBench, a benchmark designed to evaluate spatial reasoning and 2D-to-3D planning in MLLMs through origami-inspired folding tasks. GamiBench includes 186 regular and 186 impossible 2D crease patterns paired with their corresponding 3D folded shapes, produced from six distinct viewpoints across three visual question-answering (VQA) tasks: predicting 3D fold configurations, distinguishing valid viewpoints, and detecting impossible patterns. Unlike previous benchmarks that assess only final predictions, GamiBench holistically evaluates the entire reasoning process--measuring cross-view consistency, physical feasibility through impossible-fold detection, and interpretation of intermediate folding steps. It further introduces new diagnostic metrics--viewpoint consistency (VC) and impossible fold selection rate (IFSR)--to measure how well models handle folds of varying complexity. Our experiments show that even leading models such as GPT-5 and Gemini-2.5-Pro struggle on single-step spatial understanding. These contributions establish a standardized framework for evaluating geometric understanding and spatial reasoning in MLLMs. Dataset and code: https://github.com/stvngo/GamiBench.
title GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks
topic Artificial Intelligence
url https://arxiv.org/abs/2512.22207