Papers
arxiv:2506.22992

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning

Published on Jun 28
· Submitted by mdmoor on Jul 1
Authors:
,
,

Abstract

MARBLE is a challenging multimodal reasoning benchmark that highlights the limitations of existing multimodal language models in step-by-step reasoning and plan crafting under spatial and visual constraints.

AI-generated summary

The ability to process information from multiple modalities and to reason through it step-by-step remains a critical challenge in advancing artificial intelligence. However, existing reasoning benchmarks focus on text-only reasoning, or employ multimodal questions that can be answered by directly retrieving information from a non-text modality. Thus, complex reasoning remains poorly understood in multimodal domains. Here, we present MARBLE, a challenging multimodal reasoning benchmark that is designed to scrutinize multimodal language models (MLLMs) in their ability to carefully reason step-by-step through complex multimodal problems and environments. MARBLE is composed of two highly challenging tasks, M-Portal and M-Cube, that require the crafting and understanding of multistep plans under spatial, visual, and physical constraints. We find that current MLLMs perform poorly on MARBLE -- all the 12 advanced models obtain near-random performance on M-Portal and 0% accuracy on M-Cube. Only in simplified subtasks some models outperform the random baseline, indicating that complex reasoning is still a challenge for existing MLLMs. Moreover, we show that perception remains a bottleneck, where MLLMs occasionally fail to extract information from the visual inputs. By shedding a light on the limitations of MLLMs, we hope that MARBLE will spur the development of the next generation of models with the ability to reason and plan across many, multimodal reasoning steps.

Community

Paper author Paper submitter

MARBLE - A hard multimodal reasoning benchmark testing the ability of MLLMs to solve Happy cube puzzles and Portal 2 maps.

·

This looks great - you’re on a roll!

Paper author
This comment has been hidden (marked as Resolved)

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.22992 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.22992 in a Space README.md to link it from this page.

Collections including this paper 1