SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models

TL;DR

SpatialText is a diagnostic framework that evaluates whether large language models genuinely understand and manipulate internal spatial representations, revealing significant limitations in perspective transformation and local reasoning.

Contribution

The paper introduces SpatialText, a novel benchmark that isolates text-based spatial reasoning and systematically assesses models' internal spatial understanding capabilities.

Findings

Models excel at retrieving explicit spatial facts.

Models operate within global coordinate systems.

Models struggle with egocentric perspective transformation.

Abstract

Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large language models exhibit advanced capabilities across various domains, existing benchmarks fail to isolate this intrinsic spatial cognition from statistical language heuristics. Furthermore, multimodal evaluations frequently conflate genuine spatial reasoning with visual perception. To systematically investigate whether models construct flexible spatial mental models, we introduce SpatialText, a theory-driven diagnostic framework. Rather than functioning simply as a dataset, SpatialText isolates text-based spatial reasoning through a dual-source methodology. It integrates human-annotated descriptions of real 3D indoor environments, which capture natural ambiguities, perspective shifts, and functional relations, with code-generated, logically precise scenes designed to probe formal spatial deduction and epistemic boundaries. Systematic evaluation across state-of-the-art models reveals fundamental representational limitations. Although models demonstrate proficiency in retrieving explicit spatial facts and operating within global, allocentric coordinate systems, they exhibit critical failures in egocentric perspective transformation and local reference frame reasoning. These systematic errors provide strong evidence that current models rely heavily on linguistic co-occurrence heuristics rather than constructing coherent, verifiable internal spatial representations. SpatialText thus serves as a rigorous instrument for diagnosing the cognitive boundaries of artificial spatial intelligence.