# EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery

arXiv: https://arxiv.org/abs/2602.15918 · HTML: https://mlsanity.com/paper/2602.15918/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 31 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 6 of 6)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space](https://mlsanity.com/paper/2503.11094/) (2025)
- [DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response](https://mlsanity.com/paper/2505.21089/) (2025)

## Built on by (most cited first, 5 of 5)

- [SPACENUM: Revisiting Spatial Numerical Understanding in VLMs](https://mlsanity.com/paper/2605.23898/) (2026)
- [GISAgentBench: A Practitioner-Sourced Benchmark for Evaluating LLM Agents on GIS Tasks](https://mlsanity.com/paper/2608.01645/) (2026)
- [Pumpire: Unified Benchmark for Metric Distance Estimation](https://mlsanity.com/paper/2610.12423/) (2026)
- [Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing](https://mlsanity.com/paper/2610.12881/) (2026)
- [Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation](https://mlsanity.com/paper/2610.15750/) (2026)

## Abstract (arXiv)

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding boxes, polylines, and polygons). Existing benchmarks for Earth imagery primarily focus on 2D spatial grounding, image captioning, and coarse spatial relations (e.g., simple directional or proximity cues). They lack support for quantitative direction and distance reasoning, systematic topological relations, and complex object geometries beyond bounding boxes. To fill this gap, we propose EarthSpatialBench, a comprehensive benchmark for evaluating spatial reasoning in MLLMs on Earth imagery. The benchmark contains over 325K question-answer pairs spanning: (1) qualitative and quantitative reasoning about spatial distance and direction; (2) systematic topological relations; (3) single-object queries, object-pair queries, and compositional aggregate group queries; and (4) object references expressed via textual descriptions, visual overlays, and explicit geometry coordinates, including 2D bounding boxes, polylines, and polygons. We conducted extensive experiments on both open-source and proprietary models to identify limitations in the spatial reasoning of MLLMs.