# MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning

arXiv: https://arxiv.org/abs/2608.03882 · HTML: https://mlsanity.com/paper/2608.03882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 63 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 11 of 11)

- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents](https://mlsanity.com/paper/2603.14465/) (2026)
- [Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning](https://mlsanity.com/paper/2507.05418/) (2025)
- [MapQA: Open-domain Geospatial Question Answering on Map Data](https://mlsanity.com/paper/2503.07871/) (2025)
- [GPSBench: Do Large Language Models Understand GPS Coordinates?](https://mlsanity.com/paper/2602.16105/) (2026)
- [Robust Reasoning Benchmark](https://mlsanity.com/paper/2604.08571/) (2026)
- [GS-QA: A Benchmark for Geospatial Question Answering](https://mlsanity.com/paper/2605.22811/) (2026)

## Abstract (arXiv)

Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logistics, yet large language models (LLMs) struggle with the required geometric and topological computation despite storing considerable geographic knowledge. Existing benchmarks localize these failures only partially: they are synthetic or smallscale, largely monolingual, and offer limited control over geographic coverage. We introduce MultiGlobeQA, a multilingual benchmark of 46,060 question-answer pairs spanning 14 spatial-function families and 15 answer formats, with execution-based ground truth over three knowledge graphs. It covers 201 countries and territories via income- and density-stratified sampling, with parallel questions in English and 16 additional high- and low-resource languages. Across parametric, reasoning, and agentic settings, LLMs collapse on tasks requiring grid indexing and shape computation, while topological relations and directions fare best. Retrieval and tool use yield considerable gains, yet performance plateaus below two thirds even when gold facts are supplied, indicating that computation, not access to knowledge, is the bottleneck. Models also underperform on low-income regions, a gap that gold facts widen rather than close.