Paper Detail

GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks

Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno, Lynda Tamine

arxiv Score 17.2

Published 2026-08-07 · First seen 2026-08-10

General AI

Abstract

In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our results show that reasoning and size have a strong impact on overall performance. GeoBenchLLM is publicly available at https://github.com/Rfr2003/GeoBenchLLM.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{rodrigues2026geobenchllm,
  title = {GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks},
  author = {Rodrigo Ferreira Rodrigues and Karim Radouane and Jose G Moreno and Lynda Tamine},
  year = {2026},
  abstract = {In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \textbackslash{}benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our r},
  url = {https://arxiv.org/abs/2608.07411},
  keywords = {cs.AI, cs.CL, cs.IR, cs.LG},
  eprint = {2608.07411},
  archiveprefix = {arXiv},
}

Metadata

{}