COREval: A Comprehensive and Objective Benchmark for Evaluating the Remote Sensing Capabilities of Large Vision-Language Models

With the rapid development of Large Vision-Language Models (VLMs), both general-domain models and those specifically tailored for remote sensing Earth observation, have demonstrated exceptional perception and reasoning abilities within this specific field. However, the current absence of a comprehensive benchmark for holistically evaluating the remote sensing capabilities of these VLMs represents a significant gap. To bridge this gap, we propose COREval, the first benchmark designed to comprehensively and objectively evaluate the hierarchical remote sensing capabilities of VLMs. Concentrating on 2 primary capability dimensions essential to remote sensing: perception and reasoning, we further categorize 6 secondary dimensions and 22 leaf tasks to ensure a well-rounded assessment coverage for this specific field. COREval guarantees the quality of the total of 6,263 problems through a rigorous process of data collection from 50 globally distributed cities, question construction and quality control, and the format of multiple-choice questions with definitive answers allows for an objective and straightforward evaluation of VLM performance. We conducted a holistic evaluation of 13 prominent open-source VLMs from both the general and remote sensing domains, highlighting current shortcomings in their remote sensing capabilities and providing directions for improvements in their application within this specialized context. We hope that COREval will serve as a valuable resource and offer deeper insights into the challenges and potential of VLMs in the field of remote sensing.