CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
Keywords: large language model, urban science, world model, benchmark, multi-modal
TL;DR: We propose a simulator based global scale benchmark to evaluate the performance of large language models on various urban tasks.
Abstract: Recently, large language models (LLMs) with extensive general knowledge and powerful reasoning abilities have seen rapid development and widespread application. A systematic and reliable evaluation of LLMs or visual language model (VLMs) is a crucial step in applying and developing them for various fields. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dynamic nature of the urban environment. In this paper, we design CityBench, an interactive simulator based evaluation platform, as the first systematic benchmark for evaluating the capabilities of LLMs for diverse tasks in urban research. First, we build CityData to integrate the diverse urban data and CitySimu to simulate fine-grained urban dynamics. Based on CityData and CitySimu, we design 8 representative urban tasks in 2 categories of perception-understanding and decision-making as the CityBench. With extensive results from 30 well-known LLMs and VLMs in 13 cities around the world, we find that advanced LLMs and VLMs can achieve competitive performance in diverse urban tasks requiring commonsense and semantic understanding abilities, e.g., understanding the human dynamics and semantic inference of urban images. Meanwhile, they fail to solve the challenging urban tasks requiring professional knowledge and high-level reasoning abilities, e.g., geospatial prediction and traffic control task. These observations provide valuable perspectives for utilizing and developing LLMs in the future. The dataset, benchmark and source codes are openly accessible to the research community via https://github.com/CityBench24/CityBench.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6832
Loading