Papers › CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks

CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks

20 Jun 2024arXiv:2406.13945archive 2025-07-28

Jie Feng, Jun Zhang, Tianhui Liu, Xin Zhang, Tianjian Ouyang, Junbo Yan, Yuwei Du, Siqi Guo, Yong Li

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 vision-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. Codes are openly accessible via https://github.com/tsinghua-fib-lab/CityBench.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 23 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 17 ran (11 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tsinghua-fib-lab/citybench officialmentioned in papermentioned on GitHubMITSyntology: 23 samples, 17 ran (6 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
5ran · our draft was wrong
1ran; the contract check could not run
7ran
6unverified

Licence: 0 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tsinghua-fib-lab/citybench. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

tsinghua-fib-lab/citybench official repository 23 samples, 17 ran (6 instrument-failed) · 6 unverified
bd09_to_gcj02 citybench/outdoor_navigation/coordTransform_utils.py ran · honoured contract MIT (permissive) · ed0baa8be5a2be8e · report fixture: signature bd_lon:float/0/float, bd_lat:float/0/float · returned list · level recorded 2026-09-24
convert_to_12_hour_clock citybench/mobility_prediction/run_eval.py ran · our draft was wrong fingerprinted MIT (permissive) · 3dd52b32d8265d75 · report fixture: signature minutes:int/0/int · returned str · level recorded 2026-09-24
dir_all_dis citybench/geoqa/utils.py ran MIT (permissive) · afe3f93eb4daddb2 · report fixture: signature routes:list/1/dict, secondary_directions:list/1/str, primary_directions:list/1/str, secondary_dir_to_primary_dirs:dict/0/? · returned tuple · level recorded 2026-09-24
format_example in 43 papers citybench/geoqa/run_eval.py ran MIT (permissive) · fbde55d407dfbc1f · report fixture: signature line:dict/0/?, include_answer:bool/0/bool, max_choices:int/0/int · returned str · level recorded 2026-09-24
gcj02_to_bd09 citybench/outdoor_navigation/coordTransform_utils.py ran · honoured contract MIT (permissive) · 6011c01be1bc239c · report fixture: signature lng:float/0/float, lat:float/0/float · returned list · level recorded 2026-09-24
gen_options citybench/geoqa/utils.py ran MIT (permissive) · 9745e19e1e4d5474 · report fixture: signature options:list/1/str, question:str/0/str, answer:str/0/str · returned dict · level recorded 2026-09-24
get_acc1_f1 citybench/mobility_prediction/metrics.py ran; the contract check could not run (RAISES) MIT (permissive) · 901473d434f03b50 · report fixture: signature df:DataFrame/0/? · returned tuple · level recorded 2026-09-24
get_day citybench/mobility_prediction/data_gen.py ran · our draft was wrong MIT (permissive) · 00ff8bb07bb6500f · report fixture: signature day:str/0/str · returned str · level recorded 2026-09-24
get_is_correct citybench/mobility_prediction/metrics.py ran · our draft was wrong MIT (permissive) · cd1e4cb179726aa5 · report fixture: signature row:dict/0/? · returned dict · level recorded 2026-09-24
get_is_correct10 citybench/mobility_prediction/metrics.py ran · our draft was wrong MIT (permissive) · bdfec11b2815eede · report fixture: signature row:dict/0/? · returned dict · level recorded 2026-09-24
get_nearby_pois citybench/geoqa/data_gen.py ran MIT (permissive) · aafdf0d32c0ac451 · report fixture: signature input_coor:tuple/1/float, map:MockMap/0/?, category_supported:dict/0/? · returned list · level recorded 2026-09-24
get_result in 30 papers citybench/geoqa/metrics.py ran MIT (permissive) · 7a47bc523075e6d4 · report fixture: signature file_path:str/0/str, result_files:list/1/str, map_task:dict/0/? · returned DataFrame · level recorded 2026-09-24
get_time in 20 papers citybench/mobility_prediction/data_gen.py ran · honoured contract MIT (permissive) · 5642b97cf4bef5f0 · report fixture: signature time:str/0/str · returned int · level recorded 2026-09-24
get_user_data citybench/mobility_prediction/run_eval.py ran MIT (permissive) · d45560a97cfd6154 · report fixture: signature train_data:DataFrame/0/?, uid:int/0/int, num_historical_stay:int/0/int · returned DataFrame · level recorded 2026-09-24
task_files_adaption citybench/geoqa/run_eval.py ran · our draft was wrong MIT (permissive) · 4189bccf9c32f695 · report fixture: signature task_file:dict/0/?, path_prefix:str/0/str · returned dict · level recorded 2026-09-22
task_files_adaption citybench/geoqa/utils.py ran MIT (permissive) · 9b36c7f6d6007d25 · report fixture: signature task_file:dict/0/?, output_path:str/0/str · returned dict · level recorded 2026-09-24
wgs84_to_gcj02 citybench/outdoor_navigation/coordTransform_utils.py ran · honoured contract MIT (permissive) · e67cb36ee1894010 · report fixture: signature lng:float/0/float, lat:float/0/float · returned list · level recorded 2026-09-24
coord_conv citybench/outdoor_navigation/crawler_baidu.py unverified MIT (permissive) · 673d2b1bf01f10aa · report
coord_conv_back citybench/outdoor_navigation/crawler_baidu.py unverified MIT (permissive) · 17a3a8f86db336ac · report
gps_gen citybench/geoqa/data_gen.py unverified MIT (permissive) · 3205b9f39f5f2e0c · report
landmark_gen citybench/geoqa/data_gen.py unverified MIT (permissive) · 74042dda0a06339b · report
loc_to_sid citybench/outdoor_navigation/crawler_baidu.py unverified MIT (permissive) · a9cc1853676c97f4 · report
match_pos citybench/mobility_prediction/data_gen.py unverified MIT (permissive) · 8b39129551bb06a0 · report

Tasks

General KnowledgeHuman DynamicsLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections