一句话：提出开源统一工具包 UIBenchKit，标准化设计到代码（截图→HTML/CSS）生成的评测流程，支持即插即用比较与多指标分析。
近年来，从网页截图自动生成 HTML 和 CSS 的设计到代码任务进展显著，但缺乏标准化评测平台，导致方法之间难以公平比较，限制了实际应用与系统性研究。为此，本文提出 UIBenchKit——一个开源、集成的工具包，旨在统一设计到代码任务的评测。它抽象了环境配置、模型推理与代码渲染的复杂性，提供即插即用的架构，使研究者能在一致设置下比较各类方法，并给出跨多个指标的分析界面。基于 UIBenchKit，作者对现有工具进行了基准评测研究，得出若干发现并指出未来改进方向。该工具包旨在通过提供简化的实验与评测环境，加速 Web 工程领域的基准评测与创新。
Recent years have seen substantial progress in automated design-to-code generation, with many methods proposed for generating HTML and CSS from webpage screenshots. However, the absence of a standardized evaluation platform makes it difficult to compare these methods fairly, limiting both practical adoption and systematic research progress. To bridge this gap, we introduce UIBenchKit, an open-source, integrated toolkit designed to unify the evaluation of design-to-code tasks. UIBenchKit abstracts the complexities of environment setup, model inference, and code rendering, offering researchers a plug-and-play architecture to compare various methods under consistent settings. In addition, it offers an analytical interface for comparison across multiple metrics. Using UIBenchKit, we conduct a benchmarking study of existing tools and derive several findings that highlight directions for future improvement. By providing a streamlined environment for both experimentation and evaluation, UIBenchKit aims to accelerate future benchmarking and innovations in web engineering. The evaluation platform and toolkit are available at the project pages https://www.uibenchkit.com/ and https://github.com/chinh02/UIBenchKit. A video of UIBenchKit is available at https://youtu.be/UyeYyASovuU.
@inproceedings{abs-2605-13141,
title = {UIBenchKit: A Unified Toolkit for Design-to-Code Model Evaluation},
author = {Chinh T. Le and Trevor Yee Siang Ong and Jingyu Xiao and Yuxuan Wan and Yintong Huo},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834612}
}