Halluminate/WebBench
收藏Hugging Face2025-06-24 更新2025-05-31 收录
下载链接：
https://hf-mirror.com/datasets/Halluminate/WebBench
下载链接
链接失效反馈官方服务：
资源简介：
WebBench是一个开放的、面向任务的性能基准，用于衡量浏览器代理如何处理真实的网络工作流程。该数据集包含了2454个任务，分布在452个实时网站上，这些网站是从全球流量前1000名中选出的。数据集分为五大类任务：读取、创建、更新、删除和文件操作，分别占比64.4%、20.9%、7.1%、6.1%和1.5%。
WebBench is an open, task-oriented benchmark that measures how well browser agents handle realistic web workflows. The dataset contains 2,454 tasks spread across 452 live websites selected from the global top-1000 by traffic. It is categorized into five types of tasks: READ, CREATE, UPDATE, DELETE, and FILE_MANIPULATION, accounting for 64.4%, 20.9%, 7.1%, 6.1%, and 1.5% of the dataset respectively.
提供机构：
Halluminate
