cuitingru/DeepSearch-2510
收藏Hugging Face2026-04-27 更新2026-05-03 收录
下载链接：
https://hf-mirror.com/datasets/cuitingru/DeepSearch-2510
下载链接
链接失效反馈官方服务：
资源简介：
xbench-DeepSearch-2510是xbench AGI Tracking系列的一部分，专注于评估搜索和信息检索场景中的工具使用能力。该数据集包含100个新问题，用于测试AI系统在真实世界搜索任务中的表现。详细评估流程和信息可参考相关网站和评估卡片（中文版）。数据集经过加密以防止搜索引擎爬取和污染，需使用解密代码获取明文数据。
xbench-DeepSearch-2510 is part of xbenchs AGI Tracking series, focused on evaluating tool usage capabilities in search and information retrieval scenarios. This dataset features 100 new questions designed to test AI systems performance in real-world search tasks. For detailed evaluation procedures and further information, please refer to the website and Eval Card (Chinese version). Benchmark data is encrypted to prevent search engine crawling and contamination, requiring decryption code to access plain text data.
提供机构：
cuitingru
