nuprl/verbal-reasoning-challenge
收藏Hugging Face2025-07-24 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/nuprl/verbal-reasoning-challenge
下载链接
链接失效反馈官方服务：
资源简介：
Verbal Reasoning Challenge数据集是一个设计用于评估大型语言模型推理能力的基准。它基于美国任何成年人都能够理解的NPR Sunday Puzzle Challenge的离线挑战。该数据集的任务不包括代码和数学，而是通过逻辑推理、搜索和一般知识等任务来评估模型的推理能力。
The Verbal Reasoning Challenge is a benchmark designed to evaluate the reasoning abilities of Large Language Models. It is based on the off-air challenges from the NPR Sunday Puzzle Challenge, which are designed to be understandable by any adult in the United States. The tasks in this dataset do not include code and mathematics, but instead assess the models reasoning skills through logical reasoning, search, and general knowledge.
提供机构：
nuprl
