MathArena/ArXivMath-december
收藏Hugging Face2026-02-04 更新2026-02-07 收录
下载链接：
https://hf-mirror.com/datasets/MathArena/ArXivMath-december
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含使用MathArena GitHub仓库生成的ArXivMath 2025年12月问题的模型答案。数据集详细记录了每个问题的索引、完整问题陈述、模型名称、模型配置、回答索引、用户消息、模型回答、解析后的回答、正确性标志、输入输出令牌数、成本等信息。数据集旨在评估大型语言模型在未受污染的数学竞赛中的表现。
This dataset contains model answers to the questions from ArXivMath December 2025 generated using the MathArena GitHub repository. It includes detailed information such as problem index, full problem statement, model name, model configuration, answer index, user message, model answer, parsed answer, correctness flag, input/output tokens, and costs. The dataset is designed to evaluate the performance of large language models on uncontaminated math competitions.
提供机构：
MathArena
