li-lab/MMLU-ProX
收藏官方服务：
资源简介：
MMLU-ProX是一个多语言基准测试，扩展了MMLU-Pro，覆盖了13种类型多样的语言。它旨在评估大型语言模型在不同语言和文化背景下的推理能力。数据集通过严格的半自动翻译过程和专家验证，确保了概念准确性、术语一致性和文化相关性。
MMLU-ProX is a multilingual benchmark that extends MMLU-Pro to cover 13 typologically diverse languages. It is designed to evaluate the reasoning capabilities of large language models across different linguistic and cultural backgrounds. The dataset ensures conceptual accuracy, terminological consistency, and cultural relevance through a rigorous semi-automatic translation process and expert validation.
提供机构：
li-lab
