SeaLLMs/SeaBench

SeaBench是一个评估大型语言模型在东南亚语言中的多轮对话和遵循指令能力的基准数据集，包括印度尼西亚语、泰语和越南语。数据集由公开问题构成，用于测试语言模型在开放性问题回答方面的性能。

SeaBench is a benchmark dataset designed to assess the multilingual large language models abilities in multi-turn conversation and instruction following in Southeast Asian languages, including Indonesian, Thai, and Vietnamese. The dataset consists of public questions crafted to evaluate the performance of language models in open-ended question answering.