ThaiLLM-Leaderboard/mt-bench-thai

MT-Bench Thai是一个多轮对话基准测试数据集，包含9个类别：写作、角色扮演、提取、推理、数学、编程、STEM、社会科学和知识III。该数据集旨在评估对话系统在泰国文化背景理解方面的表现。MT-Bench Thai is a multi-turn dialogue benchmarking dataset covering 9 categories: Writing, Roleplay, Extraction, Reasoning, Math, Coding, STEM, Social Science, and Knowledge III. It is designed to evaluate the performance of dialogue systems in understanding the Thai cultural context.