richardyoung/llm-instruction-following-eval
收藏Hugging Face2025-10-24 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/richardyoung/llm-instruction-following-eval
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含256个大型语言模型在20个诊断性指令遵循提示下评估结果的全面数据集，总共有5,120次单独评估。评估结果涵盖了字符串操作、约束符合、文本处理、结构化数据生成和复杂操作等多个类别，并提供了模型表现、测试难度和提供商性能的详细信息。
This dataset includes comprehensive evaluation results of 256 large language models across 20 diagnostic instruction-following prompts, totaling 5,120 individual evaluations. The evaluation covers various categories such as string manipulation, constraint compliance, text processing, structured data generation, and complex operations, providing detailed information on model performance, test difficulty, and provider performance.
提供机构：
richardyoung
