Bruce-Jin/judge-results-dataset

这是一个包含多个模型输出和评估结果的数据集，用于研究和比较不同模型的性能。数据集中的每个子集都针对特定的模型和执行情况，包含了聊天会话ID、判断模型、是否有执行、判断结果等字段。

This is a dataset containing model outputs and evaluation results for research and comparison of different model performances. Each subset in the dataset is tailored for specific models and execution conditions, including fields such as chat session ID, judge model, execution presence, judgment result, etc.