mlfoundations-dev/SCP_40k_R1_with_OT_verified_eval_03-11-25_05-45-26_f912
收藏Hugging Face2025-03-11 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/SCP_40k_R1_with_OT_verified_eval_03-11-25_05-45-26_f912
下载链接
链接失效反馈官方服务：
资源简介：
这是一个用于评估的预计算模型输出数据集，包含三次独立运行的结果，用于衡量模型在特定任务上的表现。数据集提供了平均准确度以及每次运行的准确度、解决的问题数和总问题数。
This is a precomputed model output dataset for evaluation, containing results from three independent runs to measure the models performance on a specific task. The dataset provides average accuracy, accuracy of each run, number of questions solved, and total number of questions.
提供机构：
mlfoundations-dev
