mlfoundations-dev/Sky-T1-32B-Preview_1744037858_eval_0981
收藏Hugging Face2025-04-07 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/Sky-T1-32B-Preview_1744037858_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是预计算的模型输出，用于评估模型在不同数学任务上的表现。它包含了AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench等多个任务的平均准确度以及每次运行的具体准确度、解决的问题数量和总问题数量。
This dataset consists of precomputed model outputs for evaluating the performance of models on various mathematical tasks. It includes average accuracy and specific accuracy, number of questions solved, and total number of questions for each run on tasks such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench.
提供机构：
mlfoundations-dev
