kshitijthakkar/smoltrace-leaderboard
收藏Hugging Face2025-10-24 更新2025-10-25 收录
下载链接:
https://hf-mirror.com/datasets/kshitijthakkar/smoltrace-leaderboard
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了对模型性能评估的相关指标,如成功率、平均步骤数、平均持续时间等,以及与模型测试相关的元数据信息,如测试数量、总持续时间、总标记数、总成本等。数据集分为训练集,可用于进一步训练和评估模型。
The dataset includes performance metrics for model evaluation such as success rate, average number of steps, average duration, and metadata related to model testing such as number of tests, total duration, total tokens, and total cost. The dataset is split into a training set for further training and evaluation of models.
提供机构:
kshitijthakkar



