mlfoundations-dev/herorun_1_1_3epoch_eval_03-17-25_21-58-27_0981
收藏Hugging Face2025-03-17 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/herorun_1_1_3epoch_eval_03-17-25_21-58-27_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是用于模型评估的预计算输出，包含了在LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond和MATH500任务上的准确度结果。每个任务都有多个运行结果，并提供了平均准确度。
This dataset consists of precomputed model outputs for evaluation purposes, including accuracy results on LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500 tasks. Each task has multiple run results with average accuracy provided.
提供机构：
mlfoundations-dev
