mlfoundations-dev/OpenThinker-7B_eval_03-07-25_14-37_0981
收藏Hugging Face2025-03-07 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_eval_03-07-25_14-37_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了在不同基准测试上预计算的模型输出结果，用于评估模型性能。这些基准测试包括AIME24、AIME25、AMC23、GPQADiamond和MATH500。数据集详细提供了每个基准的平均准确率、运行次数、每次运行的准确率以及解决的问题数量和总问题数量。
The dataset includes precomputed model outputs for performance evaluation on various benchmarks such as AIME24, AIME25, AMC23, GPQADiamond, and MATH500. It provides detailed information on average accuracy, number of runs, accuracy per run, number of questions solved, and total questions for each benchmark.
提供机构：
mlfoundations-dev
