mlfoundations-dev/OpenThinker-7B_eval_03-11-25_18-35-50_0981
收藏Hugging Face2025-03-11 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_eval_03-11-25_18-35-50_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了针对不同数学和编程测试集的预计算模型输出，用于评估模型在LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond和MATH500上的表现。数据集提供了每个测试集的平均准确度、运行次数以及每次运行的详细准确度和解决的问题数量。
This dataset includes precomputed model outputs for evaluating the models performance on various mathematical and coding benchmarks, such as LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500. It provides the average accuracy, number of runs, and detailed accuracy and number of questions solved for each run on every benchmark.
提供机构：
mlfoundations-dev
