mlfoundations-dev/OpenThinker-7B_eval_03-10-25_06-56-31_0981
收藏数据链接：
官方服务：
资源简介：
这是一个包含OpenThinker-7B模型在不同数学和编程基准测试中的评估结果的数据集。它提供了LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond和MATH500等多个测试的准确度数据，包括每次测试的运行次数、准确度、解决的问题数和总问题数。
This dataset contains evaluation results of the OpenThinker-7B model on various math and coding benchmark tests. It provides accuracy data for LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500, including the number of runs, accuracy, questions solved, and total questions for each test.
提供机构：
mlfoundations-dev
