mlfoundations-dev/test_r1_7b_verifier_model_1743317851_eval_0771
收藏数据链接：
官方服务：
资源简介：
这是一个评估预计算模型输出的数据集，包含AIME24、AIME25和MATH500三个任务的准确度评估结果。AIME24和AIME25任务有多组运行结果，MATH500任务有一组评估结果。
This is a dataset for evaluating precomputed model outputs, containing accuracy evaluation results for three tasks: AIME24, AIME25, and MATH500. The AIME24 and AIME25 tasks have multiple run results, while the MATH500 task has one evaluation result.
提供机构：
mlfoundations-dev
