mlfoundations-dev/test_r1_7b_verifier_model_1743356168_eval_0771
收藏Hugging Face2025-03-30 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/test_r1_7b_verifier_model_1743356168_eval_0771
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含预计算模型输出的评估数据集，用于衡量模型在AIME24、AIME25和MATH500三个数据集上的表现。AIME24和AIME25包含5次独立运行的详细准确率结果，而MATH500包含一个整体的准确率结果。
This is an evaluation dataset containing precomputed model outputs to measure the performance of the model on AIME24, AIME25, and MATH500 datasets. AIME24 and AIME25 include detailed accuracy results from 5 independent runs, while MATH500 contains an overall accuracy result.
提供机构：
mlfoundations-dev
