mlfoundations-dev/qwen2-5_nemotron-sft_100000_1743049940_eval_92d0
收藏Hugging Face2025-03-27 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/qwen2-5_nemotron-sft_100000_1743049940_eval_92d0
下载链接
链接失效反馈官方服务：
资源简介：
该数据集为预计算模型输出评估数据集，包含AIME25、AIME24、MATH500和GPQADiamond四个数据集的评估结果。每个数据集都有多次运行的平均准确度，以及每次运行的详细准确度、解决的问题数量和总问题数量。
This dataset consists of precomputed model outputs for evaluation, including the results on four datasets: AIME25, AIME24, MATH500, and GPQADiamond. Each dataset has an average accuracy from multiple runs, along with detailed accuracy, number of questions solved, and total number of questions for each run.
提供机构：
mlfoundations-dev
