mlfoundations-dev/Qwen2.5-32B-Instruct_1744001655_eval_0981
收藏Hugging Face2025-04-07 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/Qwen2.5-32B-Instruct_1744001655_eval_0981
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结果的评估数据集，用于AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench等多个任务。每个任务都有多次运行的结果，数据集提供了准确率、解题数和总题数等详细评估信息。
This is an evaluation dataset containing precomputed model outputs for tasks such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench. Each task has multiple run results, and the dataset provides detailed evaluation information including accuracy, number of questions solved, and total number of questions.
提供机构：
mlfoundations-dev
