mlfoundations-dev/Light-R1-32B_1743569788_eval_0981
收藏Hugging Face2025-04-02 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/mlfoundations-dev/Light-R1-32B_1743569788_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的评估数据集,涵盖了AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench等多个任务的评估结果。
This is an evaluation dataset containing precomputed model outputs, covering the evaluation results of multiple tasks such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench.
提供机构:
mlfoundations-dev



