mlfoundations-dev/DCFT-hero_run_2_fix_conversations-etash_1743560031_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/DCFT-hero_run_2_fix_conversations-etash_1743560031_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是预计算好的模型输出，用于评估。它包含了在不同数学和编程任务上的准确度结果，如AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench。
This dataset consists of precomputed model outputs for evaluation purposes. It includes accuracy results on different mathematical and programming tasks such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench.
提供机构：
mlfoundations-dev
