mlfoundations-dev/SCP_40k_anthropic_solution_unverified_eval_03-18-25_22-14-43_0981
收藏Hugging Face2025-03-18 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/mlfoundations-dev/SCP_40k_anthropic_solution_unverified_eval_03-18-25_22-14-43_0981
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了不同数学和编程测试的预计算模型输出,用于评估。测试包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench,每个测试都有多次运行的准确度结果。
This dataset includes precomputed model outputs for evaluation on various math and programming tests, such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench, with accuracy results from multiple runs for each test.
提供机构:
mlfoundations-dev



