mlfoundations-dev/OpenThinker-32B-Unverified_1744038057_eval_0981
收藏Hugging Face2025-04-08 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-32B-Unverified_1744038057_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了在多个数学和编程任务上预计算的模型输出，用于评估模型性能。具体任务包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench，每个任务都有不同的准确度结果和运行次数。
This dataset includes precomputed model outputs on multiple math and coding tasks for the purpose of evaluating model performance. Specific tasks include AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench, each with different accuracy results and number of runs.
提供机构：
mlfoundations-dev
