mlfoundations-dev/OpenR1-Qwen-7B_eval_03-18-25_02-41-02_0981

这是一个包含预计算模型输出的评估数据集，用于评估模型在AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench等任务上的表现。每个任务都有详细的准确率和其他统计数据，包括多次运行的准确率和解决的问题数量。

This is an evaluation dataset containing precomputed model outputs for assessing the performance of models on tasks such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench. Each task has detailed accuracy and other statistics including accuracy and number of questions solved for multiple runs.