five

xinrihui/Qwen2.5-Math-7B_eval_2870

收藏
Hugging Face2026-04-06 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/xinrihui/Qwen2.5-Math-7B_eval_2870
下载链接
链接失效反馈
官方服务:
资源简介:
# xinrihui/Qwen2.5-Math-7B_eval_2870 Precomputed model outputs for evaluation. ## Evaluation Results ### AIME24 - **Average Accuracy**: 15.83% ± 0.99% - **Number of Runs**: 32 | Run | Accuracy | Questions Solved | Total Questions | |-----|----------|-----------------|----------------| | 1 | 16.67% | 5 | 30 | | 2 | 16.67% | 5 | 30 | | 3 | 10.00% | 3 | 30 | | 4 | 20.00% | 6 | 30 | | 5 | 20.00% | 6 | 30 | | 6 | 10.00% | 3 | 30 | | 7 | 16.67% | 5 | 30 | | 8 | 13.33% | 4 | 30 | | 9 | 20.00% | 6 | 30 | | 10 | 6.67% | 2 | 30 | | 11 | 6.67% | 2 | 30 | | 12 | 13.33% | 4 | 30 | | 13 | 16.67% | 5 | 30 | | 14 | 23.33% | 7 | 30 | | 15 | 13.33% | 4 | 30 | | 16 | 10.00% | 3 | 30 | | 17 | 23.33% | 7 | 30 | | 18 | 23.33% | 7 | 30 | | 19 | 13.33% | 4 | 30 | | 20 | 13.33% | 4 | 30 | | 21 | 20.00% | 6 | 30 | | 22 | 16.67% | 5 | 30 | | 23 | 3.33% | 1 | 30 | | 24 | 30.00% | 9 | 30 | | 25 | 13.33% | 4 | 30 | | 26 | 16.67% | 5 | 30 | | 27 | 16.67% | 5 | 30 | | 28 | 20.00% | 6 | 30 | | 29 | 20.00% | 6 | 30 | | 30 | 13.33% | 4 | 30 | | 31 | 20.00% | 6 | 30 | | 32 | 10.00% | 3 | 30 |
提供机构:
xinrihui
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作