CompleteSkeptic· @CompleteSkeptic · X·· 7 天前AI 评分
WorkflowEvals 评测集与复现仓库发布
链接（3/3）： 4 WorkflowEvals: huggingface.co/collections/t… 复现仓库：github.com/typesafe-ai/Workf… 附加数据集：huggingface.co/datasets/type… 关于反刷榜的博客：completeskeptic.com/p/lies-d…
Links (3/3):
4 WorkflowEvals: huggingface.co/collections/t…
Repo for reprodcution: github.com/typesafe-ai/Workf…
Bonus dataset: huggingface.co/datasets/type…
Blog on anti-benchmaxxing: completeskeptic.com/p/lies-d…
来源：CompleteSkeptic · x.com