Karina· @karinanguyen · X·· 2 小时前AI 评分52
AI 导读
Brian Zhou 推出 Benchmark Almanac，Karina Nguyen 转发推荐。该站点追踪 3,322 个基准，覆盖 1,746 个排行榜、522 篇发布帖、346 份系统卡和 1,233 个开源 GitHub 仓库，网址为 benchmarkalmanac.com。
正文 · 原文
evals evals evals
在 X 查看被引用的帖子I'm excited to launch Benchmark Almanac! It tracks 3,322 benchmarks from 1,746 leaderboards, 522 launch posts, 346 system cards, and 1,233 open-source GitHub repos. To my knowledge, it's the most comprehensive repo out there.
Website: benchmarkalmanac.com
来源：Karina · x.com