AI 导读
本次发布涵盖 17 个可执行环境和 218 个 episode，取自首批发布所选 20 个问题的一个子集。总共注册了 423 个真实世界问题。 首批领域为生物医学、临床转化和前沿模型工程。 感谢 @Apodex_AI 团队与我合作撰写此文。 在 https://t.co/uOePFfacDO 探索该基准和排行榜
正文
The current release covers 17 executable environments and 218 episodes, drawn from a subset of the 20 problems selected for the first release. 423 real-world problems are registered in total.
The first domains are biomedicine, clinical translation, and frontier-model engineering.
Thanks to the @Apodex_AI team for partnering with me on this post.
Explore the benchmark and leaderboard at https://t.co/uOePFfacDO
来源：@omarsar0 · x.com