注册并分享邀请链接,可获得视频播放与邀请奖励。

Vihar Kurama
@viharkurama
Co-founder & COO @planepowers
加入 December 2013
884 正在关注    1.1K 粉丝
Huge!!!!
Across our benchmarks, the model sets a new standard. It scores 52.6% on Terminal-Bench-Science 0.1, more than double Fable 5. On Terminal-Bench 4.0, it scores 55.8% against 42.0% for Fable 5.
显示更多