AI 导读
关于 kimi k3.1 pro 基准测试的 TLDR 是，看起来他们搞定了 RL，最初的发布是一个非常令人印象深刻的 base model，post-training 较轻。中国在能力提升方面确实跟得很紧。
正文
TLDR on the kimi k3.1 pro benchmarks is that it looks like they figured out their RL, where the initial release was a very impressive base model with lighter post-training. China is very much keeping pace with capability gains.
来源：Nathan Lambert · x.com