Kimi K3 lags far behind the US frontier models in network security vulnerability exploitation testing; knowledge distillation may be the reason

ME News message, July 24 (UTC+8): A joint assessment by the UK AI Safety Institute and the U.S. AI Standards and Innovation Center shows that Kimi K3 from the Dark Side of the Moon scored 32.2% on the ExploitBench benchmark, far lower than the 76.2% scored by the leading U.S. model, but higher than Zhipu’s GLM-5.2 at 24.4%. 🔗 Read the original article: via AI HOT ·
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned