Industry

Kimi K3 Trails US Frontier Models Sharply in Cybersecurity Exploit Test, Knowledge Distillation May Be the Cause

Original title:Kimi K3 trails frontier US models by a wide margin on cyber exploits, and distillation may explain why

AI summary

A joint evaluation by the UK AI Security Institute and the US Center for AI Standards and Innovation shows that Moonshot's Kimi K3 scored 32.2% on the ExploitBench benchmark, far below the 76.2% of leading US models but above Zhipu GLM-5.2's 24.4%.

Key Takeaways

  • A joint evaluation by the UK AI Security Institute and the US Center for AI Standards and…
  • 2% on the ExploitBench benchmark,far below the 76.
  • 2% of leading US models but above Zhipu GLM-5.

Quick Facts

Published
Updated
Source
The Decoder:AI News(RSS)
Category
Industry
AI score
73
Read the original Read the full article at the original source
Why it matters

英美安全机构的联合评测把蒸馏嫌疑拽到了台面上,Kimi K3 的漏洞利用能力仅为美国前沿模型四成,安全评估不能只看通用基准,开源模型的安全面具该摘了。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Kimi K3 Trails US Frontier Models Sharply in Cybersecurity Exploit Test, Knowledge Distillation May Be the Cause. July 24, 2026. https://new.nat6.net/en/news/cmryrih7804c9rolge6wdk3v8/

View all →