Study says Kimi K3 scores 32.2% on cyberattack ability vs 76.2% for U.S. models
pstAsiatech · x · 2026-07-25
A study cited by SCMP says Kimi K3 trails unnamed U.S. models on cyberattack capability.
The reported numbers are stark: Kimi K3 scores 32.2% overall, while the top U.S. models average 76.2%. The post also asks whether Moonshot has under-optimized for coding, implying the model may not be tuned strongly for offensive security or code-heavy tasks.
Related event: Kimi K3 Cybersecurity Eval Sparks Debate: Scores 32.2%(5 posts)→
More from Models
- Testing OpenAI Codex: 5 Minutes of Chatting Completes Weeks of Coding — soumitrashukla9 · 2026-08-07
- Users Complain About Claude Opus 5's Poor Performance, Anticipate Quick Replacement — KlausCodes · 2026-08-07
- Ling 3.0 Tiny Supports Native Function Calling with Only 1.3B Active Parameters — Danare_113 · 2026-08-07
- Latent Space Briefing: Meta Wins Olympiad Golds, OpenAI Unifies Models and MCP Ecosystem — Latent Space · 2026-08-07
- Elon Musk Announces Grok Build v1.0: Free CLI Coding Agent Powered by Grok 4.5 — elonmusk · 2026-08-07
- OpenAI's Logan Kilpatrick Teases 'Great New Models' Are in the Oven — emollick · 2026-08-07