AI · 2h ago
Anthropic's Opus 5 Leads in Prompt Injection Resistance
Anthropic's Opus 5 model shows improved resistance to prompt injection attacks, reducing success rates from 5.5% to 2.0% over 15 attempts compared to its predecessor. It outperforms all other models tested, including OpenAI's GPT-5.6 variants, which are up to 10 times more vulnerable. The benchmark highlights a significant gap in robustness among leading AI models.
Meridian48 take
This benchmark underscores a critical security differentiator in AI models, but real-world impact depends on deployment context and evolving attack techniques.
Read the full reporting
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection →
Schneier on Security
ai-securityprompt-injection