@bcherny: Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores,…

X AI KOLs Following Models

Summary

Anthropic's Claude Opus 5 is highlighted as a state-of-the-art model for coding, data analysis, and knowledge work, with unprecedented resistance to prompt injection attacks. The system card reveals that combined defenses reduce prompt injection success rates to near zero.

Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully. And when layering defenses -- strong model alignment, combined with prompt injection probes, combined with Auto Mode in Claude Code -- the success rate for prompt injection attacks drops to ~0. This is new and exciting! More about this soon. https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf#page=73…
Original Article
View Cached Full Text

Cached at: 07/25/26, 06:06 AM

Opus 5 is a great model for coding, data analysis, design, biology, knowledge work.

More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully.

And when layering defenses – strong model alignment, combined with prompt injection probes, combined with Auto Mode in Claude Code – the success rate for prompt injection attacks drops to ~0. This is new and exciting! More about this soon.

https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf#page=73…

Claude (@claudeai): On several coding and knowledge work evaluations, Opus 5 is the new state-of-the-art:

Similar Articles

Quoting Boris Cherny

Simon Willison's Blog

Boris Cherny highlights that Opus 5 is the least prompt injectable model yet, based on evaluations and red teaming.