{"slug": "anthropics-opus-5-is-better-at-resisting-prompt-injection", "title": "Anthropic’s Opus 5 Is Better at Resisting Prompt Injection", "summary": "Anthropic's Claude Opus 5 reduced prompt injection attack success from 5.5% to 2.0% within 15 attempts compared to Opus 4.8, making it the most robust model on the IPI benchmark, outperforming all non-Claude models including OpenAI's GPT 5.6 Sol, which had a 20.0% success rate within 15 attempts.", "body_md": "The [chart](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf#page=73) is interesting.\n\nOn the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9% at k=15) and Mythos 5 (2.6%), making it the most robust model evaluated. Opus 5 also outperformed all non-Claude models on this benchmark. The most robust non-Claude model was Muse Spark at 16.5% within 15 attempts—more than eight times Opus 5’s rate. The most capable GPT 5.6 variant, Sol, was comparable to its predecessor GPT 5.5 (20.0% versus 20.8% within 15 attempts), and was 10 times as likely to be successfully attacked as Claude Opus 5 at 2.0%. The other GPT 5.6 variants are less robust, at 30.4% (Terra) and 43.9% (Luna). A single attempt against GPT 5.6 Sol succeeded 3.1% of the time, higher than the 2.0% an attacker achieved against Opus 5 after fifteen attempts...", "url": "https://wpnews.pro/news/anthropics-opus-5-is-better-at-resisting-prompt-injection", "canonical_source": "https://www.schneier.com/blog/archives/2026/07/anthropics-opus-5-is-better-at-resisting-prompt-injection.html", "published_at": "2026-07-31 17:23:16+00:00", "updated_at": "2026-07-31 17:35:26.569670+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-research"], "entities": ["Anthropic", "Claude Opus 5", "Opus 4.8", "Sonnet 5", "Mythos 5", "Muse Spark", "GPT 5.6", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/anthropics-opus-5-is-better-at-resisting-prompt-injection", "markdown": "https://wpnews.pro/news/anthropics-opus-5-is-better-at-resisting-prompt-injection.md", "text": "https://wpnews.pro/news/anthropics-opus-5-is-better-at-resisting-prompt-injection.txt", "jsonld": "https://wpnews.pro/news/anthropics-opus-5-is-better-at-resisting-prompt-injection.jsonld"}}