Anthropic releases System Card for Claude Sonnet 5

The document details technical specs and safety testing for the model, which the company identifies as its most agentic Sonnet release to date. The System Card arrives alongside the general availability of Sonnet 5 for all users via the Claude interface and API.
The report covers model behavior in agentic scenarios, safety evaluations, and resilience against misuse. At the Extra High setting, Sonnet 5 matches the performance of Opus 4.8 in standard mode across the OSWorld-Verified and BrowseComp benchmarks.
The full document is available on the Anthropic website.
Up next
Anthropic adds real-time cybersecurity filtering to Opus and Sonnet
Claude Opus and Sonnet now block high-risk cyber prompts like ransomware development and mass scraping in real time. Legitimate security researchers can apply for the free Cyber Verification Program to bypass these restrictions, with approvals processed in two business days.
Related stories
- Claude Fable 5’s biology refusals drop about 85%
- Anthropic plans public release of Mythos models
- Security researchers: stop blocking defenders
- GPT-6.2 Astra costs 20% less than GPT-6 Astra in the API
- Anthropic cuts deadline for critical bugs from 90 to 30 days
- HN post: Anthropic’s CVP Defense tier needs only KYC
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

