# OpenAI Matches Anthropic's Dangerous AI on Security Test, Keeps Harder Score Private

- slug: openai-matches-anthropics-dangerous-ai-on-security-test-keeps-harder-score-private
- date: 2026-04-25
- category: Artificial Intelligence

OpenAI released a model it rated High risk for cybersecurity capabilities. The benchmark it most needs to defend is one it has not published.

---