The Wayback Machine - https://web.archive.org/web/20241207074147/https://openai.com/index/openai-o1-system-card/
Skip to main content

December 5, 2024

OpenAI o1 System Card

This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.

o1 System Card(opens in a new window)Contributions

OpenAI o1 Scorecard

Key Areas of Evaluation

  • Disallowed content
  • Training Data Regurgitation
  • Hallucinations
  • Bias

Preparedness Scorecard

  • Cybersecurity
    Low
  • CBRN
    Medium
  • Persuasion
    Medium
  • Model Autonomy
    Low

Scorecard ratings

  • Low
  • Medium
  • High
  • Critical

Only models with a post-mitigation score of "medium" or below can be deployed.
Only models with a post-mitigation score of "high" or below can be developed further.

Previous version

Read the o1-preview System Card⁠(opens in a new window) originally published on September 12, 2024.

Authors

OpenAI