SafetyPage

Lab system cards and frameworks · System card · OpenAI

ChatGPT Images 2.6 System Card

4 Nov 2026

Read at deploymentsafety.openai.com ↗Read at sourceAll rights reserved

Outline · 58 paragraphs

  1. ChatGPT Images 2.6 System Card¶2
  2. 1. Introduction¶3
  3. 2. Model Data and Training¶6
  4. 3. Model Safety¶8
  5. 3.1 Safety Stack¶9
  6. 3.2 Safety and Policy Evaluations¶21
  7. 3.2.1 Safety Evaluations¶22
  8. Table 1: Safety Evaluations Overall¶31
  9. Table 2: Safety Evaluations by Policy¶34
  10. 3.2.2 GIF Risks, Safeguards, and Evaluations¶41
  11. Table 3¶45
  12. 3.3 Preparedness Framework: Image-Specific Capability Assessment and Safeguards¶46
  13. 3.3.1 Biological-risk monitoring and enforcement¶51
  14. 4. Image Provenance¶53