SafetyPage

Lab system cards and frameworks · Model card · xAI

Grok 4.1 Model Card

Read at data.x.ai ↗Read at sourceAll rights reserved

Outline · 6 pages

  1. Introductionp. 1
  2. Evaluationsp. 1
  3. Abuse Potentialp. 1
  4. Safety Training Approachp. 1
  5. Evaluationsp. 1
  6. Resultsp. 2
  7. Concerning Propensitiesp. 2
  8. Deceptionp. 3
  9. Sycophancyp. 3
  10. Dual-Use Capabilitiesp. 3
  11. Evaluationsp. 3
  12. Resultsp. 4
  13. Transparencyp. 5
  14. Data and Trainingp. 5