Copilot's GPT-5.1 model has degraded performance

Resolved

Minor impact

Started

Lasted 1h 28m

View official incident ↗

Updates

  1. Resolved

    This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.

  2. Investigating

    We are continuing to investigate issues with the GPT-5.1 model. We are also seeing an increase in failures for Copilot Code Reviews.

  3. Investigating

    We are continuing to investigate issues with the GPT-5.1 model with our model provider. Uses of other models are not impacted.

  4. Investigating

    Copilot is experiencing degraded performance when using the GPT-5.1 model. We are investigating the issue.

  5. Investigating

    We are investigating reports of degraded performance for Copilot