From 85bb724acf61d362cd6e4931d0aa53b7e0ad3ead Mon Sep 17 00:00:00 2001 From: Faith Xu Date: Fri, 3 Apr 2026 16:51:28 -0700 Subject: [PATCH] Add preview models section to supported models documentation (#60639) Co-authored-by: Sunbrye Ly <56200261+sunbrye@users.noreply.github.com> Co-authored-by: Dan Velton <48307985+dvelton@users.noreply.github.com> --- content/copilot/reference/ai-models/supported-models.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/content/copilot/reference/ai-models/supported-models.md b/content/copilot/reference/ai-models/supported-models.md index 9b4d1a656090..95d4b288cb29 100644 --- a/content/copilot/reference/ai-models/supported-models.md +++ b/content/copilot/reference/ai-models/supported-models.md @@ -101,6 +101,14 @@ For more information about premium requests, see [AUTOTITLE](/copilot/managing-c For more information about fallback and LTS models, see [AUTOTITLE](/copilot/concepts/fallback-and-lts-models). +## Evaluation models +{% data variables.product.prodname_copilot %} offers access to evaluation models—including top-performing open source and open-weight models—to provide the most advanced coding suggestions available. + +> [!NOTE] +> Testing of evaluation models has revealed that some may perform worse than other models on security-related or other categories of prompts. Customers are encouraged to validate code, including code security, using a range of models and thorough human review before incorporating suggestions into production. + +Evaluation models may be added, updated, or removed without notice. Availability and rate limits may differ from generally available models. + ## Next steps * For task-based guidance on selecting a model, see [AUTOTITLE](/copilot/reference/ai-models/model-comparison).