diff --git a/.github/skills/azsdk-common-apiview-feedback-resolution/evals/eval.yaml b/.github/skills/azsdk-common-apiview-feedback-resolution/evals/eval.yaml
index c464c3109cf2..22daf2988b0a 100644
--- a/.github/skills/azsdk-common-apiview-feedback-resolution/evals/eval.yaml
+++ b/.github/skills/azsdk-common-apiview-feedback-resolution/evals/eval.yaml
@@ -11,7 +11,7 @@ tags:
 config:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-apiview-feedback-resolution/evals/trigger.eval.yaml b/.github/skills/azsdk-common-apiview-feedback-resolution/evals/trigger.eval.yaml
index 4baee7fd21fd..b7684015c912 100644
--- a/.github/skills/azsdk-common-apiview-feedback-resolution/evals/trigger.eval.yaml
+++ b/.github/skills/azsdk-common-apiview-feedback-resolution/evals/trigger.eval.yaml
@@ -11,7 +11,7 @@ tags:
 defaults:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-generate-sdk-locally/evals/eval.yaml b/.github/skills/azsdk-common-generate-sdk-locally/evals/eval.yaml
index ca7f153a1cc7..3ce10aed89b6 100644
--- a/.github/skills/azsdk-common-generate-sdk-locally/evals/eval.yaml
+++ b/.github/skills/azsdk-common-generate-sdk-locally/evals/eval.yaml
@@ -11,7 +11,7 @@ tags:
 config:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-pipeline-analysis/evals/trigger.eval.yaml b/.github/skills/azsdk-common-pipeline-analysis/evals/trigger.eval.yaml
index ec7e3d5c3dc7..68e32d14c6f9 100644
--- a/.github/skills/azsdk-common-pipeline-analysis/evals/trigger.eval.yaml
+++ b/.github/skills/azsdk-common-pipeline-analysis/evals/trigger.eval.yaml
@@ -11,7 +11,7 @@ tags:
 defaults:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-pipeline-fixer/evals/trigger.eval.yaml b/.github/skills/azsdk-common-pipeline-fixer/evals/trigger.eval.yaml
index 1c769875c35f..f87c05ffbde8 100644
--- a/.github/skills/azsdk-common-pipeline-fixer/evals/trigger.eval.yaml
+++ b/.github/skills/azsdk-common-pipeline-fixer/evals/trigger.eval.yaml
@@ -11,11 +11,11 @@ tags:
 defaults:
   runs: 1
   # Stimuli with a resolvable build reference (URL or build ID) make the agent
-  # run the full analyze→fix→verify workflow (~90-180s under gpt-5.4),
+  # run the full analyze→fix→verify workflow (~90-180s under gpt-6.1-sol),
   # so the per-stimulus cap matches the Vally scenario evals (5m). Non-build-ref
   # routing prompts still complete in ~10-20s.
   timeout: "5m"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-prepare-release-plan/evals/eval.yaml b/.github/skills/azsdk-common-prepare-release-plan/evals/eval.yaml
index ea7ed3db1968..548a435dd598 100644
--- a/.github/skills/azsdk-common-prepare-release-plan/evals/eval.yaml
+++ b/.github/skills/azsdk-common-prepare-release-plan/evals/eval.yaml
@@ -11,7 +11,7 @@ tags:
 config:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-prepare-release-plan/evals/schedule-risk.eval.yaml b/.github/skills/azsdk-common-prepare-release-plan/evals/schedule-risk.eval.yaml
index 145576bec41c..bc5e8a9bca30 100644
--- a/.github/skills/azsdk-common-prepare-release-plan/evals/schedule-risk.eval.yaml
+++ b/.github/skills/azsdk-common-prepare-release-plan/evals/schedule-risk.eval.yaml
@@ -11,7 +11,7 @@ tags:
 defaults:
   runs: 1
   timeout: "120s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-prepare-release-plan/evals/trigger.eval.yaml b/.github/skills/azsdk-common-prepare-release-plan/evals/trigger.eval.yaml
index 02141eaea26f..919bfa214259 100644
--- a/.github/skills/azsdk-common-prepare-release-plan/evals/trigger.eval.yaml
+++ b/.github/skills/azsdk-common-prepare-release-plan/evals/trigger.eval.yaml
@@ -11,7 +11,7 @@ tags:
 defaults:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-sdk-release/evals/eval.yaml b/.github/skills/azsdk-common-sdk-release/evals/eval.yaml
index e910ffc92eb8..e4604b9e2b05 100644
--- a/.github/skills/azsdk-common-sdk-release/evals/eval.yaml
+++ b/.github/skills/azsdk-common-sdk-release/evals/eval.yaml
@@ -11,7 +11,7 @@ tags:
 config:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring:
diff --git a/.github/skills/azsdk-common-sdk-release/evals/trigger.eval.yaml b/.github/skills/azsdk-common-sdk-release/evals/trigger.eval.yaml
index a6fb4544cc66..629b6f6ebc01 100644
--- a/.github/skills/azsdk-common-sdk-release/evals/trigger.eval.yaml
+++ b/.github/skills/azsdk-common-sdk-release/evals/trigger.eval.yaml
@@ -11,7 +11,7 @@ tags:
 defaults:
   runs: 1
   timeout: "90s"
-  model: gpt-5.4
+  model: gpt-6.1-sol
   executor: copilot-sdk
 
 scoring: