diff --git a/examples/foundational/49-ultravox-realtime.py b/examples/foundational/50-ultravox-realtime.py
similarity index 100%
rename from examples/foundational/49-ultravox-realtime.py
rename to examples/foundational/50-ultravox-realtime.py
diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py
index 68600706f..19df05da9 100644
--- a/scripts/evals/run-release-evals.py
+++ b/scripts/evals/run-release-evals.py
@@ -79,6 +79,12 @@ EVAL_FLIGHT_STATUS = EvalConfig(
     eval="The user says something about the status of flight AA100, such as whether it's on time or delayed.",
 )
 
+EVAL_ORDER = EvalConfig(
+    prompt="I'd like to order a chocolate iced doughnut and a regular brewed coffee.",
+    eval="The user acknowledges the order of a chocolate iced doughnut and regular brewed coffee.",
+    eval_speaks_first=True,
+)
+
 
 TESTS_07 = [
     # 07 series
@@ -215,6 +221,11 @@ TESTS_49 = [
     ("49d-thinking-functions-google.py", EVAL_FLIGHT_STATUS),
 ]
 
+
+TESTS_50 = [
+    ("50-ultravox-realtime.py", EVAL_ORDER),
+]
+
 TESTS = [
     *TESTS_07,
     *TESTS_12,
@@ -228,6 +239,7 @@ TESTS = [
     *TESTS_43,
     *TESTS_44,
     *TESTS_49,
+    *TESTS_50,
 ]