@@ -948,7 +948,7 @@ class RubricVerdict(_common.BaseModel):
       generated.""",
     )
     verdict: Optional[bool] = Field(
-        default=None,
+        default=False,
         description="""Required. Outcome of the evaluation against the rubric, represented as a
       boolean. `true` indicates a "Pass", `false` indicates a "Fail".""",
     )
 
@@ -48,6 +48,7 @@
 from vertexai._genai import (
     _evals_data_converters as vertexai_evals_data_converters,
 )
+from vertexai._genai import evals as vertexai_evals
 from vertexai._genai import types as vertexai_genai_types
 from google.genai import client
 from google.genai import errors as genai_errors
@@ -2361,6 +2362,49 @@ def test_eval_evaluate_with_agent_info(self, mock_execute_evaluation):
         assert kwargs["agent_info"] == agent_info
 
 
+class TestRubricVerdict:
+    """Unit tests for parsing RubricVerdict from API responses."""
+
+    @pytest.mark.parametrize(
+        "evals_module", [evals, vertexai_evals], ids=["agent_platform", "vertexai"]
+    )
+    def test_evaluate_instances_missing_verdict_is_false(self, evals_module):
+        api_client = mock.MagicMock()
+        api_client.vertexai = True
+        api_client.request.return_value.body = json.dumps(
+            {
+                "metricResults": [
+                    {
+                        "score": 0.5,
+                        "rubricVerdicts": [
+                            {
+                                "evaluatedRubric": {
+                                    "content": {
+                                        "property": {"description": "In English."}
+                                    }
+                                },
+                                "verdict": True,
+                            },
+                            {
+                                "evaluatedRubric": {
+                                    "content": {
+                                        "property": {"description": "One sentence."}
+                                    }
+                                },
+                                "reasoning": "The response has two sentences.",
+                            },
+                        ],
+                    }
+                ]
+            }
+        )
+
+        response = evals_module.Evals(api_client_=api_client)._evaluate_instances()
+
+        verdicts = response.metric_results[0].rubric_verdicts
+        assert [verdict.verdict for verdict in verdicts] == [True, False]
+
+
 class TestEvalsVisualization:
     # fmt: off
     @mock.patch(
 
@@ -948,7 +948,7 @@ class RubricVerdict(_common.BaseModel):
       generated.""",
     )
     verdict: Optional[bool] = Field(
-        default=None,
+        default=False,
         description="""Required. Outcome of the evaluation against the rubric, represented as a
       boolean. `true` indicates a "Pass", `false` indicates a "Fail".""",
     )
Original file line number	Diff line number	Diff line change
`@@ -948,7 +948,7 @@ class RubricVerdict(_common.BaseModel):`
`948`	`948`	`generated.""",`
`949`	`949`	`)`
`950`	`950`	`verdict: Optional[bool] = Field(`
`951`		`- default=None,`
	`951`	`+ default=False,`
`952`	`952`	`description="""Required. Outcome of the evaluation against the rubric, represented as a`
`953`	`953`	boolean. `true` indicates a "Pass", `false` indicates a "Fail".""",
`954`	`954`	`)`