diff --git a/tests/integration/eval/test_eval.py b/tests/integration/eval/test_eval.py
index 4a3ebfc20..15d79cd5e 100644
--- a/tests/integration/eval/test_eval.py
+++ b/tests/integration/eval/test_eval.py
@@ -81,7 +81,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
     )
     assert response.job_id == "0"
     job_status = llama_stack_client.eval.jobs.status(job_id=response.job_id, benchmark_id=benchmark_id)
-    assert job_status and job_status.value == "completed"
+    assert job_status and job_status == "completed"
 
     eval_response = llama_stack_client.eval.jobs.result(job_id=response.job_id, benchmark_id=benchmark_id)
     assert eval_response is not None