diff --git a/src/llama_stack_client/lib/cli/eval/run_benchmark.py b/src/llama_stack_client/lib/cli/eval/run_benchmark.py
index 6d246292..3a97dc53 100644
--- a/src/llama_stack_client/lib/cli/eval/run_benchmark.py
+++ b/src/llama_stack_client/lib/cli/eval/run_benchmark.py
@@ -101,7 +101,7 @@ def run_benchmark(
         output_res = {}
 
         for i, r in enumerate(tqdm(rows.rows)):
-            eval_res = client.eval.evaluate_rows_alpha(
+            eval_res = client.eval.evaluate_rows(
                 benchmark_id=benchmark_id,
                 input_rows=[r],
                 scoring_functions=scoring_functions,