diff --git a/benchmarks/backend_request_func.py b/benchmarks/backend_request_func.py
index 158705769b5e0..9521acddc5f36 100644
--- a/benchmarks/backend_request_func.py
+++ b/benchmarks/backend_request_func.py
@@ -27,7 +27,7 @@ class RequestFuncInput:
     output_len: int
     model: str
     model_name: Optional[str] = None
-    best_of: int = 1
+    best_of: Optional[int] = None if os.environ.get("VLLM_USE_V1", 0) else 1
     logprobs: Optional[int] = None
     extra_body: Optional[dict] = None
     multi_modal_content: Optional[dict] = None
diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
index 16ec0a4817a26..f68e2fd0b6297 100644
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@@ -1084,7 +1084,7 @@ def main(args: argparse.Namespace):
     parser.add_argument(
         "--best-of",
         type=int,
-        default=1,
+        default=None if os.environ.get("VLLM_USE_V1", 0) else 1,
         help="Generates `best_of` sequences per prompt and "
         "returns the best one.",
     )