diff --git a/benchmarks/benchmark_serving_structured_output.py b/benchmarks/benchmark_serving_structured_output.py
index 7c40e39ac810..9084255d2440 100644
--- a/benchmarks/benchmark_serving_structured_output.py
+++ b/benchmarks/benchmark_serving_structured_output.py
@@ -414,7 +414,6 @@ async def benchmark(
     ignore_eos: bool,
     max_concurrency: Optional[int],
     structured_output_ratio: float,
-    structured_output_backend: str,
     goodput_config_dict: Optional[dict[str, float]] = None,
 ):
     if backend in ASYNC_REQUEST_FUNCS:
@@ -426,8 +425,6 @@ async def benchmark(
         extra_body = {}
         # Add the schema to the extra_body
         extra_body[request.structure_type] = request.schema
-        # Add the specific structured_output_backend
-        extra_body["guided_decoding_backend"] = structured_output_backend
         return extra_body
 
     print("Starting initial single prompt test run...")
@@ -785,7 +782,6 @@ def main(args: argparse.Namespace):
             ignore_eos=args.ignore_eos,
             max_concurrency=args.max_concurrency,
             structured_output_ratio=args.structured_output_ratio,
-            structured_output_backend=args.structured_output_backend,
             goodput_config_dict=goodput_config_dict,
         ))
 
@@ -1000,14 +996,6 @@ if __name__ == "__main__":
                         type=float,
                         default=1.0,
                         help="Ratio of Structured Outputs requests")
-    parser.add_argument("--structured-output-backend",
-                        type=str,
-                        choices=[
-                            "outlines", "lm-format-enforcer", "xgrammar",
-                            "guidance", "auto"
-                        ],
-                        default="auto",
-                        help="Backend to use for structured outputs")
 
     args = parser.parse_args()
     main(args)
diff --git a/benchmarks/run_structured_output_benchmark.sh b/benchmarks/run_structured_output_benchmark.sh
index 126dfbc24416..53dc7ed70b9c 100755
--- a/benchmarks/run_structured_output_benchmark.sh
+++ b/benchmarks/run_structured_output_benchmark.sh
@@ -9,13 +9,10 @@ BACKEND=${2:-"vllm"}
 # Define the dataset to use
 DATASET=${3:-"xgrammar_bench"}
 
-# Define the guided decoding backend
-GUIDED_BACKEND=${4:-"xgrammar"}
-
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-OUTPUT_DIR=${5:-"$SCRIPT_DIR/structured_output_benchmark_results"}
+OUTPUT_DIR=${4:-"$SCRIPT_DIR/structured_output_benchmark_results"}
 
-GUIDED_RATIO=${6:-0.5}
+GUIDED_RATIO=${5:-0.5}
 
 # Create output directory if it doesn't exist
 mkdir -p "$OUTPUT_DIR"
@@ -27,7 +24,6 @@ QPS_VALUES=(70 60 50 25 20 15 10)
 COMMON_PARAMS="--backend $BACKEND \
                --model $MODEL \
                --dataset $DATASET \
-               --structured-output-backend $GUIDED_BACKEND \
                --structured-output-ratio $GUIDED_RATIO \
                --save-results \
                --result-dir $OUTPUT_DIR"
@@ -35,7 +31,6 @@ COMMON_PARAMS="--backend $BACKEND \
 echo "Starting structured output benchmark with model: $MODEL"
 echo "Backend: $BACKEND"
 echo "Dataset: $DATASET"
-echo "Structured output backend: $GUIDED_BACKEND"
 echo "Results will be saved to: $OUTPUT_DIR"
 echo "----------------------------------------"
 
@@ -48,7 +43,7 @@ for qps in "${QPS_VALUES[@]}"; do
   GIT_BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "unknown")
 
   # Construct filename for this run
-  FILENAME="${GUIDED_BACKEND}_${BACKEND}_${qps}qps_$(basename $MODEL)_${DATASET}_${GIT_HASH}.json"
+  FILENAME="${BACKEND}_${qps}qps_$(basename $MODEL)_${DATASET}_${GIT_HASH}.json"
 
   # Run the benchmark
   python "$SCRIPT_DIR/benchmark_serving_structured_output.py" $COMMON_PARAMS \