diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
index 886a51e1cbd9a..9b235266dff1a 100644
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@@ -551,7 +551,7 @@ async def benchmark(
         "total_input_tokens": metrics.total_input,
         "total_output_tokens": metrics.total_output,
         "request_throughput": metrics.request_throughput,
-        "request_goodput:": metrics.request_goodput if goodput_config_dict else None,
+        "request_goodput": metrics.request_goodput if goodput_config_dict else None,
         "output_throughput": metrics.output_throughput,
         "total_token_throughput": metrics.total_token_throughput,
         "input_lens": [output.prompt_len for output in outputs],
diff --git a/vllm/benchmarks/serve.py b/vllm/benchmarks/serve.py
index 419284cca042e..8b16fea9e3d3c 100644
--- a/vllm/benchmarks/serve.py
+++ b/vllm/benchmarks/serve.py
@@ -498,7 +498,7 @@ async def benchmark(
         "total_input_tokens": metrics.total_input,
         "total_output_tokens": metrics.total_output,
         "request_throughput": metrics.request_throughput,
-        "request_goodput:":
+        "request_goodput":
         metrics.request_goodput if goodput_config_dict else None,
         "output_throughput": metrics.output_throughput,
         "total_token_throughput": metrics.total_token_throughput,