diff --git a/src/pheval/cli.py b/src/pheval/cli.py
index 3bf4e235a..c9d3654f1 100644
--- a/src/pheval/cli.py
+++ b/src/pheval/cli.py
@@ -6,8 +6,8 @@
 
 from .cli_pheval import run
 from .cli_pheval_utils import (
-    benchmark,
     create_spiked_vcfs_command,
+    generate_benchmark_stats,
     generate_stats_plot,
     prepare_corpus_command,
     scramble_phenopackets_command,
@@ -56,8 +56,7 @@ def pheval_utils():
 pheval_utils.add_command(scramble_phenopackets_command)
 pheval_utils.add_command(update_phenopackets_command)
 pheval_utils.add_command(create_spiked_vcfs_command)
-pheval_utils.add_command(benchmark)
-pheval_utils.add_command(benchmark)
+pheval_utils.add_command(generate_benchmark_stats)
 pheval_utils.add_command(semsim_to_exomiserdb_command)
 pheval_utils.add_command(generate_stats_plot)
 pheval_utils.add_command(prepare_corpus_command)
diff --git a/src/pheval/cli_pheval_utils.py b/src/pheval/cli_pheval_utils.py
index dc56a5264..ab3c4aae9 100644
--- a/src/pheval/cli_pheval_utils.py
+++ b/src/pheval/cli_pheval_utils.py
@@ -359,7 +359,7 @@ def create_spiked_vcfs_command(
     help="Score threshold.",
     type=float,
 )
-def benchmark(
+def generate_benchmark_stats(
     run_data: Path,
     score_order: str,
     threshold: float,