diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp
index dd57118a..52b1dbbd 100644
--- a/examples/llama-bench/llama-bench.cpp
+++ b/examples/llama-bench/llama-bench.cpp
@@ -330,6 +330,7 @@ static void print_usage(int /* argc */, char ** argv) {
     printf("  -t, --threads <n>                   (default: %s)\n", join(cmd_params_defaults.n_threads, ",").c_str());
     printf("  -tgb, --threads-gen-batch <n1,n2>   (default: %s)\n", join(cmd_params_defaults.n_threads, ",").c_str());
     printf("  -ngl, --n-gpu-layers <n>            (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
+    printf("  --n-cpu-moe <n>                     (default: none)\n");
     printf("  -rpc, --rpc <rpc_servers>           (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
     printf("  -sm, --split-mode <none|layer|row>  (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
     printf("  -mg, --main-gpu <i>                 (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());