diff --git a/common/arg.cpp b/common/arg.cpp
index 1e04852bfb..943d0766fb 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -3340,7 +3340,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
                 params.speculative.draft.cpuparams_batch.n_threads = std::thread::hardware_concurrency();
             }
         }
-    ).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
+    ).set_spec().set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
     add_opt(common_arg(
         {"--spec-draft-cpu-mask", "-Cd", "--cpu-mask-draft"}, "M",
         "Draft model CPU affinity mask. Complements cpu-range-draft (default: same as --cpu-mask)",
diff --git a/tests/test-arg-parser.cpp b/tests/test-arg-parser.cpp
index 07d25774b7..0dd8422e73 100644
--- a/tests/test-arg-parser.cpp
+++ b/tests/test-arg-parser.cpp
@@ -40,8 +40,12 @@ int main(void) {
                     }
                 }
 
+                // exclude spec args from this check
+                // ref: https://github.com/ggml-org/llama.cpp/pull/22397
+                const bool skip = opt.is_spec;
+
                 // ensure shorter argument precedes longer argument
-                if (opt.args.size() > 1) {
+                if (!skip && opt.args.size() > 1) {
                     const std::string first(opt.args.front());
                     const std::string last(opt.args.back());
 
@@ -124,7 +128,7 @@ int main(void) {
     assert(params.n_batch == 9090);
 
     // --draft cannot be used outside llama-speculative
-    argv = {"binary_name", "--draft", "123"};
+    argv = {"binary_name", "--spec-draft-n-max", "123"};
     assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_SPECULATIVE));
     assert(params.speculative.draft.n_max == 123);