diff --git a/onnxruntime/test/perftest/command_args_parser.cc b/onnxruntime/test/perftest/command_args_parser.cc
index 83d533d5185ca..e06cca73b95b7 100644
--- a/onnxruntime/test/perftest/command_args_parser.cc
+++ b/onnxruntime/test/perftest/command_args_parser.cc
@@ -197,7 +197,9 @@ ABSL_FLAG(std::string, select_ep_devices, "", "Specifies a semicolon-separated l
 ABSL_FLAG(std::string, filter_ep_devices, "",
           "Specifies EP or Device metadata entries as key-value pairs to filter ep devices passed to AppendExecutionProvider_V2.\n"
           "[Usage]: --filter_ep_devices \"<key1>|<value1> <key2>|<value2>\" \n"
-          "Devices that match any of the key-value pair will be appended to the session. --select_ep_devices will take precedence over this option.\n");
+          "Devices that match any of the key-value pair will be appended to the session. --select_ep_devices will take precedence over this option.\n"
+          "[Example] --filter_ep_devices \"ov_device|NPU ov_device|CPU\" \n"
+          "Above example will append npu device first if available, followed by cpu device.");
 ABSL_FLAG(bool, compile_ep_context, DefaultPerformanceTestConfig().run_config.compile_ep_context, "Generate an EP context model");
 ABSL_FLAG(std::string, compile_model_path, "model_ctx.onnx", "The compiled model path for saving EP context model. Overwrites if already exists");
 ABSL_FLAG(bool, compile_binary_embed, DefaultPerformanceTestConfig().run_config.compile_binary_embed, "Embed binary blob within EP context node");
diff --git a/onnxruntime/test/perftest/ort_test_session.cc b/onnxruntime/test/perftest/ort_test_session.cc
index dd0ed75f4782f..b9ec73da40bf4 100644
--- a/onnxruntime/test/perftest/ort_test_session.cc
+++ b/onnxruntime/test/perftest/ort_test_session.cc
@@ -124,15 +124,20 @@ OnnxRuntimeTestSession::OnnxRuntimeTestSession(Ort::Env& env, std::random_device
       }
     } else if (!performance_test_config.filter_ep_device_kv_pairs.empty()) {
       // Find and select the OrtEpDevice associated with the EP in "--filter_ep_devices".
-      for (size_t index = 0; index < ep_devices.size(); ++index) {
-        auto device = ep_devices[index];
-        if (ep_set.find(std::string(device.EpName())) == ep_set.end())
-          continue;
+      for (const auto& kv : performance_test_config.filter_ep_device_kv_pairs) {
+        for (size_t index = 0; index < ep_devices.size(); ++index) {
+          auto device = ep_devices[index];
+          if (ep_set.find(std::string(device.EpName())) == ep_set.end())
+            continue;
+
+          // Skip if deviced was already added
+          if (added_ep_devices.find(device.EpName()) != added_ep_devices.end() &&
+              std::find(added_ep_devices[device.EpName()].begin(), added_ep_devices[device.EpName()].end(), device) != added_ep_devices[device.EpName()].end())
+              continue;
 
-        // Check both EP metadata and device metadata for a match
-        auto ep_metadata_kv_pairs = device.EpMetadata().GetKeyValuePairs();
-        auto device_metadata_kv_pairs = device.Device().Metadata().GetKeyValuePairs();
-        for (const auto& kv : performance_test_config.filter_ep_device_kv_pairs) {
+          // Check both EP metadata and device metadata for a match
+          auto ep_metadata_kv_pairs = device.EpMetadata().GetKeyValuePairs();
+          auto device_metadata_kv_pairs = device.Device().Metadata().GetKeyValuePairs();
           auto ep_metadata_itr = ep_metadata_kv_pairs.find(kv.first);
           auto device_metadata_itr = device_metadata_kv_pairs.find(kv.first);