diff --git a/benchmark/README.md b/benchmark/README.md
index ec2bbda..5b183de 100644
--- a/benchmark/README.md
+++ b/benchmark/README.md
@@ -3,7 +3,7 @@
 ## Introduction
 
 Build a classification system based on similarity search across embeddings.
-The core ideas in `evaluate.py`:
+The core ideas in `run.py`:
 1. create a new Milvus collection each time
 2. extract embeddings using a pretrained model with model name specified by `--model`
 3. specify inference method with `--format` in value of `pytorch` or `onnx`
diff --git a/benchmark/evaluate.py b/benchmark/run.py
similarity index 99%
rename from benchmark/evaluate.py
rename to benchmark/run.py
index 2162d4f..51016ca 100644
--- a/benchmark/evaluate.py
+++ b/benchmark/run.py
@@ -25,7 +25,7 @@ parser.add_argument('--onnx_dir', type=str, default='../saved/onnx')
 
 args = parser.parse_args()
 model_name = args.model
-onnx_path = os.path.join(args.onnx_dir, model_name.replace('/', '-'), '.onnx')
+onnx_path = os.path.join(args.onnx_dir, model_name.replace('/', '-') + '.onnx')
 dataset_name = args.dataset
 insert_size = args.insert_size
 query_size = args.query_size
diff --git a/benchmark/evaluate.sh b/benchmark/run.sh
similarity index 100%
rename from benchmark/evaluate.sh
rename to benchmark/run.sh