diff --git a/.github/workflows/ci-testing.yml b/.github/workflows/ci-testing.yml
index cda65a9..6080816 100644
--- a/.github/workflows/ci-testing.yml
+++ b/.github/workflows/ci-testing.yml
@@ -69,9 +69,9 @@ jobs:
         # detect custom
         python detect.py --weights runs/exp0/weights/last.pt --device $di
         # test official
-        python test.py --weights weights/${{ matrix.yolo5-model }}.pt --device $di --batch-size 2
+        python eval.py --weights weights/${{ matrix.yolo5-model }}.pt --device $di --batch-size 2
         # test custom
-        python test.py --weights runs/exp0/weights/last.pt --device $di  --batch-size 2
+        python eval.py --weights runs/exp0/weights/last.pt --device $di  --batch-size 2
         # inspect
         python models/yolo.py --cfg models/${{ matrix.yolo5-model }}.yaml
         # export
diff --git a/README.md b/README.md
index c80b139..0d5a38e 100755
--- a/README.md
+++ b/README.md
@@ -27,8 +27,8 @@ This repository represents Ultralytics open-source research into future object d
 
 
 ** AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results in the table denote val2017 accuracy.  
-** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by `python test.py --data coco.yaml --img 736 --conf 0.001`  
-** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img.  Reproduce by `python test.py --data coco.yaml --img 640 --conf 0.1`  
+** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by `python eval.py --data coco.yaml --img 736 --conf 0.001`  
+** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img.  Reproduce by `python eval.py --data coco.yaml --img 640 --conf 0.1`  
 ** All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). 
 
 
diff --git a/tutorial.ipynb b/tutorial.ipynb
index d3418cc..228a79b 100644
--- a/tutorial.ipynb
+++ b/tutorial.ipynb
@@ -236,7 +236,7 @@
       },
       "source": [
         "# Run YOLOv5x on COCO val2017\n",
-        "!python test.py --weights yolov5x.pt --data coco.yaml --img 672"
+        "!python eval.py --weights yolov5x.pt --data coco.yaml --img 672"
       ],
       "execution_count": null,
       "outputs": [
@@ -319,7 +319,7 @@
       },
       "source": [
         "# Run YOLOv5s on COCO test-dev2017 with argument --task test\n",
-        "!python test.py --weights yolov5s.pt --data ./data/coco.yaml --task test"
+        "!python eval.py --weights yolov5s.pt --data ./data/coco.yaml --task test"
       ],
       "execution_count": null,
       "outputs": []
@@ -717,7 +717,7 @@
         "for x in best*\n",
         "do\n",
         "  gsutil cp gs://*/*/*/$x.pt .\n",
-        "  python test.py --weights $x.pt --data coco.yaml --img 672\n",
+        "  python eval.py --weights $x.pt --data coco.yaml --img 672\n",
         "done"
       ],
       "execution_count": null,
@@ -744,8 +744,8 @@
         "  do\n",
         "    python detect.py --weights $x.pt --device $di  # detect official\n",
         "    python detect.py --weights runs/exp0/weights/last.pt --device $di  # detect custom\n",
-        "    python test.py --weights $x.pt --device $di # test official\n",
-        "    python test.py --weights runs/exp0/weights/last.pt --device $di # test custom\n",
+        "    python eval.py --weights $x.pt --device $di # test official\n",
+        "    python eval.py --weights runs/exp0/weights/last.pt --device $di # test custom\n",
         "  done\n",
         "  python models/yolo.py --cfg $x.yaml # inspect\n",
         "  python models/export.py --weights $x.pt --img 640 --batch 1 # export\n",