diff --git a/cv/classification/resnet50/paddlepaddle/README.md b/cv/classification/resnet50/paddlepaddle/README.md
index 08c89e8c5a4dc6c3598ab05724b50ba4fd086756..c3f404bbbb5cc63c6cdca7fdea94805c70f98e5d 100644
--- a/cv/classification/resnet50/paddlepaddle/README.md
+++ b/cv/classification/resnet50/paddlepaddle/README.md
@@ -44,3 +44,13 @@ export FLAGS_cudnn_batchnorm_spatial_persistent=True
 export CUDA_VISIBLE_DEVICES=0,1,2,3
 python3 -u -m paddle.distributed.launch --gpus=0,1,2,3 tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50.yaml -o Arch.pretrained=False -o Global.device=gpu
 ```
+
+## Results on BI-V100
+
+<div align="center">
+
+| GPU         | FP32                                 |
+| ----------- | ------------------------------------ |
+| 4 cards     | Acc@1=76.27,FPS=80.37,BatchSize=64   |
+
+</div>
diff --git a/cv/detection/maskrcnn/paddlepaddle/README.md b/cv/detection/maskrcnn/paddlepaddle/README.md
index 46ef1bc25b95c9349cc9b0e524b2558397bda1dd..fec7c48c7d2e04d84dfc4fbcbbf603ac428f46e2 100644
--- a/cv/detection/maskrcnn/paddlepaddle/README.md
+++ b/cv/detection/maskrcnn/paddlepaddle/README.md
@@ -40,5 +40,15 @@ sed -i "s#dataset/coco#${coco_dir}#g" configs/datasets/coco_instance.yml
 export FLAGS_cudnn_exhaustive_search=True
 export FLAGS_cudnn_batchnorm_spatial_persistent=True
 export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
-python3 -u -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml --use_vdl=true --eval --amp
+python3 -u -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml --use_vdl=true --eval
 ```
+
+## Results on BI-V100
+
+<div align="center">
+
+| GPU         | FP32                                 |
+| ----------- | ------------------------------------ |
+| 8 cards     | bbox=38.8,FPS=7.5,BatchSize=1        |
+
+</div>
diff --git a/cv/detection/ssd/paddlepaddle/README.md b/cv/detection/ssd/paddlepaddle/README.md
index 5ed24ff0f2c2b84a244d0c0901a3170201b5ff00..1cd9b60f550771f0d657758819666d620af94ac6 100644
--- a/cv/detection/ssd/paddlepaddle/README.md
+++ b/cv/detection/ssd/paddlepaddle/README.md
@@ -35,5 +35,15 @@ export CUDA_VISIBLE_DEVICES=0,1
 python3 -u -m paddle.distributed.launch --gpus 0,1 tools/train.py -c configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml --eval
 ```
 
+## Results on BI-V100
+
+<div align="center">
+
+| GPU         | FP32                                 |
+| ----------- | ------------------------------------ |
+| 2 cards     | bbox=73.62,FPS=45.49,BatchSize=32    |
+
+</div>
+
 ## Reference
-- [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)
\ No newline at end of file
+- [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)
diff --git a/nlp/language_model/bert/paddlepaddle/README.md b/nlp/language_model/bert/paddlepaddle/README.md
index cf6b895ab15dd1f2bdb69deda8ba62c820dcd40d..f259ac0d7c41693cf27dd922337ffabd2e8c5a96 100644
--- a/nlp/language_model/bert/paddlepaddle/README.md
+++ b/nlp/language_model/bert/paddlepaddle/README.md
@@ -23,3 +23,14 @@ Download the [MNLI Dataset](http://www.nyu.edu/projects/bowman/multinli/)
 # Make sure your dataset path is the same as above
 bash train_bert.sh
 ```
+
+
+## Results on BI-V100
+
+<div align="center">
+
+| GPU         | FP32                                 |
+| ----------- | ------------------------------------ |
+| 1 card      | Acc@1=84.5,FPS=5.1,BatchSize=32      |
+
+</div>