diff --git a/docs/bert_guide.md b/docs/bert_guide.md
index 94921ebe8..a618a9b4f 100644
--- a/docs/bert_guide.md
+++ b/docs/bert_guide.md
@@ -1288,15 +1288,15 @@ User can use `export NVIDIA_TF32_OVERRIDE=1` to enforce the program run under TF
 
 | <batch_size, seq_len> | FT Dense (ms) | FT Sparse (ms) | Dense EFF (ms) | Sparse EFF (ms) | FT Sparse Speedup | EFF Sparse Speedup |
 | :-------------------: | :-----------: | :------------: | :------------: | :-------------: | :---------------: | :----------------: |
-|        <1, 32>        |     0.80      |      0.86      |      1.30      |      1.61       |       0.84        |        0.83        |
-|       <1, 128>        |     0.85      |      0.87      |      1.24      |      1.62       |       0.86        |        0.85        |
-|       <1, 384>        |     1.18      |      1.18      |      1.22      |      1.68       |       0.95        |        0.86        |
-|        <8, 32>        |     0.91      |      0.91      |      1.20      |      1.65       |       0.86        |        0.85        |
-|       <8, 128>        |     1.66      |      1.58      |      1.59      |      1.86       |       1.05        |        0.99        |
-|       <8, 384>        |     4.16      |      3.79      |      2.21      |      2.36       |       1.22        |        1.11        |
-|       <32, 32>        |     1.68      |      1.58      |      1.42      |      1.77       |       1.04        |        0.91        |
-|       <32, 128>       |     4.71      |      3.98      |      2.75      |      2.60       |       1.23        |        1.12        |
-|       <32, 384>       |     14.79     |     12.20      |      7.90      |      7.72       |       1.17        |        1.07        |
+|        <1, 32>        |     1.32      |      1.58      |      1.35      |      1.62       |       0.84        |        0.83        |
+|       <1, 128>        |     1.37      |      1.59      |      1.37      |      1.61       |       0.86        |        0.85        |
+|       <1, 384>        |     1.52      |      1.60      |      1.40      |      1.62       |       0.95        |        0.86        |
+|        <8, 32>        |     1.39      |      1.61      |      1.39      |      1.63       |       0.86        |        0.85        |
+|       <8, 128>        |     1.70      |      1.62      |      1.61      |      1.63       |       1.05        |        0.99        |
+|       <8, 384>        |     3.38      |      2.78      |      2.10      |      1.89       |       1.22        |        1.11        |
+|       <32, 32>        |     1.70      |      1.63      |      1.50      |      1.65       |       1.04        |        0.91        |
+|       <32, 128>       |     3.62      |      2.94      |      2.28      |      2.04       |       1.23        |        1.12        |
+|       <32, 384>       |     10.10     |      8.60      |      5.77      |      5.38       |       1.17        |        1.07        |
 
 #### BERT performance on T4 and PyTorch