Geekbench ML Score

1915
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 23 2022 06:29 AM
Views 1

System Information

System Information
Operating System Android 13
Model Google Pixel 6 Pro
Model IDGoogle Pixel 6 Pro
Motherboard raven
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.25 GHz
Cluster 32 Cores @ 2.80 GHz
Memory Information
Size 11.25 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 800
85.7 IPS
 
Image Classification (F16)
100% 5876
629.5 IPS
 
Image Classification (I8)
79% 9967
1.07 KIPS
 
Image Segmentation (F32)
100% 1225
7.57 IPS
 
Image Segmentation (F16)
100% 6843
42.3 IPS
 
Image Segmentation (I8)
89% 29314
181.1 IPS
 
Pose Estimation (F32)
100% 797
3.23 IPS
 
Pose Estimation (F16)
80% 5472
22.1 IPS
 
Pose Estimation (I8)
80% 13590
55.0 IPS
 
Object Detection (F32)
100% 696
24.4 IPS
 
Object Detection (F16)
100% 135
4.72 IPS
 
Object Detection (I8)
50% 1815
63.7 IPS
 
Face Detection (F32)
100% 1553
17.8 IPS
 
Face Detection (F16)
100% 561
6.45 IPS
 
Face Detection (I8)
75% 17828
204.8 IPS
 
Text Classification (F32)
100% 255
100.9 IPS
 
Text Classification (F16)
100% 1138
450.0 IPS
 
Machine Translation (F32)
100% 649
100.0 IPS
 
Machine Translation (F16)
100% 678
104.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download