Geekbench ML Score

1602
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 09:13 AM
Views 1

System Information

System Information
Operating System Android 12
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 11.21 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 727
77.9 IPS
 
Image Classification (F16)
100% 5143
551.0 IPS
 
Image Classification (I8)
79% 9278
994.1 IPS
 
Image Segmentation (F32)
100% 1060
6.54 IPS
 
Image Segmentation (F16)
100% 225
1.39 IPS
 
Image Segmentation (I8)
89% 22174
137.0 IPS
 
Pose Estimation (F32)
100% 790
3.20 IPS
 
Pose Estimation (F16)
80% 4555
18.4 IPS
 
Pose Estimation (I8)
80% 11441
46.3 IPS
 
Object Detection (F32)
100% 589
20.7 IPS
 
Object Detection (F16)
100% 1217
42.7 IPS
 
Object Detection (I8)
50% 1368
48.0 IPS
 
Face Detection (F32)
100% 1739
20.0 IPS
 
Face Detection (F16)
97% 5315
61.1 IPS
 
Face Detection (I8)
75% 15786
181.4 IPS
 
Text Classification (F32)
100% 274
108.5 IPS
 
Text Classification (F16)
100% 73
29.0 IPS
 
Machine Translation (F32)
100% 596
91.9 IPS
 
Machine Translation (F16)
100% 604
93.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download