Geekbench ML Score

1294
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 14 2022 02:36 PM
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 11.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 690
74.0 IPS
 
Image Classification (F16)
100% 5662
606.6 IPS
 
Image Classification (I8)
79% 10054
1.08 KIPS
 
Image Segmentation (F32)
100% 1118
6.91 IPS
 
Image Segmentation (F16)
100% 257
1.59 IPS
 
Image Segmentation (I8)
89% 26001
160.6 IPS
 
Pose Estimation (F32)
100% 761
3.08 IPS
 
Pose Estimation (F16)
80% 5339
21.6 IPS
 
Pose Estimation (I8)
80% 13400
54.2 IPS
 
Object Detection (F32)
100% 536
18.8 IPS
 
Object Detection (F16)
100% 92
3.24 IPS
 
Object Detection (I8)
50% 1794
63.0 IPS
 
Face Detection (F32)
100% 1611
18.5 IPS
 
Face Detection (F16)
100% 521
5.99 IPS
 
Face Detection (I8)
75% 16928
194.5 IPS
 
Text Classification (F32)
100% 177
69.9 IPS
 
Text Classification (F16)
100% 82
32.5 IPS
 
Machine Translation (F32)
100% 682
105.1 IPS
 
Machine Translation (F16)
100% 681
104.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download