Geekbench ML Score

1696
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 30 2021 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 11.21 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 701
75.1 IPS
 
Image Classification (F16)
100% 5490
588.3 IPS
 
Image Classification (I8)
79% 9491
1.02 KIPS
 
Image Segmentation (F32)
100% 1186
7.33 IPS
 
Image Segmentation (F16)
100% 258
1.59 IPS
 
Image Segmentation (I8)
89% 25613
158.2 IPS
 
Pose Estimation (F32)
100% 774
3.13 IPS
 
Pose Estimation (F16)
80% 5380
21.8 IPS
 
Pose Estimation (I8)
80% 13412
54.3 IPS
 
Object Detection (F32)
100% 558
19.6 IPS
 
Object Detection (F16)
100% 1574
55.2 IPS
 
Object Detection (I8)
50% 1804
63.3 IPS
 
Face Detection (F32)
100% 1486
17.1 IPS
 
Face Detection (F16)
97% 5878
67.5 IPS
 
Face Detection (I8)
75% 16892
194.1 IPS
 
Text Classification (F32)
100% 157
62.1 IPS
 
Text Classification (F16)
100% 83
32.9 IPS
 
Machine Translation (F32)
100% 688
106.0 IPS
 
Machine Translation (F16)
100% 689
106.1 IPS
 

Compare

Set Baseline Geekbench 6 now available