Geekbench ML Score

1775
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 01 2021 02:56 AM
Views 3

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% 767
82.2 IPS
 
Image Classification (F16)
100% 5607
600.7 IPS
 
Image Classification (I8)
79% 9884
1.06 KIPS
 
Image Segmentation (F32)
100% 1240
7.66 IPS
 
Image Segmentation (F16)
100% 259
1.60 IPS
 
Image Segmentation (I8)
89% 26044
160.9 IPS
 
Pose Estimation (F32)
100% 771
3.12 IPS
 
Pose Estimation (F16)
80% 5371
21.7 IPS
 
Pose Estimation (I8)
80% 13889
56.2 IPS
 
Object Detection (F32)
100% 613
21.5 IPS
 
Object Detection (F16)
100% 1583
55.6 IPS
 
Object Detection (I8)
50% 1817
63.8 IPS
 
Face Detection (F32)
100% 1532
17.6 IPS
 
Face Detection (F16)
97% 5881
67.6 IPS
 
Face Detection (I8)
75% 17142
196.9 IPS
 
Text Classification (F32)
100% 212
83.8 IPS
 
Text Classification (F16)
100% 84
33.2 IPS
 
Machine Translation (F32)
100% 758
116.8 IPS
 
Machine Translation (F16)
100% 729
112.4 IPS
 

Compare

Set Baseline Geekbench 6 now available