Geekbench ML Score

1837
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 16 2022 12:07 PM
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 671
71.9 IPS
 
Image Classification (F16)
100% 5650
605.4 IPS
 
Image Classification (I8)
79% 9565
1.02 KIPS
 
Image Segmentation (F32)
100% 1044
6.45 IPS
 
Image Segmentation (F16)
100% 7071
43.7 IPS
 
Image Segmentation (I8)
89% 30228
186.7 IPS
 
Pose Estimation (F32)
100% 829
3.35 IPS
 
Pose Estimation (F16)
80% 5491
22.2 IPS
 
Pose Estimation (I8)
80% 13377
54.1 IPS
 
Object Detection (F32)
100% 636
22.3 IPS
 
Object Detection (F16)
100% 106
3.74 IPS
 
Object Detection (I8)
50% 1855
65.1 IPS
 
Face Detection (F32)
100% 1527
17.5 IPS
 
Face Detection (F16)
100% 628
7.22 IPS
 
Face Detection (I8)
75% 17477
200.8 IPS
 
Text Classification (F32)
100% 189
74.8 IPS
 
Text Classification (F16)
100% 1119
442.4 IPS
 
Machine Translation (F32)
100% 694
107.0 IPS
 
Machine Translation (F16)
100% 694
106.9 IPS
 

Compare

Set Baseline Geekbench 6 now available