Geekbench ML Score

1828
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 10 2022 12:14 AM
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% 672
72.1 IPS
 
Image Classification (F16)
100% 5696
610.3 IPS
 
Image Classification (I8)
79% 9650
1.03 KIPS
 
Image Segmentation (F32)
100% 1040
6.42 IPS
 
Image Segmentation (F16)
100% 7024
43.4 IPS
 
Image Segmentation (I8)
89% 29606
182.9 IPS
 
Pose Estimation (F32)
100% 809
3.27 IPS
 
Pose Estimation (F16)
80% 5444
22.0 IPS
 
Pose Estimation (I8)
80% 13468
54.5 IPS
 
Object Detection (F32)
100% 637
22.3 IPS
 
Object Detection (F16)
100% 138
4.84 IPS
 
Object Detection (I8)
50% 1847
64.8 IPS
 
Face Detection (F32)
100% 1457
16.7 IPS
 
Face Detection (F16)
100% 519
5.96 IPS
 
Face Detection (I8)
75% 17437
200.3 IPS
 
Text Classification (F32)
100% 182
72.0 IPS
 
Text Classification (F16)
100% 1118
442.3 IPS
 
Machine Translation (F32)
100% 680
104.8 IPS
 
Machine Translation (F16)
100% 678
104.5 IPS
 

Compare

Set Baseline Geekbench 6 now available