Geekbench ML Score

1822
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2022 09:51 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% 650
69.7 IPS
 
Image Classification (F16)
100% 5792
620.6 IPS
 
Image Classification (I8)
79% 9539
1.02 KIPS
 
Image Segmentation (F32)
100% 1048
6.47 IPS
 
Image Segmentation (F16)
100% 7100
43.9 IPS
 
Image Segmentation (I8)
89% 30054
185.6 IPS
 
Pose Estimation (F32)
100% 833
3.37 IPS
 
Pose Estimation (F16)
80% 5446
22.0 IPS
 
Pose Estimation (I8)
80% 13877
56.1 IPS
 
Object Detection (F32)
100% 641
22.5 IPS
 
Object Detection (F16)
100% 101
3.56 IPS
 
Object Detection (I8)
50% 1856
65.1 IPS
 
Face Detection (F32)
100% 1523
17.5 IPS
 
Face Detection (F16)
100% 532
6.11 IPS
 
Face Detection (I8)
75% 17524
201.3 IPS
 
Text Classification (F32)
100% 198
78.3 IPS
 
Text Classification (F16)
100% 1119
442.7 IPS
 
Machine Translation (F32)
100% 685
105.6 IPS
 
Machine Translation (F16)
100% 687
105.8 IPS
 

Compare

Set Baseline Geekbench 6 now available