Geekbench ML Score

1689
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Bazilgr
Upload Date February 23 2023 10:24 AM
Views 4

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% 706
75.6 IPS
 
Image Classification (F16)
100% 5411
579.7 IPS
 
Image Classification (I8)
79% 8881
951.6 IPS
 
Image Segmentation (F32)
100% 1068
6.60 IPS
 
Image Segmentation (F16)
100% 7057
43.6 IPS
 
Image Segmentation (I8)
89% 28642
176.9 IPS
 
Pose Estimation (F32)
100% 819
3.31 IPS
 
Pose Estimation (F16)
80% 5383
21.8 IPS
 
Pose Estimation (I8)
80% 13352
54.0 IPS
 
Object Detection (F32)
100% 566
19.9 IPS
 
Object Detection (F16)
100% 94
3.30 IPS
 
Object Detection (I8)
50% 1482
52.0 IPS
 
Face Detection (F32)
100% 1451
16.7 IPS
 
Face Detection (F16)
100% 501
5.76 IPS
 
Face Detection (I8)
75% 14121
162.2 IPS
 
Text Classification (F32)
100% 172
67.9 IPS
 
Text Classification (F16)
100% 1020
403.5 IPS
 
Machine Translation (F32)
100% 589
90.7 IPS
 
Machine Translation (F16)
100% 587
90.5 IPS
 

Compare

Set Baseline Geekbench 6 now available