Geekbench ML Score

1914
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 03 2022 05:36 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% 683
73.2 IPS
 
Image Classification (F16)
100% 5692
609.9 IPS
 
Image Classification (I8)
79% 9637
1.03 KIPS
 
Image Segmentation (F32)
100% 1076
6.65 IPS
 
Image Segmentation (F16)
100% 6986
43.2 IPS
 
Image Segmentation (I8)
89% 29605
182.9 IPS
 
Pose Estimation (F32)
100% 838
3.39 IPS
 
Pose Estimation (F16)
80% 5415
21.9 IPS
 
Pose Estimation (I8)
80% 13367
54.1 IPS
 
Object Detection (F32)
100% 632
22.2 IPS
 
Object Detection (F16)
100% 417
14.6 IPS
 
Object Detection (I8)
50% 1822
63.9 IPS
 
Face Detection (F32)
100% 1319
15.2 IPS
 
Face Detection (F16)
100% 572
6.57 IPS
 
Face Detection (I8)
75% 17359
199.4 IPS
 
Text Classification (F32)
100% 150
59.5 IPS
 
Text Classification (F16)
100% 1112
439.8 IPS
 
Machine Translation (F32)
100% 658
101.4 IPS
 
Machine Translation (F16)
100% 658
101.5 IPS
 

Compare

Set Baseline Geekbench 6 now available