Geekbench ML Score

1761
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 03 2021 05:58 PM
Views 2

System Information

System Information
Operating System Android 12
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 11.21 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 763
81.8 IPS
 
Image Classification (F16)
100% 5811
622.6 IPS
 
Image Classification (I8)
79% 10358
1.11 KIPS
 
Image Segmentation (F32)
100% 1212
7.49 IPS
 
Image Segmentation (F16)
100% 261
1.61 IPS
 
Image Segmentation (I8)
89% 25756
159.1 IPS
 
Pose Estimation (F32)
100% 795
3.22 IPS
 
Pose Estimation (F16)
80% 5377
21.8 IPS
 
Pose Estimation (I8)
80% 13242
53.6 IPS
 
Object Detection (F32)
100% 613
21.5 IPS
 
Object Detection (F16)
100% 1554
54.5 IPS
 
Object Detection (I8)
50% 1800
63.2 IPS
 
Face Detection (F32)
100% 1661
19.1 IPS
 
Face Detection (F16)
97% 5682
65.3 IPS
 
Face Detection (I8)
75% 16715
192.0 IPS
 
Text Classification (F32)
100% 245
97.0 IPS
 
Text Classification (F16)
100% 85
33.5 IPS
 
Machine Translation (F32)
100% 625
96.4 IPS
 
Machine Translation (F16)
100% 633
97.5 IPS
 

Compare

Set Baseline Geekbench 6 now available