Geekbench ML Score

2310
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 26 2023 09:11 AM
Views 1

System Information

System Information
Operating System Android 13
Model Google Pixel 7 Pro
Model IDGoogle Pixel 7 Pro
Motherboard cheetah
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 @ 2.35 GHz
Cluster 32 Cores @ 2.85 GHz
Memory Information
Size 11.15 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 459
49.2 IPS
 
Image Classification (F16)
100% 7452
798.4 IPS
 
Image Classification (I8)
79% 11258
1.21 KIPS
 
Image Segmentation (F32)
100% 604
3.73 IPS
 
Image Segmentation (F16)
96% 10936
67.6 IPS
 
Image Segmentation (I8)
89% 34077
210.5 IPS
 
Pose Estimation (F32)
100% 456
1.85 IPS
 
Pose Estimation (F16)
100% 5616
22.7 IPS
 
Pose Estimation (I8)
80% 12891
52.2 IPS
 
Object Detection (F32)
100% 435
15.3 IPS
 
Object Detection (F16)
100% 1620
56.9 IPS
 
Object Detection (I8)
50% 1904
66.8 IPS
 
Face Detection (F32)
100% 797
9.15 IPS
 
Face Detection (F16)
98% 12810
147.2 IPS
 
Face Detection (I8)
75% 26797
307.9 IPS
 
Text Classification (F32)
100% 120
47.5 IPS
 
Text Classification (F16)
100% 1357
536.9 IPS
 
Machine Translation (F32)
100% 699
107.8 IPS
 
Machine Translation (F16)
100% 681
104.9 IPS
 

Compare

Set Baseline Geekbench 6 now available