Geekbench ML Score

793
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 14 2023 03:39 AM
Views 1

System Information

System Information
Operating System Android 13
Model Samsung Galaxy Tab S7
Model IDsamsung SM-T870
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.09 GHz
Memory Information
Size 5.52 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 773
82.8 IPS
 
Image Classification (F16)
100% 1199
128.5 IPS
 
Image Classification (I8)
80% 1664
178.3 IPS
 
Image Segmentation (F32)
100% 1008
6.23 IPS
 
Image Segmentation (F16)
100% 1291
7.98 IPS
 
Image Segmentation (I8)
89% 3728
23.0 IPS
 
Pose Estimation (F32)
100% 462
1.87 IPS
 
Pose Estimation (F16)
100% 1727
6.99 IPS
 
Pose Estimation (I8)
80% 5734
23.2 IPS
 
Object Detection (F32)
100% 698
24.5 IPS
 
Object Detection (F16)
100% 780
27.4 IPS
 
Object Detection (I8)
52% 1251
43.9 IPS
 
Face Detection (F32)
100% 1142
13.1 IPS
 
Face Detection (F16)
97% 1382
15.9 IPS
 
Face Detection (I8)
75% 4511
51.8 IPS
 
Text Classification (F32)
54% 15
6.11 IPS
 
Text Classification (F16)
54% 14
5.35 IPS
 
Machine Translation (F32)
100% 587
90.4 IPS
 
Machine Translation (F16)
100% 597
92.1 IPS
 

Compare

Set Baseline Geekbench 6 now available