Geekbench ML Score

219
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 10 2024 01:46 AM
Views 1

System Information

System Information
Operating System Android 14
Model samsung SM-A166P
Model IDsamsung SM-A166P
Motherboard a16xm
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 3.36 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 96
10.3 IPS
 
Image Classification (F16)
100% 92
9.89 IPS
 
Image Classification (I8)
81% 150
16.1 IPS
 
Image Segmentation (F32)
100% 359
2.22 IPS
 
Image Segmentation (F16)
100% 365
2.25 IPS
 
Image Segmentation (I8)
89% 595
3.68 IPS
 
Pose Estimation (F32)
100% 137
0.56 IPS
 
Pose Estimation (F16)
100% 138
0.56 IPS
 
Pose Estimation (I8)
80% 153
0.62 IPS
 
Object Detection (F32)
100% 161
5.64 IPS
 
Object Detection (F16)
100% 162
5.70 IPS
 
Object Detection (I8)
52% 256
9.00 IPS
 
Face Detection (F32)
100% 318
3.65 IPS
 
Face Detection (F16)
100% 318
3.65 IPS
 
Face Detection (I8)
75% 376
4.31 IPS
 
Text Classification (F32)
100% 288
113.9 IPS
 
Text Classification (F16)
100% 341
135.0 IPS
 
Machine Translation (F32)
100% 198
30.6 IPS
 
Machine Translation (F16)
100% 203
31.3 IPS
 

Compare

Set Baseline Geekbench 6 now available