Geekbench ML Score

250
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date April 17 2025 03:58 AM
Views 2

System Information

System Information
Operating System Android 15
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 5.31 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 147
27.5 IPS
 
Image Classification (F16)
100% 113
21.1 IPS
 
Image Classification (I8)
97% 138
25.9 IPS
 
Image Segmentation (F32)
100% 199
3.32 IPS
 
Image Segmentation (F16)
100% 200
3.34 IPS
 
Image Segmentation (I8)
98% 313
5.23 IPS
 
Pose Estimation (F32)
100% 374
0.45 IPS
 
Pose Estimation (F16)
100% 354
0.43 IPS
 
Pose Estimation (I8)
100% 1548
1.87 IPS
 
Object Detection (F32)
100% 124
9.23 IPS
 
Object Detection (F16)
100% 121
9.07 IPS
 
Object Detection (I8)
61% 202
15.1 IPS
 
Face Detection (F32)
100% 303
3.60 IPS
 
Face Detection (F16)
100% 321
3.82 IPS
 
Face Detection (I8)
86% 532
6.33 IPS
 
Depth Estimation (F32)
100% 306
2.37 IPS
 
Depth Estimation (F16)
100% 301
2.33 IPS
 
Depth Estimation (I8)
95% 605
4.69 IPS
 
Style Transfer (F32)
100% 615
0.81 IPS
 
Style Transfer (F16)
100% 613
0.81 IPS
 
Style Transfer (I8)
98% 1870
2.46 IPS
 
Image Super-Resolution (F32)
100% 164
5.85 IPS
 
Image Super-Resolution (F16)
100% 177
6.32 IPS
 
Image Super-Resolution (I8)
98% 664
23.7 IPS
 
Text Classification (F32)
100% 81
116.8 IPS
 
Text Classification (F16)
100% 61
87.2 IPS
 
Text Classification (I8)
92% 68
97.7 IPS
 
Machine Translation (F32)
100% 140
2.58 IPS
 
Machine Translation (F16)
100% 179
3.29 IPS
 
Machine Translation (I8)
64% 151
2.79 IPS
 

Compare

Set Baseline Geekbench 6 now available