Geekbench ML Score

88
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 20 2025 10:13 AM
Views 1

System Information

System Information
Operating System Android 15
Model samsung SM-A146P
Model IDsamsung SM-A146P
Motherboard a14xm
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 @ 2.20 GHz
Memory Information
Size 3.46 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 59
6.29 IPS
 
Image Classification (F16)
100% 60
6.43 IPS
 
Image Classification (I8)
81% 82
8.80 IPS
 
Image Segmentation (F32)
100% 152
0.94 IPS
 
Image Segmentation (F16)
100% 143
0.88 IPS
 
Image Segmentation (I8)
89% 146
0.90 IPS
 
Pose Estimation (F32)
100% 43
0.18 IPS
 
Pose Estimation (F16)
100% 42
0.17 IPS
 
Pose Estimation (I8)
80% 28
0.11 IPS
 
Object Detection (F32)
100% 88
3.10 IPS
 
Object Detection (F16)
100% 90
3.15 IPS
 
Object Detection (I8)
52% 104
3.65 IPS
 
Face Detection (F32)
100% 141
1.63 IPS
 
Face Detection (F16)
100% 117
1.35 IPS
 
Face Detection (I8)
75% 96
1.10 IPS
 
Text Classification (F32)
100% 74
29.4 IPS
 
Text Classification (F16)
100% 162
63.9 IPS
 
Machine Translation (F32)
100% 122
18.9 IPS
 
Machine Translation (F16)
100% 119
18.3 IPS
 

Compare

Set Baseline Geekbench 6 now available