Geekbench ML Score

107
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 20 2025 09:36 AM
Views 2

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% 76
8.15 IPS
 
Image Classification (F16)
100% 74
7.98 IPS
 
Image Classification (I8)
81% 88
9.46 IPS
 
Image Segmentation (F32)
100% 168
1.04 IPS
 
Image Segmentation (F16)
100% 163
1.00 IPS
 
Image Segmentation (I8)
89% 170
1.05 IPS
 
Pose Estimation (F32)
100% 50
0.20 IPS
 
Pose Estimation (F16)
100% 48
0.20 IPS
 
Pose Estimation (I8)
80% 28
0.11 IPS
 
Object Detection (F32)
100% 99
3.47 IPS
 
Object Detection (F16)
100% 99
3.48 IPS
 
Object Detection (I8)
52% 122
4.27 IPS
 
Face Detection (F32)
100% 150
1.73 IPS
 
Face Detection (F16)
100% 149
1.72 IPS
 
Face Detection (I8)
75% 119
1.36 IPS
 
Text Classification (F32)
100% 195
77.1 IPS
 
Text Classification (F16)
100% 234
92.5 IPS
 
Machine Translation (F32)
100% 143
22.1 IPS
 
Machine Translation (F16)
100% 122
18.8 IPS
 

Compare

Set Baseline Geekbench 6 now available