Geekbench ML Score

84
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 20 2025 10:17 AM
Views 3

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 5.42 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 54
5.77 IPS
 
Image Classification (F16)
100% 57
6.14 IPS
 
Image Classification (I8)
81% 74
7.97 IPS
 
Image Segmentation (F32)
100% 128
0.79 IPS
 
Image Segmentation (F16)
100% 126
0.78 IPS
 
Image Segmentation (I8)
89% 128
0.79 IPS
 
Pose Estimation (F32)
100% 43
0.17 IPS
 
Pose Estimation (F16)
100% 41
0.17 IPS
 
Pose Estimation (I8)
80% 21
0.09 IPS
 
Object Detection (F32)
100% 75
2.62 IPS
 
Object Detection (F16)
100% 71
2.47 IPS
 
Object Detection (I8)
52% 88
3.09 IPS
 
Face Detection (F32)
100% 109
1.26 IPS
 
Face Detection (F16)
100% 115
1.32 IPS
 
Face Detection (I8)
75% 99
1.13 IPS
 
Text Classification (F32)
100% 165
65.4 IPS
 
Text Classification (F16)
100% 194
76.9 IPS
 
Machine Translation (F32)
100% 108
16.7 IPS
 
Machine Translation (F16)
100% 123
19.0 IPS
 

Compare

Set Baseline Geekbench 6 now available