Geekbench ML Score

278
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 13 2025 12:49 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 3.50 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 346
37.1 IPS
 
Image Classification (F16)
100% 439
47.0 IPS
 
Image Classification (I8)
80% 118
12.6 IPS
 
Image Segmentation (F32)
100% 354
2.19 IPS
 
Image Segmentation (F16)
100% 369
2.28 IPS
 
Image Segmentation (I8)
89% 553
3.42 IPS
 
Pose Estimation (F32)
100% 370
1.50 IPS
 
Pose Estimation (F16)
100% 710
2.87 IPS
 
Pose Estimation (I8)
80% 145
0.59 IPS
 
Object Detection (F32)
100% 268
9.41 IPS
 
Object Detection (F16)
100% 350
12.3 IPS
 
Object Detection (I8)
53% 141
4.94 IPS
 
Face Detection (F32)
100% 662
7.61 IPS
 
Face Detection (F16)
97% 734
8.43 IPS
 
Face Detection (I8)
75% 281
3.23 IPS
 
Text Classification (F32)
100% 114
45.1 IPS
 
Text Classification (F16)
100% 116
45.7 IPS
 
Machine Translation (F32)
100% 166
25.6 IPS
 
Machine Translation (F16)
100% 144
22.2 IPS
 

Compare

Set Baseline Geekbench 6 now available