Geekbench ML Score

237
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 21 2025 06:22 AM
Views 1

System Information

System Information
Operating System Android 15
Model samsung SM-A146U
Model IDsamsung SM-A146U
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 3.51 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 321
34.4 IPS
 
Image Classification (F16)
100% 420
45.0 IPS
 
Image Classification (I8)
80% 100
10.7 IPS
 
Image Segmentation (F32)
100% 268
1.66 IPS
 
Image Segmentation (F16)
100% 256
1.58 IPS
 
Image Segmentation (I8)
89% 399
2.47 IPS
 
Pose Estimation (F32)
100% 368
1.49 IPS
 
Pose Estimation (F16)
100% 700
2.83 IPS
 
Pose Estimation (I8)
80% 212
0.86 IPS
 
Object Detection (F32)
100% 244
8.56 IPS
 
Object Detection (F16)
100% 272
9.54 IPS
 
Object Detection (I8)
53% 107
3.74 IPS
 
Face Detection (F32)
100% 569
6.54 IPS
 
Face Detection (F16)
97% 670
7.70 IPS
 
Face Detection (I8)
75% 220
2.53 IPS
 
Text Classification (F32)
100% 85
33.7 IPS
 
Text Classification (F16)
100% 74
29.2 IPS
 
Machine Translation (F32)
100% 132
20.4 IPS
 
Machine Translation (F16)
100% 134
20.6 IPS
 

Compare

Set Baseline Geekbench 6 now available