Geekbench ML Score

338
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 25 2025 01:49 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 3.46 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 357
38.3 IPS
 
Image Classification (F16)
100% 487
52.2 IPS
 
Image Classification (I8)
80% 176
18.9 IPS
 
Image Segmentation (F32)
100% 350
2.16 IPS
 
Image Segmentation (F16)
100% 366
2.26 IPS
 
Image Segmentation (I8)
89% 762
4.71 IPS
 
Pose Estimation (F32)
100% 374
1.51 IPS
 
Pose Estimation (F16)
100% 716
2.90 IPS
 
Pose Estimation (I8)
80% 306
1.24 IPS
 
Object Detection (F32)
100% 285
9.99 IPS
 
Object Detection (F16)
100% 321
11.3 IPS
 
Object Detection (I8)
53% 197
6.90 IPS
 
Face Detection (F32)
100% 638
7.33 IPS
 
Face Detection (F16)
97% 842
9.67 IPS
 
Face Detection (I8)
75% 380
4.37 IPS
 
Text Classification (F32)
100% 248
98.0 IPS
 
Text Classification (F16)
100% 146
57.8 IPS
 
Machine Translation (F32)
100% 188
29.0 IPS
 
Machine Translation (F16)
100% 189
29.1 IPS
 

Compare

Set Baseline Geekbench 6 now available