Geekbench ML Score

348
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 11 2025 12:59 AM
Views 6

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% 357
38.3 IPS
 
Image Classification (F16)
100% 474
50.8 IPS
 
Image Classification (I8)
80% 169
18.1 IPS
 
Image Segmentation (F32)
100% 387
2.39 IPS
 
Image Segmentation (F16)
100% 423
2.62 IPS
 
Image Segmentation (I8)
89% 740
4.57 IPS
 
Pose Estimation (F32)
100% 375
1.52 IPS
 
Pose Estimation (F16)
100% 712
2.88 IPS
 
Pose Estimation (I8)
80% 286
1.16 IPS
 
Object Detection (F32)
100% 330
11.6 IPS
 
Object Detection (F16)
100% 477
16.8 IPS
 
Object Detection (I8)
53% 199
6.99 IPS
 
Face Detection (F32)
100% 659
7.57 IPS
 
Face Detection (F16)
97% 867
9.97 IPS
 
Face Detection (I8)
75% 400
4.59 IPS
 
Text Classification (F32)
100% 195
77.2 IPS
 
Text Classification (F16)
100% 126
49.7 IPS
 
Machine Translation (F32)
100% 203
31.4 IPS
 
Machine Translation (F16)
100% 212
32.7 IPS
 

Compare

Set Baseline Geekbench 6 now available