Geekbench ML Score

324
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 19 2025 02:05 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% 366
39.2 IPS
 
Image Classification (F16)
100% 504
54.0 IPS
 
Image Classification (I8)
80% 161
17.3 IPS
 
Image Segmentation (F32)
100% 383
2.37 IPS
 
Image Segmentation (F16)
100% 393
2.43 IPS
 
Image Segmentation (I8)
89% 733
4.53 IPS
 
Pose Estimation (F32)
100% 373
1.51 IPS
 
Pose Estimation (F16)
100% 712
2.88 IPS
 
Pose Estimation (I8)
80% 270
1.09 IPS
 
Object Detection (F32)
100% 326
11.4 IPS
 
Object Detection (F16)
100% 388
13.6 IPS
 
Object Detection (I8)
53% 167
5.85 IPS
 
Face Detection (F32)
100% 673
7.74 IPS
 
Face Detection (F16)
97% 834
9.58 IPS
 
Face Detection (I8)
75% 368
4.23 IPS
 
Text Classification (F32)
100% 173
68.5 IPS
 
Text Classification (F16)
100% 100
39.6 IPS
 
Machine Translation (F32)
100% 163
25.0 IPS
 
Machine Translation (F16)
100% 178
27.5 IPS
 

Compare

Set Baseline Geekbench 6 now available