Geekbench ML Score

317
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 19 2025 11:20 AM
Views 3

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 5.40 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 355
38.0 IPS
 
Image Classification (F16)
100% 486
52.1 IPS
 
Image Classification (I8)
80% 158
16.9 IPS
 
Image Segmentation (F32)
100% 318
1.96 IPS
 
Image Segmentation (F16)
100% 356
2.20 IPS
 
Image Segmentation (I8)
89% 673
4.16 IPS
 
Pose Estimation (F32)
100% 375
1.52 IPS
 
Pose Estimation (F16)
100% 705
2.85 IPS
 
Pose Estimation (I8)
80% 264
1.07 IPS
 
Object Detection (F32)
100% 297
10.4 IPS
 
Object Detection (F16)
100% 364
12.8 IPS
 
Object Detection (I8)
53% 176
6.18 IPS
 
Face Detection (F32)
100% 640
7.36 IPS
 
Face Detection (F16)
97% 789
9.06 IPS
 
Face Detection (I8)
75% 363
4.17 IPS
 
Text Classification (F32)
100% 155
61.5 IPS
 
Text Classification (F16)
100% 132
52.3 IPS
 
Machine Translation (F32)
100% 185
28.5 IPS
 
Machine Translation (F16)
100% 175
27.0 IPS
 

Compare

Set Baseline Geekbench 6 now available