Geekbench ML Score

303
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 30 2025 03:15 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% 346
37.1 IPS
 
Image Classification (F16)
100% 458
49.0 IPS
 
Image Classification (I8)
80% 154
16.5 IPS
 
Image Segmentation (F32)
100% 284
1.75 IPS
 
Image Segmentation (F16)
100% 313
1.94 IPS
 
Image Segmentation (I8)
89% 562
3.47 IPS
 
Pose Estimation (F32)
100% 377
1.52 IPS
 
Pose Estimation (F16)
100% 707
2.86 IPS
 
Pose Estimation (I8)
80% 268
1.08 IPS
 
Object Detection (F32)
100% 249
8.72 IPS
 
Object Detection (F16)
100% 356
12.5 IPS
 
Object Detection (I8)
53% 160
5.61 IPS
 
Face Detection (F32)
100% 617
7.09 IPS
 
Face Detection (F16)
97% 691
7.94 IPS
 
Face Detection (I8)
75% 373
4.28 IPS
 
Text Classification (F32)
100% 162
64.2 IPS
 
Text Classification (F16)
100% 121
48.0 IPS
 
Machine Translation (F32)
100% 197
30.4 IPS
 
Machine Translation (F16)
100% 188
29.0 IPS
 

Compare

Set Baseline Geekbench 6 now available