Geekbench ML Score

276
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 27 2025 03:32 AM
Views 3

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% 345
36.9 IPS
 
Image Classification (F16)
100% 457
48.9 IPS
 
Image Classification (I8)
80% 149
15.9 IPS
 
Image Segmentation (F32)
100% 292
1.80 IPS
 
Image Segmentation (F16)
100% 249
1.54 IPS
 
Image Segmentation (I8)
89% 538
3.32 IPS
 
Pose Estimation (F32)
100% 374
1.52 IPS
 
Pose Estimation (F16)
100% 706
2.86 IPS
 
Pose Estimation (I8)
80% 261
1.05 IPS
 
Object Detection (F32)
100% 249
8.73 IPS
 
Object Detection (F16)
100% 325
11.4 IPS
 
Object Detection (I8)
53% 148
5.19 IPS
 
Face Detection (F32)
100% 647
7.43 IPS
 
Face Detection (F16)
97% 699
8.03 IPS
 
Face Detection (I8)
75% 288
3.30 IPS
 
Text Classification (F32)
100% 147
58.1 IPS
 
Text Classification (F16)
100% 106
41.9 IPS
 
Machine Translation (F32)
100% 126
19.4 IPS
 
Machine Translation (F16)
100% 128
19.8 IPS
 

Compare

Set Baseline Geekbench 6 now available