Geekbench ML Score

394
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 17 2025 03:05 AM
Views 3

System Information

System Information
Operating System Android 15
Model samsung SM-A166P
Model IDsamsung SM-A166P
Motherboard a16xm
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 @ 2.40 GHz
Memory Information
Size 5.34 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 200
21.5 IPS
 
Image Classification (F16)
100% 589
63.1 IPS
 
Image Classification (I8)
80% 576
61.7 IPS
 
Image Segmentation (F32)
100% 390
2.41 IPS
 
Image Segmentation (F16)
100% 537
3.32 IPS
 
Image Segmentation (I8)
89% 1116
6.89 IPS
 
Pose Estimation (F32)
100% 252
1.02 IPS
 
Pose Estimation (F16)
100% 569
2.30 IPS
 
Pose Estimation (I8)
80% 378
1.53 IPS
 
Object Detection (F32)
100% 308
10.8 IPS
 
Object Detection (F16)
99% 532
18.7 IPS
 
Object Detection (I8)
53% 400
14.0 IPS
 
Face Detection (F32)
25% 535
6.14 IPS
 
Face Detection (F16)
25% 748
8.60 IPS
 
Face Detection (I8)
75% 714
8.21 IPS
 
Text Classification (F32)
100% 182
71.9 IPS
 
Text Classification (F16)
100% 176
69.8 IPS
 
Machine Translation (F32)
100% 200
30.8 IPS
 
Machine Translation (F16)
100% 201
31.0 IPS
 

Compare

Set Baseline Geekbench 6 now available