Geekbench ML Score

390
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 12 2025 01:15 AM
Views 5

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 7.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 200
21.4 IPS
 
Image Classification (F16)
100% 594
63.6 IPS
 
Image Classification (I8)
80% 563
60.3 IPS
 
Image Segmentation (F32)
100% 380
2.35 IPS
 
Image Segmentation (F16)
100% 530
3.28 IPS
 
Image Segmentation (I8)
89% 1088
6.72 IPS
 
Pose Estimation (F32)
100% 254
1.03 IPS
 
Pose Estimation (F16)
100% 573
2.32 IPS
 
Pose Estimation (I8)
80% 335
1.36 IPS
 
Object Detection (F32)
100% 307
10.8 IPS
 
Object Detection (F16)
99% 530
18.6 IPS
 
Object Detection (I8)
53% 386
13.5 IPS
 
Face Detection (F32)
25% 536
6.16 IPS
 
Face Detection (F16)
25% 757
8.70 IPS
 
Face Detection (I8)
75% 652
7.49 IPS
 
Text Classification (F32)
100% 184
72.8 IPS
 
Text Classification (F16)
100% 182
72.1 IPS
 
Machine Translation (F32)
100% 210
32.4 IPS
 
Machine Translation (F16)
100% 205
31.6 IPS
 

Compare

Set Baseline Geekbench 6 now available