Geekbench ML Score

388
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 12 2025 01:08 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 3.35 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 196
21.0 IPS
 
Image Classification (F16)
100% 588
63.0 IPS
 
Image Classification (I8)
80% 559
59.9 IPS
 
Image Segmentation (F32)
100% 380
2.35 IPS
 
Image Segmentation (F16)
100% 535
3.31 IPS
 
Image Segmentation (I8)
89% 1093
6.75 IPS
 
Pose Estimation (F32)
100% 250
1.01 IPS
 
Pose Estimation (F16)
100% 565
2.29 IPS
 
Pose Estimation (I8)
80% 349
1.41 IPS
 
Object Detection (F32)
100% 305
10.7 IPS
 
Object Detection (F16)
99% 528
18.5 IPS
 
Object Detection (I8)
53% 394
13.8 IPS
 
Face Detection (F32)
25% 521
5.98 IPS
 
Face Detection (F16)
25% 745
8.56 IPS
 
Face Detection (I8)
75% 663
7.62 IPS
 
Text Classification (F32)
100% 181
71.6 IPS
 
Text Classification (F16)
100% 176
69.5 IPS
 
Machine Translation (F32)
100% 212
32.7 IPS
 
Machine Translation (F16)
100% 201
30.9 IPS
 

Compare

Set Baseline Geekbench 6 now available