Geekbench ML Score

315
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 18 2025 03:31 PM
Views 3

System Information

System Information
Operating System Android 15
Model samsung SM-M166P
Model IDsamsung SM-M166P
Motherboard m16xm
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 7.30 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 192
20.6 IPS
 
Image Classification (F16)
100% 534
57.2 IPS
 
Image Classification (I8)
80% 327
35.0 IPS
 
Image Segmentation (F32)
100% 342
2.11 IPS
 
Image Segmentation (F16)
100% 460
2.84 IPS
 
Image Segmentation (I8)
89% 712
4.40 IPS
 
Pose Estimation (F32)
100% 247
1.00 IPS
 
Pose Estimation (F16)
100% 557
2.26 IPS
 
Pose Estimation (I8)
80% 234
0.95 IPS
 
Object Detection (F32)
100% 275
9.64 IPS
 
Object Detection (F16)
99% 473
16.6 IPS
 
Object Detection (I8)
53% 241
8.45 IPS
 
Face Detection (F32)
25% 492
5.66 IPS
 
Face Detection (F16)
25% 695
7.98 IPS
 
Face Detection (I8)
75% 462
5.31 IPS
 
Text Classification (F32)
100% 135
53.5 IPS
 
Text Classification (F16)
100% 119
47.1 IPS
 
Machine Translation (F32)
100% 177
27.3 IPS
 
Machine Translation (F16)
100% 181
27.8 IPS
 

Compare

Set Baseline Geekbench 6 now available