Geekbench ML Score

166
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 19 2025 04:29 PM
Views 3

System Information

System Information
Operating System Android 15
Model samsung SM-X216B
Model IDsamsung SM-X216B
Motherboard holi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 3.29 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 82
8.80 IPS
 
Image Classification (F16)
100% 79
8.51 IPS
 
Image Classification (I8)
81% 189
20.3 IPS
 
Image Segmentation (F32)
100% 180
1.11 IPS
 
Image Segmentation (F16)
100% 200
1.24 IPS
 
Image Segmentation (I8)
89% 352
2.18 IPS
 
Pose Estimation (F32)
100% 76
0.31 IPS
 
Pose Estimation (F16)
100% 78
0.31 IPS
 
Pose Estimation (I8)
80% 60
0.24 IPS
 
Object Detection (F32)
100% 107
3.75 IPS
 
Object Detection (F16)
100% 107
3.76 IPS
 
Object Detection (I8)
52% 234
8.21 IPS
 
Face Detection (F32)
100% 154
1.77 IPS
 
Face Detection (F16)
100% 166
1.91 IPS
 
Face Detection (I8)
75% 281
3.22 IPS
 
Text Classification (F32)
100% 444
175.6 IPS
 
Text Classification (F16)
100% 428
169.4 IPS
 
Machine Translation (F32)
100% 281
43.3 IPS
 
Machine Translation (F16)
100% 286
44.1 IPS
 

Compare

Set Baseline Geekbench 6 now available