Geekbench ML Score

171
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 21 2025 05:19 PM
Views 1

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% 91
9.78 IPS
 
Image Classification (F16)
100% 90
9.61 IPS
 
Image Classification (I8)
81% 190
20.4 IPS
 
Image Segmentation (F32)
100% 209
1.29 IPS
 
Image Segmentation (F16)
100% 197
1.22 IPS
 
Image Segmentation (I8)
89% 353
2.18 IPS
 
Pose Estimation (F32)
100% 83
0.34 IPS
 
Pose Estimation (F16)
100% 82
0.33 IPS
 
Pose Estimation (I8)
80% 58
0.23 IPS
 
Object Detection (F32)
100% 104
3.67 IPS
 
Object Detection (F16)
100% 115
4.03 IPS
 
Object Detection (I8)
52% 229
8.04 IPS
 
Face Detection (F32)
100% 164
1.89 IPS
 
Face Detection (F16)
100% 168
1.93 IPS
 
Face Detection (I8)
75% 280
3.21 IPS
 
Text Classification (F32)
100% 450
177.8 IPS
 
Text Classification (F16)
100% 442
174.6 IPS
 
Machine Translation (F32)
100% 281
43.2 IPS
 
Machine Translation (F16)
100% 275
42.4 IPS
 

Compare

Set Baseline Geekbench 6 now available