Geekbench ML Score

180
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 09 2025 08:16 PM
Views 5

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% 90
9.67 IPS
 
Image Classification (F16)
100% 128
13.7 IPS
 
Image Classification (I8)
81% 198
21.2 IPS
 
Image Segmentation (F32)
100% 219
1.35 IPS
 
Image Segmentation (F16)
100% 219
1.36 IPS
 
Image Segmentation (I8)
89% 366
2.26 IPS
 
Pose Estimation (F32)
100% 78
0.32 IPS
 
Pose Estimation (F16)
100% 78
0.31 IPS
 
Pose Estimation (I8)
80% 59
0.24 IPS
 
Object Detection (F32)
100% 116
4.07 IPS
 
Object Detection (F16)
100% 117
4.12 IPS
 
Object Detection (I8)
52% 237
8.32 IPS
 
Face Detection (F32)
100% 181
2.08 IPS
 
Face Detection (F16)
100% 185
2.13 IPS
 
Face Detection (I8)
75% 291
3.34 IPS
 
Text Classification (F32)
100% 439
173.6 IPS
 
Text Classification (F16)
100% 443
175.4 IPS
 
Machine Translation (F32)
100% 283
43.6 IPS
 
Machine Translation (F16)
100% 286
44.1 IPS
 

Compare

Set Baseline Geekbench 6 now available