Geekbench ML Score

167
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 26 2025 02:43 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% 85
9.06 IPS
 
Image Classification (F16)
100% 83
8.88 IPS
 
Image Classification (I8)
81% 193
20.6 IPS
 
Image Segmentation (F32)
100% 183
1.13 IPS
 
Image Segmentation (F16)
100% 192
1.19 IPS
 
Image Segmentation (I8)
89% 354
2.19 IPS
 
Pose Estimation (F32)
100% 80
0.32 IPS
 
Pose Estimation (F16)
100% 80
0.33 IPS
 
Pose Estimation (I8)
80% 58
0.24 IPS
 
Object Detection (F32)
100% 104
3.65 IPS
 
Object Detection (F16)
100% 108
3.79 IPS
 
Object Detection (I8)
52% 233
8.19 IPS
 
Face Detection (F32)
100% 153
1.76 IPS
 
Face Detection (F16)
100% 166
1.91 IPS
 
Face Detection (I8)
75% 278
3.19 IPS
 
Text Classification (F32)
100% 443
175.1 IPS
 
Text Classification (F16)
100% 447
176.8 IPS
 
Machine Translation (F32)
100% 282
43.5 IPS
 
Machine Translation (F16)
100% 284
43.7 IPS
 

Compare

Set Baseline Geekbench 6 now available