Geekbench ML Score

208
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 21 2025 07:04 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% 118
12.7 IPS
 
Image Classification (F16)
100% 118
12.6 IPS
 
Image Classification (I8)
81% 198
21.2 IPS
 
Image Segmentation (F32)
100% 306
1.89 IPS
 
Image Segmentation (F16)
100% 312
1.93 IPS
 
Image Segmentation (I8)
89% 377
2.33 IPS
 
Pose Estimation (F32)
100% 102
0.41 IPS
 
Pose Estimation (F16)
100% 98
0.40 IPS
 
Pose Estimation (I8)
80% 60
0.24 IPS
 
Object Detection (F32)
100% 159
5.58 IPS
 
Object Detection (F16)
100% 167
5.86 IPS
 
Object Detection (I8)
52% 245
8.59 IPS
 
Face Detection (F32)
100% 225
2.59 IPS
 
Face Detection (F16)
100% 238
2.73 IPS
 
Face Detection (I8)
75% 295
3.39 IPS
 
Text Classification (F32)
100% 467
184.6 IPS
 
Text Classification (F16)
100% 469
185.5 IPS
 
Machine Translation (F32)
100% 297
45.8 IPS
 
Machine Translation (F16)
100% 288
44.4 IPS
 

Compare

Set Baseline Geekbench 6 now available