Geekbench ML Score

1002
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:07 AM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-M536B
Model IDsamsung SM-M536B
Motherboard m53x
CPU Information
Name ARM MT6877V/ZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 7.36 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 344
36.8 IPS
 
Image Classification (F16)
100% 2075
222.3 IPS
 
Image Classification (I8)
79% 4633
496.4 IPS
 
Image Segmentation (F32)
100% 543
3.35 IPS
 
Image Segmentation (F16)
100% 939
5.80 IPS
 
Image Segmentation (I8)
89% 10571
65.3 IPS
 
Pose Estimation (F32)
100% 370
1.50 IPS
 
Pose Estimation (F16)
100% 1241
5.02 IPS
 
Pose Estimation (I8)
80% 3157
12.8 IPS
 
Object Detection (F32)
100% 397
13.9 IPS
 
Object Detection (F16)
100% 931
32.7 IPS
 
Object Detection (I8)
53% 1122
39.4 IPS
 
Face Detection (F32)
25% 756
8.69 IPS
 
Face Detection (F16)
97% 2571
29.5 IPS
 
Face Detection (I8)
75% 7306
83.9 IPS
 
Text Classification (F32)
100% 249
98.7 IPS
 
Text Classification (F16)
100% 541
214.1 IPS
 
Machine Translation (F32)
100% 232
35.7 IPS
 
Machine Translation (F16)
100% 221
34.1 IPS
 

Compare

Set Baseline