Geekbench AI Score

17
Single Precision Score
35
Half Precision Score
20
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 05:23 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6765V/CB
System Information
Operating System Android 13
Model samsung SM-A037U
Model IDsamsung SM-A037U
Motherboard a03su
CPU Information
Name ARM MT6765V/CB
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.30 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.30 GHz
Memory Information
Size 2.72 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 24
4.38 IPS
 
Image Classification (HP)
100% 34
6.38 IPS
 
Image Classification (Q)
99% 34
6.30 IPS
 
Image Segmentation (SP)
100% 35
0.57 IPS
 
Image Segmentation (HP)
100% 44
0.72 IPS
 
Image Segmentation (Q)
98% 44
0.71 IPS
 
Pose Estimation (SP)
0
 
Pose Estimation (HP)
0
 
Pose Estimation (Q)
0
 
Object Detection (SP)
100% 18
1.39 IPS
 
Object Detection (HP)
100% 26
2.03 IPS
 
Object Detection (Q)
85% 25
1.98 IPS
 
Face Detection (SP)
100% 72
0.85 IPS
 
Face Detection (HP)
100% 97
1.15 IPS
 
Face Detection (Q)
97% 90
1.08 IPS
 
Depth Estimation (SP)
100% 47
0.36 IPS
 
Depth Estimation (HP)
99% 74
0.57 IPS
 
Depth Estimation (Q)
63% 59
0.55 IPS
 
Style Transfer (SP)
0
 
Style Transfer (HP)
100% 161
0.21 IPS
 
Style Transfer (Q)
0
 
Image Super-Resolution (SP)
100% 21
0.77 IPS
 
Image Super-Resolution (HP)
100% 35
1.29 IPS
 
Image Super-Resolution (Q)
97% 32
1.20 IPS
 
Text Classification (SP)
100% 34
45.7 IPS
 
Text Classification (HP)
100% 34
45.9 IPS
 
Text Classification (Q)
91% 50
67.4 IPS
 
Machine Translation (SP)
100% 59
1.01 IPS
 
Machine Translation (HP)
100% 59
1.02 IPS
 
Machine Translation (Q)
57% 50
1.22 IPS
 

Compare

Set Baseline Geekbench 6 now available