Geekbench AI Score

92
Single Precision Score
131
Half Precision Score
125
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date October 08 2024 07:24 PM
Views 19

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT8786V/N
System Information
Operating System Android 14
Model walmart 100135794
Model IDwalmart 100135794
Motherboard tb8786p1_64_k419
CPU Information
Name ARM MT8786V/N
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.00 GHz
Memory Information
Size 2.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 68
12.7 IPS
 
Image Classification (HP)
100% 108
20.1 IPS
 
Image Classification (Q)
99% 102
19.0 IPS
 
Image Segmentation (SP)
100% 86
1.40 IPS
 
Image Segmentation (HP)
100% 137
2.22 IPS
 
Image Segmentation (Q)
98% 127
2.07 IPS
 
Pose Estimation (SP)
100% 53
0.06 IPS
 
Pose Estimation (HP)
100% 77
0.09 IPS
 
Pose Estimation (Q)
96% 77
0.09 IPS
 
Object Detection (SP)
100% 54
4.25 IPS
 
Object Detection (HP)
100% 89
7.04 IPS
 
Object Detection (Q)
83% 85
6.92 IPS
 
Face Detection (SP)
100% 208
2.47 IPS
 
Face Detection (HP)
100% 312
3.71 IPS
 
Face Detection (Q)
97% 286
3.41 IPS
 
Depth Estimation (SP)
100% 111
0.86 IPS
 
Depth Estimation (HP)
99% 172
1.32 IPS
 
Depth Estimation (Q)
62% 130
1.23 IPS
 
Style Transfer (SP)
100% 221
0.28 IPS
 
Style Transfer (HP)
100% 355
0.46 IPS
 
Style Transfer (Q)
98% 351
0.45 IPS
 
Image Super-Resolution (SP)
100% 63
2.33 IPS
 
Image Super-Resolution (HP)
100% 96
3.55 IPS
 
Image Super-Resolution (Q)
97% 95
3.54 IPS
 
Text Classification (SP)
100% 69
92.3 IPS
 
Text Classification (HP)
100% 69
92.1 IPS
 
Text Classification (Q)
91% 102
137.5 IPS
 
Machine Translation (SP)
100% 120
2.07 IPS
 
Machine Translation (HP)
100% 120
2.08 IPS
 
Machine Translation (Q)
57% 87
2.13 IPS
 

Compare

Set Baseline Geekbench 6 now available