Geekbench AI Score

199
Single Precision Score
201
Half Precision Score
219
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User shimonocyou
Upload Date September 18 2024 08:07 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6765V/WA
System Information
Operating System Android 13
Model Sony SO-41B
Model IDSony SO-41B
Motherboard huaihe212
CPU Information
Name ARM MT6765V/WA
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 3.71 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 67
12.5 IPS
 
Image Classification (HP)
100% 82
15.3 IPS
 
Image Classification (Q)
100% 151
28.0 IPS
 
Image Segmentation (SP)
100% 136
2.20 IPS
 
Image Segmentation (HP)
100% 132
2.14 IPS
 
Image Segmentation (Q)
98% 257
4.17 IPS
 
Pose Estimation (SP)
100% 510
0.59 IPS
 
Pose Estimation (HP)
100% 514
0.60 IPS
 
Pose Estimation (Q)
84% 383
0.45 IPS
 
Object Detection (SP)
100% 104
8.23 IPS
 
Object Detection (HP)
100% 96
7.58 IPS
 
Object Detection (Q)
83% 149
12.0 IPS
 
Face Detection (SP)
100% 262
3.12 IPS
 
Face Detection (HP)
100% 263
3.12 IPS
 
Face Detection (Q)
95% 441
5.27 IPS
 
Depth Estimation (SP)
100% 334
2.57 IPS
 
Depth Estimation (HP)
99% 319
2.46 IPS
 
Depth Estimation (Q)
64% 362
3.32 IPS
 
Style Transfer (SP)
89% 998
1.30 IPS
 
Style Transfer (HP)
89% 1004
1.30 IPS
 
Style Transfer (Q)
98% 951
1.23 IPS
 
Image Super-Resolution (SP)
100% 161
5.94 IPS
 
Image Super-Resolution (HP)
100% 168
6.19 IPS
 
Image Super-Resolution (Q)
97% 212
7.85 IPS
 
Text Classification (SP)
100% 120
159.7 IPS
 
Text Classification (HP)
100% 108
144.4 IPS
 
Text Classification (Q)
88% 62
83.4 IPS
 
Machine Translation (SP)
100% 124
2.14 IPS
 
Machine Translation (HP)
100% 138
2.38 IPS
 
Machine Translation (Q)
50% 59
2.08 IPS
 

Compare

Set Baseline Geekbench 6 now available