Geekbench AI Score

219
Single Precision Score
233
Half Precision Score
247
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User shimonocyou
Upload Date October 20 2024 08:26 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% 106
19.8 IPS
 
Image Classification (HP)
100% 117
21.7 IPS
 
Image Classification (Q)
100% 167
31.1 IPS
 
Image Segmentation (SP)
100% 144
2.33 IPS
 
Image Segmentation (HP)
100% 142
2.30 IPS
 
Image Segmentation (Q)
98% 252
4.10 IPS
 
Pose Estimation (SP)
100% 451
0.53 IPS
 
Pose Estimation (HP)
100% 548
0.64 IPS
 
Pose Estimation (Q)
84% 431
0.51 IPS
 
Object Detection (SP)
100% 115
9.13 IPS
 
Object Detection (HP)
100% 122
9.67 IPS
 
Object Detection (Q)
83% 179
14.5 IPS
 
Face Detection (SP)
100% 309
3.67 IPS
 
Face Detection (HP)
100% 307
3.65 IPS
 
Face Detection (Q)
95% 497
5.94 IPS
 
Depth Estimation (SP)
100% 352
2.71 IPS
 
Depth Estimation (HP)
99% 401
3.09 IPS
 
Depth Estimation (Q)
64% 377
3.46 IPS
 
Style Transfer (SP)
89% 1083
1.41 IPS
 
Style Transfer (HP)
89% 987
1.28 IPS
 
Style Transfer (Q)
98% 938
1.21 IPS
 
Image Super-Resolution (SP)
100% 180
6.64 IPS
 
Image Super-Resolution (HP)
100% 178
6.56 IPS
 
Image Super-Resolution (Q)
97% 222
8.24 IPS
 
Text Classification (SP)
100% 106
141.3 IPS
 
Text Classification (HP)
100% 132
176.2 IPS
 
Text Classification (Q)
88% 108
145.9 IPS
 
Machine Translation (SP)
100% 147
2.53 IPS
 
Machine Translation (HP)
100% 149
2.56 IPS
 
Machine Translation (Q)
50% 64
2.26 IPS
 

Compare

Set Baseline Geekbench 6 now available