Geekbench AI Score

188
Single Precision Score
280
Half Precision Score
287
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User shimonocyou
Upload Date September 18 2024 09:52 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model Sony SO-52D
Model IDSony SO-52D
Motherboard holi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 5.35 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 109
20.4 IPS
 
Image Classification (HP)
100% 182
33.8 IPS
 
Image Classification (Q)
97% 186
34.7 IPS
 
Image Segmentation (SP)
100% 127
2.06 IPS
 
Image Segmentation (HP)
100% 188
3.05 IPS
 
Image Segmentation (Q)
98% 180
2.93 IPS
 
Pose Estimation (SP)
100% 219
0.26 IPS
 
Pose Estimation (HP)
100% 296
0.35 IPS
 
Pose Estimation (Q)
95% 294
0.34 IPS
 
Object Detection (SP)
100% 95
7.50 IPS
 
Object Detection (HP)
100% 140
11.1 IPS
 
Object Detection (Q)
89% 150
12.0 IPS
 
Face Detection (SP)
100% 256
3.04 IPS
 
Face Detection (HP)
100% 456
5.42 IPS
 
Face Detection (Q)
97% 465
5.54 IPS
 
Depth Estimation (SP)
100% 256
1.98 IPS
 
Depth Estimation (HP)
99% 440
3.40 IPS
 
Depth Estimation (Q)
62% 363
3.44 IPS
 
Style Transfer (SP)
100% 506
0.65 IPS
 
Style Transfer (HP)
100% 1096
1.41 IPS
 
Style Transfer (Q)
98% 1089
1.40 IPS
 
Image Super-Resolution (SP)
100% 129
4.76 IPS
 
Image Super-Resolution (HP)
100% 216
7.98 IPS
 
Image Super-Resolution (Q)
97% 212
7.87 IPS
 
Text Classification (SP)
100% 164
218.9 IPS
 
Text Classification (HP)
100% 162
216.5 IPS
 
Text Classification (Q)
91% 312
419.4 IPS
 
Machine Translation (SP)
100% 280
4.82 IPS
 
Machine Translation (HP)
100% 280
4.82 IPS
 
Machine Translation (Q)
57% 215
5.26 IPS
 

Compare

Set Baseline Geekbench 6 now available