Geekbench AI Score

166
Single Precision Score
165
Half Precision Score
190
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 02 2025 07:27 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model Allwinner A537 PRO
Model IDAllwinner A537 PRO
Motherboard exdroid
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3337 revision 0
Base Frequency 1.42 GHz
Cluster 14 Cores @ 1.42 GHz
Cluster 22 Cores @ 1.51 GHz
Cluster 32 Cores @ 1.80 GHz
Memory Information
Size 5.62 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 101
18.7 IPS
 
Image Classification (HP)
100% 104
19.3 IPS
 
Image Classification (Q)
100% 181
33.7 IPS
 
Image Segmentation (SP)
100% 128
2.08 IPS
 
Image Segmentation (HP)
100% 122
1.98 IPS
 
Image Segmentation (Q)
98% 214
3.49 IPS
 
Pose Estimation (SP)
100% 359
0.42 IPS
 
Pose Estimation (HP)
100% 331
0.39 IPS
 
Pose Estimation (Q)
84% 255
0.30 IPS
 
Object Detection (SP)
100% 79
6.27 IPS
 
Object Detection (HP)
100% 76
6.04 IPS
 
Object Detection (Q)
83% 125
10.1 IPS
 
Face Detection (SP)
100% 204
2.43 IPS
 
Face Detection (HP)
100% 201
2.39 IPS
 
Face Detection (Q)
95% 306
3.66 IPS
 
Depth Estimation (SP)
100% 192
1.48 IPS
 
Depth Estimation (HP)
99% 197
1.52 IPS
 
Depth Estimation (Q)
64% 259
2.38 IPS
 
Style Transfer (SP)
89% 638
0.83 IPS
 
Style Transfer (HP)
89% 658
0.85 IPS
 
Style Transfer (Q)
98% 693
0.89 IPS
 
Image Super-Resolution (SP)
100% 141
5.20 IPS
 
Image Super-Resolution (HP)
100% 143
5.30 IPS
 
Image Super-Resolution (Q)
97% 163
6.04 IPS
 
Text Classification (SP)
100% 100
133.0 IPS
 
Text Classification (HP)
100% 102
136.1 IPS
 
Text Classification (Q)
88% 102
138.1 IPS
 
Machine Translation (SP)
100% 130
2.24 IPS
 
Machine Translation (HP)
100% 128
2.20 IPS
 
Machine Translation (Q)
50% 56
1.98 IPS
 

Compare

Set Baseline Geekbench 6 now available