Geekbench AI Score

163
Single Precision Score
155
Half Precision Score
187
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User kvnsalters
Upload Date November 07 2024 03:22 PM
Views 12

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model TINNO U572AA
Model IDTINNO U572AA
Motherboard ATT
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.20 GHz
Cluster 14 Cores @ 1.60 GHz
Cluster 24 Cores @ 2.20 GHz
Memory Information
Size 3.67 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 79
14.7 IPS
 
Image Classification (HP)
100% 87
16.1 IPS
 
Image Classification (Q)
100% 140
26.0 IPS
 
Image Segmentation (SP)
100% 133
2.16 IPS
 
Image Segmentation (HP)
100% 111
1.80 IPS
 
Image Segmentation (Q)
98% 185
3.01 IPS
 
Pose Estimation (SP)
100% 412
0.48 IPS
 
Pose Estimation (HP)
100% 281
0.33 IPS
 
Pose Estimation (Q)
84% 400
0.47 IPS
 
Object Detection (SP)
100% 78
6.15 IPS
 
Object Detection (HP)
100% 78
6.20 IPS
 
Object Detection (Q)
83% 110
8.89 IPS
 
Face Detection (SP)
100% 204
2.43 IPS
 
Face Detection (HP)
100% 189
2.24 IPS
 
Face Detection (Q)
95% 355
4.24 IPS
 
Depth Estimation (SP)
100% 251
1.93 IPS
 
Depth Estimation (HP)
99% 283
2.18 IPS
 
Depth Estimation (Q)
64% 311
2.85 IPS
 
Style Transfer (SP)
89% 911
1.18 IPS
 
Style Transfer (HP)
89% 946
1.23 IPS
 
Style Transfer (Q)
98% 941
1.21 IPS
 
Image Super-Resolution (SP)
100% 116
4.27 IPS
 
Image Super-Resolution (HP)
100% 119
4.38 IPS
 
Image Super-Resolution (Q)
97% 175
6.47 IPS
 
Text Classification (SP)
100% 68
90.7 IPS
 
Text Classification (HP)
100% 63
84.4 IPS
 
Text Classification (Q)
88% 72
96.5 IPS
 
Machine Translation (SP)
100% 107
1.85 IPS
 
Machine Translation (HP)
100% 102
1.76 IPS
 
Machine Translation (Q)
50% 36
1.29 IPS
 

Compare

Set Baseline Geekbench 6 now available