Geekbench AI Score

88
Single Precision Score
88
Half Precision Score
150
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 08 2024 10:27 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 15
Model UNISOC ums9230_6h10_Natv
Model IDUNISOC ums9230_6h10_Natv
Motherboard ums9230_6h10
Governoruscfreq
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.82 GHz
Cluster 16 Cores @ 1.82 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 5.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 49
9.16 IPS
 
Image Classification (HP)
100% 50
9.37 IPS
 
Image Classification (Q)
99% 91
17.0 IPS
 
Image Segmentation (SP)
100% 69
1.13 IPS
 
Image Segmentation (HP)
100% 70
1.13 IPS
 
Image Segmentation (Q)
98% 122
1.98 IPS
 
Pose Estimation (SP)
100% 96
0.11 IPS
 
Pose Estimation (HP)
100% 94
0.11 IPS
 
Pose Estimation (Q)
98% 219
0.26 IPS
 
Object Detection (SP)
100% 51
4.05 IPS
 
Object Detection (HP)
100% 51
4.08 IPS
 
Object Detection (Q)
87% 91
7.31 IPS
 
Face Detection (SP)
100% 133
1.57 IPS
 
Face Detection (HP)
100% 134
1.59 IPS
 
Face Detection (Q)
97% 266
3.17 IPS
 
Depth Estimation (SP)
100% 116
0.90 IPS
 
Depth Estimation (HP)
99% 117
0.90 IPS
 
Depth Estimation (Q)
64% 193
1.75 IPS
 
Style Transfer (SP)
100% 225
0.29 IPS
 
Style Transfer (HP)
100% 224
0.29 IPS
 
Style Transfer (Q)
98% 472
0.61 IPS
 
Image Super-Resolution (SP)
100% 58
2.16 IPS
 
Image Super-Resolution (HP)
100% 58
2.16 IPS
 
Image Super-Resolution (Q)
97% 132
4.89 IPS
 
Text Classification (SP)
100% 73
97.1 IPS
 
Text Classification (HP)
100% 72
96.5 IPS
 
Text Classification (Q)
91% 114
153.1 IPS
 
Machine Translation (SP)
100% 124
2.13 IPS
 
Machine Translation (HP)
100% 125
2.15 IPS
 
Machine Translation (Q)
57% 72
1.75 IPS
 

Compare

Set Baseline Geekbench 6 now available