Geekbench AI Score

206
Single Precision Score
213
Half Precision Score
278
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 08 2024 09:40 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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 18 Cores @ 1.82 GHz
Memory Information
Size 5.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 61
11.4 IPS
 
Image Classification (HP)
100% 84
15.6 IPS
 
Image Classification (Q)
100% 153
28.4 IPS
 
Image Segmentation (SP)
100% 142
2.30 IPS
 
Image Segmentation (HP)
100% 137
2.21 IPS
 
Image Segmentation (Q)
98% 287
4.66 IPS
 
Pose Estimation (SP)
100% 591
0.69 IPS
 
Pose Estimation (HP)
100% 678
0.79 IPS
 
Pose Estimation (Q)
84% 918
1.09 IPS
 
Object Detection (SP)
100% 94
7.48 IPS
 
Object Detection (HP)
100% 96
7.61 IPS
 
Object Detection (Q)
83% 154
12.4 IPS
 
Face Detection (SP)
100% 261
3.10 IPS
 
Face Detection (HP)
100% 273
3.24 IPS
 
Face Detection (Q)
95% 512
6.11 IPS
 
Depth Estimation (SP)
100% 300
2.31 IPS
 
Depth Estimation (HP)
99% 342
2.63 IPS
 
Depth Estimation (Q)
64% 719
6.59 IPS
 
Style Transfer (SP)
89% 1295
1.68 IPS
 
Style Transfer (HP)
89% 1292
1.68 IPS
 
Style Transfer (Q)
98% 1332
1.72 IPS
 
Image Super-Resolution (SP)
100% 204
7.55 IPS
 
Image Super-Resolution (HP)
100% 182
6.72 IPS
 
Image Super-Resolution (Q)
97% 251
9.31 IPS
 
Text Classification (SP)
100% 117
156.6 IPS
 
Text Classification (HP)
100% 84
112.4 IPS
 
Text Classification (Q)
88% 72
97.7 IPS
 
Machine Translation (SP)
100% 122
2.11 IPS
 
Machine Translation (HP)
100% 143
2.47 IPS
 
Machine Translation (Q)
50% 51
1.82 IPS
 

Compare

Set Baseline Geekbench 6 now available