Geekbench AI Score

71
Single Precision Score
71
Half Precision Score
89
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date October 27 2024 02:34 PM
Views 14

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM Rockchip
System Information
Operating System Android 12
Model Blackview Tab 7 WiFi
Model IDBlackview Tab 7 WiFi
Motherboard rk30sdk
Governorinteractive
CPU Information
Name ARM Rockchip
Topology 1 Processor, 4 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3332 revision 2
Base Frequency 1.51 GHz
Cluster 14 Cores @ 1.51 GHz
Memory Information
Size 2.89 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 28
5.16 IPS
 
Image Classification (HP)
100% 29
5.40 IPS
 
Image Classification (Q)
100% 55
10.2 IPS
 
Image Segmentation (SP)
100% 40
0.64 IPS
 
Image Segmentation (HP)
100% 39
0.64 IPS
 
Image Segmentation (Q)
98% 78
1.27 IPS
 
Pose Estimation (SP)
100% 146
0.17 IPS
 
Pose Estimation (HP)
100% 147
0.17 IPS
 
Pose Estimation (Q)
84% 120
0.14 IPS
 
Object Detection (SP)
100% 31
2.43 IPS
 
Object Detection (HP)
100% 31
2.42 IPS
 
Object Detection (Q)
83% 57
4.63 IPS
 
Face Detection (SP)
100% 104
1.24 IPS
 
Face Detection (HP)
100% 105
1.25 IPS
 
Face Detection (Q)
95% 172
2.05 IPS
 
Depth Estimation (SP)
100% 144
1.11 IPS
 
Depth Estimation (HP)
99% 145
1.12 IPS
 
Depth Estimation (Q)
64% 130
1.19 IPS
 
Style Transfer (SP)
89% 262
0.34 IPS
 
Style Transfer (HP)
89% 262
0.34 IPS
 
Style Transfer (Q)
98% 311
0.40 IPS
 
Image Super-Resolution (SP)
100% 72
2.66 IPS
 
Image Super-Resolution (HP)
100% 72
2.66 IPS
 
Image Super-Resolution (Q)
97% 72
2.68 IPS
 
Text Classification (SP)
100% 38
50.3 IPS
 
Text Classification (HP)
100% 37
49.8 IPS
 
Text Classification (Q)
88% 59
79.5 IPS
 
Machine Translation (SP)
100% 63
1.09 IPS
 
Machine Translation (HP)
100% 63
1.09 IPS
 
Machine Translation (Q)
50% 39
1.40 IPS
 

Compare

Set Baseline Geekbench 6 now available