Geekbench AI Score

72
Single Precision Score
71
Half Precision Score
91
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date October 26 2024 05:47 PM
Views 13

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% 31
5.69 IPS
 
Image Classification (HP)
100% 31
5.69 IPS
 
Image Classification (Q)
100% 59
10.9 IPS
 
Image Segmentation (SP)
100% 43
0.70 IPS
 
Image Segmentation (HP)
100% 44
0.71 IPS
 
Image Segmentation (Q)
98% 84
1.36 IPS
 
Pose Estimation (SP)
100% 162
0.19 IPS
 
Pose Estimation (HP)
100% 158
0.18 IPS
 
Pose Estimation (Q)
84% 119
0.14 IPS
 
Object Detection (SP)
100% 31
2.43 IPS
 
Object Detection (HP)
100% 30
2.42 IPS
 
Object Detection (Q)
83% 58
4.70 IPS
 
Face Detection (SP)
100% 104
1.24 IPS
 
Face Detection (HP)
100% 104
1.24 IPS
 
Face Detection (Q)
95% 171
2.04 IPS
 
Depth Estimation (SP)
100% 144
1.11 IPS
 
Depth Estimation (HP)
99% 115
0.89 IPS
 
Depth Estimation (Q)
64% 131
1.20 IPS
 
Style Transfer (SP)
89% 262
0.34 IPS
 
Style Transfer (HP)
89% 261
0.34 IPS
 
Style Transfer (Q)
98% 310
0.40 IPS
 
Image Super-Resolution (SP)
100% 69
2.53 IPS
 
Image Super-Resolution (HP)
100% 72
2.66 IPS
 
Image Super-Resolution (Q)
97% 72
2.66 IPS
 
Text Classification (SP)
100% 37
49.9 IPS
 
Text Classification (HP)
100% 37
49.4 IPS
 
Text Classification (Q)
88% 59
79.3 IPS
 
Machine Translation (SP)
100% 63
1.09 IPS
 
Machine Translation (HP)
100% 63
1.08 IPS
 
Machine Translation (Q)
50% 40
1.43 IPS
 

Compare

Set Baseline Geekbench 6 now available