Geekbench AI Score

169
Single Precision Score
167
Half Precision Score
187
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 24 2025 06:20 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model incar K12E
Model IDincar K12E
Motherboard rk30sdk
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 4 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.02 GHz
Cluster 14 Cores @ 2.02 GHz
Memory Information
Size 2.87 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 85
15.9 IPS
 
Image Classification (HP)
100% 87
16.2 IPS
 
Image Classification (Q)
100% 132
24.6 IPS
 
Image Segmentation (SP)
100% 115
1.87 IPS
 
Image Segmentation (HP)
100% 116
1.88 IPS
 
Image Segmentation (Q)
98% 185
3.02 IPS
 
Pose Estimation (SP)
100% 391
0.46 IPS
 
Pose Estimation (HP)
100% 392
0.46 IPS
 
Pose Estimation (Q)
84% 267
0.32 IPS
 
Object Detection (SP)
100% 84
6.68 IPS
 
Object Detection (HP)
100% 85
6.73 IPS
 
Object Detection (Q)
83% 125
10.1 IPS
 
Face Detection (SP)
100% 205
2.44 IPS
 
Face Detection (HP)
100% 190
2.26 IPS
 
Face Detection (Q)
95% 328
3.91 IPS
 
Depth Estimation (SP)
100% 278
2.14 IPS
 
Depth Estimation (HP)
99% 255
1.96 IPS
 
Depth Estimation (Q)
64% 260
2.39 IPS
 
Style Transfer (SP)
89% 633
0.82 IPS
 
Style Transfer (HP)
89% 636
0.83 IPS
 
Style Transfer (Q)
98% 635
0.82 IPS
 
Image Super-Resolution (SP)
100% 143
5.28 IPS
 
Image Super-Resolution (HP)
100% 141
5.22 IPS
 
Image Super-Resolution (Q)
97% 149
5.52 IPS
 
Text Classification (SP)
100% 88
118.0 IPS
 
Text Classification (HP)
100% 84
111.7 IPS
 
Text Classification (Q)
88% 112
151.7 IPS
 
Machine Translation (SP)
100% 136
2.34 IPS
 
Machine Translation (HP)
100% 140
2.41 IPS
 
Machine Translation (Q)
50% 72
2.55 IPS
 

Compare

Set Baseline Geekbench 6 now available