Geekbench AI Score

126
Single Precision Score
123
Half Precision Score
149
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 16 2024 11:40 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model incar M10_R02
Model IDincar M10_R02
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% 61
11.3 IPS
 
Image Classification (HP)
100% 59
10.9 IPS
 
Image Classification (Q)
100% 96
17.8 IPS
 
Image Segmentation (SP)
100% 86
1.39 IPS
 
Image Segmentation (HP)
100% 87
1.41 IPS
 
Image Segmentation (Q)
98% 143
2.33 IPS
 
Pose Estimation (SP)
100% 300
0.35 IPS
 
Pose Estimation (HP)
100% 294
0.34 IPS
 
Pose Estimation (Q)
84% 232
0.27 IPS
 
Object Detection (SP)
100% 64
5.11 IPS
 
Object Detection (HP)
100% 63
5.00 IPS
 
Object Detection (Q)
83% 99
8.03 IPS
 
Face Detection (SP)
100% 153
1.82 IPS
 
Face Detection (HP)
100% 149
1.77 IPS
 
Face Detection (Q)
95% 258
3.08 IPS
 
Depth Estimation (SP)
100% 197
1.52 IPS
 
Depth Estimation (HP)
99% 182
1.41 IPS
 
Depth Estimation (Q)
64% 221
2.03 IPS
 
Style Transfer (SP)
89% 528
0.69 IPS
 
Style Transfer (HP)
89% 529
0.69 IPS
 
Style Transfer (Q)
98% 569
0.73 IPS
 
Image Super-Resolution (SP)
100% 98
3.60 IPS
 
Image Super-Resolution (HP)
100% 99
3.65 IPS
 
Image Super-Resolution (Q)
97% 134
4.95 IPS
 
Text Classification (SP)
100% 65
86.9 IPS
 
Text Classification (HP)
100% 59
78.9 IPS
 
Text Classification (Q)
88% 76
102.7 IPS
 
Machine Translation (SP)
100% 99
1.70 IPS
 
Machine Translation (HP)
100% 104
1.80 IPS
 
Machine Translation (Q)
50% 52
1.85 IPS
 

Compare

Set Baseline Geekbench 6 now available