Geekbench AI Score

233
Single Precision Score
233
Half Precision Score
437
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 20 2024 08:34 PM
Views 444

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model Vortex J24
Model IDVortex J24
Motherboard s9863a1h10
Governoruscfreq
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3333 revision 0
Base Frequency 1.20 GHz
Cluster 14 Cores @ 1.20 GHz
Cluster 24 Cores @ 1.60 GHz
Memory Information
Size 2.76 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 113
21.0 IPS
 
Image Classification (HP)
100% 110
20.4 IPS
 
Image Classification (Q)
100% 317
59.0 IPS
 
Image Segmentation (SP)
100% 167
2.71 IPS
 
Image Segmentation (HP)
100% 153
2.47 IPS
 
Image Segmentation (Q)
98% 476
7.74 IPS
 
Pose Estimation (SP)
100% 517
0.60 IPS
 
Pose Estimation (HP)
100% 522
0.61 IPS
 
Pose Estimation (Q)
84% 865
1.03 IPS
 
Object Detection (SP)
100% 106
8.44 IPS
 
Object Detection (HP)
100% 110
8.70 IPS
 
Object Detection (Q)
83% 301
24.3 IPS
 
Face Detection (SP)
100% 322
3.82 IPS
 
Face Detection (HP)
100% 322
3.83 IPS
 
Face Detection (Q)
95% 816
9.74 IPS
 
Depth Estimation (SP)
100% 394
3.03 IPS
 
Depth Estimation (HP)
99% 410
3.16 IPS
 
Depth Estimation (Q)
64% 764
6.99 IPS
 
Style Transfer (SP)
89% 1034
1.34 IPS
 
Style Transfer (HP)
89% 1075
1.40 IPS
 
Style Transfer (Q)
98% 1997
2.58 IPS
 
Image Super-Resolution (SP)
100% 192
7.10 IPS
 
Image Super-Resolution (HP)
100% 188
6.93 IPS
 
Image Super-Resolution (Q)
97% 463
17.2 IPS
 
Text Classification (SP)
100% 111
148.5 IPS
 
Text Classification (HP)
100% 107
143.5 IPS
 
Text Classification (Q)
88% 134
180.7 IPS
 
Machine Translation (SP)
100% 170
2.92 IPS
 
Machine Translation (HP)
100% 171
2.95 IPS
 
Machine Translation (Q)
50% 85
3.01 IPS
 

Compare

Set Baseline Geekbench 6 now available