Geekbench AI Score

540
Single Precision Score
474
Half Precision Score
995
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 11 2024 12:02 AM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR ALI-NX3P
Model IDHONOR ALI-NX3P
Motherboard parrot
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 7.28 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 417
77.5 IPS
 
Image Classification (HP)
100% 405
75.3 IPS
 
Image Classification (Q)
100% 1342
249.6 IPS
 
Image Segmentation (SP)
100% 502
8.13 IPS
 
Image Segmentation (HP)
100% 499
8.09 IPS
 
Image Segmentation (Q)
98% 1551
25.2 IPS
 
Pose Estimation (SP)
100% 1947
2.27 IPS
 
Pose Estimation (HP)
100% 1913
2.23 IPS
 
Pose Estimation (Q)
84% 3482
4.13 IPS
 
Object Detection (SP)
100% 400
31.7 IPS
 
Object Detection (HP)
100% 377
29.9 IPS
 
Object Detection (Q)
83% 1120
90.5 IPS
 
Face Detection (SP)
100% 999
11.9 IPS
 
Face Detection (HP)
100% 1014
12.0 IPS
 
Face Detection (Q)
95% 2771
33.1 IPS
 
Depth Estimation (SP)
100% 1424
11.0 IPS
 
Depth Estimation (HP)
99% 451
3.47 IPS
 
Depth Estimation (Q)
64% 915
8.38 IPS
 
Style Transfer (SP)
89% 1046
1.36 IPS
 
Style Transfer (HP)
89% 1039
1.35 IPS
 
Style Transfer (Q)
98% 2288
2.95 IPS
 
Image Super-Resolution (SP)
100% 245
9.04 IPS
 
Image Super-Resolution (HP)
100% 241
8.91 IPS
 
Image Super-Resolution (Q)
97% 565
20.9 IPS
 
Text Classification (SP)
100% 143
190.6 IPS
 
Text Classification (HP)
100% 143
190.3 IPS
 
Text Classification (Q)
88% 229
309.3 IPS
 
Machine Translation (SP)
100% 249
4.28 IPS
 
Machine Translation (HP)
100% 244
4.20 IPS
 
Machine Translation (Q)
50% 157
5.57 IPS
 

Compare

Set Baseline Geekbench 6 now available