Geekbench AI Score

1341
Single Precision Score
1386
Half Precision Score
1879
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 08:11 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR ELP-NX9
Model IDHONOR ELP-NX9
Motherboard ELP
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.01 GHz
Memory Information
Size 11.04 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1482
275.6 IPS
 
Image Classification (HP)
100% 615
114.3 IPS
 
Image Classification (Q)
100% 1009
187.7 IPS
 
Image Segmentation (SP)
100% 1521
24.7 IPS
 
Image Segmentation (HP)
100% 1628
26.4 IPS
 
Image Segmentation (Q)
98% 2552
41.5 IPS
 
Pose Estimation (SP)
100% 2914
3.40 IPS
 
Pose Estimation (HP)
100% 2825
3.30 IPS
 
Pose Estimation (Q)
84% 6321
7.50 IPS
 
Object Detection (SP)
98% 583
46.4 IPS
 
Object Detection (HP)
98% 621
49.4 IPS
 
Object Detection (Q)
83% 1083
87.4 IPS
 
Face Detection (SP)
100% 1173
13.9 IPS
 
Face Detection (HP)
100% 1170
13.9 IPS
 
Face Detection (Q)
95% 2200
26.3 IPS
 
Depth Estimation (SP)
99% 3054
23.6 IPS
 
Depth Estimation (HP)
99% 1405
10.9 IPS
 
Depth Estimation (Q)
64% 2407
22.0 IPS
 
Style Transfer (SP)
89% 7202
9.35 IPS
 
Style Transfer (HP)
89% 7170
9.31 IPS
 
Style Transfer (Q)
98% 13682
17.6 IPS
 
Image Super-Resolution (SP)
100% 729
26.9 IPS
 
Image Super-Resolution (HP)
100% 1485
54.8 IPS
 
Image Super-Resolution (Q)
97% 1416
52.5 IPS
 
Text Classification (SP)
100% 368
490.9 IPS
 
Text Classification (HP)
99% 651
868.4 IPS
 
Text Classification (Q)
88% 529
712.8 IPS
 
Machine Translation (SP)
100% 712
12.3 IPS
 
Machine Translation (HP)
100% 1314
22.6 IPS
 
Machine Translation (Q)
50% 576
20.5 IPS
 

Compare

Set Baseline Geekbench 6 now available