Geekbench AI Score

2341
Single Precision Score
2331
Half Precision Score
3332
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 12 2025 08:18 PM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model HONOR DNP-NX9
Model IDHONOR DNP-NX9
Motherboard DNP
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 2.04 GHz
Cluster 12 Cores @ 2.04 GHz
Cluster 25 Cores @ 2.96 GHz
Cluster 31 Core @ 3.05 GHz
Memory Information
Size 11.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2033
378.1 IPS
 
Image Classification (HP)
100% 2041
379.6 IPS
 
Image Classification (Q)
100% 2597
483.0 IPS
 
Image Segmentation (SP)
100% 2096
34.0 IPS
 
Image Segmentation (HP)
100% 2120
34.4 IPS
 
Image Segmentation (Q)
98% 3184
51.8 IPS
 
Pose Estimation (SP)
100% 3899
4.55 IPS
 
Pose Estimation (HP)
100% 3906
4.56 IPS
 
Pose Estimation (Q)
84% 8750
10.4 IPS
 
Object Detection (SP)
98% 1966
156.5 IPS
 
Object Detection (HP)
98% 1949
155.1 IPS
 
Object Detection (Q)
83% 2120
171.3 IPS
 
Face Detection (SP)
100% 3269
38.8 IPS
 
Face Detection (HP)
100% 3255
38.7 IPS
 
Face Detection (Q)
95% 5176
61.8 IPS
 
Depth Estimation (SP)
99% 3365
26.0 IPS
 
Depth Estimation (HP)
99% 3404
26.3 IPS
 
Depth Estimation (Q)
64% 5283
48.4 IPS
 
Style Transfer (SP)
89% 8138
10.6 IPS
 
Style Transfer (HP)
89% 8135
10.6 IPS
 
Style Transfer (Q)
98% 15386
19.8 IPS
 
Image Super-Resolution (SP)
100% 1583
58.4 IPS
 
Image Super-Resolution (HP)
100% 1625
60.0 IPS
 
Image Super-Resolution (Q)
97% 3755
139.1 IPS
 
Text Classification (SP)
100% 712
950.2 IPS
 
Text Classification (HP)
99% 666
888.9 IPS
 
Text Classification (Q)
88% 979
1.32 KIPS
 
Machine Translation (SP)
100% 1501
25.9 IPS
 
Machine Translation (HP)
100% 1477
25.4 IPS
 
Machine Translation (Q)
50% 713
25.3 IPS
 

Compare

Set Baseline Geekbench 6 now available