Geekbench AI Score

2876
Single Precision Score
2852
Half Precision Score
4820
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 21 2025 09:33 PM
Views 3

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% 2019
375.5 IPS
 
Image Classification (HP)
100% 1972
366.7 IPS
 
Image Classification (Q)
100% 3851
716.2 IPS
 
Image Segmentation (SP)
100% 2616
42.4 IPS
 
Image Segmentation (HP)
100% 2721
44.1 IPS
 
Image Segmentation (Q)
98% 4433
72.1 IPS
 
Pose Estimation (SP)
100% 4288
5.00 IPS
 
Pose Estimation (HP)
100% 4233
4.94 IPS
 
Pose Estimation (Q)
84% 10190
12.1 IPS
 
Object Detection (SP)
98% 2247
178.8 IPS
 
Object Detection (HP)
98% 2073
164.9 IPS
 
Object Detection (Q)
83% 3583
289.5 IPS
 
Face Detection (SP)
100% 4197
49.9 IPS
 
Face Detection (HP)
100% 4287
50.9 IPS
 
Face Detection (Q)
95% 8122
97.0 IPS
 
Depth Estimation (SP)
99% 4221
32.6 IPS
 
Depth Estimation (HP)
99% 4057
31.3 IPS
 
Depth Estimation (Q)
64% 7610
69.7 IPS
 
Style Transfer (SP)
89% 10101
13.1 IPS
 
Style Transfer (HP)
89% 9990
13.0 IPS
 
Style Transfer (Q)
98% 20425
26.3 IPS
 
Image Super-Resolution (SP)
100% 2115
78.1 IPS
 
Image Super-Resolution (HP)
100% 2194
81.0 IPS
 
Image Super-Resolution (Q)
97% 5292
196.1 IPS
 
Text Classification (SP)
100% 1114
1.49 KIPS
 
Text Classification (HP)
99% 1118
1.49 KIPS
 
Text Classification (Q)
88% 1701
2.29 KIPS
 
Machine Translation (SP)
100% 1808
31.1 IPS
 
Machine Translation (HP)
100% 1779
30.6 IPS
 
Machine Translation (Q)
50% 956
33.9 IPS
 

Compare

Set Baseline Geekbench 6 now available