Geekbench AI Score

732
Single Precision Score
1166
Half Precision Score
914
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User kasid
Upload Date February 16 2026 04:35 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 16
Model HONOR DNY-NX9
Model IDHONOR DNY-NX9
Motherboard crow
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3405 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.40 GHz
Cluster 31 Core @ 2.63 GHz
Memory Information
Size 11.12 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 512
95.3 IPS
 
Image Classification (HP)
100% 805
149.6 IPS
 
Image Classification (Q)
99% 700
130.5 IPS
 
Image Segmentation (SP)
100% 877
14.2 IPS
 
Image Segmentation (HP)
100% 1516
24.6 IPS
 
Image Segmentation (Q)
98% 1037
16.9 IPS
 
Pose Estimation (SP)
100% 3268
3.81 IPS
 
Pose Estimation (HP)
99% 6278
7.35 IPS
 
Pose Estimation (Q)
97% 6101
7.14 IPS
 
Object Detection (SP)
100% 429
34.0 IPS
 
Object Detection (HP)
99% 626
49.7 IPS
 
Object Detection (Q)
82% 575
46.6 IPS
 
Face Detection (SP)
100% 1251
14.9 IPS
 
Face Detection (HP)
100% 1876
22.3 IPS
 
Face Detection (Q)
97% 1503
17.9 IPS
 
Depth Estimation (SP)
100% 1974
15.2 IPS
 
Depth Estimation (HP)
98% 3541
27.4 IPS
 
Depth Estimation (Q)
63% 2791
26.2 IPS
 
Style Transfer (SP)
100% 4203
5.40 IPS
 
Style Transfer (HP)
100% 8847
11.4 IPS
 
Style Transfer (Q)
98% 8473
10.9 IPS
 
Image Super-Resolution (SP)
100% 831
30.7 IPS
 
Image Super-Resolution (HP)
100% 1427
52.7 IPS
 
Image Super-Resolution (Q)
97% 1279
47.4 IPS
 
Text Classification (SP)
35% 30
292.3 IPS
 
Text Classification (HP)
35% 37
334.1 IPS
 
Text Classification (Q)
35% 32
308.8 IPS
 
Machine Translation (SP)
100% 274
4.73 IPS
 
Machine Translation (HP)
97% 314
5.42 IPS
 
Machine Translation (Q)
49% 111
4.17 IPS
 

Compare

Set Baseline Geekbench 6 now available