Geekbench AI Score

703
Single Precision Score
28216
Half Precision Score
63328
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date July 16 2025 05:36 PM
Views 16

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model nubia NX789J
Model IDnubia NX789J
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.32 GHz
Memory Information
Size 22.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 434
80.7 IPS
 
Image Classification (HP)
100% 21521
4.00 KIPS
 
Image Classification (Q)
97% 49457
9.23 KIPS
 
Image Segmentation (SP)
100% 548
8.89 IPS
 
Image Segmentation (HP)
100% 14657
237.6 IPS
 
Image Segmentation (Q)
98% 43786
712.0 IPS
 
Pose Estimation (SP)
100% 708
0.83 IPS
 
Pose Estimation (HP)
100% 123959
144.6 IPS
 
Pose Estimation (Q)
98% 480788
562.7 IPS
 
Object Detection (SP)
100% 403
32.0 IPS
 
Object Detection (HP)
100% 20267
1.61 KIPS
 
Object Detection (Q)
85% 23997
1.93 KIPS
 
Face Detection (SP)
100% 1065
12.7 IPS
 
Face Detection (HP)
100% 45090
535.8 IPS
 
Face Detection (Q)
97% 158663
1.89 KIPS
 
Depth Estimation (SP)
100% 894
6.88 IPS
 
Depth Estimation (HP)
99% 84782
653.2 IPS
 
Depth Estimation (Q)
63% 148548
1.37 KIPS
 
Style Transfer (SP)
100% 1520
1.95 IPS
 
Style Transfer (HP)
98% 99364
128.1 IPS
 
Style Transfer (Q)
98% 496840
640.7 IPS
 
Image Super-Resolution (SP)
100% 473
17.5 IPS
 
Image Super-Resolution (HP)
100% 55299
2.04 KIPS
 
Image Super-Resolution (Q)
97% 135553
5.02 KIPS
 
Text Classification (SP)
100% 634
846.1 IPS
 
Text Classification (HP)
100% 3960
5.29 KIPS
 
Text Classification (Q)
93% 8203
11.0 KIPS
 
Machine Translation (SP)
100% 1014
17.5 IPS
 
Machine Translation (HP)
100% 4854
83.6 IPS
 
Machine Translation (Q)
56% 3189
82.1 IPS
 

Compare

Set Baseline Geekbench 6 now available