Geekbench AI Score

427
Single Precision Score
525
Half Precision Score
1989
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date September 20 2025 10:45 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM Qualcomm
System Information
Operating System Android 12
Model HUAWEI DBY-W09
Model IDHUAWEI DBY-W09
Motherboard DBY
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 426
79.2 IPS
 
Image Classification (HP)
100% 721
134.1 IPS
 
Image Classification (Q)
97% 1442
269.2 IPS
 
Image Segmentation (SP)
100% 617
10.0 IPS
 
Image Segmentation (HP)
100% 206
3.34 IPS
 
Image Segmentation (Q)
98% 1326
21.6 IPS
 
Pose Estimation (SP)
100% 1427
1.66 IPS
 
Pose Estimation (HP)
100% 5491
6.41 IPS
 
Pose Estimation (Q)
96% 11760
13.8 IPS
 
Object Detection (SP)
100% 419
33.2 IPS
 
Object Detection (HP)
100% 156
12.4 IPS
 
Object Detection (Q)
85% 1690
136.0 IPS
 
Face Detection (SP)
100% 1213
14.4 IPS
 
Face Detection (HP)
100% 389
4.63 IPS
 
Face Detection (Q)
97% 3819
45.5 IPS
 
Depth Estimation (SP)
99% 516
3.97 IPS
 
Depth Estimation (HP)
99% 325
2.50 IPS
 
Depth Estimation (Q)
63% 6671
62.1 IPS
 
Style Transfer (SP)
100% 823
1.06 IPS
 
Style Transfer (HP)
100% 544
0.70 IPS
 
Style Transfer (Q)
98% 4093
5.28 IPS
 
Image Super-Resolution (SP)
100% 739
27.3 IPS
 
Image Super-Resolution (HP)
100% 2171
80.2 IPS
 
Image Super-Resolution (Q)
97% 5659
209.7 IPS
 
Text Classification (SP)
71% 12
17.0 IPS
 
Text Classification (HP)
100% 228
304.4 IPS
 
Text Classification (Q)
93% 175
234.5 IPS
 
Machine Translation (SP)
100% 287
4.95 IPS
 
Machine Translation (HP)
100% 372
6.41 IPS
 
Machine Translation (Q)
54% 248
7.00 IPS
 

Compare

Set Baseline Geekbench 6 now available