Geekbench AI Score

430
Single Precision Score
524
Half Precision Score
1996
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date September 20 2025 11:13 AM
Views 3

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% 439
81.6 IPS
 
Image Classification (HP)
100% 723
134.5 IPS
 
Image Classification (Q)
97% 1489
277.9 IPS
 
Image Segmentation (SP)
100% 634
10.3 IPS
 
Image Segmentation (HP)
100% 206
3.34 IPS
 
Image Segmentation (Q)
98% 1362
22.1 IPS
 
Pose Estimation (SP)
100% 1432
1.67 IPS
 
Pose Estimation (HP)
100% 5469
6.38 IPS
 
Pose Estimation (Q)
96% 11761
13.8 IPS
 
Object Detection (SP)
100% 420
33.3 IPS
 
Object Detection (HP)
100% 156
12.4 IPS
 
Object Detection (Q)
85% 1706
137.3 IPS
 
Face Detection (SP)
100% 1206
14.3 IPS
 
Face Detection (HP)
100% 390
4.63 IPS
 
Face Detection (Q)
97% 3792
45.2 IPS
 
Depth Estimation (SP)
99% 514
3.96 IPS
 
Depth Estimation (HP)
99% 325
2.51 IPS
 
Depth Estimation (Q)
63% 6562
61.1 IPS
 
Style Transfer (SP)
100% 831
1.07 IPS
 
Style Transfer (HP)
100% 544
0.70 IPS
 
Style Transfer (Q)
98% 3997
5.15 IPS
 
Image Super-Resolution (SP)
100% 739
27.3 IPS
 
Image Super-Resolution (HP)
100% 2135
78.8 IPS
 
Image Super-Resolution (Q)
97% 5491
203.5 IPS
 
Text Classification (SP)
71% 12
17.0 IPS
 
Text Classification (HP)
100% 225
301.0 IPS
 
Text Classification (Q)
93% 181
242.9 IPS
 
Machine Translation (SP)
100% 285
4.91 IPS
 
Machine Translation (HP)
100% 372
6.40 IPS
 
Machine Translation (Q)
54% 250
7.04 IPS
 

Compare

Set Baseline Geekbench 6 now available