Geekbench AI Score

430
Single Precision Score
523
Half Precision Score
1978
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date September 20 2025 11:29 AM
Views 4

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% 438
81.5 IPS
 
Image Classification (HP)
100% 722
134.2 IPS
 
Image Classification (Q)
97% 1434
267.6 IPS
 
Image Segmentation (SP)
100% 636
10.3 IPS
 
Image Segmentation (HP)
100% 206
3.34 IPS
 
Image Segmentation (Q)
98% 1338
21.8 IPS
 
Pose Estimation (SP)
100% 1428
1.67 IPS
 
Pose Estimation (HP)
100% 5476
6.39 IPS
 
Pose Estimation (Q)
96% 11738
13.7 IPS
 
Object Detection (SP)
100% 418
33.2 IPS
 
Object Detection (HP)
100% 156
12.4 IPS
 
Object Detection (Q)
85% 1747
140.6 IPS
 
Face Detection (SP)
100% 1202
14.3 IPS
 
Face Detection (HP)
100% 391
4.64 IPS
 
Face Detection (Q)
97% 3810
45.4 IPS
 
Depth Estimation (SP)
99% 517
3.98 IPS
 
Depth Estimation (HP)
99% 325
2.51 IPS
 
Depth Estimation (Q)
63% 6656
62.0 IPS
 
Style Transfer (SP)
100% 827
1.06 IPS
 
Style Transfer (HP)
100% 540
0.69 IPS
 
Style Transfer (Q)
98% 4023
5.19 IPS
 
Image Super-Resolution (SP)
100% 744
27.5 IPS
 
Image Super-Resolution (HP)
100% 2104
77.7 IPS
 
Image Super-Resolution (Q)
97% 5580
206.8 IPS
 
Text Classification (SP)
71% 12
17.2 IPS
 
Text Classification (HP)
100% 227
303.3 IPS
 
Text Classification (Q)
93% 165
221.6 IPS
 
Machine Translation (SP)
100% 286
4.92 IPS
 
Machine Translation (HP)
100% 371
6.40 IPS
 
Machine Translation (Q)
54% 249
7.02 IPS
 

Compare

Set Baseline Geekbench 6 now available