Geekbench AI Score

273
Single Precision Score
267
Half Precision Score
633
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User mpoloton
Upload Date November 19 2025 02:55 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 12
Model HUAWEI MNA-LX9
Model IDHUAWEI MNA-LX9
Motherboard MNA
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 2.02 GHz
Cluster 14 Cores @ 2.02 GHz
Cluster 23 Cores @ 2.75 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 7.23 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 200
37.1 IPS
 
Image Classification (HP)
100% 202
37.6 IPS
 
Image Classification (Q)
99% 582
108.5 IPS
 
Image Segmentation (SP)
100% 256
4.15 IPS
 
Image Segmentation (HP)
100% 198
3.20 IPS
 
Image Segmentation (Q)
98% 427
6.94 IPS
 
Pose Estimation (SP)
100% 272
0.32 IPS
 
Pose Estimation (HP)
100% 272
0.32 IPS
 
Pose Estimation (Q)
98% 1026
1.20 IPS
 
Object Detection (SP)
100% 149
11.8 IPS
 
Object Detection (HP)
100% 149
11.8 IPS
 
Object Detection (Q)
87% 431
34.6 IPS
 
Face Detection (SP)
100% 394
4.68 IPS
 
Face Detection (HP)
100% 399
4.74 IPS
 
Face Detection (Q)
97% 875
10.4 IPS
 
Depth Estimation (SP)
100% 343
2.65 IPS
 
Depth Estimation (HP)
99% 344
2.65 IPS
 
Depth Estimation (Q)
64% 836
7.59 IPS
 
Style Transfer (SP)
100% 600
0.77 IPS
 
Style Transfer (HP)
100% 600
0.77 IPS
 
Style Transfer (Q)
98% 1618
2.09 IPS
 
Image Super-Resolution (SP)
100% 169
6.25 IPS
 
Image Super-Resolution (HP)
100% 169
6.25 IPS
 
Image Super-Resolution (Q)
97% 603
22.3 IPS
 
Text Classification (SP)
100% 220
293.0 IPS
 
Text Classification (HP)
100% 221
294.7 IPS
 
Text Classification (Q)
91% 392
527.0 IPS
 
Machine Translation (SP)
100% 369
6.36 IPS
 
Machine Translation (HP)
100% 370
6.37 IPS
 
Machine Translation (Q)
57% 336
8.21 IPS
 

Compare

Set Baseline Geekbench 6 now available