Geekbench ML Score

382
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

User 46fy45
Upload Date November 05 2025 05:00 PM
Views 5

System Information

System Information
Operating System Android 10
Model HUAWEI NOH-NX9
Model IDHUAWEI NOH-NX9
Motherboard NOH
Governorschedutil
CPU Information
Name ARM vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 2.04 GHz
Cluster 14 Cores @ 2.04 GHz
Cluster 23 Cores @ 2.54 GHz
Cluster 31 Core @ 3.13 GHz
Memory Information
Size 7.25 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 267
28.6 IPS
 
Image Classification (F16)
100% 247
26.5 IPS
 
Image Classification (I8)
81% 253
27.1 IPS
 
Image Segmentation (F32)
100% 460
2.84 IPS
 
Image Segmentation (F16)
100% 519
3.21 IPS
 
Image Segmentation (I8)
89% 4145
25.6 IPS
 
Pose Estimation (F32)
100% 197
0.80 IPS
 
Pose Estimation (F16)
100% 211
0.85 IPS
 
Pose Estimation (I8)
80% 75
0.30 IPS
 
Object Detection (F32)
100% 100
3.51 IPS
 
Object Detection (F16)
100% 3715
130.4 IPS
 
Object Detection (I8)
52% 362
12.7 IPS
 
Face Detection (F32)
100% 350
4.02 IPS
 
Face Detection (F16)
100% 421
4.83 IPS
 
Face Detection (I8)
75% 366
4.20 IPS
 
Text Classification (F32)
100% 641
253.5 IPS
 
Text Classification (F16)
100% 141
55.8 IPS
 
Machine Translation (F32)
100% 587
90.5 IPS
 
Machine Translation (F16)
100% 590
90.9 IPS
 

Compare

Set Baseline Geekbench 6 now available