Geekbench ML Score

302
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date July 19 2025 01:47 PM
Views 14

System Information

System Information
Operating System Android 10
Model HUAWEI JNY-LX1
Model IDHUAWEI JNY-LX1
Motherboard JNY
CPU Information
Name vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 3 part 3392 revision 0
Base Frequency 1.88 GHz
Cluster 16 Cores @ 1.88 GHz
Cluster 22 Cores @ 2.28 GHz
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 233
24.9 IPS
 
Image Classification (F16)
100% 234
25.0 IPS
 
Image Classification (I8)
81% 193
20.7 IPS
 
Image Segmentation (F32)
100% 376
2.32 IPS
 
Image Segmentation (F16)
100% 376
2.32 IPS
 
Image Segmentation (I8)
89% 2245
13.9 IPS
 
Pose Estimation (F32)
100% 137
0.56 IPS
 
Pose Estimation (F16)
100% 137
0.55 IPS
 
Pose Estimation (I8)
80% 59
0.24 IPS
 
Object Detection (F32)
100% 356
12.5 IPS
 
Object Detection (F16)
100% 1758
61.7 IPS
 
Object Detection (I8)
52% 276
9.68 IPS
 
Face Detection (F32)
100% 364
4.18 IPS
 
Face Detection (F16)
100% 361
4.15 IPS
 
Face Detection (I8)
75% 274
3.14 IPS
 
Text Classification (F32)
100% 484
191.5 IPS
 
Text Classification (F16)
100% 130
51.2 IPS
 
Machine Translation (F32)
100% 303
46.7 IPS
 
Machine Translation (F16)
100% 304
46.9 IPS
 

Compare

Set Baseline Geekbench 6 now available