Geekbench AI Score

159
Single Precision Score
221
Half Precision Score
225
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User epicgeek
Upload Date November 26 2024 08:23 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR ALI-NX3
Model IDHONOR ALI-NX3
Motherboard parrot
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 7.28 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 124
23.1 IPS
 
Image Classification (HP)
100% 218
40.6 IPS
 
Image Classification (Q)
97% 207
38.7 IPS
 
Image Segmentation (SP)
100% 183
2.97 IPS
 
Image Segmentation (HP)
100% 228
3.70 IPS
 
Image Segmentation (Q)
98% 218
3.54 IPS
 
Pose Estimation (SP)
100% 177
0.21 IPS
 
Pose Estimation (HP)
100% 295
0.34 IPS
 
Pose Estimation (Q)
95% 292
0.34 IPS
 
Object Detection (SP)
100% 101
7.98 IPS
 
Object Detection (HP)
100% 131
10.4 IPS
 
Object Detection (Q)
89% 132
10.6 IPS
 
Face Detection (SP)
100% 367
4.36 IPS
 
Face Detection (HP)
100% 493
5.85 IPS
 
Face Detection (Q)
97% 467
5.57 IPS
 
Depth Estimation (SP)
100% 274
2.11 IPS
 
Depth Estimation (HP)
99% 451
3.49 IPS
 
Depth Estimation (Q)
63% 370
3.47 IPS
 
Style Transfer (SP)
100% 606
0.78 IPS
 
Style Transfer (HP)
100% 1220
1.57 IPS
 
Style Transfer (Q)
98% 1222
1.58 IPS
 
Image Super-Resolution (SP)
100% 109
4.02 IPS
 
Image Super-Resolution (HP)
100% 137
5.05 IPS
 
Image Super-Resolution (Q)
97% 134
4.98 IPS
 
Text Classification (SP)
100% 48
64.0 IPS
 
Text Classification (HP)
100% 48
64.5 IPS
 
Text Classification (Q)
91% 92
124.3 IPS
 
Machine Translation (SP)
100% 84
1.44 IPS
 
Machine Translation (HP)
100% 84
1.45 IPS
 
Machine Translation (Q)
57% 76
1.85 IPS
 

Compare

Set Baseline Geekbench 6 now available