Geekbench AI Score

158
Single Precision Score
220
Half Precision Score
224
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 02 2025 08:33 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR BRP-NX1M
Model IDHONOR BRP-NX1M
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 7.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 124
23.1 IPS
 
Image Classification (HP)
100% 218
40.5 IPS
 
Image Classification (Q)
97% 205
38.3 IPS
 
Image Segmentation (SP)
100% 182
2.95 IPS
 
Image Segmentation (HP)
100% 231
3.74 IPS
 
Image Segmentation (Q)
98% 225
3.65 IPS
 
Pose Estimation (SP)
100% 177
0.21 IPS
 
Pose Estimation (HP)
100% 281
0.33 IPS
 
Pose Estimation (Q)
95% 276
0.32 IPS
 
Object Detection (SP)
100% 97
7.68 IPS
 
Object Detection (HP)
100% 135
10.7 IPS
 
Object Detection (Q)
89% 133
10.6 IPS
 
Face Detection (SP)
100% 370
4.40 IPS
 
Face Detection (HP)
100% 493
5.86 IPS
 
Face Detection (Q)
97% 471
5.61 IPS
 
Depth Estimation (SP)
100% 271
2.09 IPS
 
Depth Estimation (HP)
99% 445
3.43 IPS
 
Depth Estimation (Q)
63% 368
3.46 IPS
 
Style Transfer (SP)
100% 601
0.77 IPS
 
Style Transfer (HP)
100% 1213
1.56 IPS
 
Style Transfer (Q)
98% 1226
1.58 IPS
 
Image Super-Resolution (SP)
100% 110
4.05 IPS
 
Image Super-Resolution (HP)
100% 137
5.07 IPS
 
Image Super-Resolution (Q)
97% 139
5.15 IPS
 
Text Classification (SP)
100% 47
62.1 IPS
 
Text Classification (HP)
100% 47
62.5 IPS
 
Text Classification (Q)
91% 90
121.3 IPS
 
Machine Translation (SP)
100% 82
1.41 IPS
 
Machine Translation (HP)
100% 82
1.41 IPS
 
Machine Translation (Q)
57% 73
1.79 IPS
 

Compare

Set Baseline Geekbench 6 now available