Geekbench AI Score

402
Single Precision Score
359
Half Precision Score
741
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 27 2024 08:40 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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% 429
79.7 IPS
 
Image Classification (HP)
100% 430
79.9 IPS
 
Image Classification (Q)
100% 1345
250.0 IPS
 
Image Segmentation (SP)
100% 507
8.22 IPS
 
Image Segmentation (HP)
100% 500
8.11 IPS
 
Image Segmentation (Q)
98% 1549
25.2 IPS
 
Pose Estimation (SP)
100% 1943
2.27 IPS
 
Pose Estimation (HP)
100% 623
0.73 IPS
 
Pose Estimation (Q)
84% 1169
1.39 IPS
 
Object Detection (SP)
100% 136
10.8 IPS
 
Object Detection (HP)
100% 136
10.8 IPS
 
Object Detection (Q)
83% 392
31.7 IPS
 
Face Detection (SP)
100% 345
4.10 IPS
 
Face Detection (HP)
100% 342
4.06 IPS
 
Face Detection (Q)
95% 800
9.55 IPS
 
Depth Estimation (SP)
100% 494
3.80 IPS
 
Depth Estimation (HP)
99% 494
3.81 IPS
 
Depth Estimation (Q)
64% 1001
9.17 IPS
 
Style Transfer (SP)
89% 1133
1.47 IPS
 
Style Transfer (HP)
89% 1124
1.46 IPS
 
Style Transfer (Q)
98% 2475
3.19 IPS
 
Image Super-Resolution (SP)
100% 248
9.15 IPS
 
Image Super-Resolution (HP)
100% 260
9.61 IPS
 
Image Super-Resolution (Q)
97% 616
22.8 IPS
 
Text Classification (SP)
100% 155
207.1 IPS
 
Text Classification (HP)
100% 155
206.2 IPS
 
Text Classification (Q)
88% 257
346.3 IPS
 
Machine Translation (SP)
100% 263
4.52 IPS
 
Machine Translation (HP)
100% 258
4.44 IPS
 
Machine Translation (Q)
50% 168
5.98 IPS
 

Compare

Set Baseline Geekbench 6 now available