Geekbench AI Score

635
Single Precision Score
631
Half Precision Score
1307
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 20 2025 11:44 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR BRP-NX3
Model IDHONOR BRP-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 7.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 428
79.6 IPS
 
Image Classification (HP)
100% 428
79.5 IPS
 
Image Classification (Q)
100% 1345
250.1 IPS
 
Image Segmentation (SP)
100% 506
8.20 IPS
 
Image Segmentation (HP)
100% 508
8.24 IPS
 
Image Segmentation (Q)
98% 1558
25.3 IPS
 
Pose Estimation (SP)
100% 1948
2.27 IPS
 
Pose Estimation (HP)
100% 1900
2.22 IPS
 
Pose Estimation (Q)
84% 3476
4.12 IPS
 
Object Detection (SP)
100% 423
33.5 IPS
 
Object Detection (HP)
100% 423
33.6 IPS
 
Object Detection (Q)
83% 1286
103.9 IPS
 
Face Detection (SP)
100% 1080
12.8 IPS
 
Face Detection (HP)
100% 1066
12.7 IPS
 
Face Detection (Q)
95% 3157
37.7 IPS
 
Depth Estimation (SP)
100% 1507
11.6 IPS
 
Depth Estimation (HP)
99% 1499
11.5 IPS
 
Depth Estimation (Q)
64% 3161
29.0 IPS
 
Style Transfer (SP)
89% 3419
4.44 IPS
 
Style Transfer (HP)
89% 3476
4.51 IPS
 
Style Transfer (Q)
98% 5922
7.64 IPS
 
Image Super-Resolution (SP)
100% 269
9.92 IPS
 
Image Super-Resolution (HP)
100% 263
9.72 IPS
 
Image Super-Resolution (Q)
97% 615
22.8 IPS
 
Text Classification (SP)
100% 156
207.6 IPS
 
Text Classification (HP)
100% 154
206.2 IPS
 
Text Classification (Q)
88% 255
343.3 IPS
 
Machine Translation (SP)
100% 258
4.45 IPS
 
Machine Translation (HP)
100% 257
4.43 IPS
 
Machine Translation (Q)
50% 168
5.96 IPS
 

Compare

Set Baseline Geekbench 6 now available