Geekbench AI Score

256
Single Precision Score
257
Half Precision Score
298
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 17 2024 02:06 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6765V/XBA
System Information
Operating System Android 14
Model HONOR WOD-LX3
Model IDHONOR WOD-LX3
Motherboard WDYL
CPU Information
Name ARM MT6765V/XBA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.20 GHz
Cluster 14 Cores @ 1.60 GHz
Cluster 24 Cores @ 2.20 GHz
Memory Information
Size 3.71 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 133
24.8 IPS
 
Image Classification (HP)
100% 118
21.9 IPS
 
Image Classification (Q)
100% 210
39.0 IPS
 
Image Segmentation (SP)
100% 156
2.53 IPS
 
Image Segmentation (HP)
100% 170
2.75 IPS
 
Image Segmentation (Q)
98% 294
4.78 IPS
 
Pose Estimation (SP)
100% 648
0.76 IPS
 
Pose Estimation (HP)
100% 596
0.70 IPS
 
Pose Estimation (Q)
84% 508
0.60 IPS
 
Object Detection (SP)
100% 133
10.6 IPS
 
Object Detection (HP)
100% 140
11.1 IPS
 
Object Detection (Q)
83% 193
15.6 IPS
 
Face Detection (SP)
100% 325
3.86 IPS
 
Face Detection (HP)
100% 323
3.84 IPS
 
Face Detection (Q)
95% 533
6.36 IPS
 
Depth Estimation (SP)
100% 371
2.86 IPS
 
Depth Estimation (HP)
99% 427
3.29 IPS
 
Depth Estimation (Q)
64% 483
4.42 IPS
 
Style Transfer (SP)
89% 1173
1.52 IPS
 
Style Transfer (HP)
89% 1199
1.56 IPS
 
Style Transfer (Q)
98% 1221
1.57 IPS
 
Image Super-Resolution (SP)
100% 216
7.99 IPS
 
Image Super-Resolution (HP)
100% 225
8.32 IPS
 
Image Super-Resolution (Q)
97% 279
10.4 IPS
 
Text Classification (SP)
100% 124
165.0 IPS
 
Text Classification (HP)
100% 118
157.4 IPS
 
Text Classification (Q)
88% 141
190.3 IPS
 
Machine Translation (SP)
100% 182
3.13 IPS
 
Machine Translation (HP)
100% 172
2.96 IPS
 
Machine Translation (Q)
50% 75
2.67 IPS
 

Compare

Set Baseline Geekbench 6 now available