Geekbench AI Score

156
Single Precision Score
212
Half Precision Score
207
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Keliort
Upload Date February 01 2025 11:11 AM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6853V/NZA
System Information
Operating System Android 13
Model motorola motorola edge 20 lite
Model IDmotorola motorola edge 20 lite
Motherboard kyoto
CPU Information
Name ARM MT6853V/NZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 18 Cores @ 2.00 GHz
Memory Information
Size 7.46 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 100
18.6 IPS
 
Image Classification (HP)
100% 172
31.9 IPS
 
Image Classification (Q)
99% 158
29.5 IPS
 
Image Segmentation (SP)
100% 149
2.41 IPS
 
Image Segmentation (HP)
100% 257
4.16 IPS
 
Image Segmentation (Q)
98% 246
4.00 IPS
 
Pose Estimation (SP)
100% 105
0.12 IPS
 
Pose Estimation (HP)
100% 122
0.14 IPS
 
Pose Estimation (Q)
96% 122
0.14 IPS
 
Object Detection (SP)
100% 77
6.09 IPS
 
Object Detection (HP)
100% 122
9.70 IPS
 
Object Detection (Q)
83% 116
9.40 IPS
 
Face Detection (SP)
100% 311
3.70 IPS
 
Face Detection (HP)
100% 439
5.22 IPS
 
Face Detection (Q)
97% 463
5.52 IPS
 
Depth Estimation (SP)
100% 192
1.48 IPS
 
Depth Estimation (HP)
99% 251
1.93 IPS
 
Depth Estimation (Q)
62% 203
1.92 IPS
 
Style Transfer (SP)
100% 392
0.50 IPS
 
Style Transfer (HP)
100% 534
0.69 IPS
 
Style Transfer (Q)
98% 533
0.69 IPS
 
Image Super-Resolution (SP)
100% 91
3.36 IPS
 
Image Super-Resolution (HP)
100% 143
5.27 IPS
 
Image Super-Resolution (Q)
97% 138
5.11 IPS
 
Text Classification (SP)
100% 143
190.3 IPS
 
Text Classification (HP)
100% 141
187.6 IPS
 
Text Classification (Q)
91% 230
308.9 IPS
 
Machine Translation (SP)
100% 240
4.13 IPS
 
Machine Translation (HP)
100% 241
4.15 IPS
 
Machine Translation (Q)
57% 168
4.12 IPS
 

Compare

Set Baseline Geekbench 6 now available