Geekbench AI Score

483
Single Precision Score
479
Half Precision Score
868
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date August 10 2025 09:29 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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 5.50 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 211
39.2 IPS
 
Image Classification (HP)
100% 211
39.2 IPS
 
Image Classification (Q)
100% 600
111.6 IPS
 
Image Segmentation (SP)
100% 262
4.25 IPS
 
Image Segmentation (HP)
100% 263
4.26 IPS
 
Image Segmentation (Q)
98% 648
10.5 IPS
 
Pose Estimation (SP)
100% 1048
1.22 IPS
 
Pose Estimation (HP)
100% 1043
1.22 IPS
 
Pose Estimation (Q)
84% 1494
1.77 IPS
 
Object Detection (SP)
100% 212
16.8 IPS
 
Object Detection (HP)
100% 211
16.8 IPS
 
Object Detection (Q)
83% 600
48.4 IPS
 
Face Detection (SP)
100% 689
8.18 IPS
 
Face Detection (HP)
100% 687
8.16 IPS
 
Face Detection (Q)
95% 1360
16.2 IPS
 
Depth Estimation (SP)
100% 903
6.96 IPS
 
Depth Estimation (HP)
99% 868
6.69 IPS
 
Depth Estimation (Q)
64% 1381
12.6 IPS
 
Style Transfer (SP)
89% 1722
2.24 IPS
 
Style Transfer (HP)
89% 1720
2.23 IPS
 
Style Transfer (Q)
98% 3430
4.42 IPS
 
Image Super-Resolution (SP)
100% 466
17.2 IPS
 
Image Super-Resolution (HP)
100% 466
17.2 IPS
 
Image Super-Resolution (Q)
97% 830
30.8 IPS
 
Text Classification (SP)
100% 255
340.0 IPS
 
Text Classification (HP)
100% 251
334.8 IPS
 
Text Classification (Q)
88% 420
566.4 IPS
 
Machine Translation (SP)
100% 443
7.62 IPS
 
Machine Translation (HP)
100% 440
7.57 IPS
 
Machine Translation (Q)
50% 313
11.1 IPS
 

Compare

Set Baseline Geekbench 6 now available