Geekbench AI Score

473
Single Precision Score
818
Half Precision Score
894
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User Kike
Upload Date February 13 2026 07:50 AM
Views 5

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% 196
36.5 IPS
 
Image Classification (HP)
100% 386
71.8 IPS
 
Image Classification (Q)
99% 525
97.9 IPS
 
Image Segmentation (SP)
100% 249
4.03 IPS
 
Image Segmentation (HP)
100% 468
7.59 IPS
 
Image Segmentation (Q)
98% 638
10.4 IPS
 
Pose Estimation (SP)
100% 1038
1.21 IPS
 
Pose Estimation (HP)
92% 1993
2.34 IPS
 
Pose Estimation (Q)
96% 1509
1.77 IPS
 
Object Detection (SP)
100% 211
16.7 IPS
 
Object Detection (HP)
97% 409
32.6 IPS
 
Object Detection (Q)
85% 599
48.2 IPS
 
Face Detection (SP)
100% 685
8.14 IPS
 
Face Detection (HP)
100% 1181
14.0 IPS
 
Face Detection (Q)
97% 1369
16.3 IPS
 
Depth Estimation (SP)
100% 900
6.93 IPS
 
Depth Estimation (HP)
98% 1623
12.5 IPS
 
Depth Estimation (Q)
64% 1372
12.7 IPS
 
Style Transfer (SP)
89% 1729
2.24 IPS
 
Style Transfer (HP)
88% 2180
2.83 IPS
 
Style Transfer (Q)
98% 3425
4.42 IPS
 
Image Super-Resolution (SP)
100% 471
17.4 IPS
 
Image Super-Resolution (HP)
92% 862
32.0 IPS
 
Image Super-Resolution (Q)
97% 849
31.5 IPS
 
Text Classification (SP)
100% 238
317.1 IPS
 
Text Classification (HP)
100% 405
540.5 IPS
 
Text Classification (Q)
93% 439
589.9 IPS
 
Machine Translation (SP)
100% 439
7.57 IPS
 
Machine Translation (HP)
96% 625
10.8 IPS
 
Machine Translation (Q)
55% 452
12.1 IPS
 

Compare

Set Baseline Geekbench 6 now available