Geekbench AI Score

753
Single Precision Score
747
Half Precision Score
1643
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 18 2025 03:09 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model motorola motorola edge 50 fusion
Model IDmotorola motorola edge 50 fusion
Motherboard cuscoi
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 1.96 GHz
Cluster 14 Cores @ 1.96 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 11.18 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 450
83.7 IPS
 
Image Classification (HP)
100% 430
79.9 IPS
 
Image Classification (Q)
100% 1455
270.6 IPS
 
Image Segmentation (SP)
100% 510
8.26 IPS
 
Image Segmentation (HP)
100% 525
8.52 IPS
 
Image Segmentation (Q)
98% 1662
27.0 IPS
 
Pose Estimation (SP)
100% 2028
2.37 IPS
 
Pose Estimation (HP)
100% 1945
2.27 IPS
 
Pose Estimation (Q)
84% 3773
4.48 IPS
 
Object Detection (SP)
100% 455
36.1 IPS
 
Object Detection (HP)
100% 455
36.1 IPS
 
Object Detection (Q)
83% 1404
113.4 IPS
 
Face Detection (SP)
100% 1105
13.1 IPS
 
Face Detection (HP)
100% 1108
13.2 IPS
 
Face Detection (Q)
95% 3421
40.8 IPS
 
Depth Estimation (SP)
100% 1580
12.2 IPS
 
Depth Estimation (HP)
99% 1567
12.1 IPS
 
Depth Estimation (Q)
64% 3429
31.4 IPS
 
Style Transfer (SP)
89% 3646
4.73 IPS
 
Style Transfer (HP)
89% 3644
4.73 IPS
 
Style Transfer (Q)
98% 8617
11.1 IPS
 
Image Super-Resolution (SP)
100% 862
31.8 IPS
 
Image Super-Resolution (HP)
100% 866
32.0 IPS
 
Image Super-Resolution (Q)
97% 2020
74.9 IPS
 
Text Classification (SP)
100% 175
234.2 IPS
 
Text Classification (HP)
100% 174
232.9 IPS
 
Text Classification (Q)
88% 287
387.3 IPS
 
Machine Translation (SP)
100% 290
4.99 IPS
 
Machine Translation (HP)
100% 287
4.95 IPS
 
Machine Translation (Q)
50% 192
6.82 IPS
 

Compare

Set Baseline Geekbench 6 now available