Geekbench AI Score

881
Single Precision Score
874
Half Precision Score
1882
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date March 19 2025 07:34 PM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model motorola moto g stylus 5G - 2024
Model IDmotorola moto g stylus 5G - 2024
Motherboard boston
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 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 7.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 426
79.3 IPS
 
Image Classification (HP)
100% 410
76.3 IPS
 
Image Classification (Q)
100% 1343
249.7 IPS
 
Image Segmentation (SP)
100% 504
8.18 IPS
 
Image Segmentation (HP)
100% 492
7.98 IPS
 
Image Segmentation (Q)
98% 1539
25.0 IPS
 
Pose Estimation (SP)
100% 1971
2.30 IPS
 
Pose Estimation (HP)
100% 1932
2.25 IPS
 
Pose Estimation (Q)
84% 3470
4.12 IPS
 
Object Detection (SP)
100% 433
34.3 IPS
 
Object Detection (HP)
100% 433
34.4 IPS
 
Object Detection (Q)
83% 1304
105.4 IPS
 
Face Detection (SP)
100% 1086
12.9 IPS
 
Face Detection (HP)
100% 1093
13.0 IPS
 
Face Detection (Q)
95% 3212
38.3 IPS
 
Depth Estimation (SP)
100% 1529
11.8 IPS
 
Depth Estimation (HP)
99% 1541
11.9 IPS
 
Depth Estimation (Q)
64% 3165
29.0 IPS
 
Style Transfer (SP)
89% 3484
4.52 IPS
 
Style Transfer (HP)
89% 3484
4.52 IPS
 
Style Transfer (Q)
98% 7939
10.2 IPS
 
Image Super-Resolution (SP)
100% 830
30.6 IPS
 
Image Super-Resolution (HP)
100% 824
30.4 IPS
 
Image Super-Resolution (Q)
97% 1883
69.8 IPS
 
Text Classification (SP)
100% 472
629.9 IPS
 
Text Classification (HP)
100% 467
623.6 IPS
 
Text Classification (Q)
88% 877
1.18 KIPS
 
Machine Translation (SP)
100% 682
11.8 IPS
 
Machine Translation (HP)
100% 685
11.8 IPS
 
Machine Translation (Q)
50% 449
15.9 IPS
 

Compare

Set Baseline Geekbench 6 now available