Geekbench AI Score

507
Single Precision Score
510
Half Precision Score
968
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User makarovvova924
Upload Date October 13 2024 10:37 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 720G
System Information
Operating System Android 14
Model Samsung Galaxy A52
Model IDsamsung SM-A525F
Motherboard atoll
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 15
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.32 GHz
Memory Information
Size 7.31 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 230
42.8 IPS
 
Image Classification (HP)
100% 231
43.0 IPS
 
Image Classification (Q)
100% 672
125.0 IPS
 
Image Segmentation (SP)
100% 281
4.55 IPS
 
Image Segmentation (HP)
100% 282
4.57 IPS
 
Image Segmentation (Q)
98% 729
11.9 IPS
 
Pose Estimation (SP)
100% 1121
1.31 IPS
 
Pose Estimation (HP)
100% 1116
1.30 IPS
 
Pose Estimation (Q)
84% 1674
1.99 IPS
 
Object Detection (SP)
100% 230
18.2 IPS
 
Object Detection (HP)
100% 228
18.1 IPS
 
Object Detection (Q)
83% 668
54.0 IPS
 
Face Detection (SP)
100% 669
7.95 IPS
 
Face Detection (HP)
100% 695
8.26 IPS
 
Face Detection (Q)
95% 1481
17.7 IPS
 
Depth Estimation (SP)
100% 902
6.95 IPS
 
Depth Estimation (HP)
99% 917
7.07 IPS
 
Depth Estimation (Q)
64% 1527
14.0 IPS
 
Style Transfer (SP)
89% 1887
2.45 IPS
 
Style Transfer (HP)
89% 1903
2.47 IPS
 
Style Transfer (Q)
98% 3869
4.99 IPS
 
Image Super-Resolution (SP)
100% 478
17.7 IPS
 
Image Super-Resolution (HP)
100% 486
17.9 IPS
 
Image Super-Resolution (Q)
97% 952
35.3 IPS
 
Text Classification (SP)
100% 267
356.8 IPS
 
Text Classification (HP)
100% 267
356.6 IPS
 
Text Classification (Q)
88% 491
661.8 IPS
 
Machine Translation (SP)
100% 464
8.00 IPS
 
Machine Translation (HP)
100% 457
7.87 IPS
 
Machine Translation (Q)
50% 324
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available