Geekbench AI Score

2968
Single Precision Score
2972
Half Precision Score
5391
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Maximum_Game
Upload Date February 19 2025 12:10 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S938U1
Model IDsamsung SM-S938U1
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.47 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1981
368.4 IPS
 
Image Classification (HP)
100% 2077
386.3 IPS
 
Image Classification (Q)
100% 4591
853.8 IPS
 
Image Segmentation (SP)
100% 2558
41.5 IPS
 
Image Segmentation (HP)
100% 2558
41.5 IPS
 
Image Segmentation (Q)
98% 5436
88.4 IPS
 
Pose Estimation (SP)
100% 5834
6.81 IPS
 
Pose Estimation (HP)
100% 5632
6.57 IPS
 
Pose Estimation (Q)
84% 14196
16.8 IPS
 
Object Detection (SP)
98% 1804
143.5 IPS
 
Object Detection (HP)
98% 1794
142.8 IPS
 
Object Detection (Q)
83% 4203
339.5 IPS
 
Face Detection (SP)
100% 4493
53.4 IPS
 
Face Detection (HP)
100% 4667
55.4 IPS
 
Face Detection (Q)
95% 10286
122.8 IPS
 
Depth Estimation (SP)
99% 4902
37.9 IPS
 
Depth Estimation (HP)
99% 4783
37.0 IPS
 
Depth Estimation (Q)
64% 11078
101.5 IPS
 
Style Transfer (SP)
89% 12295
16.0 IPS
 
Style Transfer (HP)
89% 12076
15.7 IPS
 
Style Transfer (Q)
98% 26410
34.1 IPS
 
Image Super-Resolution (SP)
100% 2502
92.4 IPS
 
Image Super-Resolution (HP)
100% 2600
96.0 IPS
 
Image Super-Resolution (Q)
97% 6913
256.2 IPS
 
Text Classification (SP)
100% 1019
1.36 KIPS
 
Text Classification (HP)
99% 1010
1.35 KIPS
 
Text Classification (Q)
88% 1113
1.50 KIPS
 
Machine Translation (SP)
100% 1442
24.8 IPS
 
Machine Translation (HP)
100% 1416
24.4 IPS
 
Machine Translation (Q)
50% 602
21.4 IPS
 

Compare

Set Baseline Geekbench 6 now available