Geekbench AI Score

3000
Single Precision Score
2991
Half Precision Score
5423
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Maximum_Game
Upload Date February 19 2025 04:26 PM
Views 2

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% 2017
375.1 IPS
 
Image Classification (HP)
100% 2079
386.6 IPS
 
Image Classification (Q)
100% 4682
870.7 IPS
 
Image Segmentation (SP)
100% 2637
42.8 IPS
 
Image Segmentation (HP)
100% 2630
42.6 IPS
 
Image Segmentation (Q)
98% 5512
89.6 IPS
 
Pose Estimation (SP)
100% 5967
6.96 IPS
 
Pose Estimation (HP)
100% 5807
6.78 IPS
 
Pose Estimation (Q)
84% 14707
17.4 IPS
 
Object Detection (SP)
98% 1817
144.6 IPS
 
Object Detection (HP)
98% 1855
147.6 IPS
 
Object Detection (Q)
83% 4272
345.1 IPS
 
Face Detection (SP)
100% 4659
55.4 IPS
 
Face Detection (HP)
100% 4652
55.3 IPS
 
Face Detection (Q)
95% 10376
123.9 IPS
 
Depth Estimation (SP)
99% 4996
38.6 IPS
 
Depth Estimation (HP)
99% 4793
37.0 IPS
 
Depth Estimation (Q)
64% 10959
100.4 IPS
 
Style Transfer (SP)
89% 12124
15.7 IPS
 
Style Transfer (HP)
89% 12128
15.7 IPS
 
Style Transfer (Q)
98% 27217
35.1 IPS
 
Image Super-Resolution (SP)
100% 2521
93.1 IPS
 
Image Super-Resolution (HP)
100% 2526
93.3 IPS
 
Image Super-Resolution (Q)
97% 7091
262.8 IPS
 
Text Classification (SP)
100% 1015
1.36 KIPS
 
Text Classification (HP)
99% 1019
1.36 KIPS
 
Text Classification (Q)
88% 1066
1.44 KIPS
 
Machine Translation (SP)
100% 1419
24.4 IPS
 
Machine Translation (HP)
100% 1401
24.1 IPS
 
Machine Translation (Q)
50% 581
20.6 IPS
 

Compare

Set Baseline Geekbench 6 now available