Geekbench AI Score

1316
Single Precision Score
2157
Half Precision Score
1991
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User dgbrownnt
Upload Date April 16 2025 03:19 AM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S938U
Model IDsamsung SM-S938U
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% 689
128.1 IPS
 
Image Classification (HP)
100% 798
148.4 IPS
 
Image Classification (Q)
99% 544
101.4 IPS
 
Image Segmentation (SP)
100% 1453
23.6 IPS
 
Image Segmentation (HP)
100% 1807
29.3 IPS
 
Image Segmentation (Q)
98% 1803
29.3 IPS
 
Pose Estimation (SP)
100% 1725
2.01 IPS
 
Pose Estimation (HP)
100% 2980
3.48 IPS
 
Pose Estimation (Q)
96% 2978
3.49 IPS
 
Object Detection (SP)
100% 576
45.7 IPS
 
Object Detection (HP)
100% 1174
93.2 IPS
 
Object Detection (Q)
86% 1051
84.4 IPS
 
Face Detection (SP)
100% 3190
37.9 IPS
 
Face Detection (HP)
100% 4021
47.8 IPS
 
Face Detection (Q)
97% 3217
38.4 IPS
 
Depth Estimation (SP)
100% 1687
13.0 IPS
 
Depth Estimation (HP)
99% 4951
38.2 IPS
 
Depth Estimation (Q)
63% 4066
37.8 IPS
 
Style Transfer (SP)
100% 6262
8.05 IPS
 
Style Transfer (HP)
100% 13436
17.3 IPS
 
Style Transfer (Q)
98% 13304
17.2 IPS
 
Image Super-Resolution (SP)
100% 665
24.5 IPS
 
Image Super-Resolution (HP)
100% 2289
84.5 IPS
 
Image Super-Resolution (Q)
97% 2248
83.3 IPS
 
Text Classification (SP)
100% 670
894.5 IPS
 
Text Classification (HP)
100% 685
914.4 IPS
 
Text Classification (Q)
91% 1089
1.46 KIPS
 
Machine Translation (SP)
100% 1045
18.0 IPS
 
Machine Translation (HP)
100% 1035
17.8 IPS
 
Machine Translation (Q)
57% 749
18.3 IPS
 

Compare

Set Baseline Geekbench 6 now available