Geekbench AI Score

1331
Single Precision Score
2275
Half Precision Score
2039
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User toygoon
Upload Date February 12 2025 08:42 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S938N
Model IDsamsung SM-S938N
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% 720
134.0 IPS
 
Image Classification (HP)
100% 986
183.4 IPS
 
Image Classification (Q)
99% 787
146.7 IPS
 
Image Segmentation (SP)
100% 1473
23.9 IPS
 
Image Segmentation (HP)
100% 1850
30.0 IPS
 
Image Segmentation (Q)
98% 1177
19.1 IPS
 
Pose Estimation (SP)
100% 1710
2.00 IPS
 
Pose Estimation (HP)
100% 2978
3.48 IPS
 
Pose Estimation (Q)
96% 2973
3.48 IPS
 
Object Detection (SP)
100% 575
45.6 IPS
 
Object Detection (HP)
100% 1232
97.7 IPS
 
Object Detection (Q)
86% 1144
91.9 IPS
 
Face Detection (SP)
100% 3116
37.0 IPS
 
Face Detection (HP)
100% 4814
57.2 IPS
 
Face Detection (Q)
97% 4049
48.3 IPS
 
Depth Estimation (SP)
100% 1665
12.8 IPS
 
Depth Estimation (HP)
99% 4946
38.2 IPS
 
Depth Estimation (Q)
63% 4076
37.9 IPS
 
Style Transfer (SP)
100% 6247
8.03 IPS
 
Style Transfer (HP)
100% 13400
17.2 IPS
 
Style Transfer (Q)
98% 13335
17.2 IPS
 
Image Super-Resolution (SP)
100% 680
25.1 IPS
 
Image Super-Resolution (HP)
100% 2287
84.4 IPS
 
Image Super-Resolution (Q)
97% 2229
82.6 IPS
 
Text Classification (SP)
100% 711
948.8 IPS
 
Text Classification (HP)
100% 713
952.2 IPS
 
Text Classification (Q)
91% 1117
1.50 KIPS
 
Machine Translation (SP)
100% 1071
18.4 IPS
 
Machine Translation (HP)
100% 1069
18.4 IPS
 
Machine Translation (Q)
57% 723
17.7 IPS
 

Compare

Set Baseline Geekbench 6 now available