Geekbench AI Score

1263
Single Precision Score
2183
Half Precision Score
2131
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Ivianson
Upload Date April 29 2025 07:08 AM
Views 7

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% 721
134.0 IPS
 
Image Classification (HP)
100% 1384
257.4 IPS
 
Image Classification (Q)
99% 1571
293.0 IPS
 
Image Segmentation (SP)
100% 1540
25.0 IPS
 
Image Segmentation (HP)
100% 2101
34.1 IPS
 
Image Segmentation (Q)
98% 2024
32.9 IPS
 
Pose Estimation (SP)
100% 1706
1.99 IPS
 
Pose Estimation (HP)
100% 2943
3.43 IPS
 
Pose Estimation (Q)
96% 2730
3.20 IPS
 
Object Detection (SP)
100% 509
40.3 IPS
 
Object Detection (HP)
100% 1173
93.0 IPS
 
Object Detection (Q)
86% 1078
86.6 IPS
 
Face Detection (SP)
100% 2801
33.3 IPS
 
Face Detection (HP)
100% 3476
41.3 IPS
 
Face Detection (Q)
97% 3193
38.1 IPS
 
Depth Estimation (SP)
100% 1564
12.0 IPS
 
Depth Estimation (HP)
99% 4798
37.1 IPS
 
Depth Estimation (Q)
63% 3775
35.1 IPS
 
Style Transfer (SP)
100% 5540
7.12 IPS
 
Style Transfer (HP)
100% 11137
14.3 IPS
 
Style Transfer (Q)
98% 11097
14.3 IPS
 
Image Super-Resolution (SP)
100% 635
23.4 IPS
 
Image Super-Resolution (HP)
100% 1909
70.5 IPS
 
Image Super-Resolution (Q)
97% 2015
74.7 IPS
 
Text Classification (SP)
100% 677
904.0 IPS
 
Text Classification (HP)
100% 673
898.0 IPS
 
Text Classification (Q)
91% 1060
1.42 KIPS
 
Machine Translation (SP)
100% 1033
17.8 IPS
 
Machine Translation (HP)
100% 1027
17.7 IPS
 
Machine Translation (Q)
57% 724
17.7 IPS
 

Compare

Set Baseline Geekbench 6 now available