Geekbench AI Score

2302
Single Precision Score
2381
Half Precision Score
3881
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Vwgtiron
Upload Date June 23 2025 11:36 PM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm ARMv8
System Information
Operating System Android 16
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 10.85 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2005
372.9 IPS
 
Image Classification (HP)
100% 1968
365.9 IPS
 
Image Classification (Q)
100% 4353
809.6 IPS
 
Image Segmentation (SP)
100% 2222
36.0 IPS
 
Image Segmentation (HP)
100% 2211
35.8 IPS
 
Image Segmentation (Q)
98% 4671
75.9 IPS
 
Pose Estimation (SP)
100% 4921
5.74 IPS
 
Pose Estimation (HP)
100% 3920
4.57 IPS
 
Pose Estimation (Q)
84% 8770
10.4 IPS
 
Object Detection (SP)
98% 1082
86.1 IPS
 
Object Detection (HP)
98% 1103
87.7 IPS
 
Object Detection (Q)
83% 2830
228.6 IPS
 
Face Detection (SP)
100% 3479
41.3 IPS
 
Face Detection (HP)
100% 3487
41.4 IPS
 
Face Detection (Q)
95% 7339
87.6 IPS
 
Depth Estimation (SP)
99% 3983
30.8 IPS
 
Depth Estimation (HP)
99% 4504
34.8 IPS
 
Depth Estimation (Q)
64% 9516
87.2 IPS
 
Style Transfer (SP)
89% 10332
13.4 IPS
 
Style Transfer (HP)
89% 11494
14.9 IPS
 
Style Transfer (Q)
98% 17570
22.7 IPS
 
Image Super-Resolution (SP)
100% 1711
63.2 IPS
 
Image Super-Resolution (HP)
100% 1738
64.2 IPS
 
Image Super-Resolution (Q)
97% 3441
127.5 IPS
 
Text Classification (SP)
100% 540
721.0 IPS
 
Text Classification (HP)
99% 712
950.7 IPS
 
Text Classification (Q)
88% 664
895.9 IPS
 
Machine Translation (SP)
100% 1334
23.0 IPS
 
Machine Translation (HP)
100% 1396
24.0 IPS
 
Machine Translation (Q)
50% 548
19.5 IPS
 

Compare

Set Baseline Geekbench 6 now available