Geekbench AI Score

746
Single Precision Score
27717
Half Precision Score
63188
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 03 2025 02:31 PM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-S938B
Model IDsamsung SM-S938B
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% 455
84.7 IPS
 
Image Classification (HP)
100% 21402
3.98 KIPS
 
Image Classification (Q)
97% 50128
9.35 KIPS
 
Image Segmentation (SP)
100% 596
9.66 IPS
 
Image Segmentation (HP)
100% 13596
220.4 IPS
 
Image Segmentation (Q)
98% 42240
686.8 IPS
 
Pose Estimation (SP)
100% 766
0.89 IPS
 
Pose Estimation (HP)
100% 123675
144.3 IPS
 
Pose Estimation (Q)
98% 480987
563.0 IPS
 
Object Detection (SP)
100% 433
34.4 IPS
 
Object Detection (HP)
100% 19767
1.57 KIPS
 
Object Detection (Q)
85% 23315
1.88 KIPS
 
Face Detection (SP)
100% 1077
12.8 IPS
 
Face Detection (HP)
100% 43959
522.3 IPS
 
Face Detection (Q)
97% 162752
1.94 KIPS
 
Depth Estimation (SP)
100% 941
7.25 IPS
 
Depth Estimation (HP)
99% 84639
652.1 IPS
 
Depth Estimation (Q)
63% 146973
1.36 KIPS
 
Style Transfer (SP)
100% 1585
2.04 IPS
 
Style Transfer (HP)
98% 98903
127.5 IPS
 
Style Transfer (Q)
98% 495374
638.8 IPS
 
Image Super-Resolution (SP)
100% 507
18.7 IPS
 
Image Super-Resolution (HP)
100% 54011
1.99 KIPS
 
Image Super-Resolution (Q)
97% 135110
5.01 KIPS
 
Text Classification (SP)
100% 676
902.5 IPS
 
Text Classification (HP)
100% 3920
5.23 KIPS
 
Text Classification (Q)
93% 8204
11.0 KIPS
 
Machine Translation (SP)
100% 1079
18.6 IPS
 
Machine Translation (HP)
100% 4829
83.2 IPS
 
Machine Translation (Q)
56% 3254
83.8 IPS
 

Compare

Set Baseline Geekbench 6 now available