Geekbench AI Score

742
Single Precision Score
27976
Half Precision Score
63030
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date February 01 2025 11:55 PM
Views 10

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
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 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 464
86.3 IPS
 
Image Classification (HP)
100% 21952
4.08 KIPS
 
Image Classification (Q)
97% 49488
9.24 KIPS
 
Image Segmentation (SP)
100% 599
9.70 IPS
 
Image Segmentation (HP)
100% 13752
222.9 IPS
 
Image Segmentation (Q)
98% 42315
688.1 IPS
 
Pose Estimation (SP)
100% 774
0.90 IPS
 
Pose Estimation (HP)
100% 123351
143.9 IPS
 
Pose Estimation (Q)
98% 480900
562.9 IPS
 
Object Detection (SP)
100% 427
33.8 IPS
 
Object Detection (HP)
100% 19740
1.57 KIPS
 
Object Detection (Q)
85% 23074
1.86 KIPS
 
Face Detection (SP)
100% 1088
12.9 IPS
 
Face Detection (HP)
100% 44587
529.8 IPS
 
Face Detection (Q)
97% 162306
1.94 KIPS
 
Depth Estimation (SP)
100% 942
7.26 IPS
 
Depth Estimation (HP)
99% 85043
655.2 IPS
 
Depth Estimation (Q)
63% 147813
1.37 KIPS
 
Style Transfer (SP)
100% 1574
2.02 IPS
 
Style Transfer (HP)
98% 98916
127.6 IPS
 
Style Transfer (Q)
98% 496477
640.2 IPS
 
Image Super-Resolution (SP)
100% 497
18.4 IPS
 
Image Super-Resolution (HP)
100% 55576
2.05 KIPS
 
Image Super-Resolution (Q)
97% 135649
5.03 KIPS
 
Text Classification (SP)
100% 656
875.9 IPS
 
Text Classification (HP)
100% 3925
5.24 KIPS
 
Text Classification (Q)
93% 8082
10.8 KIPS
 
Machine Translation (SP)
100% 1057
18.2 IPS
 
Machine Translation (HP)
100% 4884
84.1 IPS
 
Machine Translation (Q)
56% 3262
84.0 IPS
 

Compare

Set Baseline Geekbench 6 now available