Geekbench AI Score

744
Single Precision Score
27894
Half Precision Score
62869
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 25 2025 03:27 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
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% 467
86.9 IPS
 
Image Classification (HP)
100% 21359
3.97 KIPS
 
Image Classification (Q)
97% 49639
9.26 KIPS
 
Image Segmentation (SP)
100% 595
9.65 IPS
 
Image Segmentation (HP)
100% 13715
222.3 IPS
 
Image Segmentation (Q)
98% 42321
688.2 IPS
 
Pose Estimation (SP)
100% 762
0.89 IPS
 
Pose Estimation (HP)
100% 124054
144.8 IPS
 
Pose Estimation (Q)
98% 480173
562.0 IPS
 
Object Detection (SP)
100% 434
34.4 IPS
 
Object Detection (HP)
100% 19763
1.57 KIPS
 
Object Detection (Q)
85% 23269
1.87 KIPS
 
Face Detection (SP)
100% 1084
12.9 IPS
 
Face Detection (HP)
100% 44350
527.0 IPS
 
Face Detection (Q)
97% 161510
1.93 KIPS
 
Depth Estimation (SP)
100% 957
7.37 IPS
 
Depth Estimation (HP)
99% 84863
653.8 IPS
 
Depth Estimation (Q)
63% 147337
1.36 KIPS
 
Style Transfer (SP)
100% 1545
1.99 IPS
 
Style Transfer (HP)
98% 98973
127.6 IPS
 
Style Transfer (Q)
98% 492094
634.6 IPS
 
Image Super-Resolution (SP)
100% 502
18.5 IPS
 
Image Super-Resolution (HP)
100% 55344
2.04 KIPS
 
Image Super-Resolution (Q)
97% 135577
5.02 KIPS
 
Text Classification (SP)
100% 662
883.8 IPS
 
Text Classification (HP)
100% 3942
5.26 KIPS
 
Text Classification (Q)
93% 8070
10.8 KIPS
 
Machine Translation (SP)
100% 1069
18.4 IPS
 
Machine Translation (HP)
100% 4887
84.2 IPS
 
Machine Translation (Q)
56% 3208
82.7 IPS
 

Compare

Set Baseline Geekbench 6 now available