Geekbench AI Score

758
Single Precision Score
27884
Half Precision Score
62791
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 24 2025 04:38 AM
Views 3

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% 479
89.0 IPS
 
Image Classification (HP)
100% 21713
4.04 KIPS
 
Image Classification (Q)
97% 49584
9.25 KIPS
 
Image Segmentation (SP)
100% 608
9.86 IPS
 
Image Segmentation (HP)
100% 13682
221.8 IPS
 
Image Segmentation (Q)
98% 42300
687.8 IPS
 
Pose Estimation (SP)
100% 778
0.91 IPS
 
Pose Estimation (HP)
100% 123496
144.1 IPS
 
Pose Estimation (Q)
98% 480470
562.4 IPS
 
Object Detection (SP)
100% 453
35.9 IPS
 
Object Detection (HP)
100% 19946
1.58 KIPS
 
Object Detection (Q)
85% 22947
1.85 KIPS
 
Face Detection (SP)
100% 1120
13.3 IPS
 
Face Detection (HP)
100% 44464
528.3 IPS
 
Face Detection (Q)
97% 162175
1.93 KIPS
 
Depth Estimation (SP)
100% 976
7.52 IPS
 
Depth Estimation (HP)
99% 84609
651.9 IPS
 
Depth Estimation (Q)
63% 145435
1.35 KIPS
 
Style Transfer (SP)
100% 1612
2.07 IPS
 
Style Transfer (HP)
98% 98793
127.4 IPS
 
Style Transfer (Q)
98% 492150
634.6 IPS
 
Image Super-Resolution (SP)
100% 463
17.1 IPS
 
Image Super-Resolution (HP)
100% 54467
2.01 KIPS
 
Image Super-Resolution (Q)
97% 134169
4.97 KIPS
 
Text Classification (SP)
100% 687
916.8 IPS
 
Text Classification (HP)
100% 3920
5.23 KIPS
 
Text Classification (Q)
93% 8078
10.8 KIPS
 
Machine Translation (SP)
100% 1102
19.0 IPS
 
Machine Translation (HP)
100% 4894
84.3 IPS
 
Machine Translation (Q)
56% 3275
84.4 IPS
 

Compare

Set Baseline Geekbench 6 now available