Geekbench AI Score

723
Single Precision Score
27889
Half Precision Score
62777
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 27 2025 05:20 PM
Views 4

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% 467
86.8 IPS
 
Image Classification (HP)
100% 21936
4.08 KIPS
 
Image Classification (Q)
97% 49474
9.23 KIPS
 
Image Segmentation (SP)
100% 598
9.70 IPS
 
Image Segmentation (HP)
100% 13679
221.8 IPS
 
Image Segmentation (Q)
98% 42650
693.5 IPS
 
Pose Estimation (SP)
100% 769
0.90 IPS
 
Pose Estimation (HP)
100% 123951
144.6 IPS
 
Pose Estimation (Q)
98% 479439
561.2 IPS
 
Object Detection (SP)
100% 392
31.1 IPS
 
Object Detection (HP)
100% 19513
1.55 KIPS
 
Object Detection (Q)
85% 22519
1.81 KIPS
 
Face Detection (SP)
100% 1106
13.1 IPS
 
Face Detection (HP)
100% 44398
527.5 IPS
 
Face Detection (Q)
97% 162385
1.94 KIPS
 
Depth Estimation (SP)
100% 963
7.42 IPS
 
Depth Estimation (HP)
99% 84468
650.8 IPS
 
Depth Estimation (Q)
63% 146339
1.35 KIPS
 
Style Transfer (SP)
100% 1427
1.83 IPS
 
Style Transfer (HP)
98% 99047
127.7 IPS
 
Style Transfer (Q)
98% 495188
638.5 IPS
 
Image Super-Resolution (SP)
100% 458
16.9 IPS
 
Image Super-Resolution (HP)
100% 55515
2.05 KIPS
 
Image Super-Resolution (Q)
97% 135466
5.02 KIPS
 
Text Classification (SP)
100% 622
830.0 IPS
 
Text Classification (HP)
100% 3936
5.25 KIPS
 
Text Classification (Q)
93% 8058
10.8 KIPS
 
Machine Translation (SP)
100% 1085
18.7 IPS
 
Machine Translation (HP)
100% 4834
83.3 IPS
 
Machine Translation (Q)
56% 3249
83.7 IPS
 

Compare

Set Baseline Geekbench 6 now available