Geekbench AI Score

511
Single Precision Score
26863
Half Precision Score
60150
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date February 01 2025 04:07 PM
Views 23

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% 287
53.4 IPS
 
Image Classification (HP)
100% 20593
3.83 KIPS
 
Image Classification (Q)
97% 49067
9.16 KIPS
 
Image Segmentation (SP)
100% 405
6.57 IPS
 
Image Segmentation (HP)
100% 13654
221.3 IPS
 
Image Segmentation (Q)
98% 41851
680.5 IPS
 
Pose Estimation (SP)
100% 676
0.79 IPS
 
Pose Estimation (HP)
100% 120388
140.5 IPS
 
Pose Estimation (Q)
98% 477310
558.7 IPS
 
Object Detection (SP)
100% 366
29.0 IPS
 
Object Detection (HP)
100% 19190
1.52 KIPS
 
Object Detection (Q)
85% 22292
1.79 KIPS
 
Face Detection (SP)
100% 812
9.65 IPS
 
Face Detection (HP)
100% 41082
488.1 IPS
 
Face Detection (Q)
97% 140538
1.68 KIPS
 
Depth Estimation (SP)
100% 599
4.61 IPS
 
Depth Estimation (HP)
99% 83414
642.7 IPS
 
Depth Estimation (Q)
63% 142151
1.32 KIPS
 
Style Transfer (SP)
100% 1233
1.58 IPS
 
Style Transfer (HP)
98% 98684
127.3 IPS
 
Style Transfer (Q)
98% 491187
633.4 IPS
 
Image Super-Resolution (SP)
100% 314
11.6 IPS
 
Image Super-Resolution (HP)
100% 51604
1.91 KIPS
 
Image Super-Resolution (Q)
97% 125225
4.64 KIPS
 
Text Classification (SP)
100% 363
484.9 IPS
 
Text Classification (HP)
100% 3887
5.19 KIPS
 
Text Classification (Q)
93% 7841
10.5 KIPS
 
Machine Translation (SP)
100% 625
10.8 IPS
 
Machine Translation (HP)
100% 4441
76.5 IPS
 
Machine Translation (Q)
56% 2945
75.9 IPS
 

Compare

Set Baseline Geekbench 6 now available