Geekbench AI Score

544
Single Precision Score
26895
Half Precision Score
60296
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date February 25 2025 11:59 PM
Views 27

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% 434
80.8 IPS
 
Image Classification (HP)
100% 21236
3.95 KIPS
 
Image Classification (Q)
97% 49349
9.21 KIPS
 
Image Segmentation (SP)
100% 572
9.28 IPS
 
Image Segmentation (HP)
100% 13707
222.2 IPS
 
Image Segmentation (Q)
98% 42386
689.2 IPS
 
Pose Estimation (SP)
100% 596
0.70 IPS
 
Pose Estimation (HP)
100% 123448
144.0 IPS
 
Pose Estimation (Q)
98% 477465
558.8 IPS
 
Object Detection (SP)
100% 268
21.3 IPS
 
Object Detection (HP)
100% 18206
1.44 KIPS
 
Object Detection (Q)
85% 21028
1.69 KIPS
 
Face Detection (SP)
100% 653
7.75 IPS
 
Face Detection (HP)
100% 39851
473.5 IPS
 
Face Detection (Q)
97% 132203
1.58 KIPS
 
Depth Estimation (SP)
100% 669
5.15 IPS
 
Depth Estimation (HP)
99% 83817
645.8 IPS
 
Depth Estimation (Q)
63% 144916
1.34 KIPS
 
Style Transfer (SP)
100% 1351
1.74 IPS
 
Style Transfer (HP)
98% 98400
126.9 IPS
 
Style Transfer (Q)
98% 488913
630.5 IPS
 
Image Super-Resolution (SP)
100% 317
11.7 IPS
 
Image Super-Resolution (HP)
100% 51892
1.92 KIPS
 
Image Super-Resolution (Q)
97% 131065
4.86 KIPS
 
Text Classification (SP)
100% 395
527.1 IPS
 
Text Classification (HP)
100% 3894
5.20 KIPS
 
Text Classification (Q)
93% 7963
10.7 KIPS
 
Machine Translation (SP)
100% 783
13.5 IPS
 
Machine Translation (HP)
100% 4558
78.5 IPS
 
Machine Translation (Q)
56% 3094
79.7 IPS
 

Compare

Set Baseline Geekbench 6 now available