Geekbench AI Score

738
Single Precision Score
27816
Half Precision Score
62787
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 24 2025 07:15 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S936N
Model IDsamsung SM-S936N
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% 472
87.9 IPS
 
Image Classification (HP)
100% 21373
3.97 KIPS
 
Image Classification (Q)
97% 49549
9.25 KIPS
 
Image Segmentation (SP)
100% 598
9.69 IPS
 
Image Segmentation (HP)
100% 13686
221.9 IPS
 
Image Segmentation (Q)
98% 42417
689.7 IPS
 
Pose Estimation (SP)
100% 776
0.91 IPS
 
Pose Estimation (HP)
100% 123404
144.0 IPS
 
Pose Estimation (Q)
98% 478084
559.6 IPS
 
Object Detection (SP)
100% 392
31.1 IPS
 
Object Detection (HP)
100% 19498
1.55 KIPS
 
Object Detection (Q)
85% 22522
1.81 KIPS
 
Face Detection (SP)
100% 1105
13.1 IPS
 
Face Detection (HP)
100% 44468
528.4 IPS
 
Face Detection (Q)
97% 163403
1.95 KIPS
 
Depth Estimation (SP)
100% 968
7.46 IPS
 
Depth Estimation (HP)
99% 84878
653.9 IPS
 
Depth Estimation (Q)
63% 147284
1.36 KIPS
 
Style Transfer (SP)
100% 1602
2.06 IPS
 
Style Transfer (HP)
98% 98759
127.3 IPS
 
Style Transfer (Q)
98% 492316
634.8 IPS
 
Image Super-Resolution (SP)
100% 446
16.5 IPS
 
Image Super-Resolution (HP)
100% 55037
2.03 KIPS
 
Image Super-Resolution (Q)
97% 135366
5.02 KIPS
 
Text Classification (SP)
100% 673
898.7 IPS
 
Text Classification (HP)
100% 3943
5.26 KIPS
 
Text Classification (Q)
93% 8042
10.8 KIPS
 
Machine Translation (SP)
100% 1086
18.7 IPS
 
Machine Translation (HP)
100% 4872
83.9 IPS
 
Machine Translation (Q)
56% 3262
84.0 IPS
 

Compare

Set Baseline Geekbench 6 now available