Geekbench AI Score

2581
Single Precision Score
2673
Half Precision Score
4097
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User eldavido
Upload Date December 22 2024 01:56 PM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-S721B
Model IDsamsung SM-S721B
Motherboard s5e9945
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 10 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.96 GHz
Cluster 14 Cores @ 1.96 GHz
Cluster 23 Cores @ 2.59 GHz
Cluster 32 Cores @ 2.90 GHz
Cluster 41 Core @ 3.11 GHz
Memory Information
Size 7.06 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1946
361.9 IPS
 
Image Classification (HP)
100% 2268
421.8 IPS
 
Image Classification (Q)
100% 3190
593.2 IPS
 
Image Segmentation (SP)
100% 2591
42.0 IPS
 
Image Segmentation (HP)
100% 2576
41.8 IPS
 
Image Segmentation (Q)
98% 3998
65.0 IPS
 
Pose Estimation (SP)
100% 3679
4.29 IPS
 
Pose Estimation (HP)
100% 3713
4.33 IPS
 
Pose Estimation (Q)
84% 8597
10.2 IPS
 
Object Detection (SP)
98% 1905
151.6 IPS
 
Object Detection (HP)
98% 1973
157.0 IPS
 
Object Detection (Q)
83% 2911
235.1 IPS
 
Face Detection (SP)
100% 3806
45.2 IPS
 
Face Detection (HP)
100% 3974
47.2 IPS
 
Face Detection (Q)
95% 6850
81.8 IPS
 
Depth Estimation (SP)
99% 3755
29.0 IPS
 
Depth Estimation (HP)
99% 3670
28.4 IPS
 
Depth Estimation (Q)
64% 5931
54.3 IPS
 
Style Transfer (SP)
89% 9693
12.6 IPS
 
Style Transfer (HP)
89% 9637
12.5 IPS
 
Style Transfer (Q)
98% 18176
23.4 IPS
 
Image Super-Resolution (SP)
100% 1924
71.0 IPS
 
Image Super-Resolution (HP)
100% 2106
77.8 IPS
 
Image Super-Resolution (Q)
97% 5019
186.0 IPS
 
Text Classification (SP)
100% 828
1.11 KIPS
 
Text Classification (HP)
99% 928
1.24 KIPS
 
Text Classification (Q)
88% 1449
1.95 KIPS
 
Machine Translation (SP)
100% 1685
29.0 IPS
 
Machine Translation (HP)
100% 1587
27.3 IPS
 
Machine Translation (Q)
50% 779
27.6 IPS
 

Compare

Set Baseline Geekbench 6 now available