Geekbench AI Score

2474
Single Precision Score
2512
Half Precision Score
3956
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Alan156
Upload Date December 02 2024 08:51 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-S721W
Model IDsamsung SM-S721W
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% 1839
341.9 IPS
 
Image Classification (HP)
100% 2182
405.7 IPS
 
Image Classification (Q)
100% 3107
577.8 IPS
 
Image Segmentation (SP)
100% 2327
37.7 IPS
 
Image Segmentation (HP)
100% 2292
37.2 IPS
 
Image Segmentation (Q)
98% 3714
60.4 IPS
 
Pose Estimation (SP)
100% 3658
4.27 IPS
 
Pose Estimation (HP)
100% 3686
4.30 IPS
 
Pose Estimation (Q)
84% 8471
10.0 IPS
 
Object Detection (SP)
98% 1879
149.6 IPS
 
Object Detection (HP)
98% 1935
154.0 IPS
 
Object Detection (Q)
83% 2565
207.2 IPS
 
Face Detection (SP)
100% 3677
43.7 IPS
 
Face Detection (HP)
100% 3838
45.6 IPS
 
Face Detection (Q)
95% 6511
77.7 IPS
 
Depth Estimation (SP)
99% 3777
29.2 IPS
 
Depth Estimation (HP)
99% 3434
26.5 IPS
 
Depth Estimation (Q)
64% 6598
60.4 IPS
 
Style Transfer (SP)
89% 9259
12.0 IPS
 
Style Transfer (HP)
89% 8336
10.8 IPS
 
Style Transfer (Q)
98% 18174
23.4 IPS
 
Image Super-Resolution (SP)
100% 1968
72.7 IPS
 
Image Super-Resolution (HP)
100% 1960
72.4 IPS
 
Image Super-Resolution (Q)
97% 4857
180.0 IPS
 
Text Classification (SP)
100% 836
1.12 KIPS
 
Text Classification (HP)
99% 832
1.11 KIPS
 
Text Classification (Q)
88% 1283
1.73 KIPS
 
Machine Translation (SP)
100% 1382
23.8 IPS
 
Machine Translation (HP)
100% 1571
27.1 IPS
 
Machine Translation (Q)
50% 771
27.4 IPS
 

Compare

Set Baseline Geekbench 6 now available