Geekbench AI Score

2399
Single Precision Score
2383
Half Precision Score
3720
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User epicgeek
Upload Date August 25 2025 04:17 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
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% 1930
359.0 IPS
 
Image Classification (HP)
100% 1843
342.7 IPS
 
Image Classification (Q)
100% 3211
597.2 IPS
 
Image Segmentation (SP)
100% 2438
39.5 IPS
 
Image Segmentation (HP)
100% 2413
39.1 IPS
 
Image Segmentation (Q)
98% 3966
64.5 IPS
 
Pose Estimation (SP)
100% 3793
4.43 IPS
 
Pose Estimation (HP)
100% 3599
4.20 IPS
 
Pose Estimation (Q)
84% 8421
9.99 IPS
 
Object Detection (SP)
98% 1786
142.1 IPS
 
Object Detection (HP)
98% 1891
150.5 IPS
 
Object Detection (Q)
83% 2869
231.7 IPS
 
Face Detection (SP)
100% 3910
46.5 IPS
 
Face Detection (HP)
100% 3640
43.2 IPS
 
Face Detection (Q)
95% 6770
80.8 IPS
 
Depth Estimation (SP)
99% 3293
25.4 IPS
 
Depth Estimation (HP)
99% 3373
26.1 IPS
 
Depth Estimation (Q)
64% 6164
56.5 IPS
 
Style Transfer (SP)
89% 9293
12.1 IPS
 
Style Transfer (HP)
89% 9052
11.8 IPS
 
Style Transfer (Q)
98% 17895
23.1 IPS
 
Image Super-Resolution (SP)
100% 1782
65.8 IPS
 
Image Super-Resolution (HP)
100% 1784
65.9 IPS
 
Image Super-Resolution (Q)
97% 3820
141.6 IPS
 
Text Classification (SP)
100% 634
846.4 IPS
 
Text Classification (HP)
99% 619
826.6 IPS
 
Text Classification (Q)
88% 1026
1.38 KIPS
 
Machine Translation (SP)
100% 1467
25.3 IPS
 
Machine Translation (HP)
100% 1594
27.5 IPS
 
Machine Translation (Q)
50% 565
20.1 IPS
 

Compare

Set Baseline Geekbench 6 now available