Geekbench AI Score

2288
Single Precision Score
2382
Half Precision Score
3411
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User harsidh
Upload Date September 26 2025 05:35 AM
Views 5

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% 1859
345.7 IPS
 
Image Classification (HP)
100% 2240
416.6 IPS
 
Image Classification (Q)
100% 3188
592.9 IPS
 
Image Segmentation (SP)
100% 1647
26.7 IPS
 
Image Segmentation (HP)
100% 2128
34.5 IPS
 
Image Segmentation (Q)
98% 3893
63.3 IPS
 
Pose Estimation (SP)
100% 3591
4.19 IPS
 
Pose Estimation (HP)
100% 3684
4.30 IPS
 
Pose Estimation (Q)
84% 8193
9.72 IPS
 
Object Detection (SP)
98% 1862
148.2 IPS
 
Object Detection (HP)
98% 2003
159.4 IPS
 
Object Detection (Q)
83% 2573
207.9 IPS
 
Face Detection (SP)
100% 3741
44.5 IPS
 
Face Detection (HP)
100% 3725
44.3 IPS
 
Face Detection (Q)
95% 6104
72.9 IPS
 
Depth Estimation (SP)
99% 3927
30.3 IPS
 
Depth Estimation (HP)
99% 3928
30.4 IPS
 
Depth Estimation (Q)
64% 5741
52.6 IPS
 
Style Transfer (SP)
89% 9318
12.1 IPS
 
Style Transfer (HP)
89% 8252
10.7 IPS
 
Style Transfer (Q)
98% 13579
17.5 IPS
 
Image Super-Resolution (SP)
100% 1589
58.7 IPS
 
Image Super-Resolution (HP)
100% 1587
58.6 IPS
 
Image Super-Resolution (Q)
97% 3207
118.8 IPS
 
Text Classification (SP)
100% 591
789.5 IPS
 
Text Classification (HP)
99% 591
789.2 IPS
 
Text Classification (Q)
88% 878
1.18 KIPS
 
Machine Translation (SP)
100% 1496
25.8 IPS
 
Machine Translation (HP)
100% 1478
25.5 IPS
 
Machine Translation (Q)
50% 609
21.6 IPS
 

Compare

Set Baseline Geekbench 6 now available