Geekbench AI Score

2071
Single Precision Score
2156
Half Precision Score
3466
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User Geraedus
Upload Date January 25 2026 08:39 AM
Views 12

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 16
Model Samsung Galaxy S23 Ultra
Model IDsamsung SM-S918B
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 6.91 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1350
251.1 IPS
 
Image Classification (HP)
100% 1781
331.2 IPS
 
Image Classification (Q)
100% 2817
523.9 IPS
 
Image Segmentation (SP)
100% 1992
32.3 IPS
 
Image Segmentation (HP)
100% 1936
31.4 IPS
 
Image Segmentation (Q)
98% 3052
49.6 IPS
 
Pose Estimation (SP)
100% 2822
3.29 IPS
 
Pose Estimation (HP)
100% 2891
3.37 IPS
 
Pose Estimation (Q)
84% 6736
7.99 IPS
 
Object Detection (SP)
98% 1689
134.4 IPS
 
Object Detection (HP)
98% 1675
133.3 IPS
 
Object Detection (Q)
83% 2533
204.6 IPS
 
Face Detection (SP)
100% 3167
37.6 IPS
 
Face Detection (HP)
100% 3131
37.2 IPS
 
Face Detection (Q)
95% 5283
63.1 IPS
 
Depth Estimation (SP)
99% 2901
22.4 IPS
 
Depth Estimation (HP)
99% 3034
23.4 IPS
 
Depth Estimation (Q)
64% 5510
50.5 IPS
 
Style Transfer (SP)
89% 7260
9.43 IPS
 
Style Transfer (HP)
89% 7253
9.42 IPS
 
Style Transfer (Q)
98% 13841
17.8 IPS
 
Image Super-Resolution (SP)
100% 1630
60.2 IPS
 
Image Super-Resolution (HP)
100% 1649
60.9 IPS
 
Image Super-Resolution (Q)
97% 3791
140.5 IPS
 
Text Classification (SP)
100% 785
1.05 KIPS
 
Text Classification (HP)
99% 795
1.06 KIPS
 
Text Classification (Q)
88% 1427
1.92 KIPS
 
Machine Translation (SP)
100% 1327
22.9 IPS
 
Machine Translation (HP)
100% 1443
24.9 IPS
 
Machine Translation (Q)
50% 784
27.8 IPS
 

Compare

Set Baseline Geekbench 6 now available