Geekbench AI Score

1840
Single Precision Score
1849
Half Precision Score
2779
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User BrunoFoca
Upload Date February 16 2025 08:57 PM
Views 7

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 14
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 10.77 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1751
325.6 IPS
 
Image Classification (HP)
100% 1664
309.4 IPS
 
Image Classification (Q)
100% 2636
490.2 IPS
 
Image Segmentation (SP)
100% 1744
28.3 IPS
 
Image Segmentation (HP)
100% 1805
29.3 IPS
 
Image Segmentation (Q)
98% 2797
45.5 IPS
 
Pose Estimation (SP)
100% 2552
2.98 IPS
 
Pose Estimation (HP)
100% 2573
3.00 IPS
 
Pose Estimation (Q)
84% 5881
6.97 IPS
 
Object Detection (SP)
98% 1479
117.7 IPS
 
Object Detection (HP)
98% 1481
117.9 IPS
 
Object Detection (Q)
83% 2079
167.9 IPS
 
Face Detection (SP)
100% 2414
28.7 IPS
 
Face Detection (HP)
100% 2818
33.5 IPS
 
Face Detection (Q)
95% 4635
55.3 IPS
 
Depth Estimation (SP)
99% 2945
22.8 IPS
 
Depth Estimation (HP)
99% 2883
22.3 IPS
 
Depth Estimation (Q)
64% 3647
33.4 IPS
 
Style Transfer (SP)
89% 6024
7.82 IPS
 
Style Transfer (HP)
89% 6039
7.84 IPS
 
Style Transfer (Q)
98% 11252
14.5 IPS
 
Image Super-Resolution (SP)
100% 1325
48.9 IPS
 
Image Super-Resolution (HP)
100% 1283
47.4 IPS
 
Image Super-Resolution (Q)
97% 2891
107.1 IPS
 
Text Classification (SP)
100% 555
740.8 IPS
 
Text Classification (HP)
99% 532
710.3 IPS
 
Text Classification (Q)
88% 894
1.21 KIPS
 
Machine Translation (SP)
100% 1232
21.2 IPS
 
Machine Translation (HP)
100% 1221
21.0 IPS
 
Machine Translation (Q)
50% 622
22.1 IPS
 

Compare

Set Baseline Geekbench 6 now available