Geekbench AI Score

403
Single Precision Score
16464
Half Precision Score
37188
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date July 06 2025 04:32 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 15
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 10.79 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 271
50.5 IPS
 
Image Classification (HP)
100% 12924
2.40 KIPS
 
Image Classification (Q)
97% 32509
6.07 KIPS
 
Image Segmentation (SP)
100% 321
5.21 IPS
 
Image Segmentation (HP)
100% 7760
125.8 IPS
 
Image Segmentation (Q)
98% 21878
355.7 IPS
 
Pose Estimation (SP)
100% 450
0.53 IPS
 
Pose Estimation (HP)
100% 71271
83.2 IPS
 
Pose Estimation (Q)
98% 294734
345.0 IPS
 
Object Detection (SP)
100% 232
18.4 IPS
 
Object Detection (HP)
100% 12206
968.2 IPS
 
Object Detection (Q)
86% 13859
1.11 KIPS
 
Face Detection (SP)
100% 575
6.84 IPS
 
Face Detection (HP)
100% 25034
297.5 IPS
 
Face Detection (Q)
97% 85207
1.02 KIPS
 
Depth Estimation (SP)
100% 507
3.91 IPS
 
Depth Estimation (HP)
99% 45100
347.5 IPS
 
Depth Estimation (Q)
63% 82314
770.8 IPS
 
Style Transfer (SP)
100% 832
1.07 IPS
 
Style Transfer (HP)
98% 60506
78.0 IPS
 
Style Transfer (Q)
98% 294775
380.1 IPS
 
Image Super-Resolution (SP)
100% 268
9.89 IPS
 
Image Super-Resolution (HP)
100% 32710
1.21 KIPS
 
Image Super-Resolution (Q)
97% 82233
3.05 KIPS
 
Text Classification (SP)
100% 336
448.5 IPS
 
Text Classification (HP)
100% 2538
3.39 KIPS
 
Text Classification (Q)
93% 5643
7.57 KIPS
 
Machine Translation (SP)
100% 575
9.91 IPS
 
Machine Translation (HP)
100% 2959
51.0 IPS
 
Machine Translation (Q)
55% 1815
47.6 IPS
 

Compare

Set Baseline Geekbench 6 now available