Geekbench AI Score

215
Single Precision Score
11598
Half Precision Score
26984
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 20 2024 06:09 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
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% 142
26.4 IPS
 
Image Classification (HP)
100% 12511
2.33 KIPS
 
Image Classification (Q)
97% 31243
5.83 KIPS
 
Image Segmentation (SP)
100% 188
3.05 IPS
 
Image Segmentation (HP)
100% 7381
119.7 IPS
 
Image Segmentation (Q)
98% 19677
320.0 IPS
 
Pose Estimation (SP)
100% 238
0.28 IPS
 
Pose Estimation (HP)
100% 71211
83.1 IPS
 
Pose Estimation (Q)
98% 292867
342.8 IPS
 
Object Detection (SP)
100% 125
9.93 IPS
 
Object Detection (HP)
100% 11461
909.1 IPS
 
Object Detection (Q)
86% 12303
989.3 IPS
 
Face Detection (SP)
100% 336
4.00 IPS
 
Face Detection (HP)
100% 22730
270.1 IPS
 
Face Detection (Q)
97% 72572
865.5 IPS
 
Depth Estimation (SP)
100% 275
2.12 IPS
 
Depth Estimation (HP)
99% 42316
326.0 IPS
 
Depth Estimation (Q)
63% 79336
742.9 IPS
 
Style Transfer (SP)
100% 475
0.61 IPS
 
Style Transfer (HP)
24% 2960
89.5 IPS
 
Style Transfer (Q)
98% 220452
284.3 IPS
 
Image Super-Resolution (SP)
100% 126
4.66 IPS
 
Image Super-Resolution (HP)
100% 31671
1.17 KIPS
 
Image Super-Resolution (Q)
97% 75969
2.82 KIPS
 
Text Classification (SP)
100% 164
218.4 IPS
 
Text Classification (HP)
100% 2457
3.28 KIPS
 
Text Classification (Q)
93% 5354
7.19 KIPS
 
Machine Translation (SP)
100% 300
5.16 IPS
 
Machine Translation (HP)
100% 2638
45.4 IPS
 
Machine Translation (Q)
30% 179
36.0 IPS
 

Compare

Set Baseline Geekbench 6 now available