Geekbench AI Score

263
Single Precision Score
16131
Half Precision Score
36423
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 26 2024 10:26 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
Model IDsamsung SM-S911B
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 6.89 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 161
30.0 IPS
 
Image Classification (HP)
100% 12589
2.34 KIPS
 
Image Classification (Q)
97% 32297
6.03 KIPS
 
Image Segmentation (SP)
100% 214
3.47 IPS
 
Image Segmentation (HP)
100% 7542
122.3 IPS
 
Image Segmentation (Q)
98% 21203
344.8 IPS
 
Pose Estimation (SP)
100% 290
0.34 IPS
 
Pose Estimation (HP)
100% 72350
84.4 IPS
 
Pose Estimation (Q)
98% 293486
343.5 IPS
 
Object Detection (SP)
100% 161
12.7 IPS
 
Object Detection (HP)
100% 11884
942.6 IPS
 
Object Detection (Q)
86% 13480
1.08 KIPS
 
Face Detection (SP)
100% 443
5.26 IPS
 
Face Detection (HP)
100% 23990
285.1 IPS
 
Face Detection (Q)
97% 83088
990.9 IPS
 
Depth Estimation (SP)
100% 381
2.94 IPS
 
Depth Estimation (HP)
99% 44703
344.4 IPS
 
Depth Estimation (Q)
63% 81579
763.9 IPS
 
Style Transfer (SP)
100% 626
0.80 IPS
 
Style Transfer (HP)
98% 60836
78.4 IPS
 
Style Transfer (Q)
98% 293032
377.9 IPS
 
Image Super-Resolution (SP)
100% 154
5.69 IPS
 
Image Super-Resolution (HP)
100% 32590
1.20 KIPS
 
Image Super-Resolution (Q)
97% 81841
3.03 KIPS
 
Text Classification (SP)
100% 185
247.5 IPS
 
Text Classification (HP)
100% 2473
3.30 KIPS
 
Text Classification (Q)
93% 5612
7.53 KIPS
 
Machine Translation (SP)
100% 330
5.68 IPS
 
Machine Translation (HP)
100% 2780
47.9 IPS
 
Machine Translation (Q)
55% 1663
43.6 IPS
 

Compare

Set Baseline Geekbench 6 now available