Geekbench AI Score

390
Single Precision Score
16227
Half Precision Score
36823
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 06 2025 03:14 AM
Views 2

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-S911U
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% 306
56.9 IPS
 
Image Classification (HP)
100% 13071
2.43 KIPS
 
Image Classification (Q)
97% 32309
6.03 KIPS
 
Image Segmentation (SP)
100% 361
5.86 IPS
 
Image Segmentation (HP)
100% 7777
126.1 IPS
 
Image Segmentation (Q)
98% 21845
355.2 IPS
 
Pose Estimation (SP)
100% 478
0.56 IPS
 
Pose Estimation (HP)
100% 69111
80.6 IPS
 
Pose Estimation (Q)
98% 290860
340.4 IPS
 
Object Detection (SP)
100% 241
19.1 IPS
 
Object Detection (HP)
100% 12086
958.7 IPS
 
Object Detection (Q)
86% 13708
1.10 KIPS
 
Face Detection (SP)
100% 583
6.93 IPS
 
Face Detection (HP)
100% 24736
293.9 IPS
 
Face Detection (Q)
97% 87257
1.04 KIPS
 
Depth Estimation (SP)
100% 472
3.63 IPS
 
Depth Estimation (HP)
99% 44613
343.7 IPS
 
Depth Estimation (Q)
63% 81032
758.8 IPS
 
Style Transfer (SP)
100% 734
0.94 IPS
 
Style Transfer (HP)
98% 59310
76.5 IPS
 
Style Transfer (Q)
98% 292691
377.4 IPS
 
Image Super-Resolution (SP)
100% 231
8.52 IPS
 
Image Super-Resolution (HP)
100% 32569
1.20 KIPS
 
Image Super-Resolution (Q)
97% 81719
3.03 KIPS
 
Text Classification (SP)
100% 291
388.6 IPS
 
Text Classification (HP)
100% 2522
3.37 KIPS
 
Text Classification (Q)
93% 5591
7.50 KIPS
 
Machine Translation (SP)
100% 480
8.28 IPS
 
Machine Translation (HP)
100% 2774
47.8 IPS
 
Machine Translation (Q)
55% 1723
45.1 IPS
 

Compare

Set Baseline Geekbench 6 now available