Geekbench AI Score

377
Single Precision Score
21572
Half Precision Score
49117
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 25 2024 07:01 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 14
Model Samsung Galaxy S24 Ultra
Model IDsamsung SM-S928B
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.40 GHz
Memory Information
Size 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 308
57.3 IPS
 
Image Classification (HP)
100% 18166
3.38 KIPS
 
Image Classification (Q)
97% 40511
7.56 KIPS
 
Image Segmentation (SP)
100% 379
6.14 IPS
 
Image Segmentation (HP)
100% 10750
174.3 IPS
 
Image Segmentation (Q)
98% 30919
502.8 IPS
 
Pose Estimation (SP)
100% 486
0.57 IPS
 
Pose Estimation (HP)
100% 100148
116.9 IPS
 
Pose Estimation (Q)
98% 397843
465.7 IPS
 
Object Detection (SP)
100% 204
16.2 IPS
 
Object Detection (HP)
100% 15122
1.20 KIPS
 
Object Detection (Q)
86% 19222
1.55 KIPS
 
Face Detection (SP)
100% 489
5.81 IPS
 
Face Detection (HP)
100% 31960
379.8 IPS
 
Face Detection (Q)
97% 107638
1.28 KIPS
 
Depth Estimation (SP)
100% 451
3.48 IPS
 
Depth Estimation (HP)
99% 60615
467.0 IPS
 
Depth Estimation (Q)
63% 108106
1.01 KIPS
 
Style Transfer (SP)
100% 704
0.91 IPS
 
Style Transfer (HP)
98% 84939
109.5 IPS
 
Style Transfer (Q)
98% 420940
542.8 IPS
 
Image Super-Resolution (SP)
100% 250
9.23 IPS
 
Image Super-Resolution (HP)
100% 44270
1.63 KIPS
 
Image Super-Resolution (Q)
97% 103917
3.85 KIPS
 
Text Classification (SP)
100% 289
385.1 IPS
 
Text Classification (HP)
100% 3056
4.08 KIPS
 
Text Classification (Q)
93% 6856
9.20 KIPS
 
Machine Translation (SP)
100% 448
7.71 IPS
 
Machine Translation (HP)
100% 3316
57.1 IPS
 
Machine Translation (Q)
55% 2445
64.0 IPS
 

Compare

Set Baseline Geekbench 6 now available