Geekbench AI Score

456
Single Precision Score
16150
Half Precision Score
38846
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 16 2024 07:10 AM
Views 17

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% 270
50.2 IPS
 
Image Classification (HP)
100% 17322
3.22 KIPS
 
Image Classification (Q)
97% 41037
7.66 KIPS
 
Image Segmentation (SP)
100% 361
5.85 IPS
 
Image Segmentation (HP)
100% 10764
174.5 IPS
 
Image Segmentation (Q)
98% 29166
474.3 IPS
 
Pose Estimation (SP)
100% 485
0.57 IPS
 
Pose Estimation (HP)
100% 99883
116.5 IPS
 
Pose Estimation (Q)
98% 399179
467.2 IPS
 
Object Detection (SP)
100% 272
21.5 IPS
 
Object Detection (HP)
100% 16081
1.28 KIPS
 
Object Detection (Q)
86% 19204
1.54 KIPS
 
Face Detection (SP)
100% 659
7.83 IPS
 
Face Detection (HP)
100% 35163
417.8 IPS
 
Face Detection (Q)
97% 124219
1.48 KIPS
 
Depth Estimation (SP)
100% 583
4.49 IPS
 
Depth Estimation (HP)
99% 61015
470.1 IPS
 
Depth Estimation (Q)
63% 114272
1.07 KIPS
 
Style Transfer (SP)
100% 928
1.19 IPS
 
Style Transfer (HP)
24% 3860
116.8 IPS
 
Style Transfer (Q)
98% 306265
394.9 IPS
 
Image Super-Resolution (SP)
100% 328
12.1 IPS
 
Image Super-Resolution (HP)
100% 44391
1.64 KIPS
 
Image Super-Resolution (Q)
97% 104905
3.89 KIPS
 
Text Classification (SP)
100% 404
539.6 IPS
 
Text Classification (HP)
100% 3097
4.13 KIPS
 
Text Classification (Q)
93% 6727
9.03 KIPS
 
Machine Translation (SP)
100% 640
11.0 IPS
 
Machine Translation (HP)
100% 3542
61.0 IPS
 
Machine Translation (Q)
30% 278
55.8 IPS
 

Compare

Set Baseline Geekbench 6 now available