Geekbench AI Score

523
Single Precision Score
22420
Half Precision Score
50978
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 21 2024 09:28 PM
Views 1

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-S928U
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% 324
60.3 IPS
 
Image Classification (HP)
100% 18390
3.42 KIPS
 
Image Classification (Q)
97% 40704
7.60 KIPS
 
Image Segmentation (SP)
100% 413
6.70 IPS
 
Image Segmentation (HP)
100% 10768
174.6 IPS
 
Image Segmentation (Q)
98% 31279
508.6 IPS
 
Pose Estimation (SP)
100% 561
0.65 IPS
 
Pose Estimation (HP)
100% 100373
117.1 IPS
 
Pose Estimation (Q)
98% 398419
466.3 IPS
 
Object Detection (SP)
100% 312
24.7 IPS
 
Object Detection (HP)
100% 16273
1.29 KIPS
 
Object Detection (Q)
86% 20275
1.63 KIPS
 
Face Detection (SP)
100% 761
9.04 IPS
 
Face Detection (HP)
100% 35341
419.9 IPS
 
Face Detection (Q)
97% 128070
1.53 KIPS
 
Depth Estimation (SP)
100% 675
5.20 IPS
 
Depth Estimation (HP)
99% 63525
489.4 IPS
 
Depth Estimation (Q)
63% 114564
1.07 KIPS
 
Style Transfer (SP)
100% 1066
1.37 IPS
 
Style Transfer (HP)
98% 85557
110.3 IPS
 
Style Transfer (Q)
98% 421984
544.2 IPS
 
Image Super-Resolution (SP)
100% 363
13.4 IPS
 
Image Super-Resolution (HP)
100% 45615
1.68 KIPS
 
Image Super-Resolution (Q)
97% 104144
3.86 KIPS
 
Text Classification (SP)
100% 453
604.8 IPS
 
Text Classification (HP)
100% 3090
4.12 KIPS
 
Text Classification (Q)
93% 6883
9.24 KIPS
 
Machine Translation (SP)
100% 729
12.6 IPS
 
Machine Translation (HP)
100% 3666
63.2 IPS
 
Machine Translation (Q)
55% 2597
68.0 IPS
 

Compare

Set Baseline Geekbench 6 now available