Geekbench AI Score

475
Single Precision Score
468
Half Precision Score
1097
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

User matus201
Upload Date August 27 2024 11:48 PM
Views 10

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
Model IDsamsung SM-S921W
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 6.93 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 307
57.0 IPS
 
Image Classification (HP)
100% 289
53.8 IPS
 
Image Classification (Q)
97% 766
142.9 IPS
 
Image Segmentation (SP)
100% 368
5.97 IPS
 
Image Segmentation (HP)
100% 366
5.94 IPS
 
Image Segmentation (Q)
98% 766
12.5 IPS
 
Pose Estimation (SP)
100% 491
0.57 IPS
 
Pose Estimation (HP)
100% 478
0.56 IPS
 
Pose Estimation (Q)
98% 1869
2.19 IPS
 
Object Detection (SP)
100% 282
22.4 IPS
 
Object Detection (HP)
100% 277
22.0 IPS
 
Object Detection (Q)
89% 814
65.2 IPS
 
Face Detection (SP)
100% 690
8.20 IPS
 
Face Detection (HP)
100% 669
7.95 IPS
 
Face Detection (Q)
97% 1588
18.9 IPS
 
Depth Estimation (SP)
100% 598
4.60 IPS
 
Depth Estimation (HP)
100% 596
4.59 IPS
 
Depth Estimation (Q)
73% 1625
13.3 IPS
 
Style Transfer (SP)
100% 965
1.24 IPS
 
Style Transfer (HP)
100% 968
1.24 IPS
 
Style Transfer (Q)
98% 2424
3.13 IPS
 
Image Super-Resolution (SP)
100% 324
12.0 IPS
 
Image Super-Resolution (HP)
100% 326
12.0 IPS
 
Image Super-Resolution (Q)
97% 1113
41.2 IPS
 
Text Classification (SP)
100% 428
570.8 IPS
 
Text Classification (HP)
100% 437
583.9 IPS
 
Text Classification (Q)
91% 722
970.6 IPS
 
Machine Translation (SP)
100% 683
11.8 IPS
 
Machine Translation (HP)
100% 656
11.3 IPS
 
Machine Translation (Q)
57% 565
13.8 IPS
 

Compare

Set Baseline Geekbench 6 now available