Geekbench AI Score

412
Single Precision Score
22017
Half Precision Score
49972
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date September 18 2025 01:53 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 16
Model Samsung Galaxy S24 Ultra
Model IDsamsung SM-S928U1
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% 313
58.2 IPS
 
Image Classification (HP)
100% 18403
3.42 KIPS
 
Image Classification (Q)
97% 40019
7.47 KIPS
 
Image Segmentation (SP)
100% 390
6.33 IPS
 
Image Segmentation (HP)
100% 10840
175.7 IPS
 
Image Segmentation (Q)
98% 31341
509.6 IPS
 
Pose Estimation (SP)
100% 517
0.60 IPS
 
Pose Estimation (HP)
100% 100164
116.9 IPS
 
Pose Estimation (Q)
98% 398205
466.1 IPS
 
Object Detection (SP)
100% 227
18.0 IPS
 
Object Detection (HP)
100% 15420
1.22 KIPS
 
Object Detection (Q)
86% 19566
1.57 KIPS
 
Face Detection (SP)
100% 523
6.21 IPS
 
Face Detection (HP)
100% 32270
383.4 IPS
 
Face Detection (Q)
97% 109805
1.31 KIPS
 
Depth Estimation (SP)
100% 497
3.83 IPS
 
Depth Estimation (HP)
99% 63228
487.1 IPS
 
Depth Estimation (Q)
63% 114843
1.08 KIPS
 
Style Transfer (SP)
100% 780
1.00 IPS
 
Style Transfer (HP)
98% 85357
110.1 IPS
 
Style Transfer (Q)
98% 422742
545.1 IPS
 
Image Super-Resolution (SP)
100% 272
10.0 IPS
 
Image Super-Resolution (HP)
100% 44211
1.63 KIPS
 
Image Super-Resolution (Q)
97% 103392
3.83 KIPS
 
Text Classification (SP)
100% 323
430.5 IPS
 
Text Classification (HP)
100% 3087
4.12 KIPS
 
Text Classification (Q)
93% 6893
9.25 KIPS
 
Machine Translation (SP)
100% 560
9.64 IPS
 
Machine Translation (HP)
100% 3656
63.0 IPS
 
Machine Translation (Q)
55% 2616
68.5 IPS
 

Compare

Set Baseline Geekbench 6 now available