Geekbench AI Score

466
Single Precision Score
16343
Half Precision Score
39841
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 02:34 AM
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-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 10.81 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 291
54.2 IPS
 
Image Classification (HP)
100% 17481
3.25 KIPS
 
Image Classification (Q)
97% 43265
8.07 KIPS
 
Image Segmentation (SP)
100% 351
5.69 IPS
 
Image Segmentation (HP)
100% 11040
179.0 IPS
 
Image Segmentation (Q)
98% 29363
477.5 IPS
 
Pose Estimation (SP)
100% 480
0.56 IPS
 
Pose Estimation (HP)
100% 98356
114.8 IPS
 
Pose Estimation (Q)
98% 398630
466.6 IPS
 
Object Detection (SP)
100% 274
21.7 IPS
 
Object Detection (HP)
100% 16389
1.30 KIPS
 
Object Detection (Q)
86% 19364
1.56 KIPS
 
Face Detection (SP)
100% 688
8.17 IPS
 
Face Detection (HP)
100% 35692
424.1 IPS
 
Face Detection (Q)
97% 127625
1.52 KIPS
 
Depth Estimation (SP)
100% 594
4.57 IPS
 
Depth Estimation (HP)
99% 61992
477.6 IPS
 
Depth Estimation (Q)
63% 117505
1.10 KIPS
 
Style Transfer (SP)
100% 986
1.27 IPS
 
Style Transfer (HP)
24% 3860
116.8 IPS
 
Style Transfer (Q)
98% 306394
395.1 IPS
 
Image Super-Resolution (SP)
100% 316
11.7 IPS
 
Image Super-Resolution (HP)
100% 44459
1.64 KIPS
 
Image Super-Resolution (Q)
97% 114835
4.26 KIPS
 
Text Classification (SP)
100% 420
560.2 IPS
 
Text Classification (HP)
100% 3103
4.14 KIPS
 
Text Classification (Q)
93% 6763
9.08 KIPS
 
Machine Translation (SP)
100% 675
11.6 IPS
 
Machine Translation (HP)
100% 3709
63.9 IPS
 
Machine Translation (Q)
30% 288
57.8 IPS
 

Compare

Set Baseline Geekbench 6 now available