Geekbench AI Score

403
Single Precision Score
22065
Half Precision Score
50419
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User mihun70
Upload Date January 19 2025 09:57 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-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% 316
58.8 IPS
 
Image Classification (HP)
100% 18222
3.39 KIPS
 
Image Classification (Q)
97% 42648
7.96 KIPS
 
Image Segmentation (SP)
100% 393
6.36 IPS
 
Image Segmentation (HP)
100% 11034
178.9 IPS
 
Image Segmentation (Q)
98% 31587
513.6 IPS
 
Pose Estimation (SP)
100% 514
0.60 IPS
 
Pose Estimation (HP)
100% 100393
117.1 IPS
 
Pose Estimation (Q)
98% 398085
465.9 IPS
 
Object Detection (SP)
100% 205
16.3 IPS
 
Object Detection (HP)
100% 15692
1.24 KIPS
 
Object Detection (Q)
86% 19582
1.57 KIPS
 
Face Detection (SP)
100% 548
6.51 IPS
 
Face Detection (HP)
100% 34389
408.6 IPS
 
Face Detection (Q)
97% 117291
1.40 KIPS
 
Depth Estimation (SP)
100% 487
3.75 IPS
 
Depth Estimation (HP)
99% 63408
488.5 IPS
 
Depth Estimation (Q)
63% 114741
1.07 KIPS
 
Style Transfer (SP)
100% 790
1.02 IPS
 
Style Transfer (HP)
98% 85050
109.7 IPS
 
Style Transfer (Q)
98% 422060
544.3 IPS
 
Image Super-Resolution (SP)
100% 267
9.86 IPS
 
Image Super-Resolution (HP)
100% 44296
1.64 KIPS
 
Image Super-Resolution (Q)
97% 103592
3.84 KIPS
 
Text Classification (SP)
100% 300
401.0 IPS
 
Text Classification (HP)
100% 3043
4.06 KIPS
 
Text Classification (Q)
93% 6831
9.17 KIPS
 
Machine Translation (SP)
100% 513
8.83 IPS
 
Machine Translation (HP)
100% 3456
59.5 IPS
 
Machine Translation (Q)
55% 2515
65.9 IPS
 

Compare

Set Baseline Geekbench 6 now available