Geekbench AI Score

1023
Single Precision Score
1491
Half Precision Score
1552
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 02:26 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
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% 439
81.7 IPS
 
Image Classification (HP)
100% 703
130.8 IPS
 
Image Classification (Q)
96% 749
139.8 IPS
 
Image Segmentation (SP)
100% 1151
18.7 IPS
 
Image Segmentation (HP)
100% 1142
18.5 IPS
 
Image Segmentation (Q)
98% 1705
27.7 IPS
 
Pose Estimation (SP)
100% 1123
1.31 IPS
 
Pose Estimation (HP)
100% 2253
2.63 IPS
 
Pose Estimation (Q)
96% 2261
2.65 IPS
 
Object Detection (SP)
100% 645
51.2 IPS
 
Object Detection (HP)
100% 1021
81.0 IPS
 
Object Detection (Q)
87% 683
54.8 IPS
 
Face Detection (SP)
100% 2355
28.0 IPS
 
Face Detection (HP)
100% 1869
22.2 IPS
 
Face Detection (Q)
97% 2352
28.1 IPS
 
Depth Estimation (SP)
100% 1764
13.6 IPS
 
Depth Estimation (HP)
99% 3687
28.5 IPS
 
Depth Estimation (Q)
63% 3047
28.2 IPS
 
Style Transfer (SP)
100% 6144
7.90 IPS
 
Style Transfer (HP)
100% 9986
12.8 IPS
 
Style Transfer (Q)
98% 9914
12.8 IPS
 
Image Super-Resolution (SP)
100% 425
15.7 IPS
 
Image Super-Resolution (HP)
100% 1366
50.4 IPS
 
Image Super-Resolution (Q)
97% 1327
49.2 IPS
 
Text Classification (SP)
100% 452
602.9 IPS
 
Text Classification (HP)
100% 453
605.1 IPS
 
Text Classification (Q)
91% 740
994.3 IPS
 
Machine Translation (SP)
100% 701
12.1 IPS
 
Machine Translation (HP)
100% 695
12.0 IPS
 
Machine Translation (Q)
57% 592
14.5 IPS
 

Compare

Set Baseline Geekbench 6 now available