Geekbench AI Score

1067
Single Precision Score
1446
Half Precision Score
1514
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

User jcardoso
Upload Date August 15 2024 10:42 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model asus ASUS_AI2401_D
Model IDasus ASUS_AI2401_D
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 @ 3.30 GHz
Memory Information
Size 22.74 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 851
158.2 IPS
 
Image Classification (HP)
100% 705
131.2 IPS
 
Image Classification (Q)
99% 741
138.2 IPS
 
Image Segmentation (SP)
100% 1318
21.4 IPS
 
Image Segmentation (HP)
100% 1162
18.8 IPS
 
Image Segmentation (Q)
98% 1086
17.7 IPS
 
Pose Estimation (SP)
100% 1064
1.24 IPS
 
Pose Estimation (HP)
100% 2178
2.54 IPS
 
Pose Estimation (Q)
96% 2138
2.50 IPS
 
Object Detection (SP)
100% 662
52.5 IPS
 
Object Detection (HP)
100% 741
58.8 IPS
 
Object Detection (Q)
89% 1088
87.1 IPS
 
Face Detection (SP)
100% 2714
32.2 IPS
 
Face Detection (HP)
100% 3285
39.0 IPS
 
Face Detection (Q)
97% 2817
33.6 IPS
 
Depth Estimation (SP)
100% 1752
13.5 IPS
 
Depth Estimation (HP)
99% 3483
26.8 IPS
 
Depth Estimation (Q)
74% 3406
27.8 IPS
 
Style Transfer (SP)
100% 5961
7.66 IPS
 
Style Transfer (HP)
100% 8919
11.5 IPS
 
Style Transfer (Q)
98% 9641
12.4 IPS
 
Image Super-Resolution (SP)
100% 485
17.9 IPS
 
Image Super-Resolution (HP)
100% 1654
61.1 IPS
 
Image Super-Resolution (Q)
97% 1609
59.6 IPS
 
Text Classification (SP)
100% 326
435.7 IPS
 
Text Classification (HP)
100% 329
438.7 IPS
 
Text Classification (Q)
91% 529
710.9 IPS
 
Machine Translation (SP)
100% 544
9.37 IPS
 
Machine Translation (HP)
100% 546
9.41 IPS
 
Machine Translation (Q)
57% 431
10.5 IPS
 

Compare

Set Baseline Geekbench 6 now available