Geekbench AI Score

1865
Single Precision Score
3081
Half Precision Score
2863
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User kyhwana2
Upload Date July 17 2025 07:49 AM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 13
Model AYN Odin2
Model IDAYN Odin2
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 11.01 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1125
209.3 IPS
 
Image Classification (HP)
100% 1782
331.3 IPS
 
Image Classification (Q)
99% 1673
312.1 IPS
 
Image Segmentation (SP)
100% 2251
36.5 IPS
 
Image Segmentation (HP)
100% 3892
63.1 IPS
 
Image Segmentation (Q)
98% 3784
61.5 IPS
 
Pose Estimation (SP)
100% 7998
9.33 IPS
 
Pose Estimation (HP)
99% 14662
17.1 IPS
 
Pose Estimation (Q)
97% 14505
17.0 IPS
 
Object Detection (SP)
100% 1008
80.0 IPS
 
Object Detection (HP)
99% 1624
128.8 IPS
 
Object Detection (Q)
85% 1500
120.7 IPS
 
Face Detection (SP)
100% 4227
50.2 IPS
 
Face Detection (HP)
100% 7292
86.6 IPS
 
Face Detection (Q)
97% 6304
75.2 IPS
 
Depth Estimation (SP)
100% 4273
32.9 IPS
 
Depth Estimation (HP)
98% 6272
48.5 IPS
 
Depth Estimation (Q)
65% 5257
47.2 IPS
 
Style Transfer (SP)
100% 10200
13.1 IPS
 
Style Transfer (HP)
100% 22552
29.0 IPS
 
Style Transfer (Q)
98% 22602
29.1 IPS
 
Image Super-Resolution (SP)
100% 2372
87.6 IPS
 
Image Super-Resolution (HP)
100% 3675
135.7 IPS
 
Image Super-Resolution (Q)
97% 3692
136.8 IPS
 
Text Classification (SP)
35% 55
532.0 IPS
 
Text Classification (HP)
35% 97
877.8 IPS
 
Text Classification (Q)
35% 94
858.1 IPS
 
Machine Translation (SP)
100% 1040
17.9 IPS
 
Machine Translation (HP)
97% 1271
22.0 IPS
 
Machine Translation (Q)
64% 1035
21.3 IPS
 

Compare

Set Baseline Geekbench 6 now available