Geekbench AI Score

2170
Single Precision Score
2179
Half Precision Score
3406
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User androooooid8114471
Upload Date August 01 2025 05:27 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model Xiaomi 25053PC47G
Model IDXiaomi 25053PC47G
Motherboard sun
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 2.02 GHz
Cluster 12 Cores @ 2.02 GHz
Cluster 22 Cores @ 2.80 GHz
Cluster 33 Cores @ 3.01 GHz
Cluster 41 Core @ 3.21 GHz
Memory Information
Size 10.97 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1059
197.0 IPS
 
Image Classification (HP)
100% 891
165.7 IPS
 
Image Classification (Q)
100% 1412
262.7 IPS
 
Image Segmentation (SP)
100% 1876
30.4 IPS
 
Image Segmentation (HP)
100% 2131
34.5 IPS
 
Image Segmentation (Q)
98% 2550
41.5 IPS
 
Pose Estimation (SP)
100% 3683
4.30 IPS
 
Pose Estimation (HP)
100% 3811
4.45 IPS
 
Pose Estimation (Q)
84% 9108
10.8 IPS
 
Object Detection (SP)
98% 1541
122.6 IPS
 
Object Detection (HP)
98% 1556
123.8 IPS
 
Object Detection (Q)
83% 2628
212.2 IPS
 
Face Detection (SP)
100% 3532
42.0 IPS
 
Face Detection (HP)
100% 3630
43.1 IPS
 
Face Detection (Q)
95% 6801
81.2 IPS
 
Depth Estimation (SP)
99% 3923
30.3 IPS
 
Depth Estimation (HP)
99% 3411
26.4 IPS
 
Depth Estimation (Q)
64% 6928
63.5 IPS
 
Style Transfer (SP)
89% 10404
13.5 IPS
 
Style Transfer (HP)
89% 10341
13.4 IPS
 
Style Transfer (Q)
98% 19001
24.5 IPS
 
Image Super-Resolution (SP)
100% 1561
57.6 IPS
 
Image Super-Resolution (HP)
100% 1801
66.5 IPS
 
Image Super-Resolution (Q)
97% 4579
169.7 IPS
 
Text Classification (SP)
100% 823
1.10 KIPS
 
Text Classification (HP)
99% 789
1.05 KIPS
 
Text Classification (Q)
88% 1014
1.37 KIPS
 
Machine Translation (SP)
100% 1112
19.2 IPS
 
Machine Translation (HP)
100% 1182
20.4 IPS
 
Machine Translation (Q)
50% 588
20.9 IPS
 

Compare

Set Baseline Geekbench 6 now available