Geekbench AI Score

137
Single Precision Score
138
Half Precision Score
402
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 02 2025 05:33 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 14
Model Xiaomi 24090RA29G
Model IDXiaomi 24090RA29G
Motherboard malachite
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.50 GHz
Memory Information
Size 7.25 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 81
15.1 IPS
 
Image Classification (HP)
100% 82
15.2 IPS
 
Image Classification (Q)
99% 266
49.7 IPS
 
Image Segmentation (SP)
100% 112
1.81 IPS
 
Image Segmentation (HP)
100% 113
1.82 IPS
 
Image Segmentation (Q)
98% 311
5.05 IPS
 
Pose Estimation (SP)
100% 139
0.16 IPS
 
Pose Estimation (HP)
100% 139
0.16 IPS
 
Pose Estimation (Q)
98% 573
0.67 IPS
 
Object Detection (SP)
100% 79
6.30 IPS
 
Object Detection (HP)
100% 80
6.33 IPS
 
Object Detection (Q)
87% 273
21.9 IPS
 
Face Detection (SP)
100% 229
2.72 IPS
 
Face Detection (HP)
100% 229
2.72 IPS
 
Face Detection (Q)
97% 614
7.32 IPS
 
Depth Estimation (SP)
100% 177
1.36 IPS
 
Depth Estimation (HP)
99% 178
1.37 IPS
 
Depth Estimation (Q)
64% 524
4.75 IPS
 
Style Transfer (SP)
100% 322
0.41 IPS
 
Style Transfer (HP)
100% 322
0.41 IPS
 
Style Transfer (Q)
98% 1074
1.39 IPS
 
Image Super-Resolution (SP)
100% 85
3.14 IPS
 
Image Super-Resolution (HP)
100% 85
3.14 IPS
 
Image Super-Resolution (Q)
97% 347
12.9 IPS
 
Text Classification (SP)
100% 116
154.3 IPS
 
Text Classification (HP)
100% 115
153.7 IPS
 
Text Classification (Q)
91% 289
388.0 IPS
 
Machine Translation (SP)
100% 194
3.34 IPS
 
Machine Translation (HP)
100% 193
3.32 IPS
 
Machine Translation (Q)
57% 248
6.05 IPS
 

Compare

Set Baseline Geekbench 6 now available