Geekbench AI Score

186
Single Precision Score
187
Half Precision Score
411
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User bulmasen
Upload Date May 09 2025 07:42 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 720G
System Information
Operating System Android 12
Model Xiaomi Redmi Note 9 Pro
Model IDXiaomi Redmi Note 9 Pro
Motherboard joyeuse
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 15
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.32 GHz
Memory Information
Size 5.45 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 111
20.6 IPS
 
Image Classification (HP)
100% 112
20.8 IPS
 
Image Classification (Q)
99% 268
50.0 IPS
 
Image Segmentation (SP)
100% 152
2.47 IPS
 
Image Segmentation (HP)
100% 154
2.50 IPS
 
Image Segmentation (Q)
98% 280
4.55 IPS
 
Pose Estimation (SP)
100% 206
0.24 IPS
 
Pose Estimation (HP)
100% 205
0.24 IPS
 
Pose Estimation (Q)
98% 772
0.90 IPS
 
Object Detection (SP)
100% 112
8.88 IPS
 
Object Detection (HP)
100% 112
8.91 IPS
 
Object Detection (Q)
87% 300
24.1 IPS
 
Face Detection (SP)
100% 271
3.23 IPS
 
Face Detection (HP)
100% 278
3.31 IPS
 
Face Detection (Q)
97% 559
6.67 IPS
 
Depth Estimation (SP)
100% 234
1.80 IPS
 
Depth Estimation (HP)
99% 236
1.82 IPS
 
Depth Estimation (Q)
64% 550
4.99 IPS
 
Style Transfer (SP)
100% 383
0.49 IPS
 
Style Transfer (HP)
100% 385
0.49 IPS
 
Style Transfer (Q)
98% 1158
1.49 IPS
 
Image Super-Resolution (SP)
100% 116
4.28 IPS
 
Image Super-Resolution (HP)
100% 116
4.28 IPS
 
Image Super-Resolution (Q)
97% 404
15.0 IPS
 
Text Classification (SP)
100% 170
226.4 IPS
 
Text Classification (HP)
100% 170
227.1 IPS
 
Text Classification (Q)
91% 270
363.4 IPS
 
Machine Translation (SP)
100% 271
4.67 IPS
 
Machine Translation (HP)
100% 274
4.72 IPS
 
Machine Translation (Q)
57% 207
5.06 IPS
 

Compare

Set Baseline Geekbench 6 now available