Geekbench AI Score

176
Single Precision Score
261
Half Precision Score
259
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User bulmasen
Upload Date May 09 2025 05:59 AM
Views 16

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
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% 101
18.9 IPS
 
Image Classification (HP)
100% 161
29.9 IPS
 
Image Classification (Q)
97% 164
30.7 IPS
 
Image Segmentation (SP)
100% 125
2.02 IPS
 
Image Segmentation (HP)
100% 202
3.28 IPS
 
Image Segmentation (Q)
98% 163
2.66 IPS
 
Pose Estimation (SP)
100% 201
0.23 IPS
 
Pose Estimation (HP)
100% 276
0.32 IPS
 
Pose Estimation (Q)
95% 274
0.32 IPS
 
Object Detection (SP)
100% 86
6.82 IPS
 
Object Detection (HP)
100% 123
9.79 IPS
 
Object Detection (Q)
89% 134
10.7 IPS
 
Face Detection (SP)
100% 231
2.74 IPS
 
Face Detection (HP)
100% 400
4.76 IPS
 
Face Detection (Q)
97% 413
4.92 IPS
 
Depth Estimation (SP)
100% 241
1.86 IPS
 
Depth Estimation (HP)
99% 406
3.13 IPS
 
Depth Estimation (Q)
62% 334
3.16 IPS
 
Style Transfer (SP)
100% 472
0.61 IPS
 
Style Transfer (HP)
100% 1015
1.30 IPS
 
Style Transfer (Q)
98% 1007
1.30 IPS
 
Image Super-Resolution (SP)
100% 118
4.36 IPS
 
Image Super-Resolution (HP)
100% 193
7.11 IPS
 
Image Super-Resolution (Q)
97% 186
6.91 IPS
 
Text Classification (SP)
100% 164
219.2 IPS
 
Text Classification (HP)
100% 160
213.4 IPS
 
Text Classification (Q)
91% 272
365.0 IPS
 
Machine Translation (SP)
100% 267
4.60 IPS
 
Machine Translation (HP)
100% 271
4.67 IPS
 
Machine Translation (Q)
57% 204
4.99 IPS
 

Compare

Set Baseline Geekbench 6 now available