Geekbench AI Score

448
Single Precision Score
420
Half Precision Score
776
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date July 19 2025 08:20 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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% 168
31.2 IPS
 
Image Classification (HP)
100% 169
31.5 IPS
 
Image Classification (Q)
100% 439
81.7 IPS
 
Image Segmentation (SP)
100% 251
4.07 IPS
 
Image Segmentation (HP)
100% 257
4.17 IPS
 
Image Segmentation (Q)
98% 611
9.94 IPS
 
Pose Estimation (SP)
100% 1001
1.17 IPS
 
Pose Estimation (HP)
100% 906
1.06 IPS
 
Pose Estimation (Q)
84% 1566
1.86 IPS
 
Object Detection (SP)
100% 223
17.7 IPS
 
Object Detection (HP)
100% 201
16.0 IPS
 
Object Detection (Q)
83% 479
38.7 IPS
 
Face Detection (SP)
100% 631
7.50 IPS
 
Face Detection (HP)
100% 606
7.20 IPS
 
Face Detection (Q)
95% 1145
13.7 IPS
 
Depth Estimation (SP)
100% 830
6.39 IPS
 
Depth Estimation (HP)
99% 654
5.04 IPS
 
Depth Estimation (Q)
64% 1250
11.5 IPS
 
Style Transfer (SP)
89% 1672
2.17 IPS
 
Style Transfer (HP)
89% 1559
2.02 IPS
 
Style Transfer (Q)
98% 3231
4.17 IPS
 
Image Super-Resolution (SP)
100% 446
16.5 IPS
 
Image Super-Resolution (HP)
100% 424
15.6 IPS
 
Image Super-Resolution (Q)
97% 671
24.9 IPS
 
Text Classification (SP)
100% 208
278.0 IPS
 
Text Classification (HP)
100% 221
295.6 IPS
 
Text Classification (Q)
88% 428
577.8 IPS
 
Machine Translation (SP)
100% 434
7.48 IPS
 
Machine Translation (HP)
100% 376
6.48 IPS
 
Machine Translation (Q)
50% 300
10.7 IPS
 

Compare

Set Baseline Geekbench 6 now available