Geekbench AI Score

149
Single Precision Score
276
Half Precision Score
481
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User Teva
Upload Date January 24 2026 11:05 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
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% 178
33.1 IPS
 
Image Classification (HP)
100% 223
41.4 IPS
 
Image Classification (Q)
97% 448
83.6 IPS
 
Image Segmentation (SP)
100% 198
3.21 IPS
 
Image Segmentation (HP)
100% 154
2.50 IPS
 
Image Segmentation (Q)
98% 546
8.88 IPS
 
Pose Estimation (SP)
100% 491
0.57 IPS
 
Pose Estimation (HP)
100% 1158
1.35 IPS
 
Pose Estimation (Q)
96% 3596
4.21 IPS
 
Object Detection (SP)
100% 158
12.6 IPS
 
Object Detection (HP)
100% 112
8.90 IPS
 
Object Detection (Q)
85% 492
39.6 IPS
 
Face Detection (SP)
100% 328
3.90 IPS
 
Face Detection (HP)
100% 275
3.27 IPS
 
Face Detection (Q)
97% 1295
15.4 IPS
 
Depth Estimation (SP)
99% 295
2.27 IPS
 
Depth Estimation (HP)
99% 237
1.83 IPS
 
Depth Estimation (Q)
22% 92
21.0 IPS
 
Style Transfer (SP)
100% 498
0.64 IPS
 
Style Transfer (HP)
100% 384
0.49 IPS
 
Style Transfer (Q)
98% 1865
2.40 IPS
 
Image Super-Resolution (SP)
100% 287
10.6 IPS
 
Image Super-Resolution (HP)
100% 537
19.8 IPS
 
Image Super-Resolution (Q)
97% 1595
59.1 IPS
 
Text Classification (SP)
71% 2
2.84 IPS
 
Text Classification (HP)
100% 162
216.8 IPS
 
Text Classification (Q)
93% 40
53.6 IPS
 
Machine Translation (SP)
100% 72
1.24 IPS
 
Machine Translation (HP)
100% 268
4.62 IPS
 
Machine Translation (Q)
54% 110
3.10 IPS
 

Compare

Set Baseline Geekbench 6 now available