Geekbench AI Score

491
Single Precision Score
466
Half Precision Score
859
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date November 03 2025 07:04 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Qualcomm
System Information
Operating System Android 15
Model Xiaomi Redmi Note 9 Pro
Model IDXiaomi Redmi Note 9 Pro
Motherboard atoll
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 5.48 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 237
44.1 IPS
 
Image Classification (HP)
100% 238
44.2 IPS
 
Image Classification (Q)
100% 693
128.8 IPS
 
Image Segmentation (SP)
100% 294
4.76 IPS
 
Image Segmentation (HP)
100% 293
4.75 IPS
 
Image Segmentation (Q)
98% 743
12.1 IPS
 
Pose Estimation (SP)
100% 1138
1.33 IPS
 
Pose Estimation (HP)
100% 1133
1.32 IPS
 
Pose Estimation (Q)
84% 1714
2.03 IPS
 
Object Detection (SP)
100% 236
18.7 IPS
 
Object Detection (HP)
100% 212
16.8 IPS
 
Object Detection (Q)
83% 562
45.4 IPS
 
Face Detection (SP)
100% 716
8.50 IPS
 
Face Detection (HP)
100% 721
8.57 IPS
 
Face Detection (Q)
95% 1381
16.5 IPS
 
Depth Estimation (SP)
100% 844
6.50 IPS
 
Depth Estimation (HP)
99% 696
5.37 IPS
 
Depth Estimation (Q)
64% 1261
11.5 IPS
 
Style Transfer (SP)
89% 1835
2.38 IPS
 
Style Transfer (HP)
89% 1722
2.23 IPS
 
Style Transfer (Q)
98% 3131
4.04 IPS
 
Image Super-Resolution (SP)
100% 397
14.6 IPS
 
Image Super-Resolution (HP)
100% 375
13.9 IPS
 
Image Super-Resolution (Q)
97% 629
23.3 IPS
 
Text Classification (SP)
100% 215
286.5 IPS
 
Text Classification (HP)
100% 235
313.6 IPS
 
Text Classification (Q)
88% 441
595.2 IPS
 
Machine Translation (SP)
100% 469
8.08 IPS
 
Machine Translation (HP)
100% 383
6.59 IPS
 
Machine Translation (Q)
50% 292
10.4 IPS
 

Compare

Set Baseline Geekbench 6 now available