Geekbench AI Score

508
Single Precision Score
512
Half Precision Score
985
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 26 2024 04:08 AM
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 9S
Model IDXiaomi Redmi Note 9S
Motherboard curtana
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% 231
43.0 IPS
 
Image Classification (HP)
100% 237
44.0 IPS
 
Image Classification (Q)
100% 675
125.5 IPS
 
Image Segmentation (SP)
100% 292
4.74 IPS
 
Image Segmentation (HP)
100% 282
4.58 IPS
 
Image Segmentation (Q)
98% 743
12.1 IPS
 
Pose Estimation (SP)
100% 1120
1.31 IPS
 
Pose Estimation (HP)
100% 1139
1.33 IPS
 
Pose Estimation (Q)
84% 1705
2.02 IPS
 
Object Detection (SP)
100% 236
18.7 IPS
 
Object Detection (HP)
100% 233
18.5 IPS
 
Object Detection (Q)
83% 685
55.3 IPS
 
Face Detection (SP)
100% 678
8.05 IPS
 
Face Detection (HP)
100% 688
8.17 IPS
 
Face Detection (Q)
95% 1549
18.5 IPS
 
Depth Estimation (SP)
100% 839
6.46 IPS
 
Depth Estimation (HP)
99% 901
6.94 IPS
 
Depth Estimation (Q)
64% 1579
14.5 IPS
 
Style Transfer (SP)
89% 1835
2.38 IPS
 
Style Transfer (HP)
89% 1885
2.45 IPS
 
Style Transfer (Q)
98% 3879
5.00 IPS
 
Image Super-Resolution (SP)
100% 485
17.9 IPS
 
Image Super-Resolution (HP)
100% 489
18.1 IPS
 
Image Super-Resolution (Q)
97% 903
33.5 IPS
 
Text Classification (SP)
100% 274
365.6 IPS
 
Text Classification (HP)
100% 271
361.8 IPS
 
Text Classification (Q)
88% 512
689.9 IPS
 
Machine Translation (SP)
100% 471
8.10 IPS
 
Machine Translation (HP)
100% 453
7.81 IPS
 
Machine Translation (Q)
50% 335
11.9 IPS
 

Compare

Set Baseline Geekbench 6 now available