Geekbench AI Score

508
Single Precision Score
503
Half Precision Score
977
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 13 2024 10:38 PM
Views 3

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% 222
41.3 IPS
 
Image Classification (HP)
100% 234
43.5 IPS
 
Image Classification (Q)
100% 675
125.5 IPS
 
Image Segmentation (SP)
100% 287
4.66 IPS
 
Image Segmentation (HP)
100% 279
4.52 IPS
 
Image Segmentation (Q)
98% 734
11.9 IPS
 
Pose Estimation (SP)
100% 1102
1.29 IPS
 
Pose Estimation (HP)
100% 1121
1.31 IPS
 
Pose Estimation (Q)
84% 1706
2.02 IPS
 
Object Detection (SP)
100% 232
18.4 IPS
 
Object Detection (HP)
100% 233
18.5 IPS
 
Object Detection (Q)
83% 677
54.7 IPS
 
Face Detection (SP)
100% 682
8.10 IPS
 
Face Detection (HP)
100% 688
8.18 IPS
 
Face Detection (Q)
95% 1534
18.3 IPS
 
Depth Estimation (SP)
100% 907
6.99 IPS
 
Depth Estimation (HP)
99% 856
6.60 IPS
 
Depth Estimation (Q)
64% 1560
14.3 IPS
 
Style Transfer (SP)
89% 1893
2.46 IPS
 
Style Transfer (HP)
89% 1899
2.47 IPS
 
Style Transfer (Q)
98% 3881
5.01 IPS
 
Image Super-Resolution (SP)
100% 476
17.6 IPS
 
Image Super-Resolution (HP)
100% 449
16.6 IPS
 
Image Super-Resolution (Q)
97% 943
35.0 IPS
 
Text Classification (SP)
100% 275
367.5 IPS
 
Text Classification (HP)
100% 264
352.7 IPS
 
Text Classification (Q)
88% 481
648.1 IPS
 
Machine Translation (SP)
100% 466
8.03 IPS
 
Machine Translation (HP)
100% 461
7.93 IPS
 
Machine Translation (Q)
50% 332
11.8 IPS
 

Compare

Set Baseline Geekbench 6 now available