Geekbench AI Score

146
Single Precision Score
146
Half Precision Score
148
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 26 2024 05:42 AM
Views 8

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 430
System Information
Operating System Android 14
Model Xiaomi Redmi 4
Model IDXiaomi Redmi 4
Motherboard MSM8937
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 1.40 GHz
Cluster 14 Cores @ 1.09 GHz
Cluster 24 Cores @ 1.40 GHz
Memory Information
Size 2.74 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 66
12.2 IPS
 
Image Classification (HP)
100% 72
13.4 IPS
 
Image Classification (Q)
100% 116
21.5 IPS
 
Image Segmentation (SP)
100% 101
1.64 IPS
 
Image Segmentation (HP)
100% 93
1.51 IPS
 
Image Segmentation (Q)
98% 144
2.34 IPS
 
Pose Estimation (SP)
100% 366
0.43 IPS
 
Pose Estimation (HP)
100% 359
0.42 IPS
 
Pose Estimation (Q)
84% 224
0.27 IPS
 
Object Detection (SP)
100% 70
5.55 IPS
 
Object Detection (HP)
100% 69
5.45 IPS
 
Object Detection (Q)
83% 107
8.68 IPS
 
Face Detection (SP)
100% 185
2.19 IPS
 
Face Detection (HP)
100% 192
2.28 IPS
 
Face Detection (Q)
95% 277
3.30 IPS
 
Depth Estimation (SP)
100% 244
1.88 IPS
 
Depth Estimation (HP)
99% 257
1.98 IPS
 
Depth Estimation (Q)
64% 219
2.00 IPS
 
Style Transfer (SP)
89% 579
0.75 IPS
 
Style Transfer (HP)
89% 575
0.75 IPS
 
Style Transfer (Q)
98% 537
0.69 IPS
 
Image Super-Resolution (SP)
100% 143
5.27 IPS
 
Image Super-Resolution (HP)
100% 127
4.67 IPS
 
Image Super-Resolution (Q)
97% 122
4.54 IPS
 
Text Classification (SP)
100% 72
96.4 IPS
 
Text Classification (HP)
100% 76
101.5 IPS
 
Text Classification (Q)
88% 73
99.0 IPS
 
Machine Translation (SP)
100% 102
1.76 IPS
 
Machine Translation (HP)
100% 97
1.68 IPS
 
Machine Translation (Q)
50% 45
1.61 IPS
 

Compare

Set Baseline Geekbench 6 now available