Geekbench AI Score

98
Single Precision Score
138
Half Precision Score
134
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User LinFengJun
Upload Date October 20 2024 02:50 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device MediaTek Helio G80
System Information
Operating System Android 12
Model Xiaomi Redmi 9
Model IDXiaomi M2004J19C
Motherboard lancelot
CPU Information
Name ARM MT6769T
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.00 GHz
Memory Information
Size 3.61 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 71
13.3 IPS
 
Image Classification (HP)
100% 114
21.1 IPS
 
Image Classification (Q)
99% 108
20.2 IPS
 
Image Segmentation (SP)
100% 103
1.68 IPS
 
Image Segmentation (HP)
100% 186
3.02 IPS
 
Image Segmentation (Q)
98% 172
2.80 IPS
 
Pose Estimation (SP)
100% 56
0.07 IPS
 
Pose Estimation (HP)
100% 77
0.09 IPS
 
Pose Estimation (Q)
96% 77
0.09 IPS
 
Object Detection (SP)
100% 58
4.59 IPS
 
Object Detection (HP)
100% 95
7.56 IPS
 
Object Detection (Q)
83% 93
7.49 IPS
 
Face Detection (SP)
100% 225
2.68 IPS
 
Face Detection (HP)
100% 344
4.09 IPS
 
Face Detection (Q)
97% 328
3.91 IPS
 
Depth Estimation (SP)
100% 120
0.93 IPS
 
Depth Estimation (HP)
99% 166
1.28 IPS
 
Depth Estimation (Q)
62% 134
1.27 IPS
 
Style Transfer (SP)
100% 235
0.30 IPS
 
Style Transfer (HP)
100% 356
0.46 IPS
 
Style Transfer (Q)
98% 354
0.46 IPS
 
Image Super-Resolution (SP)
100% 65
2.39 IPS
 
Image Super-Resolution (HP)
100% 100
3.68 IPS
 
Image Super-Resolution (Q)
97% 97
3.61 IPS
 
Text Classification (SP)
100% 69
91.9 IPS
 
Text Classification (HP)
100% 69
92.1 IPS
 
Text Classification (Q)
91% 103
138.0 IPS
 
Machine Translation (SP)
100% 122
2.09 IPS
 
Machine Translation (HP)
100% 121
2.09 IPS
 
Machine Translation (Q)
57% 96
2.35 IPS
 

Compare

Set Baseline Geekbench 6 now available