Geekbench AI Score

91
Single Precision Score
127
Half Precision Score
123
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 03 2024 08:33 PM
Views 17

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6769H
System Information
Operating System Android 14
Model Xiaomi 23053RN02Y
Model IDXiaomi 23053RN02Y
Motherboard heat
CPU Information
Name ARM MT6769H
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 3.60 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 72
13.5 IPS
 
Image Classification (HP)
100% 115
21.4 IPS
 
Image Classification (Q)
99% 110
20.5 IPS
 
Image Segmentation (SP)
100% 89
1.45 IPS
 
Image Segmentation (HP)
100% 134
2.17 IPS
 
Image Segmentation (Q)
98% 135
2.20 IPS
 
Pose Estimation (SP)
100% 59
0.07 IPS
 
Pose Estimation (HP)
100% 81
0.10 IPS
 
Pose Estimation (Q)
96% 81
0.10 IPS
 
Object Detection (SP)
100% 54
4.30 IPS
 
Object Detection (HP)
100% 88
6.98 IPS
 
Object Detection (Q)
83% 85
6.91 IPS
 
Face Detection (SP)
100% 210
2.50 IPS
 
Face Detection (HP)
100% 310
3.68 IPS
 
Face Detection (Q)
97% 288
3.44 IPS
 
Depth Estimation (SP)
100% 114
0.88 IPS
 
Depth Estimation (HP)
99% 168
1.29 IPS
 
Depth Estimation (Q)
62% 128
1.21 IPS
 
Style Transfer (SP)
100% 223
0.29 IPS
 
Style Transfer (HP)
100% 347
0.45 IPS
 
Style Transfer (Q)
98% 345
0.44 IPS
 
Image Super-Resolution (SP)
100% 63
2.33 IPS
 
Image Super-Resolution (HP)
100% 95
3.50 IPS
 
Image Super-Resolution (Q)
97% 94
3.49 IPS
 
Text Classification (SP)
100% 58
77.2 IPS
 
Text Classification (HP)
100% 58
77.0 IPS
 
Text Classification (Q)
91% 80
107.5 IPS
 
Machine Translation (SP)
100% 104
1.80 IPS
 
Machine Translation (HP)
100% 104
1.80 IPS
 
Machine Translation (Q)
57% 87
2.12 IPS
 

Compare

Set Baseline Geekbench 6 now available