Geekbench AI Score

210
Single Precision Score
209
Half Precision Score
303
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 29 2024 01:04 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6769Z
System Information
Operating System Android 12
Model Xiaomi M2003J15SC
Model IDXiaomi M2003J15SC
Motherboard merlinnfc
CPU Information
Name ARM MT6769Z
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 2.63 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 90
16.7 IPS
 
Image Classification (HP)
100% 93
17.3 IPS
 
Image Classification (Q)
100% 207
38.5 IPS
 
Image Segmentation (SP)
100% 118
1.92 IPS
 
Image Segmentation (HP)
100% 115
1.86 IPS
 
Image Segmentation (Q)
98% 259
4.20 IPS
 
Pose Estimation (SP)
100% 440
0.51 IPS
 
Pose Estimation (HP)
100% 440
0.51 IPS
 
Pose Estimation (Q)
84% 405
0.48 IPS
 
Object Detection (SP)
100% 84
6.63 IPS
 
Object Detection (HP)
100% 88
6.94 IPS
 
Object Detection (Q)
83% 196
15.8 IPS
 
Face Detection (SP)
100% 293
3.48 IPS
 
Face Detection (HP)
100% 298
3.54 IPS
 
Face Detection (Q)
95% 554
6.62 IPS
 
Depth Estimation (SP)
100% 381
2.94 IPS
 
Depth Estimation (HP)
99% 344
2.65 IPS
 
Depth Estimation (Q)
64% 456
4.18 IPS
 
Style Transfer (SP)
89% 790
1.03 IPS
 
Style Transfer (HP)
89% 747
0.97 IPS
 
Style Transfer (Q)
98% 1050
1.35 IPS
 
Image Super-Resolution (SP)
100% 195
7.20 IPS
 
Image Super-Resolution (HP)
100% 198
7.31 IPS
 
Image Super-Resolution (Q)
97% 238
8.80 IPS
 
Text Classification (SP)
100% 121
161.3 IPS
 
Text Classification (HP)
100% 121
161.6 IPS
 
Text Classification (Q)
88% 164
221.0 IPS
 
Machine Translation (SP)
100% 214
3.69 IPS
 
Machine Translation (HP)
100% 216
3.72 IPS
 
Machine Translation (Q)
50% 149
5.29 IPS
 

Compare

Set Baseline Geekbench 6 now available