Geekbench AI Score

136
Single Precision Score
135
Half Precision Score
153
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 12 2025 06:13 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6762G
System Information
Operating System Android 13
Model Xiaomi M2006C3LG
Model IDXiaomi M2006C3LG
Motherboard blossom
CPU Information
Name ARM MT6762G
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.10 GHz
Cluster 14 Cores @ 1.50 GHz
Cluster 24 Cores @ 2.10 GHz
Memory Information
Size 1.78 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 49
9.05 IPS
 
Image Classification (HP)
100% 57
10.6 IPS
 
Image Classification (Q)
100% 107
19.8 IPS
 
Image Segmentation (SP)
100% 89
1.44 IPS
 
Image Segmentation (HP)
100% 94
1.52 IPS
 
Image Segmentation (Q)
98% 154
2.50 IPS
 
Pose Estimation (SP)
100% 451
0.53 IPS
 
Pose Estimation (HP)
100% 471
0.55 IPS
 
Pose Estimation (Q)
84% 359
0.43 IPS
 
Object Detection (SP)
100% 76
6.00 IPS
 
Object Detection (HP)
100% 73
5.80 IPS
 
Object Detection (Q)
83% 112
9.07 IPS
 
Face Detection (SP)
100% 168
2.00 IPS
 
Face Detection (HP)
100% 165
1.96 IPS
 
Face Detection (Q)
95% 265
3.16 IPS
 
Depth Estimation (SP)
100% 210
1.62 IPS
 
Depth Estimation (HP)
99% 252
1.94 IPS
 
Depth Estimation (Q)
64% 273
2.50 IPS
 
Style Transfer (SP)
89% 859
1.12 IPS
 
Style Transfer (HP)
89% 840
1.09 IPS
 
Style Transfer (Q)
98% 813
1.05 IPS
 
Image Super-Resolution (SP)
100% 174
6.42 IPS
 
Image Super-Resolution (HP)
100% 114
4.19 IPS
 
Image Super-Resolution (Q)
97% 151
5.59 IPS
 
Text Classification (SP)
100% 46
61.0 IPS
 
Text Classification (HP)
100% 47
62.5 IPS
 
Text Classification (Q)
88% 41
55.9 IPS
 
Machine Translation (SP)
100% 63
1.08 IPS
 
Machine Translation (HP)
100% 60
1.03 IPS
 
Machine Translation (Q)
50% 31
1.08 IPS
 

Compare

Set Baseline Geekbench 6 now available