Geekbench AI Score

153
Single Precision Score
157
Half Precision Score
191
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 19 2024 05:01 PM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT8768WT
System Information
Operating System Android 14
Model samsung SM-T225
Model IDsamsung SM-T225
Motherboard gta7lite
CPU Information
Name ARM MT8768WT
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.30 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.30 GHz
Memory Information
Size 2.69 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 73
13.6 IPS
 
Image Classification (HP)
100% 80
14.8 IPS
 
Image Classification (Q)
100% 113
21.0 IPS
 
Image Segmentation (SP)
100% 116
1.87 IPS
 
Image Segmentation (HP)
100% 111
1.79 IPS
 
Image Segmentation (Q)
98% 178
2.89 IPS
 
Pose Estimation (SP)
100% 392
0.46 IPS
 
Pose Estimation (HP)
100% 388
0.45 IPS
 
Pose Estimation (Q)
84% 303
0.36 IPS
 
Object Detection (SP)
100% 72
5.70 IPS
 
Object Detection (HP)
100% 81
6.45 IPS
 
Object Detection (Q)
83% 127
10.2 IPS
 
Face Detection (SP)
100% 162
1.93 IPS
 
Face Detection (HP)
100% 216
2.57 IPS
 
Face Detection (Q)
95% 373
4.45 IPS
 
Depth Estimation (SP)
100% 305
2.35 IPS
 
Depth Estimation (HP)
99% 279
2.15 IPS
 
Depth Estimation (Q)
64% 308
2.82 IPS
 
Style Transfer (SP)
89% 722
0.94 IPS
 
Style Transfer (HP)
89% 712
0.92 IPS
 
Style Transfer (Q)
98% 771
0.99 IPS
 
Image Super-Resolution (SP)
100% 126
4.65 IPS
 
Image Super-Resolution (HP)
100% 118
4.36 IPS
 
Image Super-Resolution (Q)
97% 181
6.70 IPS
 
Text Classification (SP)
100% 77
102.9 IPS
 
Text Classification (HP)
100% 75
100.5 IPS
 
Text Classification (Q)
88% 84
113.9 IPS
 
Machine Translation (SP)
100% 88
1.52 IPS
 
Machine Translation (HP)
100% 87
1.49 IPS
 
Machine Translation (Q)
50% 62
2.20 IPS
 

Compare

Set Baseline Geekbench 6 now available