Geekbench AI Score

134
Single Precision Score
127
Half Precision Score
152
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date March 23 2025 05:23 PM
Views 7

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT8768WT
System Information
Operating System Android 14
Model samsung SM-T220
Model IDsamsung SM-T220
Motherboard gta7litewifi
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 2.79 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 75
13.9 IPS
 
Image Classification (HP)
100% 73
13.6 IPS
 
Image Classification (Q)
100% 124
23.1 IPS
 
Image Segmentation (SP)
100% 89
1.45 IPS
 
Image Segmentation (HP)
100% 91
1.48 IPS
 
Image Segmentation (Q)
98% 177
2.88 IPS
 
Pose Estimation (SP)
100% 336
0.39 IPS
 
Pose Estimation (HP)
100% 329
0.38 IPS
 
Pose Estimation (Q)
84% 251
0.30 IPS
 
Object Detection (SP)
100% 66
5.23 IPS
 
Object Detection (HP)
100% 58
4.57 IPS
 
Object Detection (Q)
83% 94
7.61 IPS
 
Face Detection (SP)
100% 173
2.05 IPS
 
Face Detection (HP)
100% 165
1.97 IPS
 
Face Detection (Q)
95% 266
3.18 IPS
 
Depth Estimation (SP)
100% 233
1.80 IPS
 
Depth Estimation (HP)
99% 213
1.64 IPS
 
Depth Estimation (Q)
64% 215
1.97 IPS
 
Style Transfer (SP)
89% 559
0.73 IPS
 
Style Transfer (HP)
89% 566
0.74 IPS
 
Style Transfer (Q)
98% 572
0.74 IPS
 
Image Super-Resolution (SP)
100% 96
3.55 IPS
 
Image Super-Resolution (HP)
100% 95
3.51 IPS
 
Image Super-Resolution (Q)
97% 117
4.34 IPS
 
Text Classification (SP)
100% 69
91.6 IPS
 
Text Classification (HP)
100% 55
73.8 IPS
 
Text Classification (Q)
88% 73
97.9 IPS
 
Machine Translation (SP)
100% 90
1.54 IPS
 
Machine Translation (HP)
100% 89
1.54 IPS
 
Machine Translation (Q)
50% 48
1.71 IPS
 

Compare

Set Baseline Geekbench 6 now available