Geekbench AI Score

185
Single Precision Score
185
Half Precision Score
207
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 12:59 PM
Views 1

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% 91
17.0 IPS
 
Image Classification (HP)
100% 87
16.1 IPS
 
Image Classification (Q)
100% 160
29.7 IPS
 
Image Segmentation (SP)
100% 132
2.14 IPS
 
Image Segmentation (HP)
100% 127
2.06 IPS
 
Image Segmentation (Q)
98% 200
3.26 IPS
 
Pose Estimation (SP)
100% 477
0.56 IPS
 
Pose Estimation (HP)
100% 467
0.54 IPS
 
Pose Estimation (Q)
84% 350
0.42 IPS
 
Object Detection (SP)
100% 86
6.81 IPS
 
Object Detection (HP)
100% 101
7.97 IPS
 
Object Detection (Q)
83% 120
9.73 IPS
 
Face Detection (SP)
100% 244
2.90 IPS
 
Face Detection (HP)
100% 217
2.58 IPS
 
Face Detection (Q)
95% 391
4.66 IPS
 
Depth Estimation (SP)
100% 307
2.37 IPS
 
Depth Estimation (HP)
99% 297
2.29 IPS
 
Depth Estimation (Q)
64% 367
3.37 IPS
 
Style Transfer (SP)
89% 872
1.13 IPS
 
Style Transfer (HP)
89% 817
1.06 IPS
 
Style Transfer (Q)
98% 824
1.06 IPS
 
Image Super-Resolution (SP)
100% 149
5.52 IPS
 
Image Super-Resolution (HP)
100% 149
5.51 IPS
 
Image Super-Resolution (Q)
97% 207
7.67 IPS
 
Text Classification (SP)
100% 94
125.7 IPS
 
Text Classification (HP)
100% 97
130.1 IPS
 
Text Classification (Q)
88% 86
116.1 IPS
 
Machine Translation (SP)
100% 105
1.81 IPS
 
Machine Translation (HP)
100% 123
2.13 IPS
 
Machine Translation (Q)
50% 52
1.85 IPS
 

Compare

Set Baseline Geekbench 6 now available