Geekbench AI Score

213
Single Precision Score
205
Half Precision Score
248
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 17 2024 07:14 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT8768WT
System Information
Operating System Android 14
Model samsung SM-T225N
Model IDsamsung SM-T225N
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% 109
20.3 IPS
 
Image Classification (HP)
100% 106
19.8 IPS
 
Image Classification (Q)
100% 165
30.6 IPS
 
Image Segmentation (SP)
100% 138
2.23 IPS
 
Image Segmentation (HP)
100% 140
2.27 IPS
 
Image Segmentation (Q)
98% 252
4.11 IPS
 
Pose Estimation (SP)
100% 484
0.57 IPS
 
Pose Estimation (HP)
100% 443
0.52 IPS
 
Pose Estimation (Q)
84% 346
0.41 IPS
 
Object Detection (SP)
100% 110
8.73 IPS
 
Object Detection (HP)
100% 109
8.62 IPS
 
Object Detection (Q)
83% 165
13.4 IPS
 
Face Detection (SP)
100% 251
2.99 IPS
 
Face Detection (HP)
100% 249
2.96 IPS
 
Face Detection (Q)
95% 463
5.52 IPS
 
Depth Estimation (SP)
100% 379
2.92 IPS
 
Depth Estimation (HP)
99% 311
2.39 IPS
 
Depth Estimation (Q)
64% 385
3.52 IPS
 
Style Transfer (SP)
89% 903
1.17 IPS
 
Style Transfer (HP)
89% 910
1.18 IPS
 
Style Transfer (Q)
98% 867
1.12 IPS
 
Image Super-Resolution (SP)
100% 152
5.60 IPS
 
Image Super-Resolution (HP)
100% 154
5.68 IPS
 
Image Super-Resolution (Q)
97% 212
7.85 IPS
 
Text Classification (SP)
100% 115
153.7 IPS
 
Text Classification (HP)
100% 110
146.7 IPS
 
Text Classification (Q)
88% 138
185.5 IPS
 
Machine Translation (SP)
100% 164
2.83 IPS
 
Machine Translation (HP)
100% 158
2.71 IPS
 
Machine Translation (Q)
50% 84
2.96 IPS
 

Compare

Set Baseline Geekbench 6 now available