Geekbench AI Score

223
Single Precision Score
216
Half Precision Score
258
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 11 2024 04:04 AM
Views 1

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% 124
23.0 IPS
 
Image Classification (HP)
100% 116
21.6 IPS
 
Image Classification (Q)
100% 166
30.9 IPS
 
Image Segmentation (SP)
100% 147
2.39 IPS
 
Image Segmentation (HP)
100% 150
2.44 IPS
 
Image Segmentation (Q)
98% 272
4.43 IPS
 
Pose Estimation (SP)
100% 509
0.59 IPS
 
Pose Estimation (HP)
100% 529
0.62 IPS
 
Pose Estimation (Q)
84% 391
0.46 IPS
 
Object Detection (SP)
100% 114
9.04 IPS
 
Object Detection (HP)
100% 115
9.15 IPS
 
Object Detection (Q)
83% 174
14.1 IPS
 
Face Detection (SP)
100% 267
3.18 IPS
 
Face Detection (HP)
100% 275
3.26 IPS
 
Face Detection (Q)
95% 462
5.52 IPS
 
Depth Estimation (SP)
100% 388
2.99 IPS
 
Depth Estimation (HP)
99% 275
2.12 IPS
 
Depth Estimation (Q)
64% 391
3.58 IPS
 
Style Transfer (SP)
89% 915
1.19 IPS
 
Style Transfer (HP)
89% 917
1.19 IPS
 
Style Transfer (Q)
98% 928
1.20 IPS
 
Image Super-Resolution (SP)
100% 169
6.24 IPS
 
Image Super-Resolution (HP)
100% 174
6.44 IPS
 
Image Super-Resolution (Q)
97% 224
8.31 IPS
 
Text Classification (SP)
100% 113
151.3 IPS
 
Text Classification (HP)
100% 114
152.4 IPS
 
Text Classification (Q)
88% 139
187.9 IPS
 
Machine Translation (SP)
100% 164
2.82 IPS
 
Machine Translation (HP)
100% 159
2.75 IPS
 
Machine Translation (Q)
50% 84
2.98 IPS
 

Compare

Set Baseline Geekbench 6 now available