Geekbench AI Score

228
Single Precision Score
234
Half Precision Score
282
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 16 2024 10:15 AM
Views 2

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% 123
23.0 IPS
 
Image Classification (HP)
100% 124
23.1 IPS
 
Image Classification (Q)
100% 177
32.9 IPS
 
Image Segmentation (SP)
100% 152
2.47 IPS
 
Image Segmentation (HP)
100% 155
2.52 IPS
 
Image Segmentation (Q)
98% 297
4.83 IPS
 
Pose Estimation (SP)
100% 548
0.64 IPS
 
Pose Estimation (HP)
100% 520
0.61 IPS
 
Pose Estimation (Q)
84% 413
0.49 IPS
 
Object Detection (SP)
100% 113
8.94 IPS
 
Object Detection (HP)
100% 126
9.99 IPS
 
Object Detection (Q)
83% 191
15.5 IPS
 
Face Detection (SP)
100% 287
3.41 IPS
 
Face Detection (HP)
100% 293
3.48 IPS
 
Face Detection (Q)
95% 512
6.11 IPS
 
Depth Estimation (SP)
100% 381
2.93 IPS
 
Depth Estimation (HP)
99% 401
3.09 IPS
 
Depth Estimation (Q)
64% 426
3.91 IPS
 
Style Transfer (SP)
89% 971
1.26 IPS
 
Style Transfer (HP)
89% 1001
1.30 IPS
 
Style Transfer (Q)
98% 997
1.29 IPS
 
Image Super-Resolution (SP)
100% 180
6.66 IPS
 
Image Super-Resolution (HP)
100% 183
6.77 IPS
 
Image Super-Resolution (Q)
97% 256
9.47 IPS
 
Text Classification (SP)
100% 105
140.0 IPS
 
Text Classification (HP)
100% 107
142.7 IPS
 
Text Classification (Q)
88% 159
214.5 IPS
 
Machine Translation (SP)
100% 166
2.86 IPS
 
Machine Translation (HP)
100% 172
2.96 IPS
 
Machine Translation (Q)
50% 89
3.16 IPS
 

Compare

Set Baseline Geekbench 6 now available