Geekbench AI Score

235
Single Precision Score
234
Half Precision Score
281
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 18 2024 04:50 PM
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% 124
23.1 IPS
 
Image Classification (Q)
100% 208
38.7 IPS
 
Image Segmentation (SP)
100% 157
2.55 IPS
 
Image Segmentation (HP)
100% 165
2.67 IPS
 
Image Segmentation (Q)
98% 289
4.70 IPS
 
Pose Estimation (SP)
100% 565
0.66 IPS
 
Pose Estimation (HP)
100% 559
0.65 IPS
 
Pose Estimation (Q)
84% 414
0.49 IPS
 
Object Detection (SP)
100% 113
8.97 IPS
 
Object Detection (HP)
100% 116
9.20 IPS
 
Object Detection (Q)
83% 191
15.5 IPS
 
Face Detection (SP)
100% 287
3.41 IPS
 
Face Detection (HP)
100% 286
3.40 IPS
 
Face Detection (Q)
95% 508
6.06 IPS
 
Depth Estimation (SP)
100% 407
3.14 IPS
 
Depth Estimation (HP)
99% 380
2.93 IPS
 
Depth Estimation (Q)
64% 416
3.81 IPS
 
Style Transfer (SP)
89% 996
1.29 IPS
 
Style Transfer (HP)
89% 994
1.29 IPS
 
Style Transfer (Q)
98% 972
1.25 IPS
 
Image Super-Resolution (SP)
100% 180
6.66 IPS
 
Image Super-Resolution (HP)
100% 178
6.58 IPS
 
Image Super-Resolution (Q)
97% 236
8.74 IPS
 
Text Classification (SP)
100% 120
159.7 IPS
 
Text Classification (HP)
100% 119
158.5 IPS
 
Text Classification (Q)
88% 154
207.6 IPS
 
Machine Translation (SP)
100% 167
2.87 IPS
 
Machine Translation (HP)
100% 166
2.86 IPS
 
Machine Translation (Q)
50% 87
3.07 IPS
 

Compare

Set Baseline Geekbench 6 now available