Geekbench AI Score

142
Single Precision Score
196
Half Precision Score
190
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 15 2024 05:18 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6833
System Information
Operating System Android 14
Model Wingtech T Phone
Model IDWingtech T Phone
Motherboard S98317AA1T
CPU Information
Name ARM MT6833
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 3.59 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 89
16.5 IPS
 
Image Classification (HP)
100% 168
31.3 IPS
 
Image Classification (Q)
99% 149
27.8 IPS
 
Image Segmentation (SP)
100% 133
2.15 IPS
 
Image Segmentation (HP)
100% 212
3.43 IPS
 
Image Segmentation (Q)
98% 214
3.47 IPS
 
Pose Estimation (SP)
100% 89
0.10 IPS
 
Pose Estimation (HP)
100% 102
0.12 IPS
 
Pose Estimation (Q)
96% 101
0.12 IPS
 
Object Detection (SP)
100% 70
5.59 IPS
 
Object Detection (HP)
100% 116
9.23 IPS
 
Object Detection (Q)
83% 108
8.73 IPS
 
Face Detection (SP)
100% 270
3.20 IPS
 
Face Detection (HP)
100% 420
4.99 IPS
 
Face Detection (Q)
97% 406
4.84 IPS
 
Depth Estimation (SP)
100% 165
1.27 IPS
 
Depth Estimation (HP)
99% 214
1.65 IPS
 
Depth Estimation (Q)
62% 173
1.64 IPS
 
Style Transfer (SP)
100% 331
0.43 IPS
 
Style Transfer (HP)
100% 460
0.59 IPS
 
Style Transfer (Q)
98% 456
0.59 IPS
 
Image Super-Resolution (SP)
100% 82
3.03 IPS
 
Image Super-Resolution (HP)
100% 126
4.66 IPS
 
Image Super-Resolution (Q)
97% 124
4.58 IPS
 
Text Classification (SP)
100% 152
203.4 IPS
 
Text Classification (HP)
100% 153
203.6 IPS
 
Text Classification (Q)
91% 252
338.8 IPS
 
Machine Translation (SP)
100% 256
4.41 IPS
 
Machine Translation (HP)
100% 257
4.42 IPS
 
Machine Translation (Q)
57% 181
4.43 IPS
 

Compare

Set Baseline Geekbench 6 now available