Geekbench AI Score

410
Single Precision Score
411
Half Precision Score
780
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User vikarti
Upload Date September 14 2024 06:18 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6785V/CD
System Information
Operating System Android 12
Model wheatek WP19
Model IDwheatek WP19
Motherboard WP19
CPU Information
Name ARM MT6785V/CD
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.05 GHz
Memory Information
Size 7.50 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 197
36.7 IPS
 
Image Classification (HP)
100% 200
37.2 IPS
 
Image Classification (Q)
100% 541
100.7 IPS
 
Image Segmentation (SP)
100% 253
4.10 IPS
 
Image Segmentation (HP)
100% 249
4.04 IPS
 
Image Segmentation (Q)
98% 617
10.0 IPS
 
Pose Estimation (SP)
100% 849
0.99 IPS
 
Pose Estimation (HP)
100% 871
1.02 IPS
 
Pose Estimation (Q)
84% 1216
1.44 IPS
 
Object Detection (SP)
100% 169
13.4 IPS
 
Object Detection (HP)
100% 172
13.7 IPS
 
Object Detection (Q)
83% 518
41.8 IPS
 
Face Detection (SP)
100% 599
7.12 IPS
 
Face Detection (HP)
100% 599
7.12 IPS
 
Face Detection (Q)
95% 1225
14.6 IPS
 
Depth Estimation (SP)
100% 671
5.17 IPS
 
Depth Estimation (HP)
99% 694
5.35 IPS
 
Depth Estimation (Q)
64% 1224
11.2 IPS
 
Style Transfer (SP)
89% 1377
1.79 IPS
 
Style Transfer (HP)
89% 1412
1.83 IPS
 
Style Transfer (Q)
98% 3176
4.09 IPS
 
Image Super-Resolution (SP)
100% 382
14.1 IPS
 
Image Super-Resolution (HP)
100% 386
14.3 IPS
 
Image Super-Resolution (Q)
97% 655
24.3 IPS
 
Text Classification (SP)
100% 235
313.3 IPS
 
Text Classification (HP)
100% 231
308.4 IPS
 
Text Classification (Q)
88% 440
593.1 IPS
 
Machine Translation (SP)
100% 381
6.57 IPS
 
Machine Translation (HP)
100% 358
6.17 IPS
 
Machine Translation (Q)
50% 290
10.3 IPS
 

Compare

Set Baseline Geekbench 6 now available