Geekbench AI Score

223
Single Precision Score
300
Half Precision Score
307
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 07 2024 06:41 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6877V/TTZA
System Information
Operating System Android 14
Model Xiaomi 22101316UG
Model IDXiaomi 22101316UG
Motherboard rubypro
CPU Information
Name ARM MT6877V/TTZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.60 GHz
Memory Information
Size 7.37 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 166
30.9 IPS
 
Image Classification (HP)
100% 288
53.6 IPS
 
Image Classification (Q)
99% 223
41.6 IPS
 
Image Segmentation (SP)
100% 228
3.70 IPS
 
Image Segmentation (HP)
100% 370
6.00 IPS
 
Image Segmentation (Q)
98% 365
5.94 IPS
 
Pose Estimation (SP)
100% 162
0.19 IPS
 
Pose Estimation (HP)
100% 190
0.22 IPS
 
Pose Estimation (Q)
96% 189
0.22 IPS
 
Object Detection (SP)
100% 123
9.74 IPS
 
Object Detection (HP)
100% 178
14.1 IPS
 
Object Detection (Q)
83% 186
15.0 IPS
 
Face Detection (SP)
100% 464
5.52 IPS
 
Face Detection (HP)
100% 671
7.97 IPS
 
Face Detection (Q)
97% 617
7.36 IPS
 
Depth Estimation (SP)
100% 305
2.35 IPS
 
Depth Estimation (HP)
99% 393
3.03 IPS
 
Depth Estimation (Q)
62% 317
3.00 IPS
 
Style Transfer (SP)
100% 620
0.80 IPS
 
Style Transfer (HP)
100% 875
1.12 IPS
 
Style Transfer (Q)
98% 869
1.12 IPS
 
Image Super-Resolution (SP)
100% 149
5.50 IPS
 
Image Super-Resolution (HP)
100% 234
8.63 IPS
 
Image Super-Resolution (Q)
97% 229
8.48 IPS
 
Text Classification (SP)
100% 145
192.9 IPS
 
Text Classification (HP)
100% 137
183.3 IPS
 
Text Classification (Q)
91% 300
403.6 IPS
 
Machine Translation (SP)
100% 221
3.81 IPS
 
Machine Translation (HP)
100% 222
3.83 IPS
 
Machine Translation (Q)
57% 229
5.60 IPS
 

Compare

Set Baseline Geekbench 6 now available