Geekbench AI Score

144
Single Precision Score
197
Half Precision Score
191
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 27 2024 01:59 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6833
System Information
Operating System Android 14
Model HONOR CRT-AN00
Model IDHONOR CRT-AN00
Motherboard CRT
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 11.42 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 91
16.9 IPS
 
Image Classification (HP)
100% 164
30.6 IPS
 
Image Classification (Q)
99% 150
28.0 IPS
 
Image Segmentation (SP)
100% 130
2.10 IPS
 
Image Segmentation (HP)
100% 221
3.59 IPS
 
Image Segmentation (Q)
98% 215
3.50 IPS
 
Pose Estimation (SP)
100% 88
0.10 IPS
 
Pose Estimation (HP)
100% 102
0.12 IPS
 
Pose Estimation (Q)
96% 101
0.12 IPS
 
Object Detection (SP)
100% 72
5.68 IPS
 
Object Detection (HP)
100% 116
9.19 IPS
 
Object Detection (Q)
83% 111
8.96 IPS
 
Face Detection (SP)
100% 278
3.30 IPS
 
Face Detection (HP)
100% 413
4.90 IPS
 
Face Detection (Q)
97% 382
4.56 IPS
 
Depth Estimation (SP)
100% 165
1.27 IPS
 
Depth Estimation (HP)
99% 216
1.67 IPS
 
Depth Estimation (Q)
62% 175
1.66 IPS
 
Style Transfer (SP)
100% 333
0.43 IPS
 
Style Transfer (HP)
100% 460
0.59 IPS
 
Style Transfer (Q)
98% 458
0.59 IPS
 
Image Super-Resolution (SP)
100% 86
3.16 IPS
 
Image Super-Resolution (HP)
100% 131
4.85 IPS
 
Image Super-Resolution (Q)
97% 130
4.81 IPS
 
Text Classification (SP)
100% 153
204.6 IPS
 
Text Classification (HP)
100% 152
202.5 IPS
 
Text Classification (Q)
91% 253
339.5 IPS
 
Machine Translation (SP)
100% 257
4.43 IPS
 
Machine Translation (HP)
100% 256
4.42 IPS
 
Machine Translation (Q)
57% 186
4.54 IPS
 

Compare

Set Baseline Geekbench 6 now available