Geekbench AI Score

144
Single Precision Score
199
Half Precision Score
195
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 04 2025 03:38 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM MT6833
System Information
Operating System Android 14
Model HONOR CRT-NX1
Model IDHONOR CRT-NX1
Motherboard CRTN
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 7.50 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 91
17.0 IPS
 
Image Classification (HP)
100% 172
32.0 IPS
 
Image Classification (Q)
99% 166
31.0 IPS
 
Image Segmentation (SP)
100% 131
2.12 IPS
 
Image Segmentation (HP)
100% 223
3.62 IPS
 
Image Segmentation (Q)
98% 218
3.55 IPS
 
Pose Estimation (SP)
100% 88
0.10 IPS
 
Pose Estimation (HP)
100% 102
0.12 IPS
 
Pose Estimation (Q)
96% 102
0.12 IPS
 
Object Detection (SP)
100% 72
5.75 IPS
 
Object Detection (HP)
100% 122
9.67 IPS
 
Object Detection (Q)
83% 114
9.21 IPS
 
Face Detection (SP)
100% 282
3.36 IPS
 
Face Detection (HP)
100% 418
4.97 IPS
 
Face Detection (Q)
97% 396
4.73 IPS
 
Depth Estimation (SP)
100% 166
1.28 IPS
 
Depth Estimation (HP)
99% 216
1.67 IPS
 
Depth Estimation (Q)
62% 175
1.66 IPS
 
Style Transfer (SP)
100% 334
0.43 IPS
 
Style Transfer (HP)
100% 460
0.59 IPS
 
Style Transfer (Q)
98% 459
0.59 IPS
 
Image Super-Resolution (SP)
100% 86
3.17 IPS
 
Image Super-Resolution (HP)
100% 131
4.84 IPS
 
Image Super-Resolution (Q)
97% 129
4.79 IPS
 
Text Classification (SP)
100% 153
204.4 IPS
 
Text Classification (HP)
100% 152
202.4 IPS
 
Text Classification (Q)
91% 252
338.3 IPS
 
Machine Translation (SP)
100% 256
4.41 IPS
 
Machine Translation (HP)
100% 258
4.44 IPS
 
Machine Translation (Q)
57% 184
4.50 IPS
 

Compare

Set Baseline Geekbench 6 now available