HONOR CRT-NX3
Geekbench AI Score
512
Single Precision Score
511
Half Precision Score
958
Quantized Score
Geekbench AI 1.0.0 for Android AArch64
Result Information
| Upload Date | September 02 2024 01:57 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | ARM MT6833 |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | HONOR CRT-NX3 |
| Model ID | HONOR CRT-NX3 |
| 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 1 | 6 Cores @ 2.00 GHz |
| Cluster 2 | 2 Cores @ 2.20 GHz |
| Memory Information | |
|---|---|
| Size | 7.50 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
225
41.9 IPS |
|
|
Image Classification (HP)
|
100% |
225
41.9 IPS |
|
|
Image Classification (Q)
|
100% |
646
120.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
280
4.54 IPS |
|
|
Image Segmentation (HP)
|
100% |
280
4.54 IPS |
|
|
Image Segmentation (Q)
|
98% |
714
11.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
1106
1.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
1094
1.28 IPS |
|
|
Pose Estimation (Q)
|
84% |
1638
1.94 IPS |
|
|
Object Detection (SP)
|
100% |
226
18.0 IPS |
|
|
Object Detection (HP)
|
100% |
227
18.0 IPS |
|
|
Object Detection (Q)
|
87% |
658
52.8 IPS |
|
|
Face Detection (SP)
|
100% |
725
8.62 IPS |
|
|
Face Detection (HP)
|
100% |
725
8.61 IPS |
|
|
Face Detection (Q)
|
95% |
1481
17.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
928
7.15 IPS |
|
|
Depth Estimation (HP)
|
100% |
942
7.26 IPS |
|
|
Depth Estimation (Q)
|
75% |
1703
13.8 IPS |
|
|
Style Transfer (SP)
|
89% |
1859
2.41 IPS |
|
|
Style Transfer (HP)
|
89% |
1866
2.42 IPS |
|
|
Style Transfer (Q)
|
98% |
3753
4.84 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
494
18.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
494
18.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
906
33.6 IPS |
|
|
Text Classification (SP)
|
100% |
272
363.5 IPS |
|
|
Text Classification (HP)
|
100% |
267
356.7 IPS |
|
|
Text Classification (Q)
|
88% |
477
643.6 IPS |
|
|
Machine Translation (SP)
|
100% |
472
8.13 IPS |
|
|
Machine Translation (HP)
|
100% |
466
8.02 IPS |
|
|
Machine Translation (Q)
|
50% |
323
11.5 IPS |
