iPhone XR
Geekbench AI Score
548
Single Precision Score
930
Half Precision Score
848
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | Jacinth |
| Upload Date | August 26 2024 10:23 AM |
| Views | 8 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPhone XR |
| Model ID | iPhone11,8 |
| Motherboard | N841AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.77 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
341
63.4 IPS |
|
|
Image Classification (HP)
|
100% |
594
110.5 IPS |
|
|
Image Classification (Q)
|
99% |
595
111.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
365
5.92 IPS |
|
|
Image Segmentation (HP)
|
100% |
628
10.2 IPS |
|
|
Image Segmentation (Q)
|
100% |
633
10.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
946
1.10 IPS |
|
|
Pose Estimation (HP)
|
100% |
916
1.07 IPS |
|
|
Pose Estimation (Q)
|
96% |
847
0.99 IPS |
|
|
Object Detection (SP)
|
100% |
323
25.6 IPS |
|
|
Object Detection (HP)
|
99% |
656
52.1 IPS |
|
|
Object Detection (Q)
|
92% |
493
39.3 IPS |
|
|
Face Detection (SP)
|
100% |
822
9.76 IPS |
|
|
Face Detection (HP)
|
100% |
1722
20.5 IPS |
|
|
Face Detection (Q)
|
100% |
1124
13.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
654
5.04 IPS |
|
|
Depth Estimation (HP)
|
99% |
1430
11.0 IPS |
|
|
Depth Estimation (Q)
|
96% |
1368
10.6 IPS |
|
|
Style Transfer (SP)
|
100% |
1697
2.18 IPS |
|
|
Style Transfer (HP)
|
100% |
2988
3.84 IPS |
|
|
Style Transfer (Q)
|
100% |
2988
3.84 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
560
20.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
630
23.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
569
21.1 IPS |
|
|
Text Classification (SP)
|
100% |
268
357.3 IPS |
|
|
Text Classification (HP)
|
100% |
548
731.7 IPS |
|
|
Text Classification (Q)
|
93% |
545
731.4 IPS |
|
|
Machine Translation (SP)
|
100% |
471
8.11 IPS |
|
|
Machine Translation (HP)
|
98% |
853
14.7 IPS |
|
|
Machine Translation (Q)
|
98% |
861
14.9 IPS |
