iPhone 13 mini
Geekbench AI Score
1803
Single Precision Score
11249
Half Precision Score
11128
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | Auhim |
| Upload Date | August 15 2024 09:40 PM |
| Views | 7 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 13 mini |
| Model ID | iPhone14,4 |
| Motherboard | D16AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.23 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.55 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
953
177.2 IPS |
|
|
Image Classification (HP)
|
100% |
4945
919.6 IPS |
|
|
Image Classification (Q)
|
99% |
4951
923.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
628
10.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
4122
66.8 IPS |
|
|
Image Segmentation (Q)
|
100% |
4111
66.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
5637
6.58 IPS |
|
|
Pose Estimation (HP)
|
100% |
74829
87.3 IPS |
|
|
Pose Estimation (Q)
|
94% |
53937
63.3 IPS |
|
|
Object Detection (SP)
|
100% |
933
74.0 IPS |
|
|
Object Detection (HP)
|
99% |
5953
473.5 IPS |
|
|
Object Detection (Q)
|
93% |
7186
573.4 IPS |
|
|
Face Detection (SP)
|
100% |
1629
19.4 IPS |
|
|
Face Detection (HP)
|
100% |
9716
115.5 IPS |
|
|
Face Detection (Q)
|
100% |
10846
128.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
3077
23.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
37575
289.5 IPS |
|
|
Depth Estimation (Q)
|
97% |
40406
312.4 IPS |
|
|
Style Transfer (SP)
|
100% |
8183
10.5 IPS |
|
|
Style Transfer (HP)
|
100% |
119211
153.2 IPS |
|
|
Style Transfer (Q)
|
100% |
97336
125.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2050
75.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
14012
517.4 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
15057
557.9 IPS |
|
|
Text Classification (SP)
|
100% |
1008
1.35 KIPS |
|
|
Text Classification (HP)
|
100% |
2908
3.88 KIPS |
|
|
Text Classification (Q)
|
93% |
2808
3.77 KIPS |
|
|
Machine Translation (SP)
|
100% |
1361
23.4 IPS |
|
|
Machine Translation (HP)
|
100% |
2016
34.7 IPS |
|
|
Machine Translation (Q)
|
98% |
2048
35.4 IPS |
