iPad mini (6th generation)
Geekbench AI Score
2718
Single Precision Score
2960
Half Precision Score
2777
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| User | JustinGT86 |
| Upload Date | March 24 2025 07:39 AM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2.1 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,1 |
| Motherboard | J310AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.92 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.77 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
702
130.6 IPS |
|
|
Image Classification (HP)
|
100% |
659
122.5 IPS |
|
|
Image Classification (Q)
|
97% |
603
112.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2156
34.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
2276
36.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2196
35.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
10845
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
11754
13.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
10962
12.8 IPS |
|
|
Object Detection (SP)
|
100% |
1132
89.8 IPS |
|
|
Object Detection (HP)
|
100% |
1096
86.9 IPS |
|
|
Object Detection (Q)
|
91% |
935
74.7 IPS |
|
|
Face Detection (SP)
|
100% |
3796
45.1 IPS |
|
|
Face Detection (HP)
|
100% |
4024
47.8 IPS |
|
|
Face Detection (Q)
|
100% |
3564
42.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7715
59.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
7953
61.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
7022
54.9 IPS |
|
|
Style Transfer (SP)
|
100% |
18049
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
21807
28.0 IPS |
|
|
Style Transfer (Q)
|
96% |
20322
26.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2599
96.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2408
88.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2570
94.9 IPS |
|
|
Text Classification (SP)
|
100% |
2384
3.18 KIPS |
|
|
Text Classification (HP)
|
100% |
4208
5.62 KIPS |
|
|
Text Classification (Q)
|
93% |
4188
5.62 KIPS |
|
|
Machine Translation (SP)
|
100% |
362
6.23 IPS |
|
|
Machine Translation (HP)
|
100% |
378
6.52 IPS |
|
|
Machine Translation (Q)
|
98% |
368
6.36 IPS |
