iPad mini (7th generation)
Geekbench AI Score
4460
Single Precision Score
5130
Half Precision Score
4703
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | DiDidoes |
| Upload Date | March 18 2026 08:33 PM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.3.1 |
| Model | iPad mini (7th generation) |
| Model ID | iPad16,2 |
| Motherboard | J411AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.72 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1498
278.5 IPS |
|
|
Image Classification (HP)
|
100% |
1486
276.3 IPS |
|
|
Image Classification (Q)
|
96% |
892
166.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
3583
58.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
3939
63.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
3784
61.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
12197
14.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
13872
16.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
13424
15.7 IPS |
|
|
Object Detection (SP)
|
100% |
1616
128.2 IPS |
|
|
Object Detection (HP)
|
100% |
1744
138.3 IPS |
|
|
Object Detection (Q)
|
91% |
1698
135.7 IPS |
|
|
Face Detection (SP)
|
100% |
6146
73.0 IPS |
|
|
Face Detection (HP)
|
100% |
7535
89.5 IPS |
|
|
Face Detection (Q)
|
100% |
7474
88.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
10158
78.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
11023
84.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
10430
81.6 IPS |
|
|
Style Transfer (SP)
|
100% |
24759
31.8 IPS |
|
|
Style Transfer (HP)
|
100% |
29333
37.7 IPS |
|
|
Style Transfer (Q)
|
96% |
30571
39.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4850
179.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4023
148.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3426
126.5 IPS |
|
|
Text Classification (SP)
|
100% |
3200
4.27 KIPS |
|
|
Text Classification (HP)
|
99% |
5639
7.53 KIPS |
|
|
Text Classification (Q)
|
93% |
5640
7.57 KIPS |
|
|
Machine Translation (SP)
|
100% |
1228
21.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1613
27.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1495
25.8 IPS |
