iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
974
Single Precision Score
1308
Half Precision Score
377
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | September 02 2025 08:58 PM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,7 |
| Motherboard | J321AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.66 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
919
170.9 IPS |
|
|
Image Classification (HP)
|
100% |
1391
258.6 IPS |
|
|
Image Classification (Q)
|
96% |
116
21.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
254
4.13 IPS |
|
|
Image Segmentation (HP)
|
100% |
312
5.05 IPS |
|
|
Image Segmentation (Q)
|
99% |
185
3.00 IPS |
|
|
Pose Estimation (SP)
|
100% |
2173
2.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
3144
3.67 IPS |
|
|
Pose Estimation (Q)
|
96% |
1645
1.93 IPS |
|
|
Object Detection (SP)
|
100% |
234
18.5 IPS |
|
|
Object Detection (HP)
|
100% |
857
68.0 IPS |
|
|
Object Detection (Q)
|
92% |
141
11.3 IPS |
|
|
Face Detection (SP)
|
100% |
2662
31.6 IPS |
|
|
Face Detection (HP)
|
100% |
3203
38.1 IPS |
|
|
Face Detection (Q)
|
100% |
278
3.30 IPS |
|
|
Depth Estimation (SP)
|
100% |
2864
22.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
3874
29.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
456
3.56 IPS |
|
|
Style Transfer (SP)
|
100% |
6812
8.76 IPS |
|
|
Style Transfer (HP)
|
100% |
8113
10.4 IPS |
|
|
Style Transfer (Q)
|
96% |
2741
3.54 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
869
32.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1300
48.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
344
12.7 IPS |
|
|
Text Classification (SP)
|
100% |
278
371.6 IPS |
|
|
Text Classification (HP)
|
100% |
308
410.5 IPS |
|
|
Text Classification (Q)
|
93% |
285
383.0 IPS |
|
|
Machine Translation (SP)
|
100% |
517
8.90 IPS |
|
|
Machine Translation (HP)
|
100% |
313
5.39 IPS |
|
|
Machine Translation (Q)
|
98% |
351
6.06 IPS |
