iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
822
Single Precision Score
1036
Half Precision Score
417
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | September 02 2025 09:02 PM |
| Views | 6 |
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% |
207
38.4 IPS |
|
|
Image Classification (HP)
|
100% |
287
53.4 IPS |
|
|
Image Classification (Q)
|
96% |
134
25.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
339
5.50 IPS |
|
|
Image Segmentation (HP)
|
100% |
356
5.77 IPS |
|
|
Image Segmentation (Q)
|
99% |
215
3.49 IPS |
|
|
Pose Estimation (SP)
|
100% |
1431
1.67 IPS |
|
|
Pose Estimation (HP)
|
100% |
2315
2.70 IPS |
|
|
Pose Estimation (Q)
|
96% |
1624
1.90 IPS |
|
|
Object Detection (SP)
|
100% |
788
62.5 IPS |
|
|
Object Detection (HP)
|
100% |
1068
84.7 IPS |
|
|
Object Detection (Q)
|
92% |
139
11.1 IPS |
|
|
Face Detection (SP)
|
100% |
1616
19.2 IPS |
|
|
Face Detection (HP)
|
100% |
2997
35.6 IPS |
|
|
Face Detection (Q)
|
100% |
257
3.06 IPS |
|
|
Depth Estimation (SP)
|
100% |
2899
22.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
3332
25.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
533
4.16 IPS |
|
|
Style Transfer (SP)
|
100% |
6029
7.75 IPS |
|
|
Style Transfer (HP)
|
100% |
6885
8.85 IPS |
|
|
Style Transfer (Q)
|
96% |
2685
3.47 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1426
52.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1775
65.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
375
13.8 IPS |
|
|
Text Classification (SP)
|
100% |
147
196.0 IPS |
|
|
Text Classification (HP)
|
100% |
130
173.3 IPS |
|
|
Text Classification (Q)
|
93% |
365
490.3 IPS |
|
|
Machine Translation (SP)
|
100% |
304
5.24 IPS |
|
|
Machine Translation (HP)
|
100% |
358
6.16 IPS |
|
|
Machine Translation (Q)
|
98% |
492
8.50 IPS |
