iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
668
Single Precision Score
948
Half Precision Score
867
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | September 02 2025 08:50 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| 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% |
472
87.8 IPS |
|
|
Image Classification (HP)
|
100% |
792
147.2 IPS |
|
|
Image Classification (Q)
|
96% |
629
117.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
604
9.79 IPS |
|
|
Image Segmentation (HP)
|
100% |
949
15.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
1006
16.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
2572
3.00 IPS |
|
|
Pose Estimation (HP)
|
100% |
2323
2.71 IPS |
|
|
Pose Estimation (Q)
|
96% |
1914
2.24 IPS |
|
|
Object Detection (SP)
|
100% |
417
33.1 IPS |
|
|
Object Detection (HP)
|
99% |
652
51.7 IPS |
|
|
Object Detection (Q)
|
92% |
470
37.5 IPS |
|
|
Face Detection (SP)
|
100% |
748
8.89 IPS |
|
|
Face Detection (HP)
|
100% |
763
9.06 IPS |
|
|
Face Detection (Q)
|
100% |
519
6.17 IPS |
|
|
Depth Estimation (SP)
|
100% |
521
4.01 IPS |
|
|
Depth Estimation (HP)
|
98% |
564
4.36 IPS |
|
|
Depth Estimation (Q)
|
85% |
712
5.56 IPS |
|
|
Style Transfer (SP)
|
100% |
1470
1.89 IPS |
|
|
Style Transfer (HP)
|
100% |
2193
2.82 IPS |
|
|
Style Transfer (Q)
|
96% |
3446
4.45 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
672
24.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1142
42.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
833
30.7 IPS |
|
|
Text Classification (SP)
|
100% |
264
351.9 IPS |
|
|
Text Classification (HP)
|
100% |
495
660.6 IPS |
|
|
Text Classification (Q)
|
93% |
467
626.7 IPS |
|
|
Machine Translation (SP)
|
100% |
570
9.82 IPS |
|
|
Machine Translation (HP)
|
99% |
973
16.8 IPS |
|
|
Machine Translation (Q)
|
98% |
854
14.8 IPS |
