iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1027
Single Precision Score
1577
Half Precision Score
1352
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| User | Obrig |
| Upload Date | December 24 2025 08:43 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
502
93.3 IPS |
|
|
Image Classification (HP)
|
100% |
817
152.0 IPS |
|
|
Image Classification (Q)
|
96% |
631
117.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
607
9.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
984
16.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
1034
16.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
2616
3.05 IPS |
|
|
Pose Estimation (HP)
|
100% |
2324
2.71 IPS |
|
|
Pose Estimation (Q)
|
96% |
1989
2.33 IPS |
|
|
Object Detection (SP)
|
100% |
552
43.8 IPS |
|
|
Object Detection (HP)
|
99% |
967
76.7 IPS |
|
|
Object Detection (Q)
|
92% |
771
61.5 IPS |
|
|
Face Detection (SP)
|
100% |
1289
15.3 IPS |
|
|
Face Detection (HP)
|
100% |
2381
28.3 IPS |
|
|
Face Detection (Q)
|
100% |
1510
17.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
1745
13.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
2709
20.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
2270
17.7 IPS |
|
|
Style Transfer (SP)
|
100% |
5048
6.49 IPS |
|
|
Style Transfer (HP)
|
100% |
7861
10.1 IPS |
|
|
Style Transfer (Q)
|
96% |
7109
9.18 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1263
46.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1485
54.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1204
44.5 IPS |
|
|
Text Classification (SP)
|
100% |
290
387.3 IPS |
|
|
Text Classification (HP)
|
100% |
552
737.3 IPS |
|
|
Text Classification (Q)
|
93% |
552
740.9 IPS |
|
|
Machine Translation (SP)
|
100% |
720
12.4 IPS |
|
|
Machine Translation (HP)
|
99% |
1269
21.9 IPS |
|
|
Machine Translation (Q)
|
98% |
1260
21.8 IPS |
