iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1168
Single Precision Score
1430
Half Precision Score
407
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 06 2026 10:12 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
873
162.4 IPS |
|
|
Image Classification (HP)
|
100% |
1188
221.0 IPS |
|
|
Image Classification (Q)
|
96% |
160
29.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
346
5.61 IPS |
|
|
Image Segmentation (HP)
|
100% |
377
6.10 IPS |
|
|
Image Segmentation (Q)
|
99% |
230
3.73 IPS |
|
|
Pose Estimation (SP)
|
100% |
2809
3.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
3996
4.66 IPS |
|
|
Pose Estimation (Q)
|
96% |
1721
2.02 IPS |
|
|
Object Detection (SP)
|
100% |
953
75.6 IPS |
|
|
Object Detection (HP)
|
100% |
1258
99.8 IPS |
|
|
Object Detection (Q)
|
92% |
187
14.9 IPS |
|
|
Face Detection (SP)
|
100% |
3377
40.1 IPS |
|
|
Face Detection (HP)
|
100% |
4093
48.6 IPS |
|
|
Face Detection (Q)
|
100% |
301
3.58 IPS |
|
|
Depth Estimation (SP)
|
100% |
2976
22.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
4172
32.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
551
4.31 IPS |
|
|
Style Transfer (SP)
|
100% |
7999
10.3 IPS |
|
|
Style Transfer (HP)
|
100% |
9861
12.7 IPS |
|
|
Style Transfer (Q)
|
96% |
3040
3.92 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1456
53.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1852
68.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
401
14.8 IPS |
|
|
Text Classification (SP)
|
100% |
93
124.3 IPS |
|
|
Text Classification (HP)
|
100% |
102
136.6 IPS |
|
|
Text Classification (Q)
|
93% |
105
140.5 IPS |
|
|
Machine Translation (SP)
|
100% |
541
9.32 IPS |
|
|
Machine Translation (HP)
|
100% |
501
8.63 IPS |
|
|
Machine Translation (Q)
|
98% |
502
8.67 IPS |
