iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1165
Single Precision Score
1419
Half Precision Score
403
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 25 2026 10:52 PM |
| Views | 6 |
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% |
923
171.7 IPS |
|
|
Image Classification (HP)
|
100% |
1230
228.7 IPS |
|
|
Image Classification (Q)
|
96% |
163
30.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
355
5.76 IPS |
|
|
Image Segmentation (HP)
|
100% |
379
6.14 IPS |
|
|
Image Segmentation (Q)
|
99% |
226
3.66 IPS |
|
|
Pose Estimation (SP)
|
100% |
2808
3.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
4030
4.70 IPS |
|
|
Pose Estimation (Q)
|
96% |
1718
2.01 IPS |
|
|
Object Detection (SP)
|
100% |
929
73.7 IPS |
|
|
Object Detection (HP)
|
100% |
1236
98.0 IPS |
|
|
Object Detection (Q)
|
92% |
183
14.6 IPS |
|
|
Face Detection (SP)
|
100% |
3495
41.5 IPS |
|
|
Face Detection (HP)
|
100% |
3957
47.0 IPS |
|
|
Face Detection (Q)
|
100% |
297
3.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
2854
22.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4113
31.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
547
4.27 IPS |
|
|
Style Transfer (SP)
|
100% |
7854
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9645
12.4 IPS |
|
|
Style Transfer (Q)
|
96% |
3021
3.90 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1367
50.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1820
67.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
397
14.7 IPS |
|
|
Text Classification (SP)
|
100% |
95
126.7 IPS |
|
|
Text Classification (HP)
|
100% |
103
137.7 IPS |
|
|
Text Classification (Q)
|
93% |
101
135.5 IPS |
|
|
Machine Translation (SP)
|
100% |
532
9.16 IPS |
|
|
Machine Translation (HP)
|
100% |
487
8.39 IPS |
|
|
Machine Translation (Q)
|
98% |
496
8.57 IPS |
