iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1167
Single Precision Score
1412
Half Precision Score
404
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | April 04 2026 06:25 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| 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% |
920
171.1 IPS |
|
|
Image Classification (HP)
|
100% |
1172
218.0 IPS |
|
|
Image Classification (Q)
|
96% |
161
30.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
360
5.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
391
6.33 IPS |
|
|
Image Segmentation (Q)
|
99% |
226
3.66 IPS |
|
|
Pose Estimation (SP)
|
100% |
2816
3.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
3991
4.66 IPS |
|
|
Pose Estimation (Q)
|
96% |
1711
2.00 IPS |
|
|
Object Detection (SP)
|
100% |
931
73.8 IPS |
|
|
Object Detection (HP)
|
100% |
1178
93.4 IPS |
|
|
Object Detection (Q)
|
92% |
185
14.8 IPS |
|
|
Face Detection (SP)
|
100% |
3488
41.4 IPS |
|
|
Face Detection (HP)
|
100% |
3990
47.4 IPS |
|
|
Face Detection (Q)
|
100% |
306
3.63 IPS |
|
|
Depth Estimation (SP)
|
100% |
2853
22.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4076
31.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
553
4.32 IPS |
|
|
Style Transfer (SP)
|
100% |
7985
10.3 IPS |
|
|
Style Transfer (HP)
|
100% |
9899
12.7 IPS |
|
|
Style Transfer (Q)
|
96% |
3003
3.88 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1370
50.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1855
68.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
402
14.9 IPS |
|
|
Text Classification (SP)
|
100% |
93
124.2 IPS |
|
|
Text Classification (HP)
|
100% |
100
133.2 IPS |
|
|
Text Classification (Q)
|
93% |
100
134.2 IPS |
|
|
Machine Translation (SP)
|
100% |
533
9.18 IPS |
|
|
Machine Translation (HP)
|
100% |
492
8.47 IPS |
|
|
Machine Translation (Q)
|
98% |
496
8.58 IPS |
