iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1173
Single Precision Score
1412
Half Precision Score
407
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 31 2026 04:26 AM |
| Views | 7 |
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% |
909
169.0 IPS |
|
|
Image Classification (HP)
|
100% |
1191
221.5 IPS |
|
|
Image Classification (Q)
|
96% |
157
29.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
355
5.75 IPS |
|
|
Image Segmentation (HP)
|
100% |
385
6.24 IPS |
|
|
Image Segmentation (Q)
|
99% |
230
3.73 IPS |
|
|
Pose Estimation (SP)
|
100% |
2819
3.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
3991
4.66 IPS |
|
|
Pose Estimation (Q)
|
96% |
1712
2.01 IPS |
|
|
Object Detection (SP)
|
100% |
920
73.0 IPS |
|
|
Object Detection (HP)
|
100% |
1227
97.4 IPS |
|
|
Object Detection (Q)
|
92% |
183
14.6 IPS |
|
|
Face Detection (SP)
|
100% |
3422
40.7 IPS |
|
|
Face Detection (HP)
|
100% |
3885
46.2 IPS |
|
|
Face Detection (Q)
|
100% |
298
3.54 IPS |
|
|
Depth Estimation (SP)
|
100% |
2841
21.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
4072
31.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
543
4.24 IPS |
|
|
Style Transfer (SP)
|
100% |
7932
10.2 IPS |
|
|
Style Transfer (HP)
|
100% |
9622
12.4 IPS |
|
|
Style Transfer (Q)
|
96% |
3016
3.89 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1419
52.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1840
67.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
397
14.7 IPS |
|
|
Text Classification (SP)
|
100% |
100
133.3 IPS |
|
|
Text Classification (HP)
|
100% |
100
133.4 IPS |
|
|
Text Classification (Q)
|
93% |
115
153.9 IPS |
|
|
Machine Translation (SP)
|
100% |
540
9.30 IPS |
|
|
Machine Translation (HP)
|
100% |
502
8.66 IPS |
|
|
Machine Translation (Q)
|
98% |
501
8.66 IPS |
