iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
1161
Single Precision Score
1405
Half Precision Score
400
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 19 2026 09:59 AM |
| Views | 8 |
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% |
925
172.0 IPS |
|
|
Image Classification (HP)
|
100% |
1197
222.7 IPS |
|
|
Image Classification (Q)
|
96% |
156
29.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
358
5.80 IPS |
|
|
Image Segmentation (HP)
|
100% |
386
6.25 IPS |
|
|
Image Segmentation (Q)
|
99% |
225
3.65 IPS |
|
|
Pose Estimation (SP)
|
100% |
2821
3.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
3976
4.64 IPS |
|
|
Pose Estimation (Q)
|
96% |
1708
2.00 IPS |
|
|
Object Detection (SP)
|
100% |
919
72.9 IPS |
|
|
Object Detection (HP)
|
100% |
1206
95.6 IPS |
|
|
Object Detection (Q)
|
92% |
184
14.7 IPS |
|
|
Face Detection (SP)
|
100% |
3386
40.2 IPS |
|
|
Face Detection (HP)
|
100% |
3840
45.6 IPS |
|
|
Face Detection (Q)
|
100% |
297
3.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
2831
21.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
4035
31.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
547
4.27 IPS |
|
|
Style Transfer (SP)
|
100% |
7859
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9646
12.4 IPS |
|
|
Style Transfer (Q)
|
96% |
3013
3.89 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1365
50.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1808
66.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
398
14.7 IPS |
|
|
Text Classification (SP)
|
100% |
95
126.8 IPS |
|
|
Text Classification (HP)
|
100% |
103
137.8 IPS |
|
|
Text Classification (Q)
|
93% |
102
136.4 IPS |
|
|
Machine Translation (SP)
|
100% |
532
9.16 IPS |
|
|
Machine Translation (HP)
|
100% |
489
8.43 IPS |
|
|
Machine Translation (Q)
|
98% |
490
8.47 IPS |
