iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
705
Single Precision Score
2432
Half Precision Score
439
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | February 01 2026 09:21 PM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| 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% |
340
63.2 IPS |
|
|
Image Classification (HP)
|
100% |
2369
440.6 IPS |
|
|
Image Classification (Q)
|
99% |
172
32.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
295
4.78 IPS |
|
|
Image Segmentation (HP)
|
100% |
388
6.29 IPS |
|
|
Image Segmentation (Q)
|
99% |
222
3.61 IPS |
|
|
Pose Estimation (SP)
|
100% |
2174
2.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
27610
32.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
1510
1.77 IPS |
|
|
Object Detection (SP)
|
100% |
383
30.4 IPS |
|
|
Object Detection (HP)
|
100% |
1434
113.7 IPS |
|
|
Object Detection (Q)
|
94% |
202
16.1 IPS |
|
|
Face Detection (SP)
|
100% |
839
9.97 IPS |
|
|
Face Detection (HP)
|
100% |
6587
78.3 IPS |
|
|
Face Detection (Q)
|
100% |
299
3.56 IPS |
|
|
Depth Estimation (SP)
|
100% |
1040
8.01 IPS |
|
|
Depth Estimation (HP)
|
99% |
23392
180.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
597
4.67 IPS |
|
|
Style Transfer (SP)
|
100% |
3554
4.57 IPS |
|
|
Style Transfer (HP)
|
100% |
3497
4.50 IPS |
|
|
Style Transfer (Q)
|
96% |
2510
3.24 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
946
34.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3364
124.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
484
17.9 IPS |
|
|
Text Classification (SP)
|
100% |
255
340.3 IPS |
|
|
Text Classification (HP)
|
100% |
293
391.7 IPS |
|
|
Text Classification (Q)
|
93% |
290
389.6 IPS |
|
|
Machine Translation (SP)
|
100% |
489
8.42 IPS |
|
|
Machine Translation (HP)
|
100% |
375
6.46 IPS |
|
|
Machine Translation (Q)
|
98% |
371
6.41 IPS |
