iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
712
Single Precision Score
2496
Half Precision Score
447
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 06 2026 10:19 AM |
| Views | 6 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| 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% |
342
63.6 IPS |
|
|
Image Classification (HP)
|
100% |
2439
453.6 IPS |
|
|
Image Classification (Q)
|
99% |
174
32.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
293
4.76 IPS |
|
|
Image Segmentation (HP)
|
100% |
396
6.42 IPS |
|
|
Image Segmentation (Q)
|
99% |
224
3.63 IPS |
|
|
Pose Estimation (SP)
|
100% |
2183
2.55 IPS |
|
|
Pose Estimation (HP)
|
100% |
27771
32.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
1519
1.78 IPS |
|
|
Object Detection (SP)
|
100% |
382
30.3 IPS |
|
|
Object Detection (HP)
|
100% |
1525
121.0 IPS |
|
|
Object Detection (Q)
|
94% |
211
16.8 IPS |
|
|
Face Detection (SP)
|
100% |
862
10.2 IPS |
|
|
Face Detection (HP)
|
100% |
6613
78.6 IPS |
|
|
Face Detection (Q)
|
100% |
301
3.58 IPS |
|
|
Depth Estimation (SP)
|
100% |
1056
8.13 IPS |
|
|
Depth Estimation (HP)
|
99% |
23496
181.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
603
4.71 IPS |
|
|
Style Transfer (SP)
|
100% |
3545
4.56 IPS |
|
|
Style Transfer (HP)
|
100% |
3507
4.51 IPS |
|
|
Style Transfer (Q)
|
96% |
2541
3.28 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
982
36.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3721
137.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
499
18.4 IPS |
|
|
Text Classification (SP)
|
100% |
260
347.5 IPS |
|
|
Text Classification (HP)
|
100% |
300
400.0 IPS |
|
|
Text Classification (Q)
|
93% |
304
407.5 IPS |
|
|
Machine Translation (SP)
|
100% |
491
8.45 IPS |
|
|
Machine Translation (HP)
|
100% |
378
6.51 IPS |
|
|
Machine Translation (Q)
|
98% |
370
6.39 IPS |
