iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
664
Single Precision Score
2394
Half Precision Score
424
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 31 2026 04:34 AM |
| Views | 7 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| 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% |
340
63.3 IPS |
|
|
Image Classification (HP)
|
100% |
2502
465.2 IPS |
|
|
Image Classification (Q)
|
99% |
173
32.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
296
4.80 IPS |
|
|
Image Segmentation (HP)
|
100% |
388
6.28 IPS |
|
|
Image Segmentation (Q)
|
99% |
224
3.64 IPS |
|
|
Pose Estimation (SP)
|
100% |
2152
2.51 IPS |
|
|
Pose Estimation (HP)
|
100% |
28782
33.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
1478
1.73 IPS |
|
|
Object Detection (SP)
|
100% |
376
29.8 IPS |
|
|
Object Detection (HP)
|
100% |
1492
118.4 IPS |
|
|
Object Detection (Q)
|
94% |
199
15.9 IPS |
|
|
Face Detection (SP)
|
100% |
800
9.51 IPS |
|
|
Face Detection (HP)
|
100% |
6590
78.3 IPS |
|
|
Face Detection (Q)
|
100% |
283
3.36 IPS |
|
|
Depth Estimation (SP)
|
100% |
907
6.99 IPS |
|
|
Depth Estimation (HP)
|
99% |
23433
180.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
509
3.98 IPS |
|
|
Style Transfer (SP)
|
100% |
2313
2.97 IPS |
|
|
Style Transfer (HP)
|
100% |
2532
3.26 IPS |
|
|
Style Transfer (Q)
|
96% |
2108
2.72 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
971
35.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3377
124.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
484
17.9 IPS |
|
|
Text Classification (SP)
|
100% |
259
345.1 IPS |
|
|
Text Classification (HP)
|
100% |
296
394.9 IPS |
|
|
Text Classification (Q)
|
93% |
296
397.2 IPS |
|
|
Machine Translation (SP)
|
100% |
490
8.45 IPS |
|
|
Machine Translation (HP)
|
100% |
380
6.55 IPS |
|
|
Machine Translation (Q)
|
98% |
379
6.55 IPS |
