iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
712
Single Precision Score
2413
Half Precision Score
443
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | February 05 2026 02:18 AM |
| Views | 8 |
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% |
331
61.6 IPS |
|
|
Image Classification (HP)
|
100% |
2265
421.2 IPS |
|
|
Image Classification (Q)
|
99% |
164
30.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
299
4.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
361
5.85 IPS |
|
|
Image Segmentation (Q)
|
99% |
223
3.61 IPS |
|
|
Pose Estimation (SP)
|
100% |
2215
2.58 IPS |
|
|
Pose Estimation (HP)
|
100% |
27782
32.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
1529
1.79 IPS |
|
|
Object Detection (SP)
|
100% |
383
30.4 IPS |
|
|
Object Detection (HP)
|
100% |
1436
113.9 IPS |
|
|
Object Detection (Q)
|
94% |
206
16.4 IPS |
|
|
Face Detection (SP)
|
100% |
854
10.1 IPS |
|
|
Face Detection (HP)
|
100% |
6616
78.6 IPS |
|
|
Face Detection (Q)
|
100% |
301
3.57 IPS |
|
|
Depth Estimation (SP)
|
100% |
1049
8.08 IPS |
|
|
Depth Estimation (HP)
|
99% |
23336
179.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
600
4.69 IPS |
|
|
Style Transfer (SP)
|
100% |
3560
4.58 IPS |
|
|
Style Transfer (HP)
|
100% |
3527
4.53 IPS |
|
|
Style Transfer (Q)
|
96% |
2540
3.28 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
949
35.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3341
123.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
482
17.8 IPS |
|
|
Text Classification (SP)
|
100% |
271
361.5 IPS |
|
|
Text Classification (HP)
|
100% |
298
398.2 IPS |
|
|
Text Classification (Q)
|
93% |
306
410.2 IPS |
|
|
Machine Translation (SP)
|
100% |
491
8.46 IPS |
|
|
Machine Translation (HP)
|
100% |
379
6.53 IPS |
|
|
Machine Translation (Q)
|
98% |
377
6.51 IPS |
