iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
716
Single Precision Score
2468
Half Precision Score
445
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | April 05 2026 07:15 AM |
| Views | 2 |
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% |
347
64.5 IPS |
|
|
Image Classification (HP)
|
100% |
2382
442.9 IPS |
|
|
Image Classification (Q)
|
99% |
172
32.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
298
4.83 IPS |
|
|
Image Segmentation (HP)
|
100% |
379
6.14 IPS |
|
|
Image Segmentation (Q)
|
99% |
226
3.66 IPS |
|
|
Pose Estimation (SP)
|
100% |
2185
2.55 IPS |
|
|
Pose Estimation (HP)
|
100% |
27898
32.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
1512
1.77 IPS |
|
|
Object Detection (SP)
|
100% |
391
31.0 IPS |
|
|
Object Detection (HP)
|
100% |
1522
120.7 IPS |
|
|
Object Detection (Q)
|
94% |
208
16.6 IPS |
|
|
Face Detection (SP)
|
100% |
857
10.2 IPS |
|
|
Face Detection (HP)
|
100% |
6591
78.3 IPS |
|
|
Face Detection (Q)
|
100% |
301
3.57 IPS |
|
|
Depth Estimation (SP)
|
100% |
1059
8.16 IPS |
|
|
Depth Estimation (HP)
|
99% |
24824
191.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
605
4.72 IPS |
|
|
Style Transfer (SP)
|
100% |
3551
4.56 IPS |
|
|
Style Transfer (HP)
|
100% |
3495
4.49 IPS |
|
|
Style Transfer (Q)
|
96% |
2532
3.27 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
974
36.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3371
124.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
485
17.9 IPS |
|
|
Text Classification (SP)
|
100% |
261
348.7 IPS |
|
|
Text Classification (HP)
|
100% |
301
401.7 IPS |
|
|
Text Classification (Q)
|
93% |
298
400.1 IPS |
|
|
Machine Translation (SP)
|
100% |
492
8.47 IPS |
|
|
Machine Translation (HP)
|
100% |
377
6.50 IPS |
|
|
Machine Translation (Q)
|
98% |
377
6.52 IPS |
