iPad Pro 12.9-inch (4th generation)
Geekbench AI Score
1406
Single Precision Score
1758
Half Precision Score
471
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| User | randymassey |
| Upload Date | October 05 2025 08:29 AM |
| Views | 8 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12Z Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro 12.9-inch (4th generation) |
| Model ID | iPad8,12 |
| Motherboard | J421AP |
| CPU Information | |
|---|---|
| Name | Apple A12Z Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.53 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1002
186.3 IPS |
|
|
Image Classification (HP)
|
100% |
1467
272.8 IPS |
|
|
Image Classification (Q)
|
96% |
160
29.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
393
6.36 IPS |
|
|
Image Segmentation (HP)
|
100% |
386
6.26 IPS |
|
|
Image Segmentation (Q)
|
99% |
248
4.02 IPS |
|
|
Pose Estimation (SP)
|
100% |
3222
3.76 IPS |
|
|
Pose Estimation (HP)
|
100% |
4689
5.47 IPS |
|
|
Pose Estimation (Q)
|
96% |
2028
2.38 IPS |
|
|
Object Detection (SP)
|
100% |
1019
80.8 IPS |
|
|
Object Detection (HP)
|
100% |
1366
108.4 IPS |
|
|
Object Detection (Q)
|
92% |
190
15.2 IPS |
|
|
Face Detection (SP)
|
100% |
3818
45.4 IPS |
|
|
Face Detection (HP)
|
100% |
4414
52.4 IPS |
|
|
Face Detection (Q)
|
100% |
319
3.79 IPS |
|
|
Depth Estimation (SP)
|
100% |
3279
25.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
4703
36.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
588
4.59 IPS |
|
|
Style Transfer (SP)
|
100% |
9068
11.7 IPS |
|
|
Style Transfer (HP)
|
100% |
11107
14.3 IPS |
|
|
Style Transfer (Q)
|
96% |
3185
4.11 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1645
60.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2338
86.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
407
15.0 IPS |
|
|
Text Classification (SP)
|
100% |
232
310.0 IPS |
|
|
Text Classification (HP)
|
100% |
284
379.1 IPS |
|
|
Text Classification (Q)
|
93% |
287
385.8 IPS |
|
|
Machine Translation (SP)
|
100% |
541
9.32 IPS |
|
|
Machine Translation (HP)
|
100% |
508
8.75 IPS |
|
|
Machine Translation (Q)
|
98% |
504
8.70 IPS |
