iPad Pro 12.9-inch (4th generation)
Geekbench AI Score
1010
Single Precision Score
1567
Half Precision Score
1348
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | NycDriipy |
| Upload Date | December 01 2024 01:48 PM |
| Views | 11 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12Z Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| Model | iPad Pro 12.9-inch (4th generation) |
| Model ID | iPad8,11 |
| Motherboard | J420AP |
| 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% |
487
90.6 IPS |
|
|
Image Classification (HP)
|
100% |
806
150.0 IPS |
|
|
Image Classification (Q)
|
96% |
642
119.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
617
10.00 IPS |
|
|
Image Segmentation (HP)
|
100% |
981
15.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1030
16.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
2513
2.93 IPS |
|
|
Pose Estimation (HP)
|
100% |
2229
2.60 IPS |
|
|
Pose Estimation (Q)
|
96% |
1921
2.25 IPS |
|
|
Object Detection (SP)
|
100% |
546
43.3 IPS |
|
|
Object Detection (HP)
|
99% |
970
77.0 IPS |
|
|
Object Detection (Q)
|
92% |
763
60.9 IPS |
|
|
Face Detection (SP)
|
100% |
1268
15.1 IPS |
|
|
Face Detection (HP)
|
100% |
2361
28.1 IPS |
|
|
Face Detection (Q)
|
100% |
1494
17.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
1737
13.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
2691
20.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
2244
17.5 IPS |
|
|
Style Transfer (SP)
|
100% |
4857
6.24 IPS |
|
|
Style Transfer (HP)
|
100% |
7860
10.1 IPS |
|
|
Style Transfer (Q)
|
96% |
7173
9.26 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1232
45.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1514
55.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1237
45.7 IPS |
|
|
Text Classification (SP)
|
100% |
284
379.1 IPS |
|
|
Text Classification (HP)
|
99% |
550
734.0 IPS |
|
|
Text Classification (Q)
|
93% |
547
734.4 IPS |
|
|
Machine Translation (SP)
|
100% |
719
12.4 IPS |
|
|
Machine Translation (HP)
|
98% |
1257
21.7 IPS |
|
|
Machine Translation (Q)
|
98% |
1257
21.7 IPS |
