iPad Pro (12.9-inch)
Geekbench ML Score
281
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64
Result Information
| Upload Date | February 11 2025 10:18 AM |
| Views | 5 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 16.7.10 |
| Model | iPad Pro (12.9-inch) |
| Model ID | iPad6,7 |
| Motherboard | J98aAP |
| CPU Information | |
|---|---|
| Name | Apple A9X |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM |
| Base Frequency | 2.26 GHz |
| Cluster 1 | 2 Cores |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 3.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 3.90 GB |
| Inference Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
145
27.1 IPS |
|
|
Image Classification (F16)
|
100% |
129
24.2 IPS |
|
|
Image Classification (I8)
|
99% |
129
24.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
124
2.07 IPS |
|
|
Image Segmentation (F16)
|
100% |
124
2.07 IPS |
|
|
Image Segmentation (I8)
|
100% |
124
2.07 IPS |
|
|
Pose Estimation (F32)
|
100% |
809
0.98 IPS |
|
|
Pose Estimation (F16)
|
100% |
804
0.97 IPS |
|
|
Pose Estimation (I8)
|
100% |
802
0.97 IPS |
|
|
Object Detection (F32)
|
100% |
159
11.9 IPS |
|
|
Object Detection (F16)
|
100% |
143
10.7 IPS |
|
|
Object Detection (I8)
|
97% |
160
12.0 IPS |
|
|
Face Detection (F32)
|
100% |
313
3.72 IPS |
|
|
Face Detection (F16)
|
100% |
312
3.71 IPS |
|
|
Face Detection (I8)
|
99% |
312
3.70 IPS |
|
|
Depth Estimation (F32)
|
100% |
415
3.22 IPS |
|
|
Depth Estimation (F16)
|
100% |
384
2.97 IPS |
|
|
Depth Estimation (I8)
|
99% |
381
2.95 IPS |
|
|
Style Transfer (F32)
|
100% |
1322
1.74 IPS |
|
|
Style Transfer (F16)
|
100% |
1317
1.73 IPS |
|
|
Style Transfer (I8)
|
100% |
1311
1.72 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
371
13.3 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
368
13.2 IPS |
|
|
Image Super-Resolution (I8)
|
100% |
368
13.1 IPS |
|
|
Text Classification (F32)
|
100% |
136
195.7 IPS |
|
|
Text Classification (F16)
|
100% |
114
164.3 IPS |
|
|
Text Classification (I8)
|
96% |
110
158.6 IPS |
|
|
Machine Translation (F32)
|
100% |
222
4.09 IPS |
|
|
Machine Translation (F16)
|
100% |
188
3.46 IPS |
|
|
Machine Translation (I8)
|
99% |
223
4.10 IPS |
