iPad Pro (12.9-inch)
Geekbench ML Score
602
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64
Result Information
| Upload Date | September 19 2024 10:52 PM |
| Views | 2 |
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 | Neural Engine |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
296
55.4 IPS |
|
|
Image Classification (F16)
|
100% |
286
53.5 IPS |
|
|
Image Classification (I8)
|
99% |
268
50.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
171
2.86 IPS |
|
|
Image Segmentation (F16)
|
100% |
168
2.81 IPS |
|
|
Image Segmentation (I8)
|
100% |
170
2.84 IPS |
|
|
Pose Estimation (F32)
|
100% |
2032
2.46 IPS |
|
|
Pose Estimation (F16)
|
100% |
1972
2.39 IPS |
|
|
Pose Estimation (I8)
|
100% |
1962
2.38 IPS |
|
|
Object Detection (F32)
|
100% |
303
22.6 IPS |
|
|
Object Detection (F16)
|
100% |
355
26.5 IPS |
|
|
Object Detection (I8)
|
97% |
311
23.2 IPS |
|
|
Face Detection (F32)
|
100% |
1374
16.3 IPS |
|
|
Face Detection (F16)
|
100% |
1308
15.5 IPS |
|
|
Face Detection (I8)
|
99% |
1340
15.9 IPS |
|
|
Depth Estimation (F32)
|
100% |
2145
16.6 IPS |
|
|
Depth Estimation (F16)
|
100% |
2042
15.8 IPS |
|
|
Depth Estimation (I8)
|
99% |
2032
15.8 IPS |
|
|
Style Transfer (F32)
|
100% |
4836
6.36 IPS |
|
|
Style Transfer (F16)
|
100% |
5015
6.60 IPS |
|
|
Style Transfer (I8)
|
100% |
4667
6.14 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1131
40.4 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
953
34.1 IPS |
|
|
Image Super-Resolution (I8)
|
100% |
1030
36.8 IPS |
|
|
Text Classification (F32)
|
100% |
53
76.1 IPS |
|
|
Text Classification (F16)
|
100% |
98
140.9 IPS |
|
|
Text Classification (I8)
|
96% |
97
139.4 IPS |
|
|
Machine Translation (F32)
|
100% |
196
3.61 IPS |
|
|
Machine Translation (F16)
|
100% |
167
3.07 IPS |
|
|
Machine Translation (I8)
|
99% |
198
3.64 IPS |
