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 | February 11 2025 10:41 AM |
| Views | 4 |
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% |
311
58.2 IPS |
|
|
Image Classification (F16)
|
100% |
229
42.9 IPS |
|
|
Image Classification (I8)
|
99% |
217
40.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
190
3.17 IPS |
|
|
Image Segmentation (F16)
|
100% |
186
3.10 IPS |
|
|
Image Segmentation (I8)
|
100% |
186
3.10 IPS |
|
|
Pose Estimation (F32)
|
100% |
1998
2.42 IPS |
|
|
Pose Estimation (F16)
|
100% |
1970
2.39 IPS |
|
|
Pose Estimation (I8)
|
100% |
1974
2.39 IPS |
|
|
Object Detection (F32)
|
100% |
320
23.9 IPS |
|
|
Object Detection (F16)
|
100% |
322
24.0 IPS |
|
|
Object Detection (I8)
|
97% |
338
25.2 IPS |
|
|
Face Detection (F32)
|
100% |
1349
16.0 IPS |
|
|
Face Detection (F16)
|
100% |
1331
15.8 IPS |
|
|
Face Detection (I8)
|
99% |
1330
15.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
2159
16.7 IPS |
|
|
Depth Estimation (F16)
|
100% |
2029
15.7 IPS |
|
|
Depth Estimation (I8)
|
99% |
2165
16.8 IPS |
|
|
Style Transfer (F32)
|
100% |
5197
6.84 IPS |
|
|
Style Transfer (F16)
|
100% |
4692
6.17 IPS |
|
|
Style Transfer (I8)
|
100% |
4729
6.22 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1040
37.1 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
989
35.3 IPS |
|
|
Image Super-Resolution (I8)
|
100% |
1011
36.1 IPS |
|
|
Text Classification (F32)
|
100% |
43
62.4 IPS |
|
|
Text Classification (F16)
|
100% |
100
144.1 IPS |
|
|
Text Classification (I8)
|
96% |
100
144.3 IPS |
|
|
Machine Translation (F32)
|
100% |
208
3.84 IPS |
|
|
Machine Translation (F16)
|
100% |
177
3.25 IPS |
|
|
Machine Translation (I8)
|
99% |
210
3.86 IPS |
