iPad Pro (11-inch)
Geekbench AI Score
516
Single Precision Score
929
Half Precision Score
728
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| Upload Date | September 03 2025 05:09 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.6.2 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,1 |
| Motherboard | J317AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.70 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
409
76.0 IPS |
|
|
Image Classification (HP)
|
100% |
242
45.0 IPS |
|
|
Image Classification (Q)
|
96% |
216
40.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
199
3.22 IPS |
|
|
Image Segmentation (HP)
|
100% |
730
11.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
311
5.06 IPS |
|
|
Pose Estimation (SP)
|
100% |
1002
1.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
1076
1.26 IPS |
|
|
Pose Estimation (Q)
|
96% |
1059
1.24 IPS |
|
|
Object Detection (SP)
|
100% |
242
19.2 IPS |
|
|
Object Detection (HP)
|
99% |
616
48.9 IPS |
|
|
Object Detection (Q)
|
92% |
311
24.8 IPS |
|
|
Face Detection (SP)
|
100% |
414
4.91 IPS |
|
|
Face Detection (HP)
|
100% |
1298
15.4 IPS |
|
|
Face Detection (Q)
|
100% |
810
9.62 IPS |
|
|
Depth Estimation (SP)
|
100% |
659
5.08 IPS |
|
|
Depth Estimation (HP)
|
98% |
1400
10.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
1312
10.2 IPS |
|
|
Style Transfer (SP)
|
100% |
2614
3.36 IPS |
|
|
Style Transfer (HP)
|
100% |
3695
4.75 IPS |
|
|
Style Transfer (Q)
|
96% |
3957
5.11 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
575
21.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
941
34.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
734
27.1 IPS |
|
|
Text Classification (SP)
|
100% |
252
336.6 IPS |
|
|
Text Classification (HP)
|
100% |
539
718.8 IPS |
|
|
Text Classification (Q)
|
93% |
509
682.8 IPS |
|
|
Machine Translation (SP)
|
100% |
664
11.4 IPS |
|
|
Machine Translation (HP)
|
98% |
1205
20.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1203
20.8 IPS |
