iPad Pro (11-inch)
Geekbench AI Score
872
Single Precision Score
1430
Half Precision Score
1188
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | January 04 2025 04:36 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| 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% |
482
89.7 IPS |
|
|
Image Classification (HP)
|
100% |
824
153.3 IPS |
|
|
Image Classification (Q)
|
96% |
646
120.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
596
9.66 IPS |
|
|
Image Segmentation (HP)
|
100% |
973
15.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
1018
16.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2186
2.55 IPS |
|
|
Pose Estimation (HP)
|
100% |
1975
2.30 IPS |
|
|
Pose Estimation (Q)
|
96% |
1451
1.70 IPS |
|
|
Object Detection (SP)
|
100% |
475
37.7 IPS |
|
|
Object Detection (HP)
|
99% |
930
73.8 IPS |
|
|
Object Detection (Q)
|
92% |
713
56.9 IPS |
|
|
Face Detection (SP)
|
100% |
1139
13.5 IPS |
|
|
Face Detection (HP)
|
100% |
2297
27.3 IPS |
|
|
Face Detection (Q)
|
100% |
1447
17.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
1284
9.89 IPS |
|
|
Depth Estimation (HP)
|
98% |
2365
18.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
1929
15.1 IPS |
|
|
Style Transfer (SP)
|
100% |
3082
3.96 IPS |
|
|
Style Transfer (HP)
|
100% |
5251
6.75 IPS |
|
|
Style Transfer (Q)
|
96% |
4509
5.82 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1026
37.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1308
48.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1000
36.9 IPS |
|
|
Text Classification (SP)
|
100% |
271
361.3 IPS |
|
|
Text Classification (HP)
|
99% |
541
721.7 IPS |
|
|
Text Classification (Q)
|
93% |
542
727.3 IPS |
|
|
Machine Translation (SP)
|
100% |
682
11.7 IPS |
|
|
Machine Translation (HP)
|
98% |
1211
20.9 IPS |
|
|
Machine Translation (Q)
|
98% |
1215
21.0 IPS |
