iPad Pro (12.9-inch 2nd Generation)
Geekbench AI Score
630
Single Precision Score
30
Half Precision Score
29
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| Upload Date | November 01 2025 07:27 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A10X Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.7.10 |
| Model | iPad Pro (12.9-inch 2nd Generation) |
| Model ID | iPad7,2 |
| Motherboard | J121AP |
| CPU Information | |
|---|---|
| Name | Apple A10X Fusion |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 2.34 GHz |
| Cluster 1 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 3.88 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
344
64.1 IPS |
|
|
Image Classification (HP)
|
100% |
14
2.59 IPS |
|
|
Image Classification (Q)
|
96% |
13
2.49 IPS |
|
|
Image Segmentation (SP)
|
100% |
329
5.33 IPS |
|
|
Image Segmentation (HP)
|
100% |
19
0.30 IPS |
|
|
Image Segmentation (Q)
|
99% |
18
0.29 IPS |
|
|
Pose Estimation (SP)
|
100% |
1685
1.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
21
0.02 IPS |
|
|
Pose Estimation (Q)
|
94% |
21
0.02 IPS |
|
|
Object Detection (SP)
|
100% |
349
27.7 IPS |
|
|
Object Detection (HP)
|
99% |
13
1.07 IPS |
|
|
Object Detection (Q)
|
93% |
13
1.04 IPS |
|
|
Face Detection (SP)
|
100% |
711
8.44 IPS |
|
|
Face Detection (HP)
|
100% |
45
0.53 IPS |
|
|
Face Detection (Q)
|
100% |
41
0.49 IPS |
|
|
Depth Estimation (SP)
|
100% |
822
6.33 IPS |
|
|
Depth Estimation (HP)
|
98% |
31
0.24 IPS |
|
|
Depth Estimation (Q)
|
85% |
30
0.23 IPS |
|
|
Style Transfer (SP)
|
100% |
2596
3.34 IPS |
|
|
Style Transfer (HP)
|
100% |
67
0.09 IPS |
|
|
Style Transfer (Q)
|
96% |
67
0.09 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
717
26.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
14
0.51 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
14
0.50 IPS |
|
|
Text Classification (SP)
|
100% |
255
341.0 IPS |
|
|
Text Classification (HP)
|
100% |
220
293.2 IPS |
|
|
Text Classification (Q)
|
93% |
218
292.9 IPS |
|
|
Machine Translation (SP)
|
100% |
534
9.20 IPS |
|
|
Machine Translation (HP)
|
96% |
33
0.58 IPS |
|
|
Machine Translation (Q)
|
98% |
33
0.58 IPS |
