iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
245
Single Precision Score
2033
Half Precision Score
344
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | September 02 2025 09:06 PM |
| Views | 10 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,7 |
| Motherboard | J321AP |
| 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 | 3.66 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
310
57.7 IPS |
|
|
Image Classification (HP)
|
100% |
2238
416.2 IPS |
|
|
Image Classification (Q)
|
99% |
163
30.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
287
4.66 IPS |
|
|
Image Segmentation (HP)
|
100% |
368
5.97 IPS |
|
|
Image Segmentation (Q)
|
99% |
215
3.49 IPS |
|
|
Pose Estimation (SP)
|
100% |
1218
1.42 IPS |
|
|
Pose Estimation (HP)
|
100% |
26927
31.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
917
1.07 IPS |
|
|
Object Detection (SP)
|
100% |
345
27.4 IPS |
|
|
Object Detection (HP)
|
100% |
1407
111.6 IPS |
|
|
Object Detection (Q)
|
94% |
198
15.8 IPS |
|
|
Face Detection (SP)
|
100% |
824
9.79 IPS |
|
|
Face Detection (HP)
|
100% |
6558
77.9 IPS |
|
|
Face Detection (Q)
|
100% |
284
3.37 IPS |
|
|
Depth Estimation (SP)
|
100% |
891
6.87 IPS |
|
|
Depth Estimation (HP)
|
99% |
23344
179.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
498
3.89 IPS |
|
|
Style Transfer (SP)
|
0
|
||
|
Style Transfer (HP)
|
100% |
2109
2.71 IPS |
|
|
Style Transfer (Q)
|
96% |
1722
2.22 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
522
19.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2542
93.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
345
12.7 IPS |
|
|
Text Classification (SP)
|
100% |
242
323.5 IPS |
|
|
Text Classification (HP)
|
100% |
204
271.6 IPS |
|
|
Text Classification (Q)
|
93% |
211
283.4 IPS |
|
|
Machine Translation (SP)
|
100% |
227
3.90 IPS |
|
|
Machine Translation (HP)
|
100% |
232
4.00 IPS |
|
|
Machine Translation (Q)
|
98% |
210
3.62 IPS |
