iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
718
Single Precision Score
2447
Half Precision Score
444
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | April 04 2026 06:41 AM |
| Views | 6 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| 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% |
347
64.5 IPS |
|
|
Image Classification (HP)
|
100% |
2382
442.9 IPS |
|
|
Image Classification (Q)
|
99% |
165
30.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
304
4.92 IPS |
|
|
Image Segmentation (HP)
|
100% |
371
6.02 IPS |
|
|
Image Segmentation (Q)
|
99% |
227
3.67 IPS |
|
|
Pose Estimation (SP)
|
100% |
2191
2.56 IPS |
|
|
Pose Estimation (HP)
|
100% |
27703
32.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
1522
1.78 IPS |
|
|
Object Detection (SP)
|
100% |
382
30.3 IPS |
|
|
Object Detection (HP)
|
100% |
1434
113.7 IPS |
|
|
Object Detection (Q)
|
94% |
208
16.6 IPS |
|
|
Face Detection (SP)
|
100% |
865
10.3 IPS |
|
|
Face Detection (HP)
|
100% |
6747
80.2 IPS |
|
|
Face Detection (Q)
|
100% |
302
3.59 IPS |
|
|
Depth Estimation (SP)
|
100% |
1056
8.13 IPS |
|
|
Depth Estimation (HP)
|
99% |
23428
180.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
609
4.75 IPS |
|
|
Style Transfer (SP)
|
100% |
3548
4.56 IPS |
|
|
Style Transfer (HP)
|
100% |
3517
4.52 IPS |
|
|
Style Transfer (Q)
|
96% |
2538
3.28 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
970
35.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3421
126.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
494
18.2 IPS |
|
|
Text Classification (SP)
|
100% |
268
357.6 IPS |
|
|
Text Classification (HP)
|
100% |
305
406.8 IPS |
|
|
Text Classification (Q)
|
93% |
302
406.0 IPS |
|
|
Machine Translation (SP)
|
100% |
492
8.47 IPS |
|
|
Machine Translation (HP)
|
100% |
378
6.52 IPS |
|
|
Machine Translation (Q)
|
98% |
362
6.25 IPS |
