iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
720
Single Precision Score
2429
Half Precision Score
443
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | March 03 2026 09:53 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
343
63.7 IPS |
|
|
Image Classification (HP)
|
100% |
2277
423.5 IPS |
|
|
Image Classification (Q)
|
99% |
170
31.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
296
4.80 IPS |
|
|
Image Segmentation (HP)
|
100% |
383
6.21 IPS |
|
|
Image Segmentation (Q)
|
99% |
227
3.67 IPS |
|
|
Pose Estimation (SP)
|
100% |
2195
2.56 IPS |
|
|
Pose Estimation (HP)
|
100% |
27995
32.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
1516
1.78 IPS |
|
|
Object Detection (SP)
|
100% |
384
30.4 IPS |
|
|
Object Detection (HP)
|
100% |
1452
115.1 IPS |
|
|
Object Detection (Q)
|
94% |
206
16.4 IPS |
|
|
Face Detection (SP)
|
100% |
846
10.0 IPS |
|
|
Face Detection (HP)
|
100% |
6629
78.8 IPS |
|
|
Face Detection (Q)
|
100% |
307
3.65 IPS |
|
|
Depth Estimation (SP)
|
100% |
1047
8.06 IPS |
|
|
Depth Estimation (HP)
|
99% |
25026
192.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
612
4.78 IPS |
|
|
Style Transfer (SP)
|
100% |
3312
4.26 IPS |
|
|
Style Transfer (HP)
|
100% |
3117
4.01 IPS |
|
|
Style Transfer (Q)
|
96% |
2330
3.01 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
984
36.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3428
126.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
502
18.5 IPS |
|
|
Text Classification (SP)
|
100% |
311
415.4 IPS |
|
|
Text Classification (HP)
|
100% |
306
408.5 IPS |
|
|
Text Classification (Q)
|
93% |
299
401.4 IPS |
|
|
Machine Translation (SP)
|
100% |
493
8.49 IPS |
|
|
Machine Translation (HP)
|
100% |
372
6.41 IPS |
|
|
Machine Translation (Q)
|
98% |
371
6.41 IPS |
