iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
717
Single Precision Score
2460
Half Precision Score
448
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| Upload Date | January 04 2025 02:52 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,5 |
| Motherboard | J320AP |
| 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% |
351
65.3 IPS |
|
|
Image Classification (HP)
|
100% |
2332
433.7 IPS |
|
|
Image Classification (Q)
|
99% |
176
32.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
303
4.92 IPS |
|
|
Image Segmentation (HP)
|
100% |
404
6.55 IPS |
|
|
Image Segmentation (Q)
|
99% |
226
3.66 IPS |
|
|
Pose Estimation (SP)
|
100% |
2231
2.60 IPS |
|
|
Pose Estimation (HP)
|
100% |
27058
31.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
1536
1.80 IPS |
|
|
Object Detection (SP)
|
100% |
385
30.5 IPS |
|
|
Object Detection (HP)
|
100% |
1462
116.0 IPS |
|
|
Object Detection (Q)
|
94% |
210
16.7 IPS |
|
|
Face Detection (SP)
|
100% |
861
10.2 IPS |
|
|
Face Detection (HP)
|
100% |
6567
78.0 IPS |
|
|
Face Detection (Q)
|
100% |
302
3.59 IPS |
|
|
Depth Estimation (SP)
|
100% |
1052
8.10 IPS |
|
|
Depth Estimation (HP)
|
99% |
22945
176.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
599
4.68 IPS |
|
|
Style Transfer (SP)
|
100% |
3612
4.64 IPS |
|
|
Style Transfer (HP)
|
100% |
3572
4.59 IPS |
|
|
Style Transfer (Q)
|
96% |
2558
3.30 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
958
35.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3675
135.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
505
18.6 IPS |
|
|
Text Classification (SP)
|
100% |
262
349.4 IPS |
|
|
Text Classification (HP)
|
100% |
301
402.2 IPS |
|
|
Text Classification (Q)
|
93% |
303
406.9 IPS |
|
|
Machine Translation (SP)
|
100% |
481
8.28 IPS |
|
|
Machine Translation (HP)
|
100% |
366
6.31 IPS |
|
|
Machine Translation (Q)
|
98% |
364
6.30 IPS |
