iPad Pro (11-inch)
Geekbench AI Score
676
Single Precision Score
2386
Half Precision Score
420
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | dudleynyc |
| Upload Date | October 09 2024 04:59 PM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,3 |
| Motherboard | J318AP |
| 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 | 3.70 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
332
61.8 IPS |
|
|
Image Classification (HP)
|
100% |
2202
409.5 IPS |
|
|
Image Classification (Q)
|
99% |
170
31.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
300
4.87 IPS |
|
|
Image Segmentation (HP)
|
100% |
405
6.57 IPS |
|
|
Image Segmentation (Q)
|
99% |
227
3.69 IPS |
|
|
Pose Estimation (SP)
|
100% |
1930
2.25 IPS |
|
|
Pose Estimation (HP)
|
100% |
27230
31.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
1280
1.50 IPS |
|
|
Object Detection (SP)
|
100% |
377
29.9 IPS |
|
|
Object Detection (HP)
|
100% |
1565
124.1 IPS |
|
|
Object Detection (Q)
|
94% |
202
16.1 IPS |
|
|
Face Detection (SP)
|
100% |
838
9.96 IPS |
|
|
Face Detection (HP)
|
100% |
6461
76.8 IPS |
|
|
Face Detection (Q)
|
100% |
290
3.45 IPS |
|
|
Depth Estimation (SP)
|
100% |
918
7.07 IPS |
|
|
Depth Estimation (HP)
|
99% |
23197
178.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
536
4.18 IPS |
|
|
Style Transfer (SP)
|
100% |
2520
3.24 IPS |
|
|
Style Transfer (HP)
|
100% |
2513
3.23 IPS |
|
|
Style Transfer (Q)
|
96% |
1948
2.51 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
946
34.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3606
133.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
501
18.5 IPS |
|
|
Text Classification (SP)
|
100% |
306
409.0 IPS |
|
|
Text Classification (HP)
|
100% |
304
405.9 IPS |
|
|
Text Classification (Q)
|
93% |
300
402.6 IPS |
|
|
Machine Translation (SP)
|
100% |
492
8.47 IPS |
|
|
Machine Translation (HP)
|
100% |
382
6.58 IPS |
|
|
Machine Translation (Q)
|
98% |
380
6.57 IPS |
