iPad Pro (12.9-inch 5th generation)
Geekbench AI Score
4852
Single Precision Score
5768
Half Precision Score
5045
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | Wwessex |
| Upload Date | October 08 2024 11:26 PM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,8 |
| Motherboard | J522AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.35 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1927
358.4 IPS |
|
|
Image Classification (HP)
|
100% |
2191
407.4 IPS |
|
|
Image Classification (Q)
|
97% |
1991
371.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
2732
44.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
3641
59.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
3693
59.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
16967
19.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
18379
21.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
16944
19.9 IPS |
|
|
Object Detection (SP)
|
100% |
2730
216.6 IPS |
|
|
Object Detection (HP)
|
100% |
2771
219.8 IPS |
|
|
Object Detection (Q)
|
91% |
2216
177.1 IPS |
|
|
Face Detection (SP)
|
100% |
6843
81.3 IPS |
|
|
Face Detection (HP)
|
100% |
8351
99.2 IPS |
|
|
Face Detection (Q)
|
100% |
5832
69.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
12222
94.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
13709
105.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
11218
87.7 IPS |
|
|
Style Transfer (SP)
|
100% |
28732
36.9 IPS |
|
|
Style Transfer (HP)
|
100% |
34126
43.9 IPS |
|
|
Style Transfer (Q)
|
96% |
32586
42.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6425
237.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8059
297.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5417
200.0 IPS |
|
|
Text Classification (SP)
|
100% |
2266
3.02 KIPS |
|
|
Text Classification (HP)
|
100% |
3794
5.06 KIPS |
|
|
Text Classification (Q)
|
93% |
3804
5.11 KIPS |
|
|
Machine Translation (SP)
|
100% |
849
14.6 IPS |
|
|
Machine Translation (HP)
|
100% |
840
14.5 IPS |
|
|
Machine Translation (Q)
|
98% |
881
15.2 IPS |
