iPad Pro (11-inch, 4th generation)
Geekbench AI Score
1584
Single Precision Score
2491
Half Precision Score
1861
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| Upload Date | November 21 2024 01:02 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad Pro (11-inch, 4th generation) |
| Model ID | iPad14,3 |
| Motherboard | J617AP |
| CPU Information | |
|---|---|
| Name | Apple M2 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.37 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1396
259.6 IPS |
|
|
Image Classification (HP)
|
100% |
2518
468.3 IPS |
|
|
Image Classification (Q)
|
96% |
1763
329.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1538
24.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
2477
40.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
2861
46.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
6852
8.00 IPS |
|
|
Pose Estimation (HP)
|
100% |
14913
17.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
12910
15.1 IPS |
|
|
Object Detection (SP)
|
100% |
1567
124.3 IPS |
|
|
Object Detection (HP)
|
97% |
2885
229.7 IPS |
|
|
Object Detection (Q)
|
94% |
2080
165.8 IPS |
|
|
Face Detection (SP)
|
100% |
3167
37.6 IPS |
|
|
Face Detection (HP)
|
100% |
6226
74.0 IPS |
|
|
Face Detection (Q)
|
100% |
3584
42.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
5688
43.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
11658
90.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
1923
15.0 IPS |
|
|
Style Transfer (SP)
|
100% |
19063
24.5 IPS |
|
|
Style Transfer (HP)
|
100% |
29126
37.4 IPS |
|
|
Style Transfer (Q)
|
96% |
23865
30.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3465
127.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2803
103.5 IPS |
|
|
Image Super-Resolution (Q)
|
0
|
||
|
Text Classification (SP)
|
0
|
||
|
Text Classification (HP)
|
0
|
||
|
Text Classification (Q)
|
93% |
3805
5.11 KIPS |
|
|
Machine Translation (SP)
|
100% |
3635
62.6 IPS |
|
|
Machine Translation (HP)
|
98% |
5802
100.3 IPS |
|
|
Machine Translation (Q)
|
98% |
5889
101.8 IPS |
