iPad Pro (11-inch, 4th generation)
Geekbench AI Score
7005
Single Precision Score
7800
Half Precision Score
6897
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | December 24 2024 10:57 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
3640
676.9 IPS |
|
|
Image Classification (HP)
|
100% |
3637
676.4 IPS |
|
|
Image Classification (Q)
|
97% |
2993
558.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
4057
65.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
5003
81.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
5091
82.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
24635
28.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
26286
30.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
24497
28.7 IPS |
|
|
Object Detection (SP)
|
100% |
3686
292.4 IPS |
|
|
Object Detection (HP)
|
100% |
3689
292.6 IPS |
|
|
Object Detection (Q)
|
91% |
3048
243.6 IPS |
|
|
Face Detection (SP)
|
100% |
10387
123.4 IPS |
|
|
Face Detection (HP)
|
100% |
11993
142.5 IPS |
|
|
Face Detection (Q)
|
100% |
8405
99.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
16732
128.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
17812
137.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
14897
116.4 IPS |
|
|
Style Transfer (SP)
|
100% |
43196
55.5 IPS |
|
|
Style Transfer (HP)
|
100% |
48549
62.4 IPS |
|
|
Style Transfer (Q)
|
96% |
45478
58.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
9793
361.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
10108
373.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
7977
294.5 IPS |
|
|
Text Classification (SP)
|
100% |
2176
2.90 KIPS |
|
|
Text Classification (HP)
|
100% |
3630
4.84 KIPS |
|
|
Text Classification (Q)
|
93% |
3670
4.93 KIPS |
|
|
Machine Translation (SP)
|
100% |
1327
22.9 IPS |
|
|
Machine Translation (HP)
|
100% |
1242
21.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1286
22.2 IPS |
