iPad (8th generation)
Geekbench AI Score
662
Single Precision Score
1083
Half Precision Score
979
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | January 04 2025 11:17 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.88 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
391
72.6 IPS |
|
|
Image Classification (HP)
|
100% |
666
123.9 IPS |
|
|
Image Classification (Q)
|
96% |
545
101.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
422
6.83 IPS |
|
|
Image Segmentation (HP)
|
100% |
733
11.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
786
12.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
1164
1.36 IPS |
|
|
Pose Estimation (HP)
|
100% |
1113
1.30 IPS |
|
|
Pose Estimation (Q)
|
96% |
1076
1.26 IPS |
|
|
Object Detection (SP)
|
100% |
359
28.5 IPS |
|
|
Object Detection (HP)
|
99% |
700
55.5 IPS |
|
|
Object Detection (Q)
|
92% |
593
47.4 IPS |
|
|
Face Detection (SP)
|
100% |
924
11.0 IPS |
|
|
Face Detection (HP)
|
100% |
1795
21.3 IPS |
|
|
Face Detection (Q)
|
100% |
1181
14.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
945
7.28 IPS |
|
|
Depth Estimation (HP)
|
98% |
1638
12.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
1452
11.3 IPS |
|
|
Style Transfer (SP)
|
100% |
2378
3.06 IPS |
|
|
Style Transfer (HP)
|
100% |
4019
5.17 IPS |
|
|
Style Transfer (Q)
|
96% |
3921
5.06 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
642
23.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
880
32.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
775
28.6 IPS |
|
|
Text Classification (SP)
|
100% |
286
382.3 IPS |
|
|
Text Classification (HP)
|
100% |
561
748.7 IPS |
|
|
Text Classification (Q)
|
93% |
561
752.8 IPS |
|
|
Machine Translation (SP)
|
100% |
616
10.6 IPS |
|
|
Machine Translation (HP)
|
98% |
1006
17.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1017
17.6 IPS |
