iPad13,18
Geekbench AI Score
92
Single Precision Score
737
Half Precision Score
241
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| Upload Date | November 06 2025 03:33 PM |
| Views | 14 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.3.2 |
| Model | iPad13,18 |
| Model ID | iPad13,18 |
| Motherboard | J271AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.73 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1200
223.2 IPS |
|
|
Image Classification (HP)
|
100% |
1899
353.1 IPS |
|
|
Image Classification (Q)
|
96% |
1359
253.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1059
17.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1744
28.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
2164
35.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
5250
6.13 IPS |
|
|
Pose Estimation (HP)
|
100% |
10737
12.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
9513
11.2 IPS |
|
|
Object Detection (SP)
|
100% |
1299
103.1 IPS |
|
|
Object Detection (HP)
|
97% |
2132
169.7 IPS |
|
|
Object Detection (Q)
|
94% |
1559
124.2 IPS |
|
|
Face Detection (SP)
|
100% |
2385
28.3 IPS |
|
|
Face Detection (HP)
|
100% |
4481
53.2 IPS |
|
|
Face Detection (Q)
|
100% |
2591
30.8 IPS |
|
|
Depth Estimation (SP)
|
0
|
||
|
Depth Estimation (HP)
|
98% |
3519
27.2 IPS |
|
|
Depth Estimation (Q)
|
0
|
||
|
Style Transfer (SP)
|
0
|
||
|
Style Transfer (HP)
|
100% |
10634
13.7 IPS |
|
|
Style Transfer (Q)
|
0
|
||
|
Image Super-Resolution (SP)
|
0
|
||
|
Image Super-Resolution (HP)
|
0
|
||
|
Image Super-Resolution (Q)
|
0
|
||
|
Text Classification (SP)
|
0
|
||
|
Text Classification (HP)
|
100% |
3746
5.00 KIPS |
|
|
Text Classification (Q)
|
93% |
3769
5.06 KIPS |
|
|
Machine Translation (SP)
|
100% |
2109
36.3 IPS |
|
|
Machine Translation (HP)
|
0
|
||
|
Machine Translation (Q)
|
98% |
1600
27.7 IPS |
