iPad Pro (11-inch)
Geekbench AI Score
1006
Single Precision Score
1553
Half Precision Score
1344
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | clusterfreak |
| Upload Date | November 17 2024 09:12 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,1 |
| Motherboard | J317AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.70 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
498
92.6 IPS |
|
|
Image Classification (HP)
|
100% |
803
149.3 IPS |
|
|
Image Classification (Q)
|
96% |
629
117.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
618
10.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
987
16.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
1024
16.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2523
2.94 IPS |
|
|
Pose Estimation (HP)
|
100% |
2200
2.57 IPS |
|
|
Pose Estimation (Q)
|
96% |
2030
2.38 IPS |
|
|
Object Detection (SP)
|
100% |
547
43.4 IPS |
|
|
Object Detection (HP)
|
99% |
964
76.5 IPS |
|
|
Object Detection (Q)
|
92% |
765
61.0 IPS |
|
|
Face Detection (SP)
|
100% |
1267
15.1 IPS |
|
|
Face Detection (HP)
|
100% |
2346
27.9 IPS |
|
|
Face Detection (Q)
|
100% |
1503
17.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
1724
13.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
2686
20.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
2213
17.3 IPS |
|
|
Style Transfer (SP)
|
100% |
4505
5.79 IPS |
|
|
Style Transfer (HP)
|
100% |
7824
10.1 IPS |
|
|
Style Transfer (Q)
|
96% |
6988
9.02 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1242
45.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1432
52.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1210
44.7 IPS |
|
|
Text Classification (SP)
|
100% |
284
379.7 IPS |
|
|
Text Classification (HP)
|
99% |
549
732.5 IPS |
|
|
Text Classification (Q)
|
93% |
546
733.2 IPS |
|
|
Machine Translation (SP)
|
100% |
721
12.4 IPS |
|
|
Machine Translation (HP)
|
98% |
1254
21.7 IPS |
|
|
Machine Translation (Q)
|
98% |
1254
21.7 IPS |
