iPad Pro (11-inch)
Geekbench AI Score
1020
Single Precision Score
1573
Half Precision Score
1367
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| User | gefrancis |
| Upload Date | January 31 2026 06:31 AM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.6 |
| 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% |
496
92.3 IPS |
|
|
Image Classification (HP)
|
100% |
829
154.2 IPS |
|
|
Image Classification (Q)
|
96% |
654
122.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
598
9.70 IPS |
|
|
Image Segmentation (HP)
|
100% |
975
15.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
1021
16.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2577
3.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
2220
2.59 IPS |
|
|
Pose Estimation (Q)
|
96% |
2065
2.42 IPS |
|
|
Object Detection (SP)
|
100% |
550
43.6 IPS |
|
|
Object Detection (HP)
|
99% |
973
77.1 IPS |
|
|
Object Detection (Q)
|
92% |
779
62.2 IPS |
|
|
Face Detection (SP)
|
100% |
1295
15.4 IPS |
|
|
Face Detection (HP)
|
100% |
2408
28.6 IPS |
|
|
Face Detection (Q)
|
100% |
1529
18.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
1762
13.6 IPS |
|
|
Depth Estimation (HP)
|
98% |
2734
21.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
2277
17.8 IPS |
|
|
Style Transfer (SP)
|
100% |
4803
6.17 IPS |
|
|
Style Transfer (HP)
|
100% |
7753
9.97 IPS |
|
|
Style Transfer (Q)
|
96% |
7091
9.15 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1268
46.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1436
53.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1204
44.5 IPS |
|
|
Text Classification (SP)
|
100% |
288
384.4 IPS |
|
|
Text Classification (HP)
|
100% |
564
753.3 IPS |
|
|
Text Classification (Q)
|
93% |
558
749.4 IPS |
|
|
Machine Translation (SP)
|
100% |
730
12.6 IPS |
|
|
Machine Translation (HP)
|
98% |
1287
22.2 IPS |
|
|
Machine Translation (Q)
|
98% |
1283
22.2 IPS |
