iPad Pro (12.9-inch 3rd Generation)
Geekbench AI Score
965
Single Precision Score
1539
Half Precision Score
1348
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | April 15 2026 05:03 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,7 |
| Motherboard | J321AP |
| 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 | 3.66 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
491
91.4 IPS |
|
|
Image Classification (HP)
|
100% |
815
151.5 IPS |
|
|
Image Classification (Q)
|
96% |
641
119.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
606
9.82 IPS |
|
|
Image Segmentation (HP)
|
100% |
969
15.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1009
16.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
2518
2.94 IPS |
|
|
Pose Estimation (HP)
|
100% |
2303
2.69 IPS |
|
|
Pose Estimation (Q)
|
96% |
2106
2.47 IPS |
|
|
Object Detection (SP)
|
100% |
542
43.0 IPS |
|
|
Object Detection (HP)
|
99% |
953
75.6 IPS |
|
|
Object Detection (Q)
|
92% |
759
60.6 IPS |
|
|
Face Detection (SP)
|
100% |
1244
14.8 IPS |
|
|
Face Detection (HP)
|
100% |
2317
27.5 IPS |
|
|
Face Detection (Q)
|
100% |
1468
17.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
1285
9.90 IPS |
|
|
Depth Estimation (HP)
|
98% |
2422
18.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
2001
15.6 IPS |
|
|
Style Transfer (SP)
|
100% |
3079
3.96 IPS |
|
|
Style Transfer (HP)
|
100% |
5244
6.74 IPS |
|
|
Style Transfer (Q)
|
96% |
4869
6.28 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1132
41.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1317
48.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1198
44.3 IPS |
|
|
Text Classification (SP)
|
99% |
457
609.9 IPS |
|
|
Text Classification (HP)
|
99% |
880
1.17 KIPS |
|
|
Text Classification (Q)
|
93% |
884
1.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
684
11.8 IPS |
|
|
Machine Translation (HP)
|
99% |
1269
21.9 IPS |
|
|
Machine Translation (Q)
|
98% |
1272
22.0 IPS |
