iPad Pro (12.9-inch 3rd Generation)
Geekbench ML Score
1816
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | July 26 2025 10:44 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| 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 |
| L1 Instruction Cache | 48.0 KB x 1 |
| L1 Data Cache | 32.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 3.66 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
2468
264.4 IPS |
|
|
Image Classification (F16)
|
100% |
4456
477.5 IPS |
|
|
Image Classification (I8)
|
81% |
397
42.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
5194
32.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
8602
53.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
734
4.53 IPS |
|
|
Pose Estimation (F32)
|
100% |
1863
7.54 IPS |
|
|
Pose Estimation (F16)
|
100% |
5181
21.0 IPS |
|
|
Pose Estimation (I8)
|
80% |
141
0.57 IPS |
|
|
Object Detection (F32)
|
100% |
2646
92.9 IPS |
|
|
Object Detection (F16)
|
100% |
2847
99.9 IPS |
|
|
Object Detection (I8)
|
52% |
570
20.0 IPS |
|
|
Face Detection (F32)
|
100% |
4951
56.9 IPS |
|
|
Face Detection (F16)
|
97% |
9332
107.2 IPS |
|
|
Face Detection (I8)
|
75% |
552
6.35 IPS |
|
|
Text Classification (F32)
|
100% |
2054
812.4 IPS |
|
|
Text Classification (F16)
|
100% |
2018
798.2 IPS |
|
|
Machine Translation (F32)
|
100% |
961
148.2 IPS |
|
|
Machine Translation (F16)
|
100% |
989
152.4 IPS |
