iPhone 12 Pro Max
Geekbench AI Score
1325
Single Precision Score
1390
Half Precision Score
540
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| Upload Date | November 06 2024 02:46 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 12 Pro Max |
| Model ID | iPhone13,4 |
| Motherboard | D54pAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.52 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
323
60.1 IPS |
|
|
Image Classification (HP)
|
100% |
328
61.0 IPS |
|
|
Image Classification (Q)
|
97% |
308
57.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1130
18.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
1249
20.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
1229
19.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
4724
5.51 IPS |
|
|
Pose Estimation (HP)
|
100% |
5270
6.15 IPS |
|
|
Pose Estimation (Q)
|
97% |
4601
5.39 IPS |
|
|
Object Detection (SP)
|
100% |
647
51.3 IPS |
|
|
Object Detection (HP)
|
100% |
662
52.5 IPS |
|
|
Object Detection (Q)
|
92% |
610
48.7 IPS |
|
|
Face Detection (SP)
|
100% |
2685
31.9 IPS |
|
|
Face Detection (HP)
|
100% |
2946
35.0 IPS |
|
|
Face Detection (Q)
|
100% |
2113
25.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4104
31.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
4489
34.6 IPS |
|
|
Depth Estimation (Q)
|
1% |
0
29.1 IPS |
|
|
Style Transfer (SP)
|
100% |
9985
12.8 IPS |
|
|
Style Transfer (HP)
|
100% |
11700
15.0 IPS |
|
|
Style Transfer (Q)
|
96% |
11719
15.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1494
55.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1418
52.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1394
51.5 IPS |
|
|
Text Classification (SP)
|
100% |
237
316.0 IPS |
|
|
Text Classification (HP)
|
100% |
239
319.6 IPS |
|
|
Text Classification (Q)
|
93% |
163
219.2 IPS |
|
|
Machine Translation (SP)
|
100% |
386
6.64 IPS |
|
|
Machine Translation (HP)
|
100% |
361
6.22 IPS |
|
|
Machine Translation (Q)
|
98% |
353
6.10 IPS |
