iPhone 12 Pro Max
Geekbench AI Score
19
Single Precision Score
46
Half Precision Score
83
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| Upload Date | October 31 2024 09:00 AM |
| Views | 14 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| 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% |
1170
217.5 IPS |
|
|
Image Classification (HP)
|
100% |
1476
274.4 IPS |
|
|
Image Classification (Q)
|
96% |
1189
222.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1000
16.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1019
16.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
1518
24.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
5132
5.99 IPS |
|
|
Pose Estimation (HP)
|
100% |
10883
12.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
9698
11.4 IPS |
|
|
Object Detection (SP)
|
0
|
||
|
Object Detection (HP)
|
98% |
1026
81.6 IPS |
|
|
Object Detection (Q)
|
94% |
449
35.8 IPS |
|
|
Face Detection (SP)
|
100% |
1660
19.7 IPS |
|
|
Face Detection (HP)
|
0
|
||
|
Face Detection (Q)
|
0
|
||
|
Depth Estimation (SP)
|
0
|
||
|
Depth Estimation (HP)
|
0
|
||
|
Depth Estimation (Q)
|
0
|
||
|
Style Transfer (SP)
|
0
|
||
|
Style Transfer (HP)
|
0
|
||
|
Style Transfer (Q)
|
0
|
||
|
Image Super-Resolution (SP)
|
0
|
||
|
Image Super-Resolution (HP)
|
0
|
||
|
Image Super-Resolution (Q)
|
0
|
||
|
Text Classification (SP)
|
0
|
||
|
Text Classification (HP)
|
0
|
||
|
Text Classification (Q)
|
93% |
745
999.4 IPS |
|
|
Machine Translation (SP)
|
0
|
||
|
Machine Translation (HP)
|
98% |
2792
48.2 IPS |
|
|
Machine Translation (Q)
|
98% |
2744
47.4 IPS |
