[iOS 18.0 beta 6] [LPM] iPhone 14 Pro Max iPhone 14 Pro Max
Geekbench AI Score
1595
Single Precision Score
2665
Half Precision Score
2337
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | nuonuo |
| Upload Date | August 15 2024 10:25 PM |
| Views | 14 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.51 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
587
109.1 IPS |
|
|
Image Classification (HP)
|
100% |
1062
197.4 IPS |
|
|
Image Classification (Q)
|
99% |
1069
199.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
692
11.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
998
16.2 IPS |
|
|
Image Segmentation (Q)
|
100% |
996
16.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
3026
3.53 IPS |
|
|
Pose Estimation (HP)
|
100% |
6169
7.20 IPS |
|
|
Pose Estimation (Q)
|
96% |
5643
6.61 IPS |
|
|
Object Detection (SP)
|
100% |
648
51.4 IPS |
|
|
Object Detection (HP)
|
97% |
1244
99.0 IPS |
|
|
Object Detection (Q)
|
94% |
900
71.7 IPS |
|
|
Face Detection (SP)
|
100% |
1669
19.8 IPS |
|
|
Face Detection (HP)
|
100% |
2679
31.8 IPS |
|
|
Face Detection (Q)
|
100% |
1488
17.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
2658
20.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
5236
40.5 IPS |
|
|
Depth Estimation (Q)
|
97% |
5239
40.5 IPS |
|
|
Style Transfer (SP)
|
100% |
7954
10.2 IPS |
|
|
Style Transfer (HP)
|
100% |
12422
16.0 IPS |
|
|
Style Transfer (Q)
|
100% |
12264
15.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1932
71.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2251
83.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
1648
61.1 IPS |
|
|
Text Classification (SP)
|
100% |
1226
1.64 KIPS |
|
|
Text Classification (HP)
|
100% |
2133
2.85 KIPS |
|
|
Text Classification (Q)
|
93% |
2149
2.88 KIPS |
|
|
Machine Translation (SP)
|
100% |
1602
27.6 IPS |
|
|
Machine Translation (HP)
|
98% |
2657
45.9 IPS |
|
|
Machine Translation (Q)
|
98% |
2659
45.9 IPS |
