iPhone 14 Pro Max
Geekbench AI Score
3217
Single Precision Score
4947
Half Precision Score
4094
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | ak2wqkRoCBmBvqKVw |
| Upload Date | August 16 2024 02:08 AM |
| Views | 13 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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 | 5.48 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1455
270.6 IPS |
|
|
Image Classification (HP)
|
100% |
1935
359.9 IPS |
|
|
Image Classification (Q)
|
99% |
1938
361.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
1222
19.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
1255
20.3 IPS |
|
|
Image Segmentation (Q)
|
100% |
1245
20.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
6248
7.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
14453
16.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
12290
14.4 IPS |
|
|
Object Detection (SP)
|
100% |
1533
121.6 IPS |
|
|
Object Detection (HP)
|
97% |
2291
182.4 IPS |
|
|
Object Detection (Q)
|
94% |
1746
139.2 IPS |
|
|
Face Detection (SP)
|
100% |
2739
32.5 IPS |
|
|
Face Detection (HP)
|
100% |
4540
53.9 IPS |
|
|
Face Detection (Q)
|
100% |
2890
34.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
5507
42.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
8711
67.3 IPS |
|
|
Depth Estimation (Q)
|
96% |
4444
34.4 IPS |
|
|
Style Transfer (SP)
|
100% |
17596
22.6 IPS |
|
|
Style Transfer (HP)
|
100% |
27032
34.8 IPS |
|
|
Style Transfer (Q)
|
100% |
27334
35.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3886
143.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5245
193.7 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
3748
138.9 IPS |
|
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
|
Text Classification (HP)
|
100% |
4355
5.81 KIPS |
|
|
Text Classification (Q)
|
93% |
4325
5.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
2586
44.5 IPS |
|
|
Machine Translation (HP)
|
98% |
4474
77.3 IPS |
|
|
Machine Translation (Q)
|
98% |
4498
77.7 IPS |
