iPhone 15 Pro Max
Geekbench AI Score
2623
Single Precision Score
13921
Half Precision Score
17828
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| Upload Date | September 16 2024 09:44 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 15 Pro Max |
| Model ID | iPhone16,2 |
| Motherboard | D84AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1416
263.3 IPS |
|
|
Image Classification (HP)
|
100% |
6192
1.15 KIPS |
|
|
Image Classification (Q)
|
97% |
7512
1.40 KIPS |
|
|
Image Segmentation (SP)
|
100% |
789
12.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
5214
84.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
10055
163.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
7117
8.30 IPS |
|
|
Pose Estimation (HP)
|
100% |
86790
101.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
152011
178.2 IPS |
|
|
Object Detection (SP)
|
100% |
1434
113.7 IPS |
|
|
Object Detection (HP)
|
100% |
8180
648.9 IPS |
|
|
Object Detection (Q)
|
93% |
9991
797.2 IPS |
|
|
Face Detection (SP)
|
100% |
2130
25.3 IPS |
|
|
Face Detection (HP)
|
100% |
11264
133.8 IPS |
|
|
Face Detection (Q)
|
100% |
13314
158.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4433
34.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
43320
333.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
58143
454.6 IPS |
|
|
Style Transfer (SP)
|
100% |
11717
15.1 IPS |
|
|
Style Transfer (HP)
|
100% |
128249
164.9 IPS |
|
|
Style Transfer (Q)
|
96% |
137670
177.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3732
137.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18474
682.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
26084
963.2 IPS |
|
|
Text Classification (SP)
|
100% |
1749
2.33 KIPS |
|
|
Text Classification (HP)
|
71% |
4088
5.88 KIPS |
|
|
Text Classification (Q)
|
69% |
4080
5.98 KIPS |
|
|
Machine Translation (SP)
|
100% |
1879
32.4 IPS |
|
|
Machine Translation (HP)
|
100% |
2524
43.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2494
43.1 IPS |
