iPhone 15 Pro Max
Geekbench AI Score
2722
Single Precision Score
13903
Half Precision Score
15920
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | ehixson |
| Upload Date | August 29 2024 08:11 PM |
| Views | 4 |
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% |
1441
268.0 IPS |
|
|
Image Classification (HP)
|
100% |
6306
1.17 KIPS |
|
|
Image Classification (Q)
|
99% |
6874
1.28 KIPS |
|
|
Image Segmentation (SP)
|
100% |
799
13.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
5196
84.2 IPS |
|
|
Image Segmentation (Q)
|
100% |
5228
84.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
7682
8.96 IPS |
|
|
Pose Estimation (HP)
|
100% |
89717
104.7 IPS |
|
|
Pose Estimation (Q)
|
94% |
138946
163.0 IPS |
|
|
Object Detection (SP)
|
100% |
1467
116.4 IPS |
|
|
Object Detection (HP)
|
100% |
8179
648.8 IPS |
|
|
Object Detection (Q)
|
93% |
9711
774.8 IPS |
|
|
Face Detection (SP)
|
100% |
2165
25.7 IPS |
|
|
Face Detection (HP)
|
100% |
11144
132.4 IPS |
|
|
Face Detection (Q)
|
100% |
12884
153.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4581
35.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
42866
330.3 IPS |
|
|
Depth Estimation (Q)
|
97% |
47640
368.4 IPS |
|
|
Style Transfer (SP)
|
100% |
12233
15.7 IPS |
|
|
Style Transfer (HP)
|
100% |
128229
164.8 IPS |
|
|
Style Transfer (Q)
|
100% |
128313
164.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4115
152.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18125
669.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
25576
947.6 IPS |
|
|
Text Classification (SP)
|
100% |
1810
2.42 KIPS |
|
|
Text Classification (HP)
|
71% |
4581
6.59 KIPS |
|
|
Text Classification (Q)
|
69% |
4497
6.59 KIPS |
|
|
Machine Translation (SP)
|
100% |
1910
32.9 IPS |
|
|
Machine Translation (HP)
|
100% |
2207
38.0 IPS |
|
|
Machine Translation (Q)
|
98% |
2381
41.2 IPS |
