iPhone 16 Pro Max
Geekbench AI Score
4491
Single Precision Score
32111
Half Precision Score
44505
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | January 04 2025 08:33 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.0.1 |
| Model | iPhone 16 Pro Max |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | Apple A18 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1991
370.2 IPS |
|
|
Image Classification (HP)
|
100% |
15369
2.86 KIPS |
|
|
Image Classification (Q)
|
97% |
21204
3.96 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1938
31.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
14663
237.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
18276
296.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
8546
9.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
153704
179.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
291945
342.2 IPS |
|
|
Object Detection (SP)
|
100% |
2123
168.4 IPS |
|
|
Object Detection (HP)
|
100% |
16264
1.29 KIPS |
|
|
Object Detection (Q)
|
91% |
22652
1.81 KIPS |
|
|
Face Detection (SP)
|
100% |
3589
42.6 IPS |
|
|
Face Detection (HP)
|
100% |
41298
490.7 IPS |
|
|
Face Detection (Q)
|
100% |
58136
690.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
7768
59.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
95027
732.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
160539
1.26 KIPS |
|
|
Style Transfer (SP)
|
100% |
23633
30.4 IPS |
|
|
Style Transfer (HP)
|
100% |
246541
316.9 IPS |
|
|
Style Transfer (Q)
|
96% |
301779
389.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5653
208.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50824
1.88 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
85030
3.14 KIPS |
|
|
Text Classification (SP)
|
100% |
3418
4.56 KIPS |
|
|
Text Classification (HP)
|
100% |
4338
5.79 KIPS |
|
|
Text Classification (Q)
|
93% |
4363
5.86 KIPS |
|
|
Machine Translation (SP)
|
100% |
3752
64.6 IPS |
|
|
Machine Translation (HP)
|
100% |
9702
167.1 IPS |
|
|
Machine Translation (Q)
|
98% |
11385
196.7 IPS |
