iPhone 16 Pro Max
Geekbench AI Score
4431
Single Precision Score
32760
Half Precision Score
45994
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | January 05 2025 07:41 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| 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 | 7.45 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1955
363.6 IPS |
|
|
Image Classification (HP)
|
100% |
15226
2.83 KIPS |
|
|
Image Classification (Q)
|
97% |
19362
3.61 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1931
31.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
18328
297.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
24115
390.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
8381
9.78 IPS |
|
|
Pose Estimation (HP)
|
100% |
150257
175.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
293181
343.6 IPS |
|
|
Object Detection (SP)
|
100% |
2142
169.9 IPS |
|
|
Object Detection (HP)
|
100% |
16221
1.29 KIPS |
|
|
Object Detection (Q)
|
91% |
22651
1.81 KIPS |
|
|
Face Detection (SP)
|
100% |
3538
42.0 IPS |
|
|
Face Detection (HP)
|
100% |
41235
490.0 IPS |
|
|
Face Detection (Q)
|
100% |
58020
689.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7632
58.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
95303
734.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
161386
1.26 KIPS |
|
|
Style Transfer (SP)
|
100% |
23056
29.6 IPS |
|
|
Style Transfer (HP)
|
100% |
246297
316.6 IPS |
|
|
Style Transfer (Q)
|
96% |
304474
392.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5373
198.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50095
1.85 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
83594
3.09 KIPS |
|
|
Text Classification (SP)
|
100% |
3422
4.57 KIPS |
|
|
Text Classification (HP)
|
100% |
4367
5.83 KIPS |
|
|
Text Classification (Q)
|
93% |
5019
6.74 KIPS |
|
|
Machine Translation (SP)
|
100% |
3767
64.9 IPS |
|
|
Machine Translation (HP)
|
100% |
9887
170.3 IPS |
|
|
Machine Translation (Q)
|
98% |
11423
197.4 IPS |
