iPhone 16 Pro Max
Geekbench AI Score
5896
Single Precision Score
7120
Half Precision Score
6614
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | July 21 2025 08:20 PM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| 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 | 7.44 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2897
538.7 IPS |
|
|
Image Classification (HP)
|
100% |
2920
543.0 IPS |
|
|
Image Classification (Q)
|
96% |
2980
556.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
4212
68.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
4861
78.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
4702
76.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
14859
17.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
17729
20.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
17048
20.0 IPS |
|
|
Object Detection (SP)
|
100% |
3043
241.3 IPS |
|
|
Object Detection (HP)
|
100% |
3683
292.1 IPS |
|
|
Object Detection (Q)
|
92% |
3179
253.8 IPS |
|
|
Face Detection (SP)
|
100% |
6950
82.6 IPS |
|
|
Face Detection (HP)
|
100% |
10260
121.9 IPS |
|
|
Face Detection (Q)
|
100% |
7975
94.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
12824
98.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
15064
116.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
13806
107.8 IPS |
|
|
Style Transfer (SP)
|
100% |
30520
39.2 IPS |
|
|
Style Transfer (HP)
|
100% |
38546
49.6 IPS |
|
|
Style Transfer (Q)
|
96% |
38426
49.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
7371
272.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8212
303.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6958
256.9 IPS |
|
|
Text Classification (SP)
|
100% |
3616
4.83 KIPS |
|
|
Text Classification (HP)
|
99% |
6064
8.09 KIPS |
|
|
Text Classification (Q)
|
93% |
5958
8.00 KIPS |
|
|
Machine Translation (SP)
|
100% |
1270
21.9 IPS |
|
|
Machine Translation (HP)
|
100% |
1218
21.0 IPS |
|
|
Machine Translation (Q)
|
98% |
1204
20.8 IPS |
