iPhone 16 Pro Max
Geekbench AI Score
2602
Single Precision Score
18702
Half Precision Score
24597
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | December 11 2024 11:30 AM |
| Views | 2 |
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% |
1217
226.4 IPS |
|
|
Image Classification (HP)
|
100% |
8210
1.53 KIPS |
|
|
Image Classification (Q)
|
97% |
11635
2.17 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1060
17.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
9229
149.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
12673
205.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
3571
4.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
75406
88.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
135506
158.8 IPS |
|
|
Object Detection (SP)
|
100% |
1333
105.7 IPS |
|
|
Object Detection (HP)
|
100% |
9552
757.7 IPS |
|
|
Object Detection (Q)
|
91% |
12179
973.1 IPS |
|
|
Face Detection (SP)
|
100% |
2376
28.2 IPS |
|
|
Face Detection (HP)
|
100% |
20425
242.7 IPS |
|
|
Face Detection (Q)
|
100% |
32055
380.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
4517
34.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
47824
368.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
80474
629.2 IPS |
|
|
Style Transfer (SP)
|
100% |
12348
15.9 IPS |
|
|
Style Transfer (HP)
|
100% |
124013
159.4 IPS |
|
|
Style Transfer (Q)
|
96% |
162371
209.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3550
131.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
34770
1.28 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
48320
1.78 KIPS |
|
|
Text Classification (SP)
|
100% |
2102
2.81 KIPS |
|
|
Text Classification (HP)
|
100% |
2786
3.72 KIPS |
|
|
Text Classification (Q)
|
93% |
2535
3.40 KIPS |
|
|
Machine Translation (SP)
|
100% |
2345
40.4 IPS |
|
|
Machine Translation (HP)
|
100% |
8177
140.9 IPS |
|
|
Machine Translation (Q)
|
98% |
6495
112.2 IPS |
