iPhone 16 Pro Max
Geekbench AI Score
3656
Single Precision Score
27096
Half Precision Score
36465
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| Upload Date | August 21 2025 08:25 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| 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% |
1635
304.0 IPS |
|
|
Image Classification (HP)
|
100% |
12932
2.41 KIPS |
|
|
Image Classification (Q)
|
97% |
17010
3.17 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1497
24.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
14615
236.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
19801
321.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
8105
9.46 IPS |
|
|
Pose Estimation (HP)
|
100% |
99723
116.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
186905
219.1 IPS |
|
|
Object Detection (SP)
|
100% |
1960
155.5 IPS |
|
|
Object Detection (HP)
|
100% |
13885
1.10 KIPS |
|
|
Object Detection (Q)
|
91% |
17871
1.43 KIPS |
|
|
Face Detection (SP)
|
100% |
2508
29.8 IPS |
|
|
Face Detection (HP)
|
100% |
29500
350.5 IPS |
|
|
Face Detection (Q)
|
100% |
38089
452.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
6809
52.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
78260
602.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
131627
1.03 KIPS |
|
|
Style Transfer (SP)
|
100% |
19408
24.9 IPS |
|
|
Style Transfer (HP)
|
100% |
176542
226.9 IPS |
|
|
Style Transfer (Q)
|
96% |
219947
283.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4737
174.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
42913
1.58 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
65909
2.43 KIPS |
|
|
Text Classification (SP)
|
100% |
3085
4.12 KIPS |
|
|
Text Classification (HP)
|
99% |
5431
7.25 KIPS |
|
|
Text Classification (Q)
|
93% |
5350
7.18 KIPS |
|
|
Machine Translation (SP)
|
100% |
2266
39.0 IPS |
|
|
Machine Translation (HP)
|
100% |
8582
147.8 IPS |
|
|
Machine Translation (Q)
|
98% |
9503
164.2 IPS |
