iPhone 16 Pro Max
Geekbench AI Score
4679
Single Precision Score
33166
Half Precision Score
44506
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| Upload Date | January 24 2026 12:49 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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 | 7.44 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1997
371.3 IPS |
|
|
Image Classification (HP)
|
100% |
13915
2.59 KIPS |
|
|
Image Classification (Q)
|
97% |
18173
3.39 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1850
30.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
18125
293.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
23715
384.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
9531
11.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
152246
177.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
290693
340.7 IPS |
|
|
Object Detection (SP)
|
100% |
2351
186.5 IPS |
|
|
Object Detection (HP)
|
100% |
15471
1.23 KIPS |
|
|
Object Detection (Q)
|
91% |
21166
1.69 KIPS |
|
|
Face Detection (SP)
|
100% |
3671
43.6 IPS |
|
|
Face Detection (HP)
|
100% |
39837
473.3 IPS |
|
|
Face Detection (Q)
|
100% |
54323
645.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
8306
64.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
94469
727.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
146486
1.15 KIPS |
|
|
Style Transfer (SP)
|
100% |
22734
29.2 IPS |
|
|
Style Transfer (HP)
|
100% |
244900
314.8 IPS |
|
|
Style Transfer (Q)
|
96% |
295112
380.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5744
212.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
51708
1.91 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
78866
2.91 KIPS |
|
|
Text Classification (SP)
|
100% |
3676
4.91 KIPS |
|
|
Text Classification (HP)
|
99% |
6121
8.17 KIPS |
|
|
Text Classification (Q)
|
93% |
6080
8.16 KIPS |
|
|
Machine Translation (SP)
|
100% |
4152
71.5 IPS |
|
|
Machine Translation (HP)
|
100% |
9295
160.1 IPS |
|
|
Machine Translation (Q)
|
98% |
10212
176.5 IPS |
