iPhone 16 Pro Max
Geekbench AI Score
4687
Single Precision Score
33014
Half Precision Score
44476
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| Upload Date | November 13 2025 11:36 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
2014
374.5 IPS |
|
|
Image Classification (HP)
|
100% |
13485
2.51 KIPS |
|
|
Image Classification (Q)
|
97% |
18405
3.43 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1808
29.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
18148
294.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
23379
379.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
9533
11.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
151968
177.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
291066
341.1 IPS |
|
|
Object Detection (SP)
|
100% |
2368
187.9 IPS |
|
|
Object Detection (HP)
|
100% |
15430
1.22 KIPS |
|
|
Object Detection (Q)
|
91% |
21244
1.70 KIPS |
|
|
Face Detection (SP)
|
100% |
3680
43.7 IPS |
|
|
Face Detection (HP)
|
100% |
39582
470.3 IPS |
|
|
Face Detection (Q)
|
100% |
53551
636.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
8311
64.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
94253
726.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
148287
1.16 KIPS |
|
|
Style Transfer (SP)
|
100% |
23619
30.4 IPS |
|
|
Style Transfer (HP)
|
100% |
244966
314.9 IPS |
|
|
Style Transfer (Q)
|
96% |
292729
377.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5763
212.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
51394
1.90 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
79025
2.92 KIPS |
|
|
Text Classification (SP)
|
100% |
3682
4.91 KIPS |
|
|
Text Classification (HP)
|
99% |
6170
8.24 KIPS |
|
|
Text Classification (Q)
|
93% |
6074
8.15 KIPS |
|
|
Machine Translation (SP)
|
100% |
4061
69.9 IPS |
|
|
Machine Translation (HP)
|
100% |
9249
159.3 IPS |
|
|
Machine Translation (Q)
|
98% |
10203
176.3 IPS |
