iPhone 16 Pro Max
Geekbench AI Score
4714
Single Precision Score
35290
Half Precision Score
48167
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | March 31 2026 11:56 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| 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% |
1969
366.2 IPS |
|
|
Image Classification (HP)
|
100% |
14409
2.68 KIPS |
|
|
Image Classification (Q)
|
97% |
19363
3.61 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1894
30.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
18125
293.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
24404
395.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
7584
8.85 IPS |
|
|
Pose Estimation (HP)
|
100% |
152146
177.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
289237
339.0 IPS |
|
|
Object Detection (SP)
|
100% |
2390
189.6 IPS |
|
|
Object Detection (HP)
|
100% |
15605
1.24 KIPS |
|
|
Object Detection (Q)
|
89% |
21668
1.73 KIPS |
|
|
Face Detection (SP)
|
100% |
3865
45.9 IPS |
|
|
Face Detection (HP)
|
100% |
41123
488.6 IPS |
|
|
Face Detection (Q)
|
100% |
61271
728.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
7603
58.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
93942
723.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
150583
1.18 KIPS |
|
|
Style Transfer (SP)
|
100% |
20568
26.4 IPS |
|
|
Style Transfer (HP)
|
100% |
246101
316.4 IPS |
|
|
Style Transfer (Q)
|
96% |
295243
381.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4834
178.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50830
1.88 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
78786
2.91 KIPS |
|
|
Text Classification (SP)
|
99% |
6894
9.20 KIPS |
|
|
Text Classification (HP)
|
100% |
10971
14.6 KIPS |
|
|
Text Classification (Q)
|
92% |
10402
14.0 KIPS |
|
|
Machine Translation (SP)
|
100% |
3982
68.6 IPS |
|
|
Machine Translation (HP)
|
100% |
9115
157.0 IPS |
|
|
Machine Translation (Q)
|
98% |
10168
175.7 IPS |
