iPhone 16 Pro Max
Geekbench AI Score
6527
Single Precision Score
7977
Half Precision Score
7822
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | February 21 2026 08:46 AM |
| Views | 7 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
3163
588.2 IPS |
|
|
Image Classification (HP)
|
100% |
3224
599.6 IPS |
|
|
Image Classification (Q)
|
96% |
3050
569.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
4132
67.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
4892
79.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
4716
76.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
14862
17.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
17764
20.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
16992
19.9 IPS |
|
|
Object Detection (SP)
|
100% |
3165
251.0 IPS |
|
|
Object Detection (HP)
|
100% |
3528
279.9 IPS |
|
|
Object Detection (Q)
|
91% |
3558
284.4 IPS |
|
|
Face Detection (SP)
|
100% |
7172
85.2 IPS |
|
|
Face Detection (HP)
|
100% |
10980
130.5 IPS |
|
|
Face Detection (Q)
|
100% |
10414
123.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
12682
97.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
15048
115.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
14250
111.5 IPS |
|
|
Style Transfer (SP)
|
100% |
31478
40.5 IPS |
|
|
Style Transfer (HP)
|
100% |
40314
51.8 IPS |
|
|
Style Transfer (Q)
|
96% |
37638
48.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
7534
278.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8344
308.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6910
255.2 IPS |
|
|
Text Classification (SP)
|
99% |
6950
9.28 KIPS |
|
|
Text Classification (HP)
|
99% |
10411
13.9 KIPS |
|
|
Text Classification (Q)
|
92% |
10644
14.3 KIPS |
|
|
Machine Translation (SP)
|
100% |
1524
26.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1826
31.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2401
41.5 IPS |
