iPhone 14 Pro Max
Geekbench AI Score
3523
Single Precision Score
23173
Half Precision Score
26863
Quantized Score
Geekbench AI 1.4.0 for iOS AArch64
Result Information
| Upload Date | July 06 2025 04:47 PM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.5 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.51 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1421
264.3 IPS |
|
|
Image Classification (HP)
|
100% |
10274
1.91 KIPS |
|
|
Image Classification (Q)
|
97% |
12915
2.41 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1405
22.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
14114
228.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
19271
312.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
6820
7.96 IPS |
|
|
Pose Estimation (HP)
|
100% |
97723
114.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
104780
122.8 IPS |
|
|
Object Detection (SP)
|
100% |
1565
124.2 IPS |
|
|
Object Detection (HP)
|
100% |
12723
1.01 KIPS |
|
|
Object Detection (Q)
|
91% |
14527
1.16 KIPS |
|
|
Face Detection (SP)
|
100% |
3035
36.1 IPS |
|
|
Face Detection (HP)
|
100% |
31267
371.5 IPS |
|
|
Face Detection (Q)
|
100% |
39841
473.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
6035
46.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
74914
577.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
96933
757.9 IPS |
|
|
Style Transfer (SP)
|
100% |
18894
24.3 IPS |
|
|
Style Transfer (HP)
|
100% |
175918
226.1 IPS |
|
|
Style Transfer (Q)
|
96% |
177372
228.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4100
151.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
32051
1.18 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
37268
1.38 KIPS |
|
|
Text Classification (SP)
|
100% |
2714
3.62 KIPS |
|
|
Text Classification (HP)
|
100% |
2473
3.30 KIPS |
|
|
Text Classification (Q)
|
93% |
2432
3.26 KIPS |
|
|
Machine Translation (SP)
|
100% |
3597
62.0 IPS |
|
|
Machine Translation (HP)
|
100% |
7583
130.6 IPS |
|
|
Machine Translation (Q)
|
98% |
8320
143.8 IPS |
