iPhone 14 Pro Max
Geekbench AI Score
3523
Single Precision Score
23907
Half Precision Score
27176
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | June 12 2025 10:26 PM |
| Views | 3 |
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% |
1376
256.0 IPS |
|
|
Image Classification (HP)
|
100% |
10408
1.94 KIPS |
|
|
Image Classification (Q)
|
97% |
12831
2.39 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1400
22.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
16068
260.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
19276
312.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
7066
8.24 IPS |
|
|
Pose Estimation (HP)
|
100% |
101609
118.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
101081
118.5 IPS |
|
|
Object Detection (SP)
|
100% |
1569
124.4 IPS |
|
|
Object Detection (HP)
|
100% |
13033
1.03 KIPS |
|
|
Object Detection (Q)
|
91% |
14861
1.19 KIPS |
|
|
Face Detection (SP)
|
100% |
2979
35.4 IPS |
|
|
Face Detection (HP)
|
100% |
31321
372.2 IPS |
|
|
Face Detection (Q)
|
100% |
38312
455.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
6170
47.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
75755
583.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
97752
764.3 IPS |
|
|
Style Transfer (SP)
|
100% |
19109
24.6 IPS |
|
|
Style Transfer (HP)
|
100% |
174563
224.4 IPS |
|
|
Style Transfer (Q)
|
96% |
176897
228.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4102
151.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
31583
1.17 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
37800
1.40 KIPS |
|
|
Text Classification (SP)
|
100% |
2680
3.58 KIPS |
|
|
Text Classification (HP)
|
100% |
2811
3.75 KIPS |
|
|
Text Classification (Q)
|
93% |
2763
3.71 KIPS |
|
|
Machine Translation (SP)
|
100% |
3580
61.7 IPS |
|
|
Machine Translation (HP)
|
100% |
7492
129.0 IPS |
|
|
Machine Translation (Q)
|
98% |
8547
147.7 IPS |
