iPhone 12 Pro Max
Geekbench AI Score
2743
Single Precision Score
11027
Half Precision Score
11158
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | chimpur |
| Upload Date | August 15 2024 05:22 PM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPhone 12 Pro Max |
| Model ID | iPhone13,4 |
| Motherboard | D54pAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.56 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1265
235.2 IPS |
|
|
Image Classification (HP)
|
100% |
4511
839.0 IPS |
|
|
Image Classification (Q)
|
99% |
4987
930.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1145
18.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
5388
87.3 IPS |
|
|
Image Segmentation (Q)
|
100% |
5451
88.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
5304
6.19 IPS |
|
|
Pose Estimation (HP)
|
100% |
57561
67.2 IPS |
|
|
Pose Estimation (Q)
|
94% |
58810
69.0 IPS |
|
|
Object Detection (SP)
|
100% |
1325
105.1 IPS |
|
|
Object Detection (HP)
|
99% |
5369
427.1 IPS |
|
|
Object Detection (Q)
|
91% |
5252
419.6 IPS |
|
|
Face Detection (SP)
|
100% |
2560
30.4 IPS |
|
|
Face Detection (HP)
|
100% |
11479
136.4 IPS |
|
|
Face Detection (Q)
|
100% |
10991
130.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
4889
37.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
33918
261.3 IPS |
|
|
Depth Estimation (Q)
|
97% |
38227
295.6 IPS |
|
|
Style Transfer (SP)
|
100% |
13493
17.3 IPS |
|
|
Style Transfer (HP)
|
100% |
93561
120.3 IPS |
|
|
Style Transfer (Q)
|
100% |
99142
127.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2886
106.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
21510
794.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
18793
696.2 IPS |
|
|
Text Classification (SP)
|
100% |
2142
2.86 KIPS |
|
|
Text Classification (HP)
|
100% |
2254
3.01 KIPS |
|
|
Text Classification (Q)
|
93% |
2261
3.03 KIPS |
|
|
Machine Translation (SP)
|
100% |
2276
39.2 IPS |
|
|
Machine Translation (HP)
|
100% |
2004
34.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2014
34.8 IPS |
