iPhone 13 Pro Max
Geekbench AI Score
3269
Single Precision Score
18859
Half Precision Score
21218
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | December 27 2024 12:24 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone 13 Pro Max |
| Model ID | iPhone14,3 |
| Motherboard | D64AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.23 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.51 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1349
251.0 IPS |
|
|
Image Classification (HP)
|
100% |
7844
1.46 KIPS |
|
|
Image Classification (Q)
|
96% |
9090
1.70 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1345
21.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
13088
212.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
13931
225.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
6333
7.39 IPS |
|
|
Pose Estimation (HP)
|
100% |
86351
100.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
93318
109.4 IPS |
|
|
Object Detection (SP)
|
100% |
1461
115.9 IPS |
|
|
Object Detection (HP)
|
99% |
11001
875.1 IPS |
|
|
Object Detection (Q)
|
91% |
11730
937.2 IPS |
|
|
Face Detection (SP)
|
100% |
2717
32.3 IPS |
|
|
Face Detection (HP)
|
100% |
27543
327.3 IPS |
|
|
Face Detection (Q)
|
100% |
35893
426.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
5514
42.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
52986
408.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
73453
574.0 IPS |
|
|
Style Transfer (SP)
|
100% |
17542
22.6 IPS |
|
|
Style Transfer (HP)
|
100% |
153849
197.8 IPS |
|
|
Style Transfer (Q)
|
96% |
152086
196.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3898
143.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
26195
967.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
29244
1.08 KIPS |
|
|
Text Classification (SP)
|
100% |
2403
3.21 KIPS |
|
|
Text Classification (HP)
|
100% |
2220
2.96 KIPS |
|
|
Text Classification (Q)
|
93% |
2254
3.03 KIPS |
|
|
Machine Translation (SP)
|
100% |
3379
58.2 IPS |
|
|
Machine Translation (HP)
|
100% |
4471
77.0 IPS |
|
|
Machine Translation (Q)
|
98% |
5049
87.3 IPS |
