iPhone 16 Pro Max iPhone17,2
Geekbench AI Score
5692
Single Precision Score
6775
Half Precision Score
5888
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | Mojoxer |
| Upload Date | November 18 2024 12:22 AM |
| Views | 18 |
| Notes | 6-core GPU |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone17,2 |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2890
537.5 IPS |
|
|
Image Classification (HP)
|
100% |
2850
530.1 IPS |
|
|
Image Classification (Q)
|
97% |
2741
511.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
3306
53.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
4433
71.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
4389
71.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
15678
18.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
16338
19.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
15552
18.2 IPS |
|
|
Object Detection (SP)
|
100% |
3134
248.6 IPS |
|
|
Object Detection (HP)
|
100% |
3660
290.3 IPS |
|
|
Object Detection (Q)
|
91% |
2788
222.8 IPS |
|
|
Face Detection (SP)
|
100% |
7837
93.1 IPS |
|
|
Face Detection (HP)
|
100% |
10549
125.3 IPS |
|
|
Face Detection (Q)
|
100% |
7156
85.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
13424
103.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
14230
109.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
12318
96.3 IPS |
|
|
Style Transfer (SP)
|
100% |
32696
42.0 IPS |
|
|
Style Transfer (HP)
|
100% |
39280
50.5 IPS |
|
|
Style Transfer (Q)
|
96% |
36245
46.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
8003
295.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8362
308.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6801
251.1 IPS |
|
|
Text Classification (SP)
|
100% |
3420
4.56 KIPS |
|
|
Text Classification (HP)
|
100% |
5866
7.83 KIPS |
|
|
Text Classification (Q)
|
93% |
5805
7.79 KIPS |
|
|
Machine Translation (SP)
|
100% |
808
13.9 IPS |
|
|
Machine Translation (HP)
|
100% |
933
16.1 IPS |
|
|
Machine Translation (Q)
|
98% |
762
13.2 IPS |
