iPhone XS Max
Geekbench AI Score
429
Single Precision Score
707
Half Precision Score
635
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | December 26 2024 07:46 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPhone XS Max |
| Model ID | iPhone11,6 |
| Motherboard | D331pAP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.67 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
240
44.6 IPS |
|
|
Image Classification (HP)
|
100% |
431
80.2 IPS |
|
|
Image Classification (Q)
|
96% |
362
67.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
281
4.55 IPS |
|
|
Image Segmentation (HP)
|
100% |
475
7.70 IPS |
|
|
Image Segmentation (Q)
|
99% |
522
8.48 IPS |
|
|
Pose Estimation (SP)
|
100% |
749
0.87 IPS |
|
|
Pose Estimation (HP)
|
100% |
811
0.95 IPS |
|
|
Pose Estimation (Q)
|
96% |
792
0.93 IPS |
|
|
Object Detection (SP)
|
100% |
246
19.5 IPS |
|
|
Object Detection (HP)
|
99% |
460
36.5 IPS |
|
|
Object Detection (Q)
|
92% |
388
30.9 IPS |
|
|
Face Detection (SP)
|
100% |
671
7.97 IPS |
|
|
Face Detection (HP)
|
100% |
1261
15.0 IPS |
|
|
Face Detection (Q)
|
100% |
849
10.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
599
4.62 IPS |
|
|
Depth Estimation (HP)
|
98% |
1169
9.03 IPS |
|
|
Depth Estimation (Q)
|
85% |
1036
8.09 IPS |
|
|
Style Transfer (SP)
|
100% |
1213
1.56 IPS |
|
|
Style Transfer (HP)
|
100% |
2009
2.58 IPS |
|
|
Style Transfer (Q)
|
96% |
1977
2.55 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
428
15.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
571
21.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
451
16.6 IPS |
|
|
Text Classification (SP)
|
100% |
197
263.5 IPS |
|
|
Text Classification (HP)
|
100% |
387
516.0 IPS |
|
|
Text Classification (Q)
|
93% |
386
517.4 IPS |
|
|
Machine Translation (SP)
|
100% |
414
7.14 IPS |
|
|
Machine Translation (HP)
|
98% |
628
10.8 IPS |
|
|
Machine Translation (Q)
|
98% |
610
10.5 IPS |
