iPhone XS Max
Geekbench AI Score
582
Single Precision Score
989
Half Precision Score
880
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | Osoczer |
| Upload Date | March 05 2026 07:08 AM |
| Views | 9 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.5 |
| 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% |
361
67.2 IPS |
|
|
Image Classification (HP)
|
100% |
648
120.5 IPS |
|
|
Image Classification (Q)
|
96% |
533
99.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
409
6.63 IPS |
|
|
Image Segmentation (HP)
|
100% |
712
11.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
756
12.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
1132
1.32 IPS |
|
|
Pose Estimation (HP)
|
100% |
933
1.09 IPS |
|
|
Pose Estimation (Q)
|
96% |
848
0.99 IPS |
|
|
Object Detection (SP)
|
100% |
294
23.3 IPS |
|
|
Object Detection (HP)
|
99% |
639
50.7 IPS |
|
|
Object Detection (Q)
|
92% |
536
42.8 IPS |
|
|
Face Detection (SP)
|
100% |
821
9.76 IPS |
|
|
Face Detection (HP)
|
100% |
1789
21.3 IPS |
|
|
Face Detection (Q)
|
100% |
1143
13.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
748
5.77 IPS |
|
|
Depth Estimation (HP)
|
98% |
1404
10.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
1226
9.58 IPS |
|
|
Style Transfer (SP)
|
100% |
1806
2.32 IPS |
|
|
Style Transfer (HP)
|
100% |
3167
4.07 IPS |
|
|
Style Transfer (Q)
|
96% |
2964
3.83 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
568
21.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
750
27.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
679
25.1 IPS |
|
|
Text Classification (SP)
|
100% |
286
381.9 IPS |
|
|
Text Classification (HP)
|
100% |
566
755.3 IPS |
|
|
Text Classification (Q)
|
93% |
562
754.7 IPS |
|
|
Machine Translation (SP)
|
100% |
506
8.71 IPS |
|
|
Machine Translation (HP)
|
98% |
966
16.7 IPS |
|
|
Machine Translation (Q)
|
98% |
966
16.7 IPS |
