iPhone XS
Geekbench AI Score
634
Single Precision Score
691
Half Precision Score
284
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| User | andreasphh |
| Upload Date | October 14 2025 05:43 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.1 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| 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 | 3.69 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
265
49.3 IPS |
|
|
Image Classification (HP)
|
100% |
291
54.1 IPS |
|
|
Image Classification (Q)
|
96% |
136
25.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
219
3.56 IPS |
|
|
Image Segmentation (HP)
|
100% |
238
3.86 IPS |
|
|
Image Segmentation (Q)
|
99% |
171
2.77 IPS |
|
|
Pose Estimation (SP)
|
100% |
1194
1.39 IPS |
|
|
Pose Estimation (HP)
|
100% |
1498
1.75 IPS |
|
|
Pose Estimation (Q)
|
96% |
680
0.80 IPS |
|
|
Object Detection (SP)
|
100% |
523
41.5 IPS |
|
|
Object Detection (HP)
|
100% |
563
44.6 IPS |
|
|
Object Detection (Q)
|
92% |
155
12.4 IPS |
|
|
Face Detection (SP)
|
100% |
1920
22.8 IPS |
|
|
Face Detection (HP)
|
100% |
2224
26.4 IPS |
|
|
Face Detection (Q)
|
100% |
260
3.09 IPS |
|
|
Depth Estimation (SP)
|
100% |
1688
13.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
2168
16.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
413
3.22 IPS |
|
|
Style Transfer (SP)
|
100% |
4082
5.25 IPS |
|
|
Style Transfer (HP)
|
100% |
3354
4.31 IPS |
|
|
Style Transfer (Q)
|
96% |
1486
1.92 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
764
28.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
833
30.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
273
10.1 IPS |
|
|
Text Classification (SP)
|
100% |
147
196.6 IPS |
|
|
Text Classification (HP)
|
100% |
200
267.6 IPS |
|
|
Text Classification (Q)
|
93% |
198
265.1 IPS |
|
|
Machine Translation (SP)
|
100% |
195
3.36 IPS |
|
|
Machine Translation (HP)
|
100% |
160
2.75 IPS |
|
|
Machine Translation (Q)
|
98% |
164
2.84 IPS |
