iPhone 16 Pro Max
Geekbench AI Score
4387
Single Precision Score
32988
Half Precision Score
44552
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| Upload Date | December 07 2025 07:46 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 16 Pro Max |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | Apple A18 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2003
372.4 IPS |
|
|
Image Classification (HP)
|
100% |
14726
2.74 KIPS |
|
|
Image Classification (Q)
|
97% |
17824
3.33 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1755
28.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
18141
294.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
23382
379.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
8756
10.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
148749
173.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
288912
338.6 IPS |
|
|
Object Detection (SP)
|
100% |
2295
182.0 IPS |
|
|
Object Detection (HP)
|
100% |
15530
1.23 KIPS |
|
|
Object Detection (Q)
|
91% |
21107
1.69 KIPS |
|
|
Face Detection (SP)
|
100% |
3448
41.0 IPS |
|
|
Face Detection (HP)
|
100% |
39894
474.0 IPS |
|
|
Face Detection (Q)
|
100% |
53842
639.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
7572
58.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
93850
723.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
158468
1.24 KIPS |
|
|
Style Transfer (SP)
|
100% |
20211
26.0 IPS |
|
|
Style Transfer (HP)
|
100% |
243418
312.9 IPS |
|
|
Style Transfer (Q)
|
96% |
296606
382.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4983
184.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50737
1.87 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
81549
3.01 KIPS |
|
|
Text Classification (SP)
|
100% |
3722
4.97 KIPS |
|
|
Text Classification (HP)
|
99% |
6250
8.34 KIPS |
|
|
Text Classification (Q)
|
93% |
6083
8.16 KIPS |
|
|
Machine Translation (SP)
|
100% |
3827
65.9 IPS |
|
|
Machine Translation (HP)
|
100% |
8557
147.4 IPS |
|
|
Machine Translation (Q)
|
98% |
9657
166.9 IPS |
