iPhone 17 Pro Max
Geekbench AI Score
9024
Single Precision Score
16754
Half Precision Score
17456
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| User | alfred_heinze |
| Upload Date | January 16 2026 12:05 PM |
| Views | 6 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A19 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 17 Pro Max |
| Model ID | iPhone18,2 |
| Motherboard | V54AP |
| CPU Information | |
|---|---|
| Name | Apple A19 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.26 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 11.42 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4284
796.6 IPS |
|
|
Image Classification (HP)
|
100% |
8039
1.49 KIPS |
|
|
Image Classification (Q)
|
97% |
7491
1.40 KIPS |
|
|
Image Segmentation (SP)
|
100% |
6062
98.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
9533
154.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
10535
170.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
20229
23.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
53676
62.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
58312
68.3 IPS |
|
|
Object Detection (SP)
|
100% |
4408
349.6 IPS |
|
|
Object Detection (HP)
|
100% |
8079
640.8 IPS |
|
|
Object Detection (Q)
|
93% |
8055
642.6 IPS |
|
|
Face Detection (SP)
|
100% |
11800
140.2 IPS |
|
|
Face Detection (HP)
|
100% |
23121
274.7 IPS |
|
|
Face Detection (Q)
|
100% |
17967
213.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
17949
138.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
35585
274.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
38580
301.2 IPS |
|
|
Style Transfer (SP)
|
100% |
43504
55.9 IPS |
|
|
Style Transfer (HP)
|
100% |
94859
121.9 IPS |
|
|
Style Transfer (Q)
|
96% |
120082
155.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
10413
384.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18485
682.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
22348
825.2 IPS |
|
|
Text Classification (SP)
|
100% |
3262
4.35 KIPS |
|
|
Text Classification (HP)
|
99% |
6066
8.10 KIPS |
|
|
Text Classification (Q)
|
93% |
6381
8.56 KIPS |
|
|
Machine Translation (SP)
|
100% |
4941
85.1 IPS |
|
|
Machine Translation (HP)
|
100% |
5992
103.2 IPS |
|
|
Machine Translation (Q)
|
98% |
5973
103.2 IPS |
