iPad Pro 13-inch (M4)
Geekbench AI Score
10055
Single Precision Score
11925
Half Precision Score
10301
Quantized Score
Geekbench AI 1.5.0 for iOS AArch64
Result Information
| User | gnu08 |
| Upload Date | November 12 2025 12:06 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro 13-inch (M4) |
| Model ID | iPad16,6 |
| Motherboard | J721AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.21 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4566
849.0 IPS |
|
|
Image Classification (HP)
|
100% |
4999
929.7 IPS |
|
|
Image Classification (Q)
|
96% |
4509
842.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
7107
115.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
8026
130.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
7692
124.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
26986
31.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
30978
36.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
30151
35.3 IPS |
|
|
Object Detection (SP)
|
100% |
4597
364.7 IPS |
|
|
Object Detection (HP)
|
100% |
5213
413.5 IPS |
|
|
Object Detection (Q)
|
92% |
4793
382.6 IPS |
|
|
Face Detection (SP)
|
100% |
12785
151.9 IPS |
|
|
Face Detection (HP)
|
100% |
16952
201.4 IPS |
|
|
Face Detection (Q)
|
100% |
13527
160.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
20073
154.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
22268
171.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
20447
159.7 IPS |
|
|
Style Transfer (SP)
|
100% |
55967
71.9 IPS |
|
|
Style Transfer (HP)
|
100% |
67092
86.2 IPS |
|
|
Style Transfer (Q)
|
96% |
64783
83.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11360
419.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11733
433.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10357
382.5 IPS |
|
|
Text Classification (SP)
|
100% |
3274
4.37 KIPS |
|
|
Text Classification (HP)
|
99% |
5735
7.65 KIPS |
|
|
Text Classification (Q)
|
93% |
5804
7.79 KIPS |
|
|
Machine Translation (SP)
|
100% |
4916
84.7 IPS |
|
|
Machine Translation (HP)
|
100% |
5270
90.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2493
43.1 IPS |
