iPad (11th generation)
Geekbench AI Score
3682
Single Precision Score
22920
Half Precision Score
26692
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | April 14 2026 09:58 AM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A16 |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| Model | iPad (11th generation) |
| Model ID | iPad15,7 |
| Motherboard | J481AP |
| CPU Information | |
|---|---|
| Name | Apple A16 |
| Topology | 1 Processor, 5 Cores |
| Identifier | ARM |
| Base Frequency | 3.44 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 5.78 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1389
258.3 IPS |
|
|
Image Classification (HP)
|
100% |
9810
1.82 KIPS |
|
|
Image Classification (Q)
|
97% |
10967
2.05 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1465
23.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
15922
258.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
19570
317.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
6162
7.19 IPS |
|
|
Pose Estimation (HP)
|
100% |
97386
113.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
101942
119.5 IPS |
|
|
Object Detection (SP)
|
100% |
1510
119.8 IPS |
|
|
Object Detection (HP)
|
100% |
12032
954.4 IPS |
|
|
Object Detection (Q)
|
89% |
14450
1.16 KIPS |
|
|
Face Detection (SP)
|
100% |
3273
38.9 IPS |
|
|
Face Detection (HP)
|
100% |
33476
397.8 IPS |
|
|
Face Detection (Q)
|
100% |
46555
553.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
5897
45.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
71385
550.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
90641
708.3 IPS |
|
|
Style Transfer (SP)
|
100% |
18472
23.7 IPS |
|
|
Style Transfer (HP)
|
100% |
170738
219.5 IPS |
|
|
Style Transfer (Q)
|
96% |
173134
223.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3797
140.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
32782
1.21 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
36279
1.34 KIPS |
|
|
Text Classification (SP)
|
100% |
5262
7.02 KIPS |
|
|
Text Classification (HP)
|
100% |
2311
3.08 KIPS |
|
|
Text Classification (Q)
|
93% |
2673
3.59 KIPS |
|
|
Machine Translation (SP)
|
100% |
3400
58.6 IPS |
|
|
Machine Translation (HP)
|
100% |
7075
121.9 IPS |
|
|
Machine Translation (Q)
|
98% |
8197
141.7 IPS |
