iPad (6th generation)
Geekbench AI Score
323
Single Precision Score
303
Half Precision Score
238
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | frank_m_h_jaeger |
| Upload Date | August 18 2024 03:43 PM |
| Views | 8 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A10 Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad (6th generation) |
| Model ID | iPad7,5 |
| Motherboard | J71bAP |
| CPU Information | |
|---|---|
| Name | Apple A10 Fusion |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM |
| Base Frequency | 2.32 GHz |
| Cluster 1 | 2 Cores |
| Memory Information | |
|---|---|
| Size | 1.93 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
197
36.6 IPS |
|
|
Image Classification (HP)
|
100% |
178
33.0 IPS |
|
|
Image Classification (Q)
|
99% |
177
33.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
156
2.54 IPS |
|
|
Image Segmentation (HP)
|
100% |
160
2.60 IPS |
|
|
Image Segmentation (Q)
|
100% |
156
2.53 IPS |
|
|
Pose Estimation (SP)
|
100% |
891
1.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
869
1.01 IPS |
|
|
Pose Estimation (Q)
|
94% |
634
0.74 IPS |
|
|
Object Detection (SP)
|
100% |
168
13.3 IPS |
|
|
Object Detection (HP)
|
100% |
153
12.1 IPS |
|
|
Object Detection (Q)
|
92% |
92
7.36 IPS |
|
|
Face Detection (SP)
|
100% |
365
4.34 IPS |
|
|
Face Detection (HP)
|
100% |
349
4.15 IPS |
|
|
Face Detection (Q)
|
100% |
145
1.72 IPS |
|
|
Depth Estimation (SP)
|
100% |
447
3.44 IPS |
|
|
Depth Estimation (HP)
|
99% |
415
3.20 IPS |
|
|
Depth Estimation (Q)
|
97% |
413
3.19 IPS |
|
|
Style Transfer (SP)
|
100% |
1253
1.61 IPS |
|
|
Style Transfer (HP)
|
100% |
1250
1.61 IPS |
|
|
Style Transfer (Q)
|
100% |
1228
1.58 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
371
13.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
361
13.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
193
7.16 IPS |
|
|
Text Classification (SP)
|
100% |
149
198.4 IPS |
|
|
Text Classification (HP)
|
100% |
131
174.9 IPS |
|
|
Text Classification (Q)
|
93% |
130
174.6 IPS |
|
|
Machine Translation (SP)
|
100% |
243
4.18 IPS |
|
|
Machine Translation (HP)
|
100% |
206
3.54 IPS |
|
|
Machine Translation (Q)
|
98% |
204
3.53 IPS |
