Geekbench ML Score

390
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 10 2024 07:56 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad Pro (10.5-inch)
Model IDiPad7,4
Motherboard J208AP
CPU Information
Name Apple A10X Fusion
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 2.34 GHz
Cluster 13 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.91 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 246
46.1 IPS
 
Image Classification (F16)
100% 214
40.1 IPS
 
Image Classification (I8)
99% 209
39.1 IPS
 
Image Segmentation (F32)
100% 144
2.40 IPS
 
Image Segmentation (F16)
100% 143
2.39 IPS
 
Image Segmentation (I8)
100% 143
2.39 IPS
 
Pose Estimation (F32)
100% 1402
1.70 IPS
 
Pose Estimation (F16)
100% 1378
1.67 IPS
 
Pose Estimation (I8)
100% 1341
1.62 IPS
 
Object Detection (F32)
100% 244
18.2 IPS
 
Object Detection (F16)
100% 213
15.9 IPS
 
Object Detection (I8)
97% 240
17.9 IPS
 
Face Detection (F32)
100% 474
5.63 IPS
 
Face Detection (F16)
100% 466
5.55 IPS
 
Face Detection (I8)
99% 466
5.54 IPS
 
Depth Estimation (F32)
100% 602
4.67 IPS
 
Depth Estimation (F16)
100% 543
4.21 IPS
 
Depth Estimation (I8)
99% 547
4.24 IPS
 
Style Transfer (F32)
100% 1909
2.51 IPS
 
Style Transfer (F16)
100% 1892
2.49 IPS
 
Style Transfer (I8)
100% 1847
2.43 IPS
 
Image Super-Resolution (F32)
100% 600
21.4 IPS
 
Image Super-Resolution (F16)
100% 590
21.1 IPS
 
Image Super-Resolution (I8)
100% 593
21.2 IPS
 
Text Classification (F32)
100% 142
203.8 IPS
 
Text Classification (F16)
100% 119
170.4 IPS
 
Text Classification (I8)
96% 118
169.7 IPS
 
Machine Translation (F32)
100% 231
4.26 IPS
 
Machine Translation (F16)
100% 198
3.64 IPS
 
Machine Translation (I8)
99% 235
4.32 IPS
 

Compare

Set Baseline Geekbench 6 now available