Geekbench ML Score

93
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date April 25 2024 05:31 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (10.5-inch)
Model IDiPad7,3
Motherboard J207AP
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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 340
63.7 IPS
 
Image Classification (F16)
100% 14
2.60 IPS
 
Image Classification (I8)
99% 14
2.61 IPS
 
Image Segmentation (F32)
100% 222
3.71 IPS
 
Image Segmentation (F16)
100% 18
0.30 IPS
 
Image Segmentation (I8)
100% 18
0.30 IPS
 
Pose Estimation (F32)
100% 1634
1.98 IPS
 
Pose Estimation (F16)
100% 20
0.02 IPS
 
Pose Estimation (I8)
100% 20
0.02 IPS
 
Object Detection (F32)
100% 344
25.7 IPS
 
Object Detection (F16)
100% 14
1.07 IPS
 
Object Detection (I8)
97% 343
25.6 IPS
 
Face Detection (F32)
100% 703
8.36 IPS
 
Face Detection (F16)
98% 45
0.53 IPS
 
Face Detection (I8)
97% 45
0.53 IPS
 
Depth Estimation (F32)
100% 826
6.41 IPS
 
Depth Estimation (F16)
100% 31
0.24 IPS
 
Depth Estimation (I8)
99% 30
0.24 IPS
 
Style Transfer (F32)
100% 2463
3.24 IPS
 
Style Transfer (F16)
100% 62
0.08 IPS
 
Style Transfer (I8)
100% 62
0.08 IPS
 
Image Super-Resolution (F32)
100% 720
25.7 IPS
 
Image Super-Resolution (F16)
100% 13
0.47 IPS
 
Image Super-Resolution (I8)
100% 13
0.48 IPS
 
Text Classification (F32)
100% 213
306.2 IPS
 
Text Classification (F16)
100% 183
263.2 IPS
 
Text Classification (I8)
96% 183
263.1 IPS
 
Machine Translation (F32)
100% 318
5.86 IPS
 
Machine Translation (F16)
100% 31
0.56 IPS
 
Machine Translation (I8)
99% 314
5.77 IPS
 

Compare

Set Baseline Geekbench 6 now available