Geekbench ML Score

547
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date November 13 2024 03:39 PM
Views 1

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (9.7-inch)
Model IDiPad6,4
Motherboard J128AP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.92 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 247
46.2 IPS
 
Image Classification (F16)
100% 232
43.4 IPS
 
Image Classification (I8)
99% 248
46.5 IPS
 
Image Segmentation (F32)
100% 180
3.01 IPS
 
Image Segmentation (F16)
100% 181
3.02 IPS
 
Image Segmentation (I8)
100% 180
3.00 IPS
 
Pose Estimation (F32)
100% 2044
2.48 IPS
 
Pose Estimation (F16)
100% 2035
2.46 IPS
 
Pose Estimation (I8)
100% 2017
2.44 IPS
 
Object Detection (F32)
100% 348
26.0 IPS
 
Object Detection (F16)
100% 292
21.8 IPS
 
Object Detection (I8)
97% 324
24.2 IPS
 
Face Detection (F32)
100% 1263
15.0 IPS
 
Face Detection (F16)
100% 1178
14.0 IPS
 
Face Detection (I8)
99% 1034
12.3 IPS
 
Depth Estimation (F32)
100% 2002
15.5 IPS
 
Depth Estimation (F16)
100% 2008
15.6 IPS
 
Depth Estimation (I8)
99% 1969
15.3 IPS
 
Style Transfer (F32)
100% 4128
5.43 IPS
 
Style Transfer (F16)
100% 4085
5.37 IPS
 
Style Transfer (I8)
100% 4091
5.38 IPS
 
Image Super-Resolution (F32)
100% 875
31.3 IPS
 
Image Super-Resolution (F16)
100% 839
29.9 IPS
 
Image Super-Resolution (I8)
100% 831
29.7 IPS
 
Text Classification (F32)
100% 65
93.4 IPS
 
Text Classification (F16)
100% 92
131.8 IPS
 
Text Classification (I8)
96% 95
136.0 IPS
 
Machine Translation (F32)
100% 130
2.39 IPS
 
Machine Translation (F16)
100% 117
2.15 IPS
 
Machine Translation (I8)
99% 138
2.53 IPS
 

Compare

Set Baseline Geekbench 6 now available