Geekbench ML Score

2558
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 28 2024 10:42 AM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad13,18
Model IDiPad13,18
Motherboard J271AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.73 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1087
203.3 IPS
 
Image Classification (F16)
100% 1452
271.7 IPS
 
Image Classification (I8)
99% 1447
270.7 IPS
 
Image Segmentation (F32)
100% 496
8.28 IPS
 
Image Segmentation (F16)
100% 488
8.15 IPS
 
Image Segmentation (I8)
100% 483
8.07 IPS
 
Pose Estimation (F32)
100% 4867
5.89 IPS
 
Pose Estimation (F16)
100% 10537
12.8 IPS
 
Pose Estimation (I8)
100% 10812
13.1 IPS
 
Object Detection (F32)
100% 1090
81.4 IPS
 
Object Detection (F16)
100% 1442
107.6 IPS
 
Object Detection (I8)
97% 1091
81.4 IPS
 
Face Detection (F32)
100% 1712
20.4 IPS
 
Face Detection (F16)
97% 3291
39.1 IPS
 
Face Detection (I8)
97% 3291
39.1 IPS
 
Depth Estimation (F32)
100% 4374
33.9 IPS
 
Depth Estimation (F16)
100% 7060
54.7 IPS
 
Depth Estimation (I8)
99% 7058
54.7 IPS
 
Style Transfer (F32)
100% 12891
17.0 IPS
 
Style Transfer (F16)
100% 21310
28.0 IPS
 
Style Transfer (I8)
100% 21183
27.9 IPS
 
Image Super-Resolution (F32)
100% 2841
101.5 IPS
 
Image Super-Resolution (F16)
100% 4232
151.1 IPS
 
Image Super-Resolution (I8)
100% 4176
149.1 IPS
 
Text Classification (F32)
100% 1929
2.77 KIPS
 
Text Classification (F16)
100% 3065
4.40 KIPS
 
Text Classification (I8)
96% 3047
4.38 KIPS
 
Machine Translation (F32)
100% 667
12.3 IPS
 
Machine Translation (F16)
100% 762
14.0 IPS
 
Machine Translation (I8)
99% 635
11.7 IPS
 

Compare

Set Baseline Geekbench 6 now available