Geekbench ML Score

2020
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 17 2024 09:05 AM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad (9th generation)
Model IDiPad12,1
Motherboard J181AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.87 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 788
147.5 IPS
 
Image Classification (F16)
100% 1370
256.3 IPS
 
Image Classification (I8)
99% 1368
256.0 IPS
 
Image Segmentation (F32)
100% 437
7.30 IPS
 
Image Segmentation (F16)
100% 551
9.20 IPS
 
Image Segmentation (I8)
100% 545
9.10 IPS
 
Pose Estimation (F32)
100% 3547
4.30 IPS
 
Pose Estimation (F16)
100% 6406
7.76 IPS
 
Pose Estimation (I8)
100% 6419
7.77 IPS
 
Object Detection (F32)
100% 698
52.1 IPS
 
Object Detection (F16)
100% 1363
101.7 IPS
 
Object Detection (I8)
97% 699
52.2 IPS
 
Face Detection (F32)
100% 1597
19.0 IPS
 
Face Detection (F16)
97% 3119
37.1 IPS
 
Face Detection (I8)
97% 3122
37.1 IPS
 
Depth Estimation (F32)
100% 3134
24.3 IPS
 
Depth Estimation (F16)
100% 5977
46.4 IPS
 
Depth Estimation (I8)
99% 5982
46.4 IPS
 
Style Transfer (F32)
100% 7707
10.1 IPS
 
Style Transfer (F16)
100% 13752
18.1 IPS
 
Style Transfer (I8)
100% 13936
18.3 IPS
 
Image Super-Resolution (F32)
100% 2167
77.4 IPS
 
Image Super-Resolution (F16)
100% 2756
98.4 IPS
 
Image Super-Resolution (I8)
100% 2739
97.8 IPS
 
Text Classification (F32)
100% 1210
1.74 KIPS
 
Text Classification (F16)
100% 2020
2.90 KIPS
 
Text Classification (I8)
96% 2014
2.89 KIPS
 
Machine Translation (F32)
100% 638
11.7 IPS
 
Machine Translation (F16)
100% 918
16.9 IPS
 
Machine Translation (I8)
99% 637
11.7 IPS
 

Compare

Set Baseline Geekbench 6 now available