Geekbench ML Score

2432
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 09:16 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.60 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5020
537.9 IPS
 
Image Classification (F16)
100% 5040
540.0 IPS
 
Image Classification (I8)
81% 647
69.4 IPS
 
Image Segmentation (F32)
100% 1860
11.5 IPS
 
Image Segmentation (F16)
100% 1858
11.5 IPS
 
Image Segmentation (I8)
89% 1183
7.31 IPS
 
Pose Estimation (F32)
100% 16766
67.8 IPS
 
Pose Estimation (F16)
100% 18279
74.0 IPS
 
Pose Estimation (I8)
80% 224
0.91 IPS
 
Object Detection (F32)
100% 6379
223.9 IPS
 
Object Detection (F16)
100% 6438
226.0 IPS
 
Object Detection (I8)
52% 916
32.2 IPS
 
Face Detection (F32)
100% 6824
78.4 IPS
 
Face Detection (F16)
100% 6844
78.6 IPS
 
Face Detection (I8)
75% 875
10.1 IPS
 
Text Classification (F32)
100% 1031
407.7 IPS
 
Text Classification (F16)
100% 1038
410.7 IPS
 
Machine Translation (F32)
100% 1688
260.1 IPS
 
Machine Translation (F16)
100% 1693
260.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download