Geekbench ML Score

2325
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 09:36 AM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4739
507.7 IPS
 
Image Classification (F16)
100% 4787
512.9 IPS
 
Image Classification (I8)
81% 646
69.2 IPS
 
Image Segmentation (F32)
100% 1806
11.2 IPS
 
Image Segmentation (F16)
100% 1813
11.2 IPS
 
Image Segmentation (I8)
89% 1135
7.01 IPS
 
Pose Estimation (F32)
100% 17210
69.6 IPS
 
Pose Estimation (F16)
100% 17694
71.6 IPS
 
Pose Estimation (I8)
80% 207
0.84 IPS
 
Object Detection (F32)
100% 6277
220.3 IPS
 
Object Detection (F16)
100% 6066
212.9 IPS
 
Object Detection (I8)
52% 867
30.4 IPS
 
Face Detection (F32)
100% 6050
69.5 IPS
 
Face Detection (F16)
100% 6063
69.7 IPS
 
Face Detection (I8)
75% 871
10.0 IPS
 
Text Classification (F32)
100% 949
375.4 IPS
 
Text Classification (F16)
100% 948
374.8 IPS
 
Machine Translation (F32)
100% 1683
259.4 IPS
 
Machine Translation (F16)
100% 1679
258.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download