Geekbench ML Score

2417
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 05 2021 04:44 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
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 3.63 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5316
569.6 IPS
 
Image Classification (F16)
100% 5122
548.8 IPS
 
Image Classification (I8)
81% 636
68.1 IPS
 
Image Segmentation (F32)
100% 1891
11.7 IPS
 
Image Segmentation (F16)
100% 1975
12.2 IPS
 
Image Segmentation (I8)
89% 1088
6.72 IPS
 
Pose Estimation (F32)
100% 17481
70.7 IPS
 
Pose Estimation (F16)
100% 17119
69.3 IPS
 
Pose Estimation (I8)
80% 209
0.84 IPS
 
Object Detection (F32)
100% 6381
223.9 IPS
 
Object Detection (F16)
100% 6403
224.7 IPS
 
Object Detection (I8)
52% 873
30.6 IPS
 
Face Detection (F32)
100% 6882
79.1 IPS
 
Face Detection (F16)
100% 6865
78.9 IPS
 
Face Detection (I8)
75% 840
9.65 IPS
 
Text Classification (F32)
100% 1037
410.3 IPS
 
Text Classification (F16)
100% 1070
423.3 IPS
 
Machine Translation (F32)
100% 1678
258.7 IPS
 
Machine Translation (F16)
100% 1664
256.5 IPS
 

Compare

Set Baseline Geekbench 6 now available