Geekbench ML Score

1498
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:17 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone 11 Pro
Model IDiPhone12,3
Motherboard D421AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3207
343.6 IPS
 
Image Classification (F16)
100% 3234
346.5 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 1542
9.53 IPS
 
Image Segmentation (F16)
100% 1553
9.59 IPS
 
Image Segmentation (I8)
89% 837
5.17 IPS
 
Pose Estimation (F32)
100% 8765
35.5 IPS
 
Pose Estimation (F16)
100% 8653
35.0 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
94% 5325
186.9 IPS
 
Object Detection (F16)
94% 5127
179.9 IPS
 
Object Detection (I8)
52% 641
22.5 IPS
 
Face Detection (F32)
67% 4106
47.2 IPS
 
Face Detection (F16)
67% 3812
43.8 IPS
 
Face Detection (I8)
75% 634
7.28 IPS
 
Text Classification (F32)
100% 691
273.3 IPS
 
Text Classification (F16)
100% 423
167.3 IPS
 
Machine Translation (F32)
100% 565
87.0 IPS
 
Machine Translation (F16)
100% 697
107.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download