Geekbench ML Score

1628
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date July 22 2021 09:23 AM
Views 1

System Information

System Information
Operating System iOS 14.4.2
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% 3251
348.4 IPS
 
Image Classification (F16)
100% 3126
334.9 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 1570
9.70 IPS
 
Image Segmentation (F16)
100% 1557
9.62 IPS
 
Image Segmentation (I8)
89% 830
5.13 IPS
 
Pose Estimation (F32)
100% 8661
35.0 IPS
 
Pose Estimation (F16)
100% 8775
35.5 IPS
 
Pose Estimation (I8)
80% 153
0.62 IPS
 
Object Detection (F32)
94% 5107
179.2 IPS
 
Object Detection (F16)
94% 5101
179.0 IPS
 
Object Detection (I8)
52% 640
22.5 IPS
 
Face Detection (F32)
67% 4042
46.4 IPS
 
Face Detection (F16)
67% 3982
45.8 IPS
 
Face Detection (I8)
75% 630
7.23 IPS
 
Text Classification (F32)
100% 743
293.7 IPS
 
Text Classification (F16)
100% 529
209.3 IPS
 
Machine Translation (F32)
100% 1215
187.3 IPS
 
Machine Translation (F16)
100% 1213
186.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download