Geekbench ML Score

1660
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 09:39 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone SE (2nd generation)
Model IDiPhone12,8
Motherboard D79AP
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 2.89 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3947
422.9 IPS
 
Image Classification (F16)
100% 3994
427.9 IPS
 
Image Classification (I8)
81% 371
39.8 IPS
 
Image Segmentation (F32)
100% 1466
9.05 IPS
 
Image Segmentation (F16)
100% 1498
9.25 IPS
 
Image Segmentation (I8)
89% 756
4.67 IPS
 
Pose Estimation (F32)
100% 7639
30.9 IPS
 
Pose Estimation (F16)
100% 7784
31.5 IPS
 
Pose Estimation (I8)
80% 134
0.54 IPS
 
Object Detection (F32)
94% 5041
176.9 IPS
 
Object Detection (F16)
94% 5141
180.4 IPS
 
Object Detection (I8)
52% 608
21.3 IPS
 
Face Detection (F32)
67% 5369
61.7 IPS
 
Face Detection (F16)
67% 5396
62.0 IPS
 
Face Detection (I8)
75% 552
6.34 IPS
 
Text Classification (F32)
100% 749
296.2 IPS
 
Text Classification (F16)
100% 749
296.1 IPS
 
Machine Translation (F32)
100% 1181
182.1 IPS
 
Machine Translation (F16)
100% 1181
182.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download