Geekbench ML Score

2442
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 10:25 AM
Views 2

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
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 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5225
559.8 IPS
 
Image Classification (F16)
100% 5240
561.5 IPS
 
Image Classification (I8)
81% 641
68.7 IPS
 
Image Segmentation (F32)
100% 1889
11.7 IPS
 
Image Segmentation (F16)
100% 1912
11.8 IPS
 
Image Segmentation (I8)
89% 1127
6.96 IPS
 
Pose Estimation (F32)
100% 15787
63.9 IPS
 
Pose Estimation (F16)
100% 19077
77.2 IPS
 
Pose Estimation (I8)
80% 215
0.87 IPS
 
Object Detection (F32)
100% 6661
233.8 IPS
 
Object Detection (F16)
100% 6680
234.4 IPS
 
Object Detection (I8)
52% 867
30.4 IPS
 
Face Detection (F32)
100% 6930
79.6 IPS
 
Face Detection (F16)
100% 6926
79.6 IPS
 
Face Detection (I8)
75% 878
10.1 IPS
 
Text Classification (F32)
100% 1046
413.7 IPS
 
Text Classification (F16)
100% 1071
423.5 IPS
 
Machine Translation (F32)
100% 1668
257.0 IPS
 
Machine Translation (F16)
100% 1667
256.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download