Geekbench ML Score

2731
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 04:54 AM
Views 1

System Information

System Information
Operating System iOS 15.6
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5288
566.6 IPS
 
Image Classification (F16)
100% 5403
578.9 IPS
 
Image Classification (I8)
81% 694
74.3 IPS
 
Image Segmentation (F32)
100% 2181
13.5 IPS
 
Image Segmentation (F16)
100% 2160
13.3 IPS
 
Image Segmentation (I8)
89% 1267
7.82 IPS
 
Pose Estimation (F32)
100% 24868
100.6 IPS
 
Pose Estimation (F16)
100% 23969
97.0 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 7050
247.4 IPS
 
Object Detection (F16)
100% 6947
243.8 IPS
 
Object Detection (I8)
52% 992
34.8 IPS
 
Face Detection (F32)
100% 7907
90.8 IPS
 
Face Detection (F16)
100% 7873
90.4 IPS
 
Face Detection (I8)
75% 968
11.1 IPS
 
Text Classification (F32)
100% 1023
404.5 IPS
 
Text Classification (F16)
100% 1023
404.8 IPS
 
Machine Translation (F32)
100% 1940
298.9 IPS
 
Machine Translation (F16)
100% 1943
299.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download