Geekbench ML Score

2732
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:45 PM
Views 1

System Information

System Information
Operating System iOS 15.2.1
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 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5270
564.7 IPS
 
Image Classification (F16)
100% 5281
565.8 IPS
 
Image Classification (I8)
81% 696
74.6 IPS
 
Image Segmentation (F32)
100% 2102
13.0 IPS
 
Image Segmentation (F16)
100% 2206
13.6 IPS
 
Image Segmentation (I8)
89% 1260
7.78 IPS
 
Pose Estimation (F32)
100% 23646
95.7 IPS
 
Pose Estimation (F16)
100% 22922
92.8 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 6884
241.6 IPS
 
Object Detection (F16)
100% 6932
243.3 IPS
 
Object Detection (I8)
52% 991
34.8 IPS
 
Face Detection (F32)
100% 7884
90.6 IPS
 
Face Detection (F16)
100% 7990
91.8 IPS
 
Face Detection (I8)
75% 949
10.9 IPS
 
Text Classification (F32)
100% 1098
434.4 IPS
 
Text Classification (F16)
100% 1103
436.2 IPS
 
Machine Translation (F32)
100% 1980
305.1 IPS
 
Machine Translation (F16)
100% 1963
302.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download