Geekbench ML Score

2382
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:46 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,11
Motherboard J523xAP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.34 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6146
658.6 IPS
 
Image Classification (F16)
100% 6352
680.6 IPS
 
Image Classification (I8)
81% 412
44.2 IPS
 
Image Segmentation (F32)
100% 1487
9.19 IPS
 
Image Segmentation (F16)
100% 1220
7.54 IPS
 
Image Segmentation (I8)
89% 473
2.92 IPS
 
Pose Estimation (F32)
100% 16682
67.5 IPS
 
Pose Estimation (F16)
100% 14309
57.9 IPS
 
Pose Estimation (I8)
80% 222
0.90 IPS
 
Object Detection (F32)
100% 8045
282.3 IPS
 
Object Detection (F16)
100% 8095
284.1 IPS
 
Object Detection (I8)
52% 961
33.7 IPS
 
Face Detection (F32)
100% 8117
93.3 IPS
 
Face Detection (F16)
100% 8531
98.0 IPS
 
Face Detection (I8)
75% 942
10.8 IPS
 
Text Classification (F32)
100% 1185
468.9 IPS
 
Text Classification (F16)
100% 1209
478.4 IPS
 
Machine Translation (F32)
100% 1811
279.1 IPS
 
Machine Translation (F16)
100% 1879
289.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download