Geekbench ML Score

1795
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:29 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPad12,1
Model IDiPad12,1
Motherboard J181AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.65 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.87 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4467
478.6 IPS
 
Image Classification (F16)
100% 4494
481.5 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 1506
9.30 IPS
 
Image Segmentation (F16)
100% 1500
9.27 IPS
 
Image Segmentation (I8)
89% 838
5.18 IPS
 
Pose Estimation (F32)
100% 8722
35.3 IPS
 
Pose Estimation (F16)
100% 8590
34.8 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
94% 4967
174.3 IPS
 
Object Detection (F16)
94% 4989
175.1 IPS
 
Object Detection (I8)
52% 635
22.3 IPS
 
Face Detection (F32)
67% 5810
66.8 IPS
 
Face Detection (F16)
67% 5705
65.5 IPS
 
Face Detection (I8)
75% 636
7.30 IPS
 
Text Classification (F32)
100% 849
335.9 IPS
 
Text Classification (F16)
100% 851
336.7 IPS
 
Machine Translation (F32)
100% 1196
184.4 IPS
 
Machine Translation (F16)
100% 1192
183.8 IPS
 

Compare

Set Baseline