Geekbench ML Score

1380
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 05:34 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad (8th generation)
Model IDiPad11,6
Motherboard J171aAP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.88 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3759
402.8 IPS
 
Image Classification (F16)
100% 3858
413.4 IPS
 
Image Classification (I8)
81% 404
43.3 IPS
 
Image Segmentation (F32)
100% 1412
8.72 IPS
 
Image Segmentation (F16)
100% 1385
8.55 IPS
 
Image Segmentation (I8)
89% 731
4.52 IPS
 
Pose Estimation (F32)
100% 7365
29.8 IPS
 
Pose Estimation (F16)
100% 7373
29.8 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
94% 3949
138.6 IPS
 
Object Detection (F16)
94% 4022
141.1 IPS
 
Object Detection (I8)
52% 572
20.1 IPS
 
Face Detection (F32)
67% 3822
43.9 IPS
 
Face Detection (F16)
67% 3742
43.0 IPS
 
Face Detection (I8)
75% 544
6.25 IPS
 
Text Classification (F32)
100% 335
132.5 IPS
 
Text Classification (F16)
100% 314
124.4 IPS
 
Machine Translation (F32)
100% 985
151.7 IPS
 
Machine Translation (F16)
100% 980
151.0 IPS
 

Compare

Set Baseline