Geekbench ML Score

1536
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:06 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPad Pro (11-inch)
Model IDiPad8,3
Motherboard J318AP
CPU Information
Name Apple A12X Bionic
Topology 1 Processor, 8 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 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4408
472.3 IPS
 
Image Classification (F16)
100% 4375
468.7 IPS
 
Image Classification (I8)
81% 406
43.5 IPS
 
Image Segmentation (F32)
100% 1507
9.31 IPS
 
Image Segmentation (F16)
100% 1521
9.39 IPS
 
Image Segmentation (I8)
89% 753
4.65 IPS
 
Pose Estimation (F32)
100% 8789
35.6 IPS
 
Pose Estimation (F16)
100% 8632
34.9 IPS
 
Pose Estimation (I8)
80% 142
0.58 IPS
 
Object Detection (F32)
94% 4411
154.8 IPS
 
Object Detection (F16)
94% 4591
161.1 IPS
 
Object Detection (I8)
52% 573
20.1 IPS
 
Face Detection (F32)
67% 4913
56.4 IPS
 
Face Detection (F16)
67% 5235
60.1 IPS
 
Face Detection (I8)
75% 558
6.41 IPS
 
Text Classification (F32)
100% 379
149.9 IPS
 
Text Classification (F16)
100% 375
148.2 IPS
 
Machine Translation (F32)
100% 1006
155.0 IPS
 
Machine Translation (F16)
100% 1007
155.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download