Geekbench ML Score

1417
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:19 PM
Views 1

System Information

System Information
Operating System iOS 15.7
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% 3485
373.4 IPS
 
Image Classification (F16)
100% 3491
374.0 IPS
 
Image Classification (I8)
81% 403
43.2 IPS
 
Image Segmentation (F32)
100% 1493
9.22 IPS
 
Image Segmentation (F16)
100% 1488
9.19 IPS
 
Image Segmentation (I8)
89% 750
4.63 IPS
 
Pose Estimation (F32)
100% 8021
32.5 IPS
 
Pose Estimation (F16)
100% 8015
32.4 IPS
 
Pose Estimation (I8)
80% 142
0.58 IPS
 
Object Detection (F32)
94% 4132
145.0 IPS
 
Object Detection (F16)
94% 4117
144.5 IPS
 
Object Detection (I8)
52% 570
20.0 IPS
 
Face Detection (F32)
67% 4771
54.8 IPS
 
Face Detection (F16)
67% 4753
54.6 IPS
 
Face Detection (I8)
75% 553
6.36 IPS
 
Text Classification (F32)
100% 293
116.0 IPS
 
Text Classification (F16)
100% 292
115.3 IPS
 
Machine Translation (F32)
100% 985
151.8 IPS
 
Machine Translation (F16)
100% 987
152.1 IPS
 

Compare

Set Baseline