Geekbench ML Score

2704
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 11:16 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,8
Motherboard J522AP
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 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6112
654.8 IPS
 
Image Classification (F16)
100% 6067
650.1 IPS
 
Image Classification (I8)
81% 688
73.7 IPS
 
Image Segmentation (F32)
100% 2233
13.8 IPS
 
Image Segmentation (F16)
100% 2231
13.8 IPS
 
Image Segmentation (I8)
89% 1256
7.76 IPS
 
Pose Estimation (F32)
100% 19448
78.7 IPS
 
Pose Estimation (F16)
100% 19491
78.9 IPS
 
Pose Estimation (I8)
80% 238
0.96 IPS
 
Object Detection (F32)
100% 7282
255.5 IPS
 
Object Detection (F16)
100% 7275
255.3 IPS
 
Object Detection (I8)
52% 975
34.2 IPS
 
Face Detection (F32)
100% 7862
90.3 IPS
 
Face Detection (F16)
100% 7858
90.3 IPS
 
Face Detection (I8)
75% 966
11.1 IPS
 
Text Classification (F32)
100% 1045
413.3 IPS
 
Text Classification (F16)
100% 1040
411.2 IPS
 
Machine Translation (F32)
100% 1835
282.8 IPS
 
Machine Translation (F16)
100% 1832
282.4 IPS
 

Compare

Set Baseline