Geekbench ML Score

2807
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 10 2023 08:49 PM
Views 4

System Information

System Information
Operating System iOS 16.5
Model iPad13,16
Model IDiPad13,16
Motherboard J407AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6770
725.4 IPS
 
Image Classification (F16)
100% 6769
725.3 IPS
 
Image Classification (I8)
81% 689
73.8 IPS
 
Image Segmentation (F32)
100% 2095
12.9 IPS
 
Image Segmentation (F16)
100% 2070
12.8 IPS
 
Image Segmentation (I8)
89% 1234
7.63 IPS
 
Pose Estimation (F32)
100% 19444
78.7 IPS
 
Pose Estimation (F16)
100% 19120
77.4 IPS
 
Pose Estimation (I8)
80% 236
0.96 IPS
 
Object Detection (F32)
100% 8026
281.7 IPS
 
Object Detection (F16)
100% 7923
278.0 IPS
 
Object Detection (I8)
52% 979
34.3 IPS
 
Face Detection (F32)
100% 8633
99.2 IPS
 
Face Detection (F16)
100% 8596
98.8 IPS
 
Face Detection (I8)
75% 951
10.9 IPS
 
Text Classification (F32)
100% 1234
487.9 IPS
 
Text Classification (F16)
100% 1212
479.4 IPS
 
Machine Translation (F32)
100% 1840
283.6 IPS
 
Machine Translation (F16)
100% 1839
283.4 IPS
 

Compare

Set Baseline Geekbench 6 now available