Geekbench ML Score

2621
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 04:00 AM
Views 1

System Information

System Information
Operating System iOS 16.1
Model iPad mini (6th generation)
Model IDiPad14,2
Motherboard J311AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.78 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5642
604.5 IPS
 
Image Classification (F16)
100% 5656
606.0 IPS
 
Image Classification (I8)
81% 606
64.9 IPS
 
Image Segmentation (F32)
100% 1895
11.7 IPS
 
Image Segmentation (F16)
100% 1921
11.9 IPS
 
Image Segmentation (I8)
89% 1075
6.64 IPS
 
Pose Estimation (F32)
100% 21055
85.2 IPS
 
Pose Estimation (F16)
100% 20674
83.7 IPS
 
Pose Estimation (I8)
80% 210
0.85 IPS
 
Object Detection (F32)
100% 7194
252.5 IPS
 
Object Detection (F16)
100% 7012
246.1 IPS
 
Object Detection (I8)
52% 873
30.6 IPS
 
Face Detection (F32)
100% 8327
95.7 IPS
 
Face Detection (F16)
100% 8368
96.1 IPS
 
Face Detection (I8)
75% 837
9.61 IPS
 
Text Classification (F32)
100% 1184
468.4 IPS
 
Text Classification (F16)
100% 1160
458.9 IPS
 
Machine Translation (F32)
100% 1919
295.7 IPS
 
Machine Translation (F16)
100% 1919
295.8 IPS
 

Compare

Set Baseline Geekbench 6 now available