Geekbench ML Score

2727
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User toygoon
Upload Date September 27 2024 10:34 AM
Views 2

System Information

System Information
Operating System iOS 15.0.1
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5338
571.9 IPS
 
Image Classification (F16)
100% 5517
591.1 IPS
 
Image Classification (I8)
81% 693
74.2 IPS
 
Image Segmentation (F32)
100% 2058
12.7 IPS
 
Image Segmentation (F16)
100% 2195
13.6 IPS
 
Image Segmentation (I8)
89% 1193
7.37 IPS
 
Pose Estimation (F32)
100% 23088
93.4 IPS
 
Pose Estimation (F16)
100% 23056
93.3 IPS
 
Pose Estimation (I8)
80% 228
0.92 IPS
 
Object Detection (F32)
100% 6941
243.6 IPS
 
Object Detection (F16)
100% 7351
258.0 IPS
 
Object Detection (I8)
52% 956
33.6 IPS
 
Face Detection (F32)
100% 7836
90.0 IPS
 
Face Detection (F16)
100% 7818
89.8 IPS
 
Face Detection (I8)
75% 913
10.5 IPS
 
Text Classification (F32)
100% 1146
453.4 IPS
 
Text Classification (F16)
100% 1170
462.9 IPS
 
Machine Translation (F32)
100% 1960
302.1 IPS
 
Machine Translation (F16)
100% 1986
306.0 IPS
 

Compare

Set Baseline Geekbench 6 now available