Geekbench ML Score

700
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:47 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPhone 13 Pro
Model IDiPhone14,2
Motherboard D63AP
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 5.52 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 345
37.0 IPS
 
Image Classification (F16)
100% 367
39.4 IPS
 
Image Classification (I8)
81% 391
41.9 IPS
 
Image Segmentation (F32)
100% 707
4.37 IPS
 
Image Segmentation (F16)
100% 663
4.09 IPS
 
Image Segmentation (I8)
89% 1288
7.95 IPS
 
Pose Estimation (F32)
100% 259
1.05 IPS
 
Pose Estimation (F16)
100% 215
0.87 IPS
 
Pose Estimation (I8)
80% 327
1.32 IPS
 
Object Detection (F32)
100% 783
27.5 IPS
 
Object Detection (F16)
100% 870
30.5 IPS
 
Object Detection (I8)
52% 728
25.5 IPS
 
Face Detection (F32)
100% 872
10.0 IPS
 
Face Detection (F16)
100% 835
9.60 IPS
 
Face Detection (I8)
75% 883
10.1 IPS
 
Text Classification (F32)
100% 1454
575.2 IPS
 
Text Classification (F16)
100% 1079
426.6 IPS
 
Machine Translation (F32)
100% 2052
316.2 IPS
 
Machine Translation (F16)
100% 2051
316.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download